Timeless Autonomy

Can the Medicare Home Health Benefit be a Tool to Accelerate Palliative Care?

Dana Prommel Strauss — Mon, 06 Jul 2026 00:15:00 +0000

On July 1, 2026, CMS posted the CY 2027 Home Health PPS proposed rule, with comments due August 31, 2026. While most will focus on the payment increase of 2.4% (notably, almost identical to what we’ve seen in prior PPS rules this year and the Medicare Advantage Final Notice), CMS did even include in the Fact Sheet and Press Release, not just buried in the text of the proposed rule text, that palliative care can be provided within the existing home health benefit to patients with serious illness and that they want to see more community-based palliative care.

They emphasized that palliative care is separate from hospice and may support patients earlier in the course of serious illness. CMS notes they plan to add examples of qualifying skilled care in home health through sub-regulatory guidance after the final rule is published, which is in November. It appears these examples will be added to Chapter 7 of the Medicare Benefit Policy Manual (BPM), which is for home health. They do offer a few examples in the Home Health proposed rule itself, starting on Federal Register page 41275. You can access the proposed rule and download the pdf version here.

They also posted a Request for Information (RFI) in the 2027 Hospice proposed rule, which they directly reference in the HH proposed rule, where they ask how to best promote access to community-based palliative care.

I went back and reviewed that proposed rule. Here’s some of what was in that RFI, including the questions asked. Unfortunately, that RFI comment period is closed. The approach to take here is to answer these RFI questions in your comment letter to the 2027 HH proposed rule as it relates to home health.

From the RFI in the 2027 Hospice proposed rule:

Palliative care is often thought of in concert with hospice care; however, it is not mutually exclusive to the end of life
Although Medicare does not currently offer a dedicated palliative care benefit, because palliative services are offered across existing Medicare programs, we are interested in soliciting public feedback regarding ways in which we can optimize current coverage and billing practices under various outpatient or home-based benefits… Understanding how Medicare providers currently support palliative care, how providers bill for these services, and where gaps persist is critical to strengthening community-based palliative care within today's regulatory and payment structure.
Because Medicare does not recognize palliative care as a distinct billable service, providers must rely on a variety of codes and benefit categories
Code Z51.5 Encounter for Palliative Care can be used; however, it does not specify what services this code encompasses. These codes also may not reflect the time-intensive nature of holistic, interdisciplinary palliative care
Do the E/M codes, care management codes, and ACP codes represent the majority of the billing codes providers use to capture community palliative care services?
What services are typically provided when Z51.5 is billed?
Are there challenges in meeting documentation requirements or integrating non-billable team members, such as social workers, chaplains, or nurses who are crucial to palliative care delivery?
Is there uncertainty about compliance requirements or concern that billing for palliative care will result in claims denials?
What non-medical services, such as caregiver training or spiritual care, would most benefit patients if reimbursed? And what enhancements to existing benefits (not requiring legislation) could strengthen palliative care? These might include expanding social worker billing privileges or creating standardized codes or definitions for serious-illness care.
What aspects of palliative care are financially unsustainable for providers?
What documentation requirements do providers typically use, or suggest using, to identify the provision of palliative care?
Do providers commonly refer patients for home health services when a patient needs palliative care concurrently with curative or life-sustaining care?
What services do providers typically offer patients who are not eligible or ready to elect hospice care but require palliative services?
Interested party feedback is essential for guiding CMS toward policies that expand access to high-quality community palliative care without requiring legislative reform or the creation of an entirely new benefit… we are soliciting input on any additional targeted enhancements within current benefits, such as expanding billable services, simplifying documentation, standardizing definitions, or increasing beneficiary education that could meaningfully expand access to palliative care services.
CMS in the 2027 Hospice proposed rule

A note about RFIs: CMS will often post them when they are looking for feedback and ideas prior to doing rulemaking on something that’s a goal, but that they weren’t ready to act on yet.

Medicare policy runs on two layers.

The bottom layer is statute, the Social Security Act, the part that actually says what Medicare is and who it covers. Only Congress can change it, and Congress makes permanent changes in Medicare statute VERY infrequently.

The top layer is where CMS lives: the regulations and guidance that spell out how the statute works in practice. You'll hear people say regulators can't make new policy. That's not quite right. They can, but only inside the room Congress already built for them.

So when CMS wants more palliative care in the community, it has a choice. It can go wait for Congress’ stars to align to create a brand new benefit, which might never happen. Or it can look at the benefits that already exist and clarify that palliative care fits inside one of them. CMS took the second path.

In the companion hospice rule earlier this year, the agency wrote that it wanted to expand palliative care "without requiring legislative reform or the creation of an entirely new benefit." Two rules in a row now, hospice in April and home health in July, working the same angle. That's intentional. I wouldn’t be surprised to see something in the 2027 Physical Fee Schedule proposed rule, which could be out as early as this week (this is the week of 7.5.26).

There's also a legal reason the “clarify-what-exists” approach is likely a smart one right now.

After the Supreme Court ended Chevron deference in 2024, agencies get a lot less benefit of the doubt when they stretch a statute to do something new. Pointing out what a benefit already covers stands on much firmer ground than inventing something the text never mentioned. So "no new benefit" is CMS picking the version most likely to survive.

A clarification like this changes what patients actually get, not just what's printed in a manual. Because when rules are murky, providers default to self-protection over clinical innovation. Let’s look at how we decide what to offer in the first place

When we agree to bill a third party payer, including Medicare, we agree to something specific. We'll submit claims for covered services, and if a service isn't covered, we understand the patient may end up on the hook for it. No provider wants to be the one having that second conversation.

We might also risk being accused of providing care that wasn’t medically necessary and attempting to submit claims for that outside of what’s considered “covered.” Because is Medicare fee-for-service for home health, for example, there’s no “prior authorization.” This would mean an audit could be what surfaces a potential issue.

So we do the rational thing and hold back on anything we're not confident will be paid and what we aren’t confident would be considered “following Medicare’s guidelines.” (I’ve seen Medicare’s definitions be interpreted almost by habit in different sites of care, not by what I read in the Medicare Benefit Policy Manual. But I digress…) Spread that across an entire industry in something like the care of patients with serious illness, and it’s a massive missed opportunity with major downstream impacts.

Also, plenty of us honestly don't know the guidance well enough to be sure. Coverage rules are dense and scattered across manuals nobody reads for fun (except maybe the odd duck like me 😀 ). CMS seems to understand that decoding the dense policy is a problem, too. The questions it asked in the hospice rule were all about exactly this: claims denials, uncertainty about compliance, services people deliver but can't figure out how to bill. If they can take away that uncertainty, they may be offering access to care that was sitting there available the whole time.

Which brings me to the confusion that costs patients the most

A lot of people, including plenty of clinicians, hear "palliative care" and picture hospice, or some lighter version of it. It isn't that. Hospice is for the (approximate) final six months of life when curative treatment is no longer the chosen path and/or a viable option, and the patient is willing to stop the curative route.

Palliative care runs right alongside curative treatment, and it can start years before anyone is talking about hospice. It's for serious illness, a much bigger cohort. It’s also the cohort who commonly has unmanaged symptoms and conditions that land them in the emergency room.

Part of why the confusion holds is that, surprise surprise, the value of palliative care isn't obvious to everyone. Our fee-for-service, transactional system trains our brains to look only for line-item line billing codes, not the underlying clinical gaps. Palliative care often looks like a conversation, a medication list that finally gets untangled, and symptoms that finally get controlled. For someone living with one or more serious illnesses, that can be worth more than almost anything else we do for them.

In their 2012 New England Journal of Medicine article, Dr. Michael Barry and Susan Edgman-Levitan from the MGH Stoeckle Center for Primary Care Innovation introduced this concept of asking “What Matters to You?”, which increased clinicians’ awareness of important issues in their patient’s lives that could drive customized plans of care.
From “What Matters to You?” by Andy Beggs, in Volume 7, Issue 3 of “Medical Interpreter Services

If you want to see palliative care hiding in plain sight, borrow a trick from Toyota. On the factory floor, when something breaks, you ask "why" five times to get past the symptom and down to the real cause.

Apply the “Five Whys”
Picture an 84-year-old with advanced congestive heart failure, back in the hospital for the third time this year.
Why? She's in fluid overload.
Why? She stopped taking her diuretic.
Why? It had her up all night running to the bathroom, and she's terrified of falling in the dark.
Why? She lives alone, and her daughter is three states away.
Why? Because nobody has actually sat down with her and asked what living well looks like to her, then built a plan around the answer.
Five questions in, a heart failure readmission has turned into a crucial conversation. That conversation is palliative care. And notice that not one readmission metric and not one billing code captures the thing that would have actually helped her. The value was real but invisible until somebody went looking for it.

That invisibility is a money problem and a clinical one.

So much of what palliative care does well is work the payment system has no clean slot for. CMS admits it. The agency wrote that "because Medicare does not recognize palliative care as a distinct billable service, providers must rely on a variety of codes and benefit categories." There's a code for a palliative care encounter, Z51.5, but as CMS points out, it doesn't say what services it's supposed to cover. The social worker, the chaplain, the nurse spending an hour on symptoms and fears, these are often the heart of the visit and the hardest parts to put on a claim.

Work that doesn't get paid doesn't get done at scale. so it doesn’t help an organization keep its doors open. Not to mention, this isn’t a skill every physician has or they don’t feel comfortable doing it. It may not be something they have done regularly or saw the value in, or saw it as their job. These are real issues to be tackled when we want palliative care to be carried out by medical providers.

Tucking palliative care into an existing, billable benefit matters more than it sounds. Home health is a place where this work can finally get delivered and paid for under rules that are already on the books.

Take action and provide your comments by the deadline

Comments on the home health proposed rule are due August 31, 2026. CMS said that it wants comments "on any concerns or suggestions regarding reaching this goal."

Don't send a comment that just says you're in favor. Say what you actually see. Name the skilled services you provide to seriously ill patients. Describe a real patient who would have qualified and what stood in the way. Point out where the coverage still feels murky enough that your team hesitates to bill. CMS already published the questions it cares about in the hospice rule, which services get billed under that Z code, where claims get denied, which team members you can't bill for at all. Answer those, with specifics. Specifics are what turn into guidance.

And don’t be afraid to call out what doesn’t make sense. Here’s what I want to explore: palliative care is ideally provided in care teams. However, the physician, NP, or PA is required to discuss medical orders and patient wishes, and is required to make sure patients understand their options.

If someone is making decisions about Medical/Physician Orders for Life-Sustaining Treatment (MOLST/POLST), that requires their involvement and signature. If a patient’s medication is causing unmanageable symptoms, it will be the physician/APP who partners with the patient to potentially make changes.

Home health providers may be concerned that they will need strong partnerships with the referring physicians so the care teams in the home can collaborate with them and the patient on medical treatment changes. Physicians and APPs providing the palliative medical care often don’t have the incentives in fee-for-service to make home visits because of windshield time and the impact home visits have on their daily “RVU productivity.”

I want to call this palliative care's time to shine—and it very well might be. But it also opens up a massive can of worms: what is the actual dividing line between medical palliative care and team-based care? And is the fee-for-service system even capable of yielding what CMS expects through mere sub-regulatory guidance?

Home-based primary care programs serving the seriously ill population, like the ACO REACH High Needs ACO Model, provide a monthly payment to cover the costs of the full team to provide home-based, team-based care.

Here’s my take:

CMS has seen the benefit of programs like the ACO High Needs ACO and similar programs in Medicare Advantage, which provide home-based, team-based, advanced primary care, and they want to see those concepts scale to fee-for-service. I see alignment here with CMS creating and expanding the advanced primary care management (APCM) codes, where . These are steps to make the fee-for-service system more value-oriented, and to provide another starting glide path towards managing patients with the long view in mind.

Palliative care is an obvious success lever in value-based care. Helping patients with serious illness better manage their chronic conditions and symptoms is often a multi-year exercise and should be inherent to how this large population is treated across the board. I’ve seen first hand the push-back.

Maybe this nudge will at least help build momentum.

Additional reading from pages 41275,6 of the Federal Register on the 2027 Home Health proposed rule:

Palliative care is defined at § 418.3 to mean ‘‘patient and family-centered care that optimizes quality of life by anticipating, preventing, and treating suffering. Palliative care throughout the continuum of illness involves addressing physical, intellectual, emotional, social, and spiritual needs and to facilitate patient autonomy, access to information, and choice.’’ We believe that this definition encompasses all the services provided under the Medicare home health benefit.
Additionally, these important interventions are often the primary reason for home health services. Section 1861(m) of the Act requires the 30-day period to include all covered home health services: skilled nursing; home health aide; physical therapy; speech and language pathology; occupational therapy; medical social services, and medical supplies.
Skilled nursing services can address advanced symptom management, including specialized care to manage pain, nausea and vomiting, depression and anxiety, and respiratory distress. This may also include medication management to monitor therapeutic and adverse effects and review and adjust medications in coordination with allowed practitioners.
Medical social services can help address advance care planning needs (including discussion on transition to hospice) as well as offer referrals for social and emotional support for families and caregivers.
Physical therapists (PTs), occupational therapists (OTs), and speech language pathologists (SLPs) enhance patient quality of life, comfort, and dignity by maximizing functional independence and managing symptoms. PTs focus on mobility, pain management, and safe transfers, while OTs specialize in adapting activities of daily living (ADLs) and environments to maintain independence for as long as possible. SLPs support safe eating and drinking and help facilitate communication and decision making for those patients with deficits….
CMS, pages 41276 and 41277 of the document on the Federal Register (pages 60-61 if you download the pdf).

Talk with Dana Strauss on Pensight

You can find all the ways to follow my work and explore my other digital spaces right here. If you want to pick my brain or dive deeper into a specific topic 1:1, you can also use this link to book a dedicated session and get my undivided attention.

links.danastrauss.com

Sources & further reading

The rules this piece is about:

📄 Calendar Year 2027 Home Health Prospective Payment System (HH PPS) Rate Update (CMS-1844-P) — Centers for Medicare & Medicaid Services, issued July 1, 2026, published in the Federal Register July 6, 2026. The palliative care discussion is Section III.F, "Palliative Care Services as Home Health Services." Read the rule · CMS fact sheet · CMS press release
📄 FY 2027 Hospice Wage Index and Payment Rate Update — Centers for Medicare & Medicaid Services, Federal Register, April 6, 2026. This is where the formal palliative care Request for Information lives (Section III.E.1, "Ways To Enhance the Provision of Palliative Care Outside of Hospice Care"). Its questions on billing, denials, and unbillable team members are the clearest read on CMS's thinking. Read the rule · full PDF · note: this RFI's comment period already closed (June 1, 2026).

Where to actually comment (this is the open door):

🗳️ Comments on the home health rule are due 5 p.m. EDT, August 31, 2026, referencing file code CMS-1844-P. Use the "Submit a formal comment" button on the Federal Register page, or search CMS-1844-P at regulations.gov.

The coverage rules and law I reference:

The "skilled service" test and home health coverage qualifications — 42 CFR § 409.32 (definition of a skilled service) and § 409.42 (conditions a beneficiary must meet), on the eCFR.
Where the promised palliative care examples will actually appear — the Medicare Benefit Policy Manual (Pub. 100-02), Chapter 7, Home Health Services (direct link to the CMS PDF).
The end of Chevron deference, in my one-line aside — Loper Bright Enterprises v. Raimondo (U.S. Supreme Court, 2024).

To understand palliative care (start here):

Center to Advance Palliative Care (CAPC) — the field's central hub for clinicians and health systems, plus the patient-facing explainer at GetPalliativeCare.org. The single best starting point if palliative care still feels fuzzy.
Clinical Practice Guidelines for Quality Palliative Care, 4th edition — the National Coalition for Hospice and Palliative Care "NCP Guidelines," the consensus standard for what quality palliative care actually is (a 5th edition is in the works). Read the guidelines
CAPC Serious Illness Scorecard — a state-by-state look at palliative care capacity. Pull your own state before you write a comment letter and you'll have specifics instead of generalities.
Palliative care fact sheet — World Health Organization — for the clean global definition and the "quality of life across serious illness, not just the end of it" framing. Read it
American Academy of Hospice and Palliative Medicine (AAHPM) and the National Alliance for Care at Home (the merged NAHC + NHPCO) — the specialty society and the care-at-home advocacy body, both worth watching as this rule moves toward a final version.

The evidence that it's valuable, not just nice:

Temel JS, et al. Early Palliative Care for Patients with Metastatic Non–Small-Cell Lung Cancer — New England Journal of Medicine, 2010;363:733–742. The landmark trial: early palliative care improved quality of life and patients lived longer than those getting standard care alone. Read the study
Ariadne Labs — Serious Illness Care Program — the research showing structured serious-illness conversations happen earlier and cut patient anxiety and depression.

The framework I use (the "5 Whys" at the bedside):

The Serious Illness Conversation Guide — Ariadne Labs — is the clinician version of what the 5 Whys does in my heart-failure example: a short, structured set of questions that walks you from the surface problem to what the patient actually wants. Download the guide

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Don't Compare It To The Almighty. Compare It To The Alternative

Dana Prommel Strauss — Mon, 29 Jun 2026 00:15:00 +0000

Sponsored by Saatva. Use my link for 15% off! In a showroom, tell them Dr. Dana Strauss sent you for the same 15% discount. I purchased mine in the Paramus, N.J. store a couple of years ago and couldn’t be happier with it.

“Better than it is today” is the real baseline for clinical technology

Do you feel like there is a persistent disconnect in healthcare where the people who design the systems don’t talk enough to the clinicians doing the actual work? They talk to each other instead, trading ideas, insights, and predictions on insider podcasts, in investor memos, and inside essays that never reach the clinical frontline.

For clinicians, understanding these high-level system trends and financial models is a major competitive advantage. Gaining this “systems knowledge” positions you to advance your career anywhere in healthcare, whether that means stepping into executive leadership or driving high-value initiatives within your present clinical role for your current employer.

Right now, tech investors like Marc Andreessen and Ben Horowitz write influential essays on how AI should reshape medicine, while federal policymakers at CMS draft thousands of pages of payment regulations. More and more, industry insurgents see the value in debating these massive shifts publicly so that anyone paying attention can learn.

That is exactly why I write this newsletter. I invest the time to track these policies and synthesize what is being said across all of these different venues. By mixing my own policy expertise with these public signals, I can often identify what actually matters long before it becomes conventional wisdom. I do the heavy lifting to translate these complex trends so that busy clinicians can build the systems literacy they need to level up their careers.

This week, two pieces of content I consumed stood out. One came from deep inside clinical medicine, and the other came from the venture capital side. They approach AI from completely different angles yet land in nearly the exact same place. When a crossover like that happens, it deserves our attention.

Made with Claude Design

The underlying theme of both pieces brings to mind a favorite political maxim of Joe Biden, a line he frequently used on the campaign trail: "Don't compare me to the Almighty, compare me to the alternative."

When it comes to deploying technology on the medical frontline, demanding absolute perfection from digital tools is a trap. The real baseline we should be measuring against isn't a flawless utopia; it is simply the reality of the alternative we are working in right now.

Dr. Bob Wachter on "Healthcare is Hard: A Podcast for Insiders" (hosted by Keith Figlioli)

I first caught wind of this discussion on the Healthcare is Hard podcast last week, where Dr. Bob Wachter spent nearly an hour breaking down what technology is actually doing to medicine. If you aren't familiar with him, he is the UCSF physician who coined the term "hospitalist" and has spent 15 years studying digital health.

His perspective is incredibly grounding for anyone feeling overwhelmed by the constant noise around AI. Here is what matters for your day-to-day work:

"Better than today" is the right bar, not perfection. If you are already expected to digest a massive chart in minutes and keep pace with an endless flood of literature, tools that summarize and support—even imperfectly—are a massive step forward. The real risk isn’t flawed technology; it is letting a few headline mistakes halt progress that is fundamentally helpful.
Electronic health records were just the floor, not the ceiling. Up until now, electronic records have felt like a burden. But their actual purpose was to build the digital foundation so that truly useful tools could finally emerge.

Made with Claude Desgin

Patients are already changing the dynamic. Patients are arriving at appointments with AI-generated symptom maps and second opinions. This shifts the dynamic of the visit and adds pressure to already tight time slots.
Primary care gets elevated. He frames AI as a "specialist in your pocket," allowing primary care providers to manage much more complex cases natively.

Eric Larsen on Healthcare’s "Oppenheimer Moment"

The second perspective comes from a 369-page essay by Eric Larsen, President of TowerBrook Advisors. I first caught wind of this when I listened to his interview on the Heart of Healthcare podcast this week, which immediately sent me clicking over to read his full write-up. It reads like a field report from the middle of a storm, covering everything from economics to clinical tech.

You do not have to read all 369 pages to get the value out of it. In fact, if you want to absorb it during your commute or while folding laundry, you can use a free tool called Google NotebookLM to turn the entire PDF into a realistic, two-host audio podcast. All you do is upload the essay, click Audio Overview in the Studio panel, and hit Customize to tell it exactly what to focus on. Using a prompt like this works perfectly for our purposes:

"Focus on clinical AI, the liability arguments, the changing role of the clinician, and behavioral health. Emphasize practical implications for working clinicians. Skip the abstract history and geopolitics."

Select the Deep Dive option, and in a few minutes, you will have a customized audio conversation you can play on the go. You can even use the interactive mode to interrupt the hosts and ask follow-up questions.

(As a quick reminder on doing this responsibly: creating an audio version for your own learning is perfectly fine for personal use, but be sure to point colleagues to the original essay source if they want to generate their own copy.)

Whether you listen to it or scan it, or don’t have a chance to get around to either, here are my core takeaways specifically for clinicians, in two minutes:

The biggest bottleneck right now is liability. The technology is already good enough in narrow areas. The real question is who agrees to carry the legal responsibility when using it. The organizations that step up and assume that liability will win the market. Once that happens, the standard of care flips. Using AI becomes the baseline protection, and not using it becomes the mistake, because if a clinician bypasses the tool and misses something the technology would have caught, they are suddenly legally exposed.

Made with Claude Design

You become the clinical anchor, not the data entry clerk. Instead of losing hours to hunting down templates or copy-pasting notes, you step into the role of the expert evaluator. Your value shifts from doing the manual grunt work to verifying the accuracy of the tools—like auditing an AI-generated patient summary before it goes into the chart, validating a diagnostic recommendation against your own clinical judgment, or guiding how a communication model interacts with your patients. You are the final safety check that ensures the technology is clinically sound and safe.
The quickest win is in behavioral health. The near-term unlock is behavioral health, where AI's unlimited patience and availability meet a system that has been failing patients for decades.

Larsen is direct and critical of organized medicine, arguing that professional groups sometimes dress up self-protection as patient safety. It might make you uncomfortable, but it is worth engaging with anyway!

What This Means for Your Career

When a clinical insider like Wachter and an investor like Larsen describe the exact same trends from two completely different viewpoints, it means the shift is real.

The real risk to clinicians is not that AI will replace you. The risk is that the healthcare system moves slowly, and people outside the clinic will redraw the career landscape while you are busy focusing on your patients.

That is exactly why I write this weekly email. These insights should not be locked away in corporate board packets, podcasts meant for an investor audience, investor memos, or buried under layers of industry jargon that you do not have time to wade through. My job is to take those high-level signals, strip out the buzzwords, and translate them into exactly what they mean for your daily practice and your long-term career. The clinicians seeing patients every day are the ones whose roles are actually changing, and you deserve to see these shifts coming just as early as the people betting capital on them.

Understanding these high-level trends gives you options. The forces shifting our industry are opening up adjacent career paths that did not exist in the recent past, like clinical informatics, AI governance, product design, and strategic advisory roles.

Also, you don’t have to leave your current employer or exit clinical practice to benefit from this. Simply building this literacy lets you drive practical, high-value projects right where you are, establishing a foundation for future career optionality. For example, instead of waiting for a corporate-mandated technology roll-out to disrupt your floor, you can volunteer to pilot a new clinical protocol or champion an efficiency initiative inside your own department.

When you can look at a problem, like a bottleneck in patient discharge, and propose a workflow adjustment that uses existing tools to shave thirty minutes off the process, leadership is likely to listen. And it proves you understand how operational efficiency connects to the bottom line, repositioning you as a strategic leader.

If you’ve managed to pull off a workflow pilot or a small efficiency project in your own department, reply and tell me how you did it. I’d love to feature real frontline examples in a future essay!

Talk with Dana Strauss on Pensight

links.danastrauss.com

Sources & further reading

The two pieces of content I referenced:

🎧 A Giant Leap for Healthcare: Dr. Bob Wachter on AI, Clinical Workflows and the Patient-Doctor Relationship — Healthcare is Hard: A Podcast for Insiders (hosted by Keith Figlioli), April 16, 2026 · 46 min. Listen to the episode · Browse the show
📄 Eric Larsen, Healthcare's Oppenheimer Moment: The Industrialization of Intelligence and the Future of U.S. Healthcare — TowerBrook Healthcare Institute, June 2026. The essay is circulated by TowerBrook (where he shares it), and can also be found in the show notes of this Heart of Healthcare episode. Also, hear him unpack the argument on The Heart of Healthcare's listener Q&A episode.

Referenced:

Andreessen Horowitz (a16z) on AI in healthcare — Bio + Health hub · a strong single read: Julie Yoo, Why Will Healthcare Be the Industry That Benefits the Most from AI?
CMS payment regulations — cms.gov

The tool for creating an audio overview of content:

Google NotebookLM — notebooklm.google · Audio Overviews

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Who Decides What You Need?

Dana Prommel Strauss — Mon, 22 Jun 2026 01:24:48 +0000

When it all clicks.

Why does business news feel like it's written for people who already get it?

Morning Brew changes that.

It's a free newsletter that breaks down what's going on in business, finance, and tech — clearly, quickly, and with enough personality to keep things interesting. The result? You don't just skim headlines. You actually understand what's going on.

Try it yourself and join over 4 million professionals reading daily.

Check it out

The Need You Were Never Asked About

There's a crucial distinction between what a patient needs and what a patient wants — and it's the one almost no one is allowed to make.

A woman with stage 4 lung cancer that has spread to her brain sits with her family while the oncologist lays out the plan. Four rounds of chemotherapy, starting now. The tone is calm, kind, and certain.

Notice what nobody says. Nobody says the word "need." Nobody has to. The recommendation arrives as the plan. This is what we do next.

The oncologist isn't pressuring anyone, and that's exactly the point. The family feels guided, not pushed. That's the reason it works, and it's also why it keeps happening.

The most consequential decisions in medicine often don't feel like decisions at all. They feel like instructions. And they feel certain.

The options you were never told you had

But the choice in that room was shaped long before it reached the patient. It was shaped by everything that went unsaid, including, often, the option of doing less, on purpose. Had those options and their likely outcomes been laid out plainly, the patient and family could have made a truly informed choice: one rooted in knowledge rather than fear, and backed by the sense that whatever they chose, their physician would support them.

There are questions a patient or a loved one would need to ask, if only they knew the questions existed, or that another path was even realistic:

"When you say this is what we should do, do you mean it will cure the cancer? Or extend my life? By weeks, or by months? What will I suffer to buy that time: the pain, the nausea, the exhaustion? What are the other options, and what happens if I choose one of them instead?"

Or simply: "What would you do if this were your own mother?"

You can't weigh an option you don't know exists or that you're too afraid to ask about. And the silence right after a recommendation is itself a kind of persuasion.

This isn't an uncommon scenario. Consider patients who get stents for stable coronary disease. In one well-known study, the large majority believed the stent would lower their risk of a future heart attack, even though it wouldn't, and even though the cardiologists who referred them generally didn't believe it would either. The trials had already shown as much. The patients simply weren't told.

What "need" actually is

Need is a professional judgment, and it depends on realistic, achievable goals grounded in an evidence-based medical (and sometimes rehabilitative) prognosis.

Is cure a realistic goal? Is more time? Does this person want to die at home, surrounded by the people they love? Each of those goals points to a completely different need. And the goals belong to the patient.

Yes, a patient can want something unrealistic. That's exactly why the conversation is supposed to happen. That’s the back-and-forth where clinician and family trade what each of them knows until both understand enough to make the next best decision. But that conversation requires that the patient actually be given the knowledge. When it doesn't happen, the goals just get filled in by the person writing the treatment plan and making the referrals. That’s the one with the knowledge, and, too often, a financial stake in the answer.

Need should be close to scientific. Instead, it is almost always authored by someone other than the person who has to live, or die, with the consequences.

How necessity gets built without an argument

So how does a "need" get installed without anyone ever arguing for it? It happens through the way a recommendation is delivered.

There's a name for this: a nudge. A nudge is a feature of how a choice is presented that shifts behavior in a predictable direction without removing any options. Medicine runs on them.

The default is the strongest nudge. "We'll get you scheduled for your first round" makes the intervention the path and inaction the deviation. In other words, it’s an opt-out, not an opt-in. Framing is subtler but just as real: "70 of 100 patients do well" and "30 of 100 don't" are the same fact, yet they pull people toward different choices, and survival framing reliably nudges patients toward the more aggressive option.

Authority matters too. Said with enough certainty, a recommendation stops sounding like a recommendation at all. The white coat turns "an option" into "what's done."

But perhaps the most powerful nudge of all is the one I already described: the alternatives left off the table.

This is the layer that can feel uncomfortable to acknowledge. The people with the power to shape all of this, including what gets framed, what gets defaulted, and what gets left unsaid, are very often the same people who benefit financially when the patient says yes to the intervention. This usually isn't malice. Most clinicians barely notice they're doing it, because it's simply how they were trained to practice. Their job, as they understand it, is to treat, to act, to do. But the incentive sits there all the same, and it rarely points toward "less."

The obvious answer often isn't the evidence

It would be comforting to assume the "obvious" intervention is at least the evidence-based one. Often, it isn't.

For ordinary low back pain, imaging doesn't improve outcomes. This has been studied extensively, yet its overuse tracks with a two- to threefold rise in surgery. A scan often turns up some incidental "abnormality," usually nothing more than the normal wear of being alive, and that finding alone can leave a patient more afraid, more fragile, and more likely to spiral into procedures they never needed. The test manufactures the need.

Arthroscopy for a worn knee performs no better than a placebo procedure, and frequently leads to more surgery. A stent for stable disease carries real risk even when it goes perfectly. About 1 in 100 patients has a heart attack or stroke during or soon after the procedure, on top of the bleeding risk from the procedure itself and the blood thinners that follow.

The takeaway is that a great deal of what we do reflects habit and training far more than the highest-quality, most current evidence. And, lest we forget, doing too much is never free to those of us paying for it. That’s all of us. Overtreatment carries its own harms like cascading tests, anxiety from false alarms, and real physical damage from procedures that were never going to help.

"Medically necessary" and what that was supposed to mean

Which brings me to a phrase we have hollowed out: medically necessary.

There is such a thing as medically necessary care, and it matters enormously. Properly understood, it means care that is genuinely necessary for a person's health and judged against their actual prognosis, both medical and functional, and matched to the achievable, realistic goals shared by the patient, their care partner, and the clinician. That is a real and demanding standard, and one we should all care about: as clinicians, leaders, patients, and policymakers.

In practice, though, "medical necessity" has been bastardized into a billing term. We treat it as "what must be documented and justified to get a claim paid." That is not the same thing as proof that the right clinician applied the best available evidence to this particular person's situation.

Watch it happen in post-acute care. constantly. After a hospital stay, a patient might recover in an inpatient rehab facility, a skilled nursing facility, or at home with home health. In theory, where they go is a medical-necessity decision. But as I've seen in practice, because the overlap in where a patient could appropriately recover is so large, that distinction often barely gets made. The choice turns on who has an open bed, on a case manager's habit, on family logistics. A patient gets sent to a facility not because they medically require that intensity of care, but because their daughter works during the day and can't be home while her mother regains her strength and mobility. Oh, and they can’t afford or refuse to hire short-term help. That is a custodial need, a convenience, a real human problem, for sure. But it is not medical necessity, and we shouldn't pretend it is.

And to be clear, the answer is not "always less." A stroke patient, for example, often genuinely needs the intensity of inpatient rehab to recover the most function possible. That is exactly where they belong! The point is that care should be matched to what this person can realistically achieve, to what genuinely meets the standard of medical necessity, and to the right frequency and intensity of therapy the patient will tolerate and benefit from. Too often, referral habits, preferences, assumptions, misunderstood rules, and bed availability decide it instead.

This is why the distinction between a need and a want is one that should be getting air time.

Payers are not bottomless. Whether it's Medicare, Medicaid, a commercial insurer, or an employer's health plan, the money comes from somewhere real, like taxpayers, employers, states, and the premiums the rest of us pay. T

There is no separate, infinite account that "unnecessary" care draws down without consequence. Every dollar spent on care a fully-informed patient would not have chosen is a dollar that isn't there for care someone genuinely needs.

And the pot is under more strain than it has been in a long time. U.S. prescription drug spending hit roughly $806 billion in 2024 and is on track to pass $1 trillion in 2026. A single class of drugs (GLP-1s) ran about $132 billion in 2025 and drove nearly a third of all drug-spending growth, while insurers watched their drug costs jump more than 20% in a single year. Add the surge in acute care, high-cost oncology, neurological, and rare-disease therapies, and you have a system absorbing enormous, legitimate new expenses. And the pressure isn't only pharmaceutical: the single largest driver of projected Medicare spending growth over the next decade is, quite simply, doing more. It’s a rising volume and intensity of services. In that environment, money wasted on care that wasn’t truly needed is care someone else didn't get.

We seem to get this backwards. As a country, we decided long ago that outside of Medicaid's long-term services and supports, and some VA benefits, we don't cover custodial care. Payers, including CMS, also say they don't cover unnecessary care, the procedure a patient would have declined if they'd understood their options and their likely outcomes, and the non-medically-necessary wants of clinicians or patients. But the fact is, we ALL do pay for those things every day.

When the system spends on those things anyway, we reflexively call it the payer's failure. But payers want the money spent on what's needed. The failure happens in the room where a want was quietly dressed up as a need, and where no one was asked what they actually wanted in the first place.

That's also what makes this so hard to fix: there's no villain to point at. Everyone who holds the knowledge also carries a default consequence and an associated risk. And almost no one inside the system experiences themselves as doing this. They believe they're following the standard of care, being thorough, and being kind. They think this is what patients want.

What value was always for

This is part of what value-based care was actually for, and what the field mistranslated from the very beginning. It got sold as a way to save money, and I think that's why it hasn't landed the way it should (though I believe it still can). Value-based care, especially in the "downstream" part of healthcare, is partly an attempt to hold the system accountable for whether care matched the patient's real, achievable goals, their understood options, and their likely outcomes, rather than the provider's default plan and framing.

“Value” does not mean “cheaper.” Its definition includes the care a person would actually choose if they were fully informed. And that choice requires understanding their prognosis, every option genuinely available to them, and the outcomes and trade-offs of each, all grounded in the best available evidence. The industry hears the word "value" and reflexively translates it to "discount." That single mistranslation is why we keep failing the woman in that first room.

What matters to you

Back to the room. Listen to the silence. Now you can hear it. "We'll start with four rounds." But toward what goal? Measured against what alternative? And decided by whom?

The medicine we should want for ourselves, and should insist on for everyone, sounds different. It sounds like: Here's what you're facing. Here's what each path is likely to give you, and here's what it will cost you. Here are all of your options. The need is yours to define, so tell me what matters to you, and let's choose the next step together. The one that fits you.

When a clinician stops implying that you need this, they free themselves to ask a question palliative care has understood the power of for years: What matters to you?

It's the first step any clinician can take tomorrow. And for everyone else in healthcare like the case managers, the rehab teams, the administrators, the people who design and pay for and carry out plans of care, it is the missing perspective. Start there, and "need" stops being something done to a patient. It becomes something decided with them.

Talk with Dana Strauss on Pensight

links.danastrauss.com

Sources & further reading

The study behind the opening scene. Most people receiving chemotherapy for incurable cancer don't understand it can't cure them. Weeks JC, et al. "Patients' Expectations about Effects of Chemotherapy for Advanced Cancer." New England Journal of Medicine, 2012;367(17):1616–1625. nejm.org/doi/full/10.1056/NEJMoa1204410

Why patients think a stent does more than it does. The study that found patients believe stents prevent heart attacks while the cardiologists referring them generally don't — a textbook informed-consent gap. Rothberg MB, Sivalingam SK, Ashraf J, et al. "Patients' and Cardiologists' Perceptions of the Benefits of Percutaneous Coronary Intervention for Stable Coronary Disease." Annals of Internal Medicine, 2010;153(5):307–313. acpjournals.org/doi/10.7326/0003-4819-153-5-201009070-00005

The evidence that stents don't help in stable disease. Three landmark trials, ending with the first sham-controlled one. COURAGE: Boden WE, et al. NEJM, 2007;356(15):1503–1516. ISCHEMIA: Maron DJ, et al. NEJM, 2020;382(15):1395–1407. ORBITA: Al-Lamee R, et al. The Lancet, 2018;391(10115):31–40. nejm.org/doi/full/10.1056/NEJMoa070829 · nejm.org/doi/full/10.1056/NEJMoa1915922 · imperial.ac.uk/news/182879/study-heart-stents-stable-angina-highlights

The risk a stent carries even when it works. A plain-language summary from Harvard, with cardiologist William Boden: roughly a 1% risk of heart attack or stroke during or soon after the procedure, plus bleeding from the procedure and the blood thinners that follow. "Does a coronary stent make sense for stable angina?" Harvard Health, 2024. health.harvard.edu/heart-health/does-a-coronary-stent-make-sense-for-stable-angina

What a "nudge" actually is. The concept comes from Thaler RH and Sunstein CR, Nudge: Improving Decisions About Health, Wealth, and Happiness (2008). For how it operates in medicine — including the ladder from light "information framing" to powerful "defaults" — see the AMA Journal of Ethics: "Designing Nudges for Success in Health Care," 2020. journalofethics.ama-assn.org/article/designing-nudges-success-health-care/2020-09

Why "70 survive" and "30 die" lead to different choices. The classic study showing that framing identical outcomes as survival versus mortality flips treatment decisions — in patients and physicians alike. McNeil BJ, Pauker SG, Sox HC Jr, Tversky A. "On the Elicitation of Preferences for Alternative Therapies." New England Journal of Medicine, 1982;306(21):1259–1262. nejm.org/doi/full/10.1056/NEJM198205273062103

Habit, not evidence, driving how much care patients get. Within the same organization, low-value-service rates varied dramatically across primary care physicians — and almost none of that variation could be explained by anything measurable about the doctors themselves. Schwartz AL, Jena AB, Zaslavsky AM, McWilliams JM. "Analysis of Physician Variation in Provision of Low-Value Services." JAMA Internal Medicine, 2019;179(1):16–25. jamanetwork.com/journals/jamainternalmedicine/fullarticle/2717501

Imaging for ordinary low back pain — and the harm it can do. Routine imaging doesn't improve outcomes, tracks with a two- to threefold rise in surgery, and can leave patients more fearful and worse off after an incidental finding. Flynn TW, Smith B, Chou R. "Appropriate Use of Diagnostic Imaging in Low Back Pain: A Reminder That Unnecessary Imaging May Do as Much Harm as Good." Journal of Orthopaedic & Sports Physical Therapy, 2011;41(11):838–846. jospt.org/doi/10.2519/jospt.2011.3618

Knee surgery that works no better than a fake one. Two sham-controlled trials found arthroscopy for a degenerative knee performed no better than placebo surgery. Moseley JB, et al. "A Controlled Trial of Arthroscopic Surgery for Osteoarthritis of the Knee." NEJM, 2002;347(2):81–88. Sihvonen R, et al. "Arthroscopic Partial Meniscectomy versus Sham Surgery for a Degenerative Meniscal Tear." NEJM, 2013;369(26):2515–2524. nejm.org/doi/full/10.1056/NEJMoa013259 · nejm.org/doi/full/10.1056/NEJMoa1305189

How little evidence guides where patients recover. A systematic review of post-stroke rehabilitation found minimal evidence to determine which setting — inpatient rehab versus skilled nursing — is right for an individual patient, despite heavily overlapping populations. Alcusky M, et al. "Post-Acute Care Setting, Facility Characteristics, and Post-Stroke Outcomes: A Systematic Review." Archives of Physical Medicine and Rehabilitation, 2018. pmc.ncbi.nlm.nih.gov/articles/PMC5874162

Where the "volume and intensity" point comes from. MedPAC's finding that growth in the volume and intensity of services is the single largest driver of projected Medicare spending growth over the next decade. MedPAC, Report to the Congress: Medicare and the Health Care Delivery System, June 2026, Chapter 1. medpac.gov

The pressure on the shared pot. U.S. prescription drug spending reached $805.9 billion in 2024 (up 10.2%) and is projected to top $1 trillion in 2026, with GLP-1s alone around $132 billion and nearly a third of all drug-spending growth — while insurers' drug costs rose more than 20% in a single year. ASHP national trends report (via AJHP): news.ashp.org/.../us-drug-spending-up-10-in-2024-with-weight-loss-drugs-remaining-top-driver · 2026 projection: pharmexec.com/view/us-prescription-drug-spending-set-exceed-trillion-2026-report · Insurer trend: statnews.com/2025/12/08/health-insurers-spending-more-on-prescriptions-glp-1-drugs-cited

Where "What matters to you?" comes from. The reframe from "What's the matter?" to "What matters to you?" as the heart of shared decision making. Barry MJ, Edgman-Levitan S. "Shared Decision Making — The Pinnacle of Patient-Centered Care." New England Journal of Medicine, 2012;366(9):780–781. nejm.org/doi/full/10.1056/NEJMp1109283

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Patient Safety is the Ultimate Value-Based Care Strategy

Dana Prommel Strauss — Mon, 15 Jun 2026 00:15:00 +0000

AI Is About to Force Healthcare to Confront Patient Harm at Scale

And the regulators are already moving in the same direction.

I’m calling this now. One of AI's most valuable use cases in healthcare will be exposing how often patients are harmed in the settings we trust most. And that will be the forcing function for the kind of systemic change that’s desperately needed.

We talk constantly about AI lightening the documentation load. Absolutely! It’s important, low-hanging fruit. Burnout is real. The clerical burden is crushing. Healthcare desperately needs workflow (and often care) redesign. But the most transformative use of AI in healthcare may be something less comfortable to talk about. That’s AI identifying patients who were harmed by the care they did or did not receive.

That was my biggest takeaway from the KFF Business of Health podcast episode featuring Dr. David Bates, "Can AI Break the Measurement Paradigm?" The conversation named something healthcare still struggles to confront and prioritize in a standardized way.

We talk about "quality" constantly.

But much of what we measure is process metrics, compliance activity, documentation requirements, and lagging indicators. The actual patient experience inside hospitals can look very different. The research is blunt: roughly 1 in 4 hospitalized patients experiences harm.

Twenty-five percent.

25%!

If one in four patients are harmed during a hospitalization, improving patient safety needs to be the operational challenge.

And most of that harm is still invisible.

What a High Reliability Organization (HRO) journey actually teaches you

Earlier in my career, I was fortunate to be part of a hospital system on an HRO journey while we were simultaneously operating in value-based care arrangements. One of the first things you learn on a real HRO journey is deeply counterintuitive:

Patient safety events initially go up. That’s a reason to keep going on the journey. Why does it go up? Because people finally feel safe enough to report what was already happening. That is one of the hardest truths in healthcare. Harm is often all around us, but it’s underreported because people fear retribution, blame, embarrassment, litigation, peer judgment, leadership fallout, or being labeled "the problem."

In weak “safety cultures,” silence becomes normalized and sometimes even expected. “Near misses” disappear. Patterns stay hidden. Small failures compound. And systems never learn. True HRO transformation requires the opposite:

Daily reporting
Constant surfacing of near misses
Psychological safety
Structured root cause analysis
Relentless transparency
A shared understanding that reporting is not betrayal. It is protection.

That is why we call it a journey. It takes years.

Years to build trust.

Years to normalize transparency.

Years to redesign workflows.

Years to find the structural weaknesses buried deep inside operational processes.

But when organizations stay committed long enough, the root causes start to surface. And many of them are structural, not individual. They include things like:

Communication failures
Unsafe handoffs
Poor workflow design
Medication management gaps
Fragmented transitions
Data buried in disconnected systems
Staffing strain
Alert fatigue
No real-time visibility into deterioration
Excessive top-down hierarchy

Healthcare treats safety events as isolated human mistakes when so many are predictable system failures. That is exactly where AI becomes transformational.

Not faster notes. Visible harm.

AI may finally let health systems identify patterns of harm at scale and in real time.

Right now, organizations sit on enormous amounts of data trapped inside the EHR. For years, most of it has been operationally unusable.

Structured fields. Unstructured notes. Radiology reports. Medication histories. Nursing documentation. Discharge summaries. Lab trends. Consult notes. Follow-up recommendations.

We digitized healthcare and, in many ways, simply turned paper chaos into digital chaos.

The EHR era built the foundation. AI may finally operationalize it.

Here is the connection I keep coming back to.

Remember the counterintuitive truth from the HRO journey? Events only surface when people feel safe enough to report them. AI offers a second path to that same visibility. It doesn't wait for a clinician to feel safe enough to file a report. It reads the record itself.

It can ingest fragmented information and detect subtle patterns humans cannot consistently catch across thousands or millions of encounters. This includes things like medication-related issues, missed follow-up, delayed interventions, early deterioration, diagnostic drift, unsafe transitions, and the compounding low-level failures that eventually become catastrophic outcomes.

And it can do this continuously.

Healthcare has historically reviewed safety retrospectively. When it’s too late to prevent a serious safety event from happening in the first place. After discharge. After readmission. After litigation. After mortality review. After the preventable harm already occurred.

AI creates the possibility of catching those signals while there is still time to intervene.

CMS is already moving

Here is the part most people missed in the noise of the 2026 OPPS final rule.

For years, the Overall Hospital Quality Star Rating let strong performance in one area paper over weakness in another. In terms of patient safety, that meant a hospital could land in the lowest-performing quartile on the Safety of Care measure, which means they are in the bottom 25% on healthcare-associated infections and patient harm, and still earn an overall rating of five stars. Carried by good numbers everywhere else, it was easy for a consumer to overlook the low rating in Safety of Care.

CMS called out the problem and closed the gap. In the CY 2026 final rule, the agency finalized a two-stage change:

2026 ratings: any hospital in the lowest Safety of Care quartile (with at least three safety measures) is capped at four stars regardless of how strong the hospital looks everywhere else.
2027 and beyond: that cap becomes a blanket one-star reduction. Bottom quartile on safety, and your overall rating drops a full star, with one star as the floor.

CMS estimates the second stage alone will pull down roughly 459 hospitals. THAT MANY HOSPITALS score in the bottom quartile of safety! Read the language the agency used and the intent is hard to miss. CMS tied the change directly to its "commitment to improving health outcomes and advancing patient safety."

This also represents a philosophical shift in what "quality" is allowed to mean.

And I don't think the timing is an accident.

Look at what's converging. The research says one in four patients is harmed. The tools to see that harm continuously, at scale, and in real time, are arriving right now. And CMS just built a rule that turns safety into the thing that caps your reputation.

This reads like a rule written in anticipation of what is about to become much easier to measure.

For most of the EHR era, harm was hard to surface and easy to externalize. When AI makes harm patterns visible across millions of encounters, "we didn't know" stops being a defense. I read this as CMS effectively putting hospitals on notice. The direction is set. The incentive is public and reputational.

No health system will be able to say it wasn't told to look hard at its own safety practices.

The economics finally line up

Patient safety journeys are, in many ways, de facto value-based care exercises. Hear me out.

There is no billable CPT code for becoming a High Reliability Organization. No fee-for-service reward for reducing near misses. No reimbursement line for building psychological safety across clinical teams.

Historically, healthcare economics did not align cleanly with harm reduction. Preventable medical errors cost the system tens of billions of dollars a year — but many of those costs were shifted outward, to payers, employers, patients, families, and society. That weakened the direct financial incentive for hospitals to aggressively invest in safety.

Value-based care flips that.

In risk-bearing arrangements, preventable harm destroys margin. Unsafe care raises total cost of care. Complications drive utilization. Readmissions rise. Length of stay expands. Downstream costs compound.

The organizations furthest along in patient safety and HRO principles are already positioning themselves better for the future of value-based reimbursement.

Safer care is lower-cost care. But more importantly, safer care saves lives and reduces suffering.

Now stack the three forces together. AI is making harm visible. CMS is making safety the gate on your public rating. Value-based care is making harm a direct hit to your margin. The moral case, the regulatory case, and the financial case for patient safety are pointing the same direction.

What this means right now

For decades, organizations leaned on manual reporting to find safety risk. HRO work is an investment in time and money, and requires an all-of-health-system-approach. But humans still miss things. They get overwhelmed, they normalize dysfunction, and adapt to unsafe systems because they have no choice.

AI does not replace culture, leadership, or accountability when applied to patient safety. However, it should dramatically increase visibility into hidden risk of harm.

This is the moment for owners, operators, executives, and policymakers to lean in. Early movers may redesign care delivery around safety intelligence itself:

Real-time harm surveillance
Predictive deterioration monitoring
Closed-loop follow-up systems
AI-assisted medication management
Continuous risk detection
Dynamic safety workflows

This calls for a celebration! This is where healthcare is headed, and the organizations that embrace it earliest may become the highest performers in both quality and financial sustainability as the market increasingly rewards better outcomes at lower total cost. And if the prevention of harm is not one of the outcomes we care about most, then what are we even doing?

We should want hospitals and inpatient settings to be obsessed with patient safety.

Especially for the frail, the medically complex, and the vulnerable, who suffer some of the worst consequences when systems fail.

One of the most important eras of AI in healthcare will be exposing where care delivery is failing patients. CMS is already writing the rules for the world that exposure creates. After that comes the transformation many of us have hoped for all along.

Talk with Dana Strauss on Pensight

links.danastrauss.com

If you work in a hospital, here's how to bring this up now

Maybe you're a bedside nurse. A hospitalist. A quality director. A service-line leader. An executive.

Wherever you sit, you can move this conversation today. You don't need a budget or a mandate to start.

Look up your own numbers. Pull your hospital's current Overall Star Rating and, specifically, its Safety of Care performance on Care Compare. Know whether you're near the bottom quartile before CMS tells the public in 2027.
Name the stakes in the room's language. With leadership, frame safety as the gate on your public rating and a direct hit to margin under risk. It’s a reputational and financial project,
Report the thing you've been sitting on. The near miss. The workaround. The handoff that almost went wrong. Surfacing it is the raw material every improvement depends on.
Ask the AI question differently. Your organization is already at least talking about AI for documentation and efficiency. Ask the harder one: what are we doing to surface harm with the data we already have?
Find the process, not the person. When something goes wrong, push the conversation past "who" toward "what in the system made this likely." That single reframe is the start of every HRO journey.

You don't have to fix the culture this week. You just have to refuse to let the silence stay normal.

Start one conversation. Then another.

That is how every safety transformation actually begins.

Sources & further reading

The podcast that started this. "Can AI Break the 'Measurement Paradigm?'" — Chip Kahn in conversation with Dr. David Bates, KFF's The Business of Health (AI series, Episode 7). kff.org/other-health/can-ai-break-the-measurement-paradigm
Where the 1-in-4 number comes from. Bates DW, et al. "The Safety of Inpatient Health Care." New England Journal of Medicine, 2023;388(2):142–153. The study that found roughly a quarter of hospital admissions involved an adverse event. nejm.org/doi/full/10.1056/NEJMsa2206117
The CMS rule, in CMS's own words. "CMS Empowers Patients and Boosts Transparency by Modernizing Hospital Payments" — the agency's announcement of the CY 2026 OPPS final rule, including the Star Rating change. cms.gov/newsroom/press-releases/cms-empowers-patients-boosts-transparency-modernizing-hospital-payments
The technical details of the two-stage change. CMS fact sheet on the CY 2026 OPPS/ASC rule, laying out the four-star cap (2026) and the one-star reduction (2027 and beyond). cms.gov/newsroom/fact-sheets/calendar-year-2026-hospital-outpatient-prospective-payment-system-opps-ambulatory-surgical-center-0
Where the idea of a High Reliability Organization comes from. The concept was coined by a research group at UC Berkeley — Todd LaPorte, Gene Rochlin, and Karlene Roberts — who studied error-free operations in aircraft carriers, air traffic control, and nuclear power starting in 1984. Foundational articulation: Roberts KH. "Some Characteristics of One Type of High Reliability Organization." Organization Science, 1990;1(2):160–176. A plain-language overview is here: AHRQ PSNet, "High Reliability." psnet.ahrq.gov/primer/high-reliability
HRO translated for hospitals. Chassin MR, Loeb JM. "High-Reliability Health Care: Getting There from Here." The Milbank Quarterly, 2013;91(3):459–490. The paper that brought HRO thinking — leadership commitment to zero harm, a true safety culture, robust process improvement — into mainstream hospital practice. pmc.ncbi.nlm.nih.gov/articles/PMC3790522
How many hospitals we're talking about. American Hospital Association, Fast Facts on U.S. Hospitals, 2026: 6,093 hospitals in the U.S., of which 5,121 are community hospitals (the acute-care group most affected by the Star Rating change). Useful for putting the ~459 hospitals hit by Stage 2 in context. aha.org/statistics/fast-facts-us-hospitals
What the Safety of Care measures actually are. The Star Rating's Safety of Care group is built mostly from outcome measures: the CDC/NHSN healthcare-associated infections (CLABSI, CAUTI, surgical site infection, MRSA bacteremia, and C. diff), the AHRQ PSI-90 patient-safety composite, and hip/knee complication rates. CMS overview of the measure groups: data.cms.gov/provider-data/topics/hospitals/overall-hospital-quality-star-rating · Measure definitions: cms.gov/medicare/quality/value-based-programs/hospital-acquired-conditions

Read more from me about the HRO journey in the context of hospital mobility here:

Hospital Mobility: Cost or Profit Center?

The case for building a program today

Timeless Autonomy • Dana Prommel Strauss

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

How to Close the Knowledge Asymmetry Gap in Healthcare

Dana Prommel Strauss — Mon, 08 Jun 2026 00:15:00 +0000

A New Space for Quick Insights & Real-Time Thoughts

While this essay publication will remain the exclusive home for my deep-dive, long-form, evergreen essays, I’ve found myself wanting a space to share quicker, real-time ideas between editions.

To do that, I’ve set up a companion space on Substack. I’ll be using it specifically to post shorter articles, quick clinical and industry takes, and day-to-day insights on healthcare policy and strategy.

If you want to grab those shorter updates via Substack “Articles” and “Notes” and join the discussion, come follow along!

👉 Dana Strauss: Health, And... on Substack

Break the Invisible Ceiling in Healthcare

Why knowledge asymmetry, not ability, limits healthcare careers (and the blueprint for breaking through it).

Picture someone you know. Maybe it's you. They're good at their job, they've earned a solid income for twenty years, and they're still quietly anxious about money. They're doing fine on the surface, yet they feel behind somehow, with no real plan and most decisions made on the fly. There's a vague sense that other people figured out something they never did.

That person is plenty intelligent. The information they were missing was never hidden. Index funds, retirement accounts, the math of compounding, the true cost of fees, all of it sat in public and free the entire time. They lacked just one thing: an understanding that financial institutions and certified financial planners held and they did not.

We have a precise name for that. Knowledge asymmetry. And personal finance is the one place almost everyone agrees the gap can be closed. People teach themselves this material all the time. It takes effort and it takes time, yet the door is open, and walking through it changes the trajectory of a life. When you retire. How much fear you carry into your sixties.

Let’s talk about a different gap. One that's quietly setting the ceiling on your career, that almost no one names, and that, like the money one, is far more closable than it feels.

Attack the informational gap

Start with the bigger idea. In most areas of modern life, the difference between people comes down mostly to knowledge asymmetry: who knows what, how early they know it, how well they read it, and whether they can act on it. The person on the favorable side of that asymmetry gets better outcomes, because they can see the whole board while everyone else plays half blind.

Knowledge, though, comes in different kinds, and they close in different ways.

There's informational knowledge: how a system works, what the incentives are, what the words mean. You close that gap by reading, by asking, by finding the right person to explain it. It's cheap and it's fast.

There's also experiential knowledge: judgment, pattern recognition, the instinct for a room that comes only from having sat in a hundred of them. You can't download it. It takes reps, and reps take time.

Real leverage goes to the people who can tell these two apart, and who then attack the informational gap aggressively, because it's wildly underpriced relative to what it unlocks.

The mirror

Healthcare is the ultimate economic asymmetry because you are trapped inside the asset being traded. You cannot be a detached, rational consumer when the product being bargained over is your own survival.

Think about a patient. They arrive, often frightened and often rushed, without the vocabulary, without a map of the system, without any view of the incentives shaping the care they're being offered. The clinician across from them holds all of it. That gap shapes outcomes: what gets asked, what gets caught, what gets agreed to.

For the first time, that patient gap is genuinely shrinking. AI can translate the jargon on a discharge summary, suggest the three questions someone should walk in with, and surface what a short visit had no time to cover. None of this turns the patient into a clinician, but we have to admit that it makes them less vulnerable, and less vulnerable is the entire point.

So here's the question I want to turn back on you. If a patient can close their gap, what about you?

A quick word before that lands, because not everyone reading this is a clinician. I'll keep using clinicians as the running example, since theirs is the sharpest version of it, but if you work anywhere in healthcare, this is about you too. The coder, the nurse manager, the revenue cycle analyst, whatever your corner of the system is: you hold deep, hard earned knowledge of it, and you sit on the short side of the same larger gap. Wherever the example says clinician, read your own role into it.

There’s an uncomfortable irony at play here. The very person who closes a patient’s knowledge gap every morning is the exact same person sitting on the wrong side of a much larger one the moment they look at the broader healthcare economy.

Across the table from you sit your employer, the payers, the policymakers, the investors, the consultants, the technology companies, and the executives setting strategy. They operate with a fluency in reimbursement, incentives, operations, capital, and market dynamics that you were almost certainly never taught. This has little to do with intelligence. Your training and your role were built, correctly, around doing your job well: caring for patients, running the floor, closing the claims, keeping the place moving. They were never built to teach you how the system that employs you actually works.

That gap is expensive. It's why leadership decisions feel arbitrary, or even perhaps hostile. It's why the path into bigger, broader, or nonclinical roles feels gated. It's why capable people across healthcare hit a ceiling and quietly conclude the ceiling is theirs, when really it's just the edge of what they were ever shown.

Here’s the truth: Deep expertise creates credibility, and systems knowledge creates leverage. For a clinician, that expertise is clinical. For another, it might be operational, financial, technical, or relational. The structure is identical in every case. You've spent years building the first kind. Almost no one ever offered you the second.

Here's what "systems knowledge" actually is

So let me say plainly what that second thing is, because it's the whole point. Systems knowledge is the operating logic running underneath everything you do at work. Healthcare is the only place in the economy where you can spend your entire life living in the neighborhood and still not know where any of the streets lead.

There are reasons your department got cut while another expanded. There are reasons a sensible improvement never gets funded, reasons your employer suddenly cares about one metric and forgets another, reasons the role you want exists at one organization and nowhere near you. All of it traces back to a small set of forces that include how money flows, who actually holds the power to decide, what incentives are pulling on whom, what the regulators just changed, where the market is moving. When you can read those forces, a decision that felt arbitrary or even hostile suddenly makes complete sense, and you understand precisely why it was always going to happen.

This is why it belongs in the category of things you simply must know. These forces act on you whether you understand them or not.

The other option is staying ignorant. If you choose that, you play the game with the board turned away from you while the people across the table read it in full view. Your compensation, your workload, your autonomy, and your ceiling are all set by a logic you were never taught to recognize. Most people in healthcare spend an entire career experiencing the system. Very few ever learn to read it, and the distance between those two people decides whether someone feels acted upon or finally feels able to act.

Here's what makes it learnable. Clinical mastery takes years of compounding, patient by patient experience, because it lives in the physical world. It's built rep by rep, case by case, steeped in human nuance.

But systems knowledge lives somewhere else. It's information. It's a finite, mappable body of patterns, vocabulary, and incentives that can be organized, sequenced, and handed to another person. That's exactly why it took me ten years to assemble alone in my own brain.

And here's what makes the whole thing worth caring about. Someone who holds both kinds of knowledge is unstoppable.

This combination is your ultimate leverage. The executives, policymakers, and investors across the table might understand the business, but they rarely understand the frontline. They cannot fake your credibility, and they can never retroactively buy the years you’ve spent seeing how healthcare actually works. This might include work in the clinic, one the revenue cycle, or in the patient's home. When you add a deep understanding of the system to your real-world experience, you become the rarest asset in the room.

You need a map

So where does this knowledge actually live? If you wanted a map of the territory you were never handed, it looks roughly like this.

Money, reimbursement, and capital. This is the operating logic underneath every decision your organization makes. How does it actually earn? Fee for service, value based care, Medicare Advantage, risk contracts, margins. And one layer up, how is it financed and owned? Private equity, venture, mergers, and the question of who holds the risk and why. Understand the money, and behavior that looked random starts to look rational.

Operations. This is where many leaders are made: throughput, staffing models, workflow, care transitions, and the quality metrics that organizations live and die by. It's the most direct bridge from frontline work to leadership, because it's the language of the problems executives are judged on.

Organizational power and decision making. This is the layer nobody admits exists, the question of how decisions actually get made. Budget cycles, who holds the pen, which targets a leader is chasing, the politics of getting something approved. Once you can see this, the question "why did they decide that?" stops being a mystery.

Policy and regulation. This is where entire industries and roles are born. CMS and CMMI, prior authorization trends, interoperability rules, quality programs. Learn to read policy and who holds what authority, and you can see where healthcare is heading before it arrives, which is where opportunity comes from.

Technology and informatics. This is the new mediator of nearly all care. What matters is systems understanding: how the EHR shapes behavior, how data moves or fails to move, and where AI genuinely changes a workflow versus where it's only theater.

And here's the one I'd weight above all the others, because it multiplies every item above it.

Communication and translation. Most people in healthcare are overflowing with insight. You see things every day that the people allocating resources never will: where the workflow actually breaks, what the patient actually experiences, why a great idea from above will fail the moment it reaches the patient. The valuable, scarce skill is rendering all of it in the language of the people who control budgets, strategy, and headcount.

Those people speak a different language. They think in margin, risk, throughput, return on investment, downstream cost. When you walk into that room and frame a problem in the terms of your own world, saying that something is bad for patients or unsafe or exhausting, the concern is real, but it still fails to move money.

Now imagine the same person framing the same problem this way instead: this discharge bottleneck is costing us roughly this many bed days a month and exposing us to readmission penalties, and here's a workflow fix and what it saves and in what time period. It's the very same observation. The second version is the one that gets heard, and the one that gets funded.

That's what translation is: moving an idea across the boundary between the clinical world and the business, technical, and executive worlds, in both directions. Making clinical reality legible to a chief financial officer, and making a strategy deck legible to a nursing unit. Almost everyone in healthcare is fluent in only their own domain. The rare few who are fluent in several become the connective tissue the whole system runs on, and they get pulled into rooms, projects, and roles that the rest never even see.

It's also the most learnable of the six and the fastest to compound. It's a craft, and like any craft, you build it by practicing: writing a clear memo on a single page, presenting to a nonclinical audience, framing a clinical problem as a business problem, getting a complicated idea onto one slide. It also happens to be something AI is unusually good at helping with, whether you need it for drafting, tightening, reframing for a different audience, or even playing the skeptical executive so you can rehearse. Knowing reimbursement cold is worth very little if you can't turn it into a proposal that lands. Translation is the multiplier on everything else you learn.

How to future-proof your expertise

Which brings me to what's genuinely new.

Closing these gaps used to require things like an expensive second degree, an insider network, and years of being welcomed into the right rooms. AI has changed the economics of explanation. It can decode the jargon in a payer contract, compress a long policy proposal into something you'll actually retain, simulate a business scenario, and build you a sequenced learning path instead of leaving you to forage.

Here's an important takeaway:

AI narrows informational asymmetry far faster than it narrows experiential asymmetry.

It can shrink the learnable gap, the what and the why and the vocabulary, from years down to weeks. It cannot shrink the earned gap, the judgment that comes only from reps.

Here's the part almost no one says out loud. As the informational gap collapses, the value of the experiential gap climbs. The years you spent at the bedside, in the revenue cycle, or on the unit did not lose value when AI arrived. They gained it, because everything around them grew cheap while they stayed scarce. AI commoditized the context around your expertise. Your expertise itself became rarer.

AI is also the same tool that lowers the cost of learning while it lowers the cost of confident nonsense. AI is incredibly advanced, which means that for now, its failures are just as articulate as its successes. It will hand you an oversight with the exact same flawless delivery as a breakthrough. Since anyone can access these models, access is a commodity. The real skill is knowing how to vet the output: thinking in probabilities, cross referencing systemic inputs, and ensuring your own competence stays one step ahead of the machine's capabilities.

Where to start

If you're wondering where to begin, start with a bet most people get wrong. They reach for another credential, or they go deep on operations, when the highest return by far comes from two things: understanding the money, and learning to translate. Begin there, and the rest compounds faster.

Begin with the incentives. Learn who gets paid, how they get paid, and what they're optimizing for. Almost everything downstream makes sense once you can see that.

Then learn the language. Vocabulary is the key to the room. Without it, strategy conversations stay opaque and opportunities stay invisible even when they're sitting right in front of you.

Change your inputs. Follow the operators, the founders, the payer executives, the policy writers. Your mental models drift toward whatever you read.

Practice translation on purpose. Take something you understand deeply and force yourself to explain it to an imaginary chief financial officer. Then to a software engineer. Then to a patient.

And apply it in public. Write the post. Volunteer for the project that reaches outside your department. Raise your hand for the committee. Knowledge compounds far faster when it's visible than when it stays private.

Here's what I most want you to take from all of this. You are far more equipped for this than you have been led to believe. You already carry the half that takes the longest to earn, the credibility that comes from doing real work in a real corner of the system. The other half is information, and information has never been cheaper, faster, or more learnable than it is right now. The barrier was never your intelligence, and it was never access. It was only ever that no one sat you down and showed you what to look at.

I'd be doing you a disservice to skip one thing, though. You can build all of this yourself. None of it is secret, and no degree is gatekeeping it. I'm proof of that, since I assembled this map on my own. But self direction carries a hidden cost, and the studying itself turns out to be the easy part. The hard part is everything around it.

Filtering the noise. Spending months just figuring out what is worth learning at all, wading through an endless ocean of articles, podcasts, and earnings calls with no reliable way to separate signal from noise.
Finding what moves the needle. Learning the hard way, usually by guessing wrong, the difference between knowledge that actually changes things and knowledge that is merely interesting.
Translating it into leverage. Figuring out how to position what you know so it reads as a genuine differentiator. This is the piece most people never crack on their own.

It is doable, but it is slow. It cost me years of my life, on top of full work days, to figure it all out. So I won't pretend you can skip the whole journey and become an executive by Friday. The truth is simpler than that.

The future of healthcare will belong to those who aggressively close the gap between what they know and what the system around them knows.

So begin. Pull one thread and follow it. You’ll be surprised how quickly the picture starts to resolve, and how much of it you were already half-seeing.

What I keep coming back to is a question I can’t quite put down: What would it have been worth to me, ten years ago, to have someone simply hand me the map? To point and say: learn this first, ignore that, here is what it means, and here is why it matters. I never had that. Almost no one in healthcare ever does.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Value-Based Care Lit the Match. Precision Health Is the Accelerant.

Dana Prommel Strauss — Mon, 01 Jun 2026 00:15:00 +0000

VBC Lit the Match. Personalized Medicine Is the Accelerant.

Why my partner is right that nothing much has changed yet, and why I think he's about to be wrong.

My partner spends his days in the rooms where the grand theories of healthcare policy go to face reality. After thirty years as a nursing home social worker, and now in hospice, he has seen exactly how the system treats its most vulnerable.

So when I get excited about value-based care—about a system designed to reward keeping people well rather than tallying up procedures—he gives me a look I’ve come to know well.

"Dana," he says, "I've been doing this for three decades. I’ve watched you work in value-based care for one. On the ground, nothing has changed."

And when I push, he doubles down, conveying that we are dealing with deeply ingrained legacy expectations. This generation has spent decades being conditioned to want constant treatment and endless testing. Until that consumer demand naturally shifts, the game won't change.

He’s right about a lot of it from his lens. He sees the absolute downstream results of our delivery system and its incentives. But working now in hospice, where the incentives actually are aligned, gives him a unique baseline. And I still think he’s about to be wrong, for a reason that has less to do with the traditional levers value-based care has spent fifteen years pulling.

Take the skeptic seriously

Prevention's signature is an absence of something. The heart attack that didn't happen. The pre-diabetes that never converted to insulin dependence. The middle-of-the-night ER admission that never materialized. The vaccine-preventable disabling disease that faded away with a prior generation. (But on that, we seem to have a short memory.)

Because my partner’s entire career has been spent managing the Medicare population in these downstream roles, he has arrived at an entirely understandable conclusion: little has changed.

The clinician at the end of the line is structurally the last to see prevention working, because prevention's biggest victories are the people who never show up in his facility. It’s a completely valid vantage point. And any honest case for change has to start right there, facing that reality, or it's just hype.

So let me make the honest case.

VBC has been largely a supply-side project

Value-based care, as we've built it, is almost entirely a supply-side strategy. It changes how the delivery system gets paid. Shared savings, capitation, full risk, penalties…you get the picture. Every single one of those is an external incentive pointed at the people delivering care.

Is it a necessary step to change the system? Absolutely. Does it have limitations on its own? Also absolutely.

External incentives aimed at large swaths of the healthcare economy are exactly the kind of changes that are slow, diluted, and entirely invisible at the bedside. A healthcare delivery organization can quietly restructure a corporate contract, but the nurse, the social worker, and the patient feel absolutely nothing different over the course of months or even years.

That is the exact ceiling my partner keeps bumping into. His skepticism describes both an absence of progress and the structural limits of a model that has spent fifteen years pulling primarily one lever.

The lever VBC never had a way to substantively pull is the one inside the patient. Patient engagement and empowerment are non-negotiables if we want to bend the cost curve at wide scale, especially when the cost of individual units of care is rising faster than inflation itself. But real behavioral change is something value-based care has never been able to manufacture at scale using a payment formula aimed strictly at care delivery teams.

Working in the VBC business and in policy, I have seen pockets of progress here. We're starting to see it in the new generation of AI-assisted care management systems that help clinicians engage with patients more authentically, for example.

One example is from a company called CareCo. (I’ve never worked with the tool myself and have no affiliation.) My understanding of how it works is when a care team member pulls up a patient chart, the system surfaces (among other things) info from their past conversations and reminds them of small personal tidbits the patient shared on a prior call. It helps build genuine trust and relationship continuity in a much more seamless way.

Another approach is embedding resource-intensive clinical care teams directly into physician practices to build the kind of patient-clinician alliances that drive actual behavior change. This can work beautifully and meaningfully, too.

But both of these models face the exact same hurdle: they are incredibly difficult to scale widely.

Does Fixing Healthcare Require a Generational Shift? I Don't Buy It

His theory is that demand is the real bottleneck. We are stuck with an entire generation conditioned to equate good care with more care, and the only path forward is waiting on a generational turnover.

If the only way to shift that demand is through traditional, slow-moving public health campaigns, he’d be right. But the tool arriving to disrupt that demand pattern is highly personalized, always-on digital health tech. And that’s why his premise begins to fall apart.

First, the idea that older patients are a tech-proof wall that this strategy will crash into is mostly a story the industry has told itself to excuse slow progress. The data simply doesn't bear it out. KFF's Drew Altman put it bluntly in a recent column titled “Medicare Beneficiaries Are Not Luddites”: roughly 8 in 10 Medicare beneficiaries 65 and older used a healthcare app or website in the past year. Even more striking, a majority reported that it made the system easier to navigate, showing no meaningful difference in adoption or utility when compared to 30-to-49-year-olds. (To be fair to the skeptics, the survey does highlight real income gaps and genuine worries about AI privacy. Adoption isn't uniform, but it is widespread.)

Second, and this is the heart of the matter: “treat, treat, test, test” is a learned behavior, but that doesn’t make it a fixed behavior. It’s the natural byproduct of a system that spent decades teaching patients that the only way to "do something" about their health is to get a scan, secure a referral, or undergo a procedure. Of course patients demand volume! We trained them to.

Personalized, continuous feedback offers a completely different way to feel like you're taking action. The shift moves from “the doctor ordered another test” to “my own daily numbers are moving, and I can see it.”

The new Medicare payment model tests are engineered to pay for exactly that swap. They reward the actual outcome rather than the volume of tests and visits that produced it.

You don't have to wait for a generation to pass away to change the game.

You do have to change what taking action feels like.

The near term is already here

This isn’t a “someday” argument. Look at what is hitting the market right now.

Earlier this year, Paralympian Hunter Woodhall got an biometric alert from his Oura ring. (Story found here.) It pushed him to see a doctor immediately, and he was diagnosed with appendicitis before his appendix could rupture. That is the entire ballgame in a single anecdote: catching an acute medical event before it transforms into a devastating, five-figure hospital admission and human suffering. It’s also why Oura, which is now an 11 billion company with over 5.5 million rings sold, just filed to go public explicitly as a healthcare company, not a fitness gadget.

There’s already an example of a payer realizing they are worth the investment. Missouri's Essence Healthcare is now giving Medicare Advantage members a free Oura ring. Think about it. When the entity holding the financial risk hands out a continuous, biometric engagement tool for free, the traditional incentives have quietly inverted.

But the biggest structural shift just landed on the fee-for-service side.

CMS’s Innovation Center has launched the ACCESS Model (Advancing Chronic Care with Effective, Scalable Solutions), a 10-year voluntary test in Original Medicare with a first performance period beginning July 5, 2026. If you want to see where the external payment lever and the internal consumer lever finally click into the same gear, this is it.

The design of the model does a few radically new things:

It creates a dedicated billing pathway for tech: Historically, fee-for-service Medicare paid for a rigid, face-to-face set of activities that completely ignored how digital, asynchronous care is actually delivered. Many digital health companies survived by avoiding Medicare and selling straight to employers. ACCESS changes the plumbing.
It pays for outcomes, not volume: Participating organizations receive a recurring Outcome-Aligned Payment (OAP) to manage a patient’s condition. The amounts are deliberately modest and meant to be “deflationary.” They range from 180 dollars per patient per year for musculoskeletal and behavioral health, up to 420 dollars for complex cardio-kidney-metabolic cases. That is a rounding error compared to a single avoidable ER visit.
It features a strict 50% skin-in-the-game withhold: CMS holds back half of every payment, reconciling it at the end of the year. An organization only earns that withhold back if at least half of their patients hit a clinical target set relative to their own individual starting point. Examples are a meaningful drop in a personalized pain or A1c score. No one-size-fits-all bar. Plus, CMS will publicly post these risk-adjusted outcomes. The intent is that the platforms that actually deliver results win the trust of the public, healthcare delivery teams, and policymakers.
It explicitly penalizes what it considers duplicative care: It’s debatable and remains to be seen if some of this penalized “duplication” or “substitution” is a good idea. I’m skeptical about some of that. The ideas is that if an enrolled patient starts accessing certain services elsewhere, the model automatically docks the managing organization's payment. Digital management is explicitly engineered to substitute for the volume play. Example: someone who is enrolled with an ACCESS org to manage chronic musculoskeletal pain should theoretically not seek an evaluation from a physical therapist or initiate remote therapeutic monitoring services.

The model’s four tracks target the rising-risk, prevention-adjacent conditions that touch more than two-thirds of the entire Medicare population. (CMMI notes additional tracks are coming in the future). More than 150 organizations were accepted for the launch, many of them entirely new to serving Medicare, and major commercial health plans have already pledged to roll out their own ACCESS-aligned payment options by 2028.

Supply side, meet demand side.

The pillar everyone forgets is the patient experience

We talk about value-based care as cost and outcomes. But the foundational Triple Aim eventually became the Quadruple Aim to protect clinician well-being, and has now rightly expanded into the Quintuple Aim to explicitly incorporate health equity. Yet through all these iterations, the patient’s actual experience of care has remained the hardest pillar to move.

This is exactly where agentic AI and digital tools are beginning to quietly do some of that work.

An AI "navigator" that handles the logistics like booking an appointment, rescheduling it, explaining a complex lab result at 11 p.m., and routing you to a human clinician only when it truly matters is important because they remove the structural friction from the parts of healthcare people actually hate.

And we don’t engage in things we hate unless we have to, which makes that behavior inherently downstream.

The industry sees the potential. While health system executives are still figuring out the backend plumbing, consumers are already moving ahead on their own. A March 2026 Microsoft Research report, "How people use Copilot for Health", analyzed more than 500,000 real-world health conversations. The data shows that conversational AI has quickly become an active first point of contact for patients triaging new symptoms, parsing complex medical records, and managing medications. The demand side isn't waiting for the supply side to catch up.

Here is the exact part that ties back to my partner’s skepticism: trust starts low, but it is earned through direct experience.

A national survey by National Opinion Research Center (NORC) at the University of Chicago found that most US adults have low baseline trust that their health system will use AI responsibly. Yet, separate data shows that patients with personal experience using AI show meaningfully greater approval of it in healthcare. Trust gets built through positive, day-to-day interactions, not corporate press releases.

That trust flywheel is already spinning faster than the skeptics realize. Rock Health’s 2025 Consumer Adoption Survey, which surveyed 8,000 US adults, found that roughly a third (32%) have already turned to AI chatbots for health information, doubling the share from just a year prior. Even better, 64% of those users return weekly or more.

Two findings also speak directly to the Quintuple Aim goal of equity:

The Equity Gap is Breaking: Unlike earlier waves of digital health tools that tracked strictly with wealth, the data showed no meaningful differences in AI adoption across income or education levels.
It Drives Real-World Action: An astonishing 81% of AI users took a concrete action afterward. Those actions include things like researching a health behavior, tracking a symptom, or going to see a doctor. That number is almost unbelievable.

KFF’s independent polling from early 2026 initially landed in the exact same place, confirming that about a third of adults were using AI for health info. However, that baseline is already outdated. A spring 2026 study by Boston Consulting Group shows just how fast this curve is accelerating, finding that nearly 60% of consumers are now using generative AI for personal health, and 44% are interacting with health chatbots on a weekly or daily basis. General web searches are quickly giving way to active, conversational interactions.

There are honest caveats to list, of course. Some are: most people remain highly worried about data privacy, chatbots still hallucinate, and always-on availability can sometimes outrun standard clinical guidelines. But the direction is unmistakable. And the technology is improving exponentially at a pace never seen in prior technology rollouts.

Engagement, experience, trust, and equitable access are the loop that VBC’s external payment levers could never close on their own. I believe they are finally closing from the inside out.

The long game

I started thinking about all of this after hearing Eric Topol speak about his book, Super Agers. Driven by everything from semaglutides to AI, Dr. Topol bets that we can meaningfully prevent and delay the chronic diseases of aging decades before they ever manifest. A recent MedCity piece, “Aging is Soon to Be a Preventable Disease,” makes the same case. They note that the biology is currently running ahead of the clinical tools, which are running ahead of the payment systems required to scale them.

But the tools are catching up. Take a term that is about to enter everyday conversation. Or maybe you heard it here first! It’s the Polygenic Risk Score (PRS).

Unlike a traditional single-gene test (like BRCA) that hunts for one high-impact mutation, a PRS adds up the tiny effects of thousands, sometimes millions, of common genetic variants across your entire genome. As the National Human Genome Research Institute (NHGRI) points out, it doesn't give you a definitive diagnosis or a timeline. Instead, it gives you your relative risk compared to everyone else. Knowing you are in the top 1% of inherited risk for type 2 diabetes or heart disease changes the game, allowing for hyper-targeted screenings and lifestyle interventions decades before a symptom appears.

The caveat is that most of the genetic data behind these scores comes from people of European ancestry, making them currently less accurate for everyone else. It’s a massive equity problem that the field is actively working to fix.

When you pair polygenic risk scores and longevity medicine with AI that excels at early diagnosis, you get the ultimate long-term accelerant: healthcare that is predictive, deeply personal, and aimed at the right person before they are sick.

If you want the cleanest proof that the timeline for prevention can actually be collapsed, look at GLP-1s. Semaglutide and its cousins are the first prevention-adjacent interventions with an effect size that’s large and fast enough on impacting weight, A1c, and cardiovascular outcomes that potentially a payer can underwrite the ROI.

It would be a major unlock if the time-to-benefit fits neatly inside the window that a risk-bearing organization is actually accountable for.

Closing the loop

Value-based care spent fifteen years pulling the external lever of paying delivery systems and clinicians to behave differently. The ACCESS model is the most serious, outcome-aligned version of that work that we have ever seen.

An external, corporate payment lever alone was always going to feel completely invisible from where my partner stands.

The real “kerosene on the flame” is the internal lever.

Personalized, continuous, and highly visible tech-enabled feedback can have the power to make a distant health payoff feel immediately present. It creates a smooth patient experience that actually earns consumer trust. It is the exact engagement mechanism that shifts a patient's mindset from "go get treated, go get tested" to "let me actively manage this."

Longevity medicine, advanced upstream diagnostics, and agentic AI tools light the crucial intrinsic motivation we need to change the direction of healthcare in this country.

So here is what I tell my partner and others like him now:

You are completely right that the day-to-day on the ground looks the same right now. Prevention’s wins are the hospital admissions that never happen, and you have spent three decades standing exactly where the structural failures show up over and over.

But we don't have to wait around for a massive demographic shift to change the game. We just need to give patients a tool that makes "taking action" feel like something other than demanding another test. Eight in ten Medicare beneficiaries already opened a health app this year. The time-to-benefit on chronic metabolic disease has completely collapsed. A risk-bearing payer will now hand a senior a free biometric monitor because the math finally pencils out.

And this summer, Medicare officially starts paying based on whether those patients actually get better. The question isn’t whether structural change is coming. It’s which lever pulls next. For maybe the first time in the history of healthcare policy, that lever belongs to the consumer.

It’s all connected.

Sources:

CMS: ACCESS Model overview (July 5, 2026 launch; four tracks; outcome-aligned payments; public outcomes directory; PCP co-management; multi-payer alignment): https://www.cms.gov/priorities/innovation/innovation-models/access
CMS: ACCESS Model Payment Amounts and Performance Targets, Effective Period July 5, 2026–Dec 31, 2027 (per-track OAP amounts, 50% withhold/reconcile, 50% Outcome Attainment Threshold, Substitute Spend Adjustment, rural add-on): https://www.cms.gov/priorities/innovation/files/access-payments-amts-perf-targets.pdf
CMS: Major health plans join the ACCESS payer pledge: https://www.cms.gov/priorities/innovation/innovation-insight-major-health-plans-join-access-payer-pledge
CMS: ACCESS accepted applicants (150+ organizations; many new to Medicare): https://www.cms.gov/priorities/innovation/access-model-accepted-applicants
CMS: ACCESS Request for Applications (PDF): https://www.cms.gov/priorities/innovation/files/access-rfa.pdf
CMS: ACCESS Technical FAQs: https://www.cms.gov/priorities/innovation/access-technical-frequently-asked-questions
KFF (Drew Altman): "Medicare Beneficiaries Are Not Luddites" (Oct 29, 2025): https://www.kff.org/from-drew-altman/medicare-beneficiaries-are-not-luddites/
Boston Consulting Group: "Consumers Are Ready for AI-Enabled Health Care. Health Systems Need to Be, Too." (Nearly 60% using GenAI for health; 44% weekly/daily chatbot use; April 2026): https://www.bcg.com/publications/2026/consumers-are-ready-for-ai-health-care-are-systems
MedCity News : "How Oura Expanded from Wellness to Healthcare" (Hunter Woodhall appendicitis; Essence Healthcare partnership; $11B; 5.5M rings): https://medcitynews.com/2025/11/oura-wearable-healthcare/
MedCity News: "Oura Files for IPO As Healthcare Ambitions Grow" (May 2026): https://medcitynews.com/2026/05/oura-ipo-healthcare-ring-device/
Microsoft Research: "How people use Copilot for Health" (Analysis of 500,000+ real consumer health conversations; AI acting as a first point of contact for symptoms and medication; March 2026): https://www.microsoft.com/en-us/research/wp-content/uploads/2026/03/copilot-health-usage-report.pdf
Guidehouse — "From generative to agentic AI in healthcare" (the AI "navigator"): https://guidehouse.com/insights/healthcare/2025/from-generative-to-agentic-ai
JAMA Network Open / NORC: "Patients' Trust in Health Systems to Use Artificial Intelligence" (baseline trust is low): https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11829222/
Artificial Intelligence Survey Aachen (AISA): personal experience with AI is associated with greater approval of AI in healthcare: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12770056/
California Health Care Foundation: "Patients Say Yes to AI — If Doctors Stay in Charge": https://www.chcf.org/resource/patients-say-yes-artificial-intelligence-doctors-stay-charge/
Rock Health: "The tortoise and the hare of care: Health AI insights from Rock Health's 2025 Consumer Adoption Survey" (primary report; 32% vs. 16%; 64% weekly; no income/education gap; 81% took action; N=8,000, fielded Dec 2025): https://rockhealth.com/insights/the-tortoise-and-the-hare-of-care-health-ai-insights-from-rock-healths-2025-consumer-adoption-survey/
KFF : "1 in 3 Adults Are Turning to AI Chatbots for Health Information" (32%; 77% privacy concern; Feb–Mar 2026): https://www.kff.org/health-information-trust/poll-1-in-3-adults-are-turning-to-ai-chatbots-for-health-information-equaling-the-share-who-use-social-media-for-health/
Fierce Healthcare on OpenAI:1 in 4 weekly ChatGPT users asks a health question; ~600k weekly health messages from rural "hospital deserts": https://www.fiercehealthcare.com/ai-and-machine-learning/40m-people-use-chatgpt-answer-healthcare-questions-openai-says
Eric Topol: Super Agers: An Evidence-Based Approach to Longevity (Simon & Schuster, May 6, 2025): https://www.simonandschuster.com/books/Super-Agers/Eric-Topol/9781668067666
MedCity News: "Aging is Soon to Be a Preventable Disease" (May 2026): https://medcitynews.com/2026/05/aging-is-soon-to-be-a-preventable-disease/
NHGRI (genome.gov): Polygenic Risk Scores explainer: https://www.genome.gov/Health/Genomics-and-Medicine/Polygenic-risk-scores

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

How to Bulletproof Your Healthcare Career Against the Risks You Can and Can't See Coming

Dana Prommel Strauss — Mon, 25 May 2026 00:15:00 +0000

There are Two Kinds of Risks. Prepare for Them Both.

There are risks in healthcare we can learn about and study. They are out in plain sight and their repercussions are predictable. Then there are risks no one sees coming. But healthcare professionals need to be prepared for both. To learn about these two types of risks, let’s look first at a way to apply the concept to personal financial planning.

Black Swan Events

These are the risks most people don’t prepare for. We know black swan events happen periodically during the course of history and that the occurrence of them is predictable. Unfortunately, the timing is not.

We tend not to prepare for black swan events because we can’t predict their TIMING or how they might impact us. It’s a human flaw.

One of my favorite authors, Morgan Housel, talks about black swan events that could have downstream impacts on his personal financial independence journey and how he prepares for them.

He uses a “barbell” approach in his financial planning. When he explains it to his readers, he also notes he would not recommend it to others because of how conservative one side of the barbell is, but he needs it to sleep at night.

Here’s what he shares:

He keeps 20% of his money in cash. He paid off his mortgage even when he had a very low rate loan, and he has zero other debt. He owes no one anything and has a very large cash stockpile. It gives him options, the ability to persevere in unpredictable times. He notes in Same as Ever, “The world breaks about once every ten years.”

On the other end of the barbell, he invests fully in stocks, investing nearly entirely in ETFs and broad market funds. He doesn’t time the market with this money. He doesn’t try to pick the winners.

The reasoning for his barbell approach is this: the most dangerous risk is what you can’t see coming.

Examples:

· 9/11

· The 2008 financial crisis

· Inflation of the 1970s

· Pandemics

· Political unrest

· Natural disasters

· And other events you can’t predict and that would disrupt our ways of life.

But the risks he CAN see coming?

The predictable risks?

They are part of his calculations and plans.

He knows that without being invested in stocks, his money isn’t working for him. Without being invested in stocks, he risks not achieving financial freedom. Because remember, only when your assets compound to earn enough on their own to fund your life are you truly financially free. And since being free is his goal, he takes the long view on investing. He takes the barbell approach.

Investing is not the only way to be financially free, of course. Real estate, business ownership, and other options are available. But stock market investing is likely the most approachable for those working in healthcare, so I use it here.

Sure, there are market corrections, ups and downs. Since 1954, the S&P 500 has dropped 10% every 18 months (considered a market correction). It drops 20%-40% (20% is considered a bear market) every six years. Bear markets are often months long, not years. But sometimes it’s much longer. After the 2008 crash, it took until 2014 for the same dollars from 2007 to regain purchasing power. After the Great Depression, it took from 1929-1954.

Of course, those who stayed in the market during the drop and through the recovery AND added to their portfolio over that time bought at sale prices, and have been rewarded handsomely.

Morgan Housel is prepared, so he can weather the rough times and leave his money invested while buying into the market “on sale.” When the market recovers, as it always eventually does, his money is there, he owns more because he bought at lows, and he played the risks to his advantage.

Because with 20% of his money in cash, he is prepared for major downturns that can take years, which will mitigate the need to lose his freedom by selling investments while they are down, therefore giving up his freedom.

He still recognizes that this 20% cash is losing value to inflation. But he is okay with that. He has incorporated that risk into his decisions. He mitigates it by being aggressive on the other end of the financial barbell and being ready to buy even more with some of that cash when the market is “on sale.”

He doesn’t talk about bonds, munis, or other investments that many believe help balance out the risk of the stock market. Since 1954, the S&P 500 has averaged 10.5-11% per year returns with dividends reinvested, and 6.5-7% after inflation. But it’s the power of compounding where the magic happens and of which you can only reap the rewards if you stay invested through it all. You have to be willing and able to take the risks of the short-term downturns to benefit from the rewards of the long-term. Timing the market is a fool’s errand.

Here’s a summary of the stock market in the arbitrary years chosen from 1995 through December 2025:
Dot-com bubble and crash (1995–2002): The S&P roughly tripled, then lost about half its value.
Recovery and housing bubble (2003–2007): Strong returns leading to a new peak in October 2007.
Global Financial Crisis (2007–2009): A 57% drawdown — one of the worst in history.
Post-GFC bull market (2009–2020): One of the longest bull markets ever.
COVID crash and recovery (2020): A 34% drop in five weeks, fully recovered within months.
2022 bear market: -19% as the Fed hiked rates aggressively.
2023–2025 AI-driven rally: Three strong years in a row, with the S&P setting dozens of new all-time highs.
I found this calculator for looking up the historical returns of the S&P 500 for any period of time starting in January 1871.

Morgan Housel made decisions after educating himself on how financial markets and risk work. He incorporates human behavior, history, philosophy, and more into his thought leadership and his content.

His lessons are applicable to healthcare, too.

Black Swan and Predictable Risks Have Implications for Healthcare and Your Career

You learned above about black swan events and predictable risks, and how one expert thinks about managing both to achieve his goal of financial independence. Morgan Housel educated himself on more than just investing in the stock market. He learned how to make his personal finances as bulletproof as possible while benefiting from the gifts of compounding in stock market investing.

Let’s apply this concept to the healthcare industry, and develop a framework for bulletproofing your career to manage the risk you do and don’t see in healthcare.

Managing Both Black Swan and Predictable Risks Requires Preparation

Preparation starts with education.

What might cause the next black swan event that will impact healthcare and those whose careers depend on it?

We have no idea.

What we do know is the more diversified your knowledge, the more risks you will see earlier and the more solutions you will identify and be able to create and implement. This will give you career leverage and the ability to pivot. You will become more valuable. You will become more versatile.

It should help you sleep better at night, too.

The kind of non-clinical knowledge that will serve you in times of change will also serve you in the quest for career development in any area, including leadership and operational roles in healthcare provider organizations, and/or non-clinical career paths such as those in health tech or working with diversified healthcare companies. The topics to study include payment policy, federal laws and regulations, the role of data analytics, medical economics functions, what governs healthcare laws, etc.

Telehealth, Hospital-at-Home (HAH), and the COVID Pandemic

For years, advocates had been working to lobby Congress on changing the federal statute (law) to allow greater adoption of telehealth in healthcare. Because of statutory limitations, telehealth was severely restricted in Traditional Medicare until the pandemic. The only people who could receive telehealth if they had Traditional Medicare were those both living in rural areas and who went to a clinical site to receive that telehealth. These are called “geographic and originating site requirements.”

There were some flexibilities for patients in certain MSSP ACOs and CMMI ACOs (for patients whose physicians in those ACOs were in prospective-alignment ACOs). In 2019, CMS gave MA plans the flexibility to waive “geographic and originating site requirements” and add telehealth to their basic benefits.

Hospital-at-Home was also not being done for Medicare beneficiaries due to statutory requirements around hospital-level care. Innovators were doing good work here, but the uptake was limited without Medicare rules and payment policy in place.

Then came COVID-19.

Patients with chronic disease couldn’t see their doctors or get medications adjusted and modified. Patients needing medical evaluation for new-onset, non-COVID illnesses needed a way to access care without the risk associated with going to a public place or a hospital.

Hospitals wanted to limit admissions to only those with COVID-19 as much as possible. Some patients could be managed clinically in their own homes and receive hospital-level care, but statute didn’t allow it.

In both cases, also note that the technology was there to allow healthcare innovation to happen, but statute prevented it.

Section 1135 Waivers

The President has the authority to waive statute in certain crises. President Trump declared a National Emergency under the Stafford Act and National Emergencies Act on March 13, 2020, unlocking waiver authority used by HHS and CMS. Both telehealth and HAH benefited from that.

Why wasn’t advocacy successful up until then? Some was political malalignment and political will (an underestimated reason laws do or don’t change), especially with HAH. Critics didn’t believe the quality of HAH would be equal to or better than the actual hospital. But the lack of a funding source was a major culprit.

While HAH is very low cost, (the Congressional Budget Office (CBO) estimate is “negligible,” or about one million dollars per year), telehealth must be funded in addition to acute care hospital funding under the IPPS. The CBO doesn’t consider whether the care reduces downstream costs so that’s not part of the calculation.

It has a hefty price tag. The CONNECT for Health Act of 2025 has not been scored by CBO yet, but the cost for the present two-year extension in the Consolidated Appropriations Act of 2026 was $3.8 billion. See the KFF resource found here for more information.

Expiration of Telehealth and Hospital-at-Home is Not Popular

For both of these temporary policy changes, the public doesn’t want to go back to pre-COVID times and the limitations of statute. There is likely no one in Congress who wants to tell their constituents who have experienced telehealth and HAH that they can’t have that anymore. Taking things away is really hard.

So Congress has “temporarily” extended both through that annual appropriations bill (CAA of 2026) and continuing resolutions. These permit these services outside permanent statute and fund their care delivery. I think it’s highly unlikely they won’t eventually become permanent and funded through the budget process.

The black swan event had many repercussions, including how this would impact healthcare. Those “long tail” impacts are often positive. Telehealth and then digital health would become common and innovation would continue, spurring investments in research and development leading to changes we are seeing today. Hospital-at-Home is growing in popularity and in line with current and ongoing trends towards community-based care vs. hospital-based care.

I’ve heard telehealth advocates say the pandemic advanced telehealth policy 10 years ahead of what they likely would have accomplished through traditional advocacy channels. The advocates were ready. They were educated, they had planned, and now they are advancing it the rest of the way. While I can’t predict when telehealth and HAH will become a permanent part of statute, I can comfortably predict it will happen.

That prediction doesn’t come without accepting the short-term risks to healthcare industry stakeholders in the meantime. Because FY 2026 appropriations process collapsed, and telehealth and HAH were bills riding on that broader funding package, their funding was suspended. So the reasons that package stalled and caused the lapse had nothing to do with telehealth or HAH themselves This is the reality of the inherent uncertainty in Congressional action. But that’s no comfort to clinicians providing telehealth and hospitals admitting patients to HAH.

Predictable Risks

Unlike how Morgan Housel considered the predictable risks of the short-term bumpy rides his investments will make, which history tells him will pay off in the long run, most clinicians I meet aren’t prepared for the predictable risks in the healthcare industry that will impact their careers. It’s the predictable risks that make us most vulnerable to career disruption and the need to prepare for and get ahead of them.

Like the actions you take to protect your financial security from stock market volatility, it makes sense to approach career growth and development by considering the risks of not building and adding to your knowledge of the healthcare industry.

It’s just not enough to gain more clinical skills and more advanced certifications. My profession of PT is particularly at risk in this area. Adding specialties and certifications that add little to the salary you can command while staying oblivious to what makes your employer successful or how to leverage alternative payment model opportunities does not compute for me.

Keeping up with current events in healthcare writ large is also very important in ongoing career development to take advantage of the compounding of knowledge over time. Current events include policy changes and healthcare-adjacent news and developments like those in health tech innovation, as well as how the current political team running CMS is carrying out its priorities and strategy.

CMS Strategy Refresh At-A-Glance

Here’s the audio content I consume every week related to healthcare, health policy, and health tech. It helps me keep up with news and hear the perspectives of others who think about the healthcare industry in a variety of ways. The variety helps me hone my opinions and projections on the industry and develop frameworks for thinking about its future path.
The Heart of Healthcare
Health Tech Nerds Radio
KFF Health News
McKinsey on Healthcare
Health Affairs This Week and A Health Podyssey
Relentless Health Value
I like podcasts because they fit into my chores like cooking dinner and driving my dog to day care. When something I hear triggers an idea, I pause the podcast and speak into the audio device I use to capture my thoughts.

Don’t Do This Anymore

Humans working in the healthcare industry tend to defend what’s familiar, push for small improvements that won’t meaningfully move the needle, overestimate what we can expect from Congressional advocacy and on what timeline, and don’t understand how CMS regulates the industry and innovates via CMMI.

Employing a wide-angle lens to ongoing learning as a tool to steer your own career prepares you to adapt to both the black swan events and, more commonly, the predictable changes that compound over time. Not knowing them is the risk. Preparing for them and incorporating them into your career development is the reward.

So don’t be like that.

Learn what’s changing and why.

Learn what’s most nascent.

Learn to predict what changes WILL happen. You will learn to be directionally right more often than you think.

The timing of predictions coming true? That’s much harder and largely unnecessary.

Healthcare Will Improve More if Clinicians Push Beyond the Clinical Lane

No industry stays the same forever.

No business that fails to evolve stays intact forever.

And no career path — even in healthcare — is a straight, stable line forever.

The clinicians who see this clearly are already preparing.

Compounding Problems Lead to a Perfect Storm for Change

These are the predictable risks compounding in healthcare right now. None of them are surprises. All of them are reshaping the industry whether you engage with them or not.

The clinicians who study them, who incorporate them into their career thinking, are the ones who will have options when the model shifts.

There are health and healthcare problems so large, creating so many industry risks, that we can predict the model we are familiar with will change dramatically in the near future.

Here are just a few:

· Healthcare spend will continue to outpace GDP growth

· Chronic disease prevalence will continue to rise

· Heavy dependence on the high cost of humans to deliver healthcare. (Leftover from the black swan event of the pandemic are more turnover, fewer available clinicians, and greater dissatisfaction than ever from healthcare professionals.)

· Disability rates will continue to increase

· Outcomes trail far behind our peer nations

The predictable risks interact with each other, creating the negative compounding effect (not in the good way like stock market returns over long periods of time).

Sponsors don’t have enough budgeted to fund payers.
Payers don’t have enough to cover expenditures.
Employers devote more to healthcare benefits and less to salaries.
Benefits become less generous.
People wait to get care and screenings.
People are going bankrupt from healthcare debt.
More people are uninsured and underinsured.
Uninsured people have no way to pay for emergency care.

It’s simply unsustainable.

About 100 million U.S. adults carry some form of medical debt, totaling around $220 billion. About one-third say they’ll never be able to pay it off.
Most of those with medical debt are employed. People in California and Oregon are least likely to have medical debt (<5%) and people in South Dakota and Mississippi are most likely to have medical debt (>14%).
5% of those with medical debt owe more than $100,000.
66.5% of people who file for bankruptcy blame medical bills as the primary cause.

Your Career Barbell

Morgan Housel's barbell is a useful frame for clinicians, too. Here's what it looks like applied to your career.

One end of the barbell is the conservative side.

This is what gives you options when something you didn't see coming hits like a service line closing, a private equity rollup, a payment model change that wipes out the role you trained for. It's not exciting. But it's what lets you sleep at night.

For a clinician, that side includes:

· Financial runway. Enough cash to walk away from a bad job, take a pay cut to pivot, or wait out a hiring freeze.

· Licensure that travels. Compact licenses, multi-state credentials, anything that gives you geographic optionality.

· A network outside your immediate role. People who know you, who can refer you, who work in adjacent parts of the industry.

The other end is the offensive side.

This is where you compound knowledge over time, the way Morgan Housel compounds returns in broad market funds. You're not trying to time it. You're not chasing the credential of the moment. You're building, steadily, in areas that will matter no matter what the next decade looks like. (Morgan Housel talks about the concept of things in any industry that don’t change in his book Same as Ever).

For a clinician, that side includes:

· Payment policy and how it actually works.

· How CMS and CMMI operate and what they prioritize.

· Healthcare economics and the business model of your employer.

· Health tech, AI, and where the industry is investing.

You don't need to master all of it. But you need to be building in it. A little every week. A little every month. Set up the compounding to work its magic.

The mistake most clinicians make is putting everything on the clinical end like more certifications, more specialties, more letters after their name. That's the equivalent of stock-picking in a bull market. It might pay off. It might not. But it leaves you exposed when the model itself changes underneath you.

Don't be exposed.

Two Risks. Two Sides of the Barbell.

You can't predict the next black swan in healthcare. You can prepare for the predictable risks based on what will force change. Do this by building runway, optionality, and a network beyond your role.

There is a storm that's already forming. Prepare by compounding non-clinical knowledge, steadily and consistently.

Bulletproof your clinical career.

In Policy Pulse, I walked through the career barbell. Two sides. Conservative on one end. Offensive on the other.

The offensive side gets most of the attention, like building non-clinical knowledge, compounding it over time, learning about payment policy and CMS and health tech. That's the side that grows your career.

But it's the conservative side that lets you sleep at night. The conservative side is what makes a black swan event survivable. It’s what prepares you for the change that finally happens when the predictable risks reach a breaking point. Without it, even the best-built offensive side can collapse under pressure.

So let's build it.

The defensive side of your career barbell could include these three pieces:

· Financial runway

· Licensure that travels

· A network outside your immediate role

Most clinicians have none of these in any deliberate way.

Here's how to start.

1. Financial Runway (note: this is not financial advice, just an example for educational purposes)

Morgan Housel keeps 20% of his money in cash. That cash isn't earning him much. He knows it's losing to inflation. He keeps it anyway.

Why? Options.

Your career version is the same. You need enough cash that you can walk away from a bad job. Take a pay cut to pivot. Wait out a hiring freeze. Say no to a contract that isn’t favorable.

The starting target: 6 months of expenses in a high-yield savings account.

The real-autonomy target: 12-24 months.

That second number sounds extreme. It is. It's also what changes the conversation you have with yourself when your employer announces restructuring, when a service line closes, when a payment model shifts. You stop negotiating from fear.

You can't build the offensive side of the barbell if the defensive side is empty. You'll make career decisions out of survival instead of strategy.

2. Licensure That Travels

The single most underused defensive move in clinical careers is multi-state licensure.

Most clinicians keep one license, in one state, and never think about it again. Then their job disappears, or their specialty contracts, or a payment policy change makes their role unviable — and they realize their entire career is geographically locked.

Don't be locked.

Find your compact, such as:

· PTs: The PT Compact.

· Nurses: The Nurse Licensure Compact (NLC).

· Physicians: The Interstate Medical Licensure Compact (IMLC).

· Psychologists, OTs, SLPs, counselors: PsyPact, OT Compact, ASLP-IC, Counseling Compact.

Get the credential, even if you never use it.

Optionality has value even when unused. Especially when unused.

3. A Network Outside Your Immediate Role

When a service line closes or a payment model shifts, every clinician in your specialty starts looking for the exits at the same time. Your colleagues can even become your competition.

The clinicians who weather these moments best already know people outside their specialty and outside direct patient care. People in health tech. In payer organizations. In operator roles. In policy. In adjacent industries.

You have to build that network deliberately.

Three specific moves:

· Pick one non-clinical conference per year. that’s not specific to your profession: HLTH, ViVE, HIMSS, AHIP, NAACOS, Accountable for Health, etc. Some are free, so no excuses. Any of them will expand your network beyond your specialty in a way no clinical conference specific to your profession will.

· Use LinkedIn like it matters. Post at least once a week. Comment on the people you'd want to know. Share what you're learning from Policy Pulse and the podcasts. Your offensive-side learning becomes the fuel for your defensive-side networking.

· Have one (even virtual) coffee a month with someone outside your role. A health tech founder. A health system operator. A CMMI alum. A payer medical director. Make it a habit, not a project. Joining a community like Health Tech Nerds can make that easier.

Health Tech Nerds

Insightful content and vibrant community trusted by over 30,000 healthcare leaders and innovators.

The goal is being known by people who do work you might like to do someday.

The Defensive Side Isn't Glamorous

Morgan Housel's 20% in cash isn't glamorous. Holding compact privileges you don't use isn't glamorous. Building a network for a career move you may never make isn't glamorous.

But it's how you build timeless autonomy.

The offensive side grows your career.

The defensive side protects your ability to choose your career.

Build both.

You don't have to overhaul anything. Start small, but start now.

For the offensive side of the barbell:

· Subscribe to one of the podcasts above. Pick the one that sounds least familiar. That's the one with the most to teach you.

· Read the CMMI strategy document linked above. It's free, it's short, and it tells you exactly what's coming.

· Pick one non-clinical topic such as payment policy, medical economics, health tech innovation, and commit to learning the foundations for the next 60 days.

For the defensive side:

· Open a high-yield savings account and automate a transfer from each paycheck. Even $200 a month is a start. The habit matters more than the amount.

· Look up your compact. Twenty minutes of research today. Find out if your state participates, what it costs, what it takes to add the privilege.

· Reach out to one person outside your clinical specialty. A short message. No agenda. Just "I'd love to learn what you're working on."

Six small things. Pick one. Or two. Start where it's easiest.

Done consistently, they compound.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The Long Tail of AI Will Accelerate VBC

Dana Prommel Strauss — Sun, 17 May 2026 23:18:40 +0000

The 8-week course that teaches you how to actually evaluate deals.

Learn the same investing frameworks used at BlackRock, KKR, Ares, and other top firms.

Over 8 weeks:

Underwrite live deal scenarios end to end
Build and analyze institutional-level real estate models
Make go/no-go decisions based on risk-adjusted returns

Join the June 8 cohort of the Wharton Online Real Estate Investing program. Use code SAVE300 to get $300 off tuition.

Explore the Program

Policy Pulse: The Long Tail of AI in Healthcare Is Where the Transformation Lives

"We don't have to pay AI a living wage."

I heard someone say that on a panel last week. On another panel the same week, the topic was the second stage of AI. This is what policymakers are setting up for next. Two very different framings of the same technology, and both stuck with me.

Last week's Policy Pulse was about what AI is taking apart in healthcare, including the eroding moats, the care management margin being absorbed by tech-enabled platforms, the moment where "humans alone can't compete." This week, I want to flip the camera around and look at what AI is building. Because most of what we're seeing today is the head of healthcare's AI trend, while most of what I'm excited about is the tail. And it’s long one!

What I Mean by Head and Tail

Quick framing before I dig in.

The head-and-tail concept is borrowed from Chris Anderson's 2004 Wired piece and in his book “The Long Tail: Why the Future of Business is Selling Less of More.” What you should know as you read on: when the cost of reaching consumers drops, individualized and niche solutions can reach the masses. The supply and demand mismatch disappears. Think about Netflix and Amazon as the classic examples of market disruption via the long tail of possibilities opened up by technology .

In healthcare, the head is the concentrated, obvious stuff the high-visibility, high-dollar use cases dominating the market today. Tools built to maximize revenue inside fee-for-service systems: automated coding, ambient documentation, billing optimization. Easy to see because they're loud, well-funded, and already at scale.

The tail is the vast ecosystem of micro-tasks that happen between doctor visits. Tracking medication adherence. Troubleshooting home health devices. Coordinating transportation. Managing weirdly specific workflows like outpatient therapy scheduling or DME onboarding. Thousands of small, scattered workflows that actually hold the key to improving long-term, population-level outcomes.

Here's why this matters:

In traditional economics, healthcare organizations couldn't afford to put enough human care managers on this work because human labor is a constrained and expensive resource. Commonly, care managers would be deployed to help manage the care for the highest 1-5% risk (in a VBC program).

Software developers largely skipped it also, because each workflow was too small to justify custom-built software, although in the last few years progress has been made here.

AI changes the unit economics.

Generalized models adapt to thousands of small tasks at very low marginal cost.

Suddenly it's viable to solve the small stuff at scale.

The cumulative impact of fixing thousands of minor friction points ends up larger than the impact of optimizing a handful of big administrative processes. Technology starts being about supporting a patient continuously, throughout their actual daily life.

That's the foundation for everything below.

The Head: Where AI Is Showing Up First

The first wave is doing what you'd expect a profit-maximizing tool to do inside a fee-for-service system (squeeze more revenue out of every encounter).

Ambient AI and AI coding assistants can now detect every possible billable code, extracting every available dollar from the payer. That payer could be CMS, a commercial insurer, a self-funded employer, an individual paying privately, or someone chipping away at a high-deductible plan.

Tech can integrate inputs automatically and maximize billing across any clinician type or site of care. This solution was imagined first.

Billing and coding optimization (RCM)
Ambient documentation
Prior authorization support
Radiology read assistance
Chatbots and triage front doors

Is any of this contributing to better outcomes? Some, I’m sure, especially if it gives clinicians time back. What it will do and already is doing is push medical cost trend higher for transactional care. That's the head. It's loud, it's quantifiable, and it's already here. 🙃

The Tail: Where the Real Transformation Lives

The tail takes more imagination. It's the part where AI does what humans in healthcare have struggled to do. It’s because the economics never worked, the technology wasn’t ready yet, and the workforce couldn't stretch far enough to reach most patients.

Also:

AI makes small problems economically actionable

As noted already, this is the unit economics shift in action. Healthcare has effectively long- ignored countless small issues because human attention is too expensive and time-constrained. Now it's viable to do, at scale, what was previously valuable individually but operationally impossible. These are things like:

Medication adherence follow-up
Discharge instruction reinforcement
Transportation coordination
Diet and symptom monitoring between visits
Caregiver education
Social barrier identification and tucking patients into support
Home device troubleshooting
Specialist referral navigation
Behavioral “nudges” to manage chronic disease

AI extends care beyond the clinic walls

Healthcare today is still mostly organized around encounters, including office visits, medical testing, admissions, procedures, and more. AI shifts the center of gravity to continuous, longitudinal support: home-based care coordination, chronic disease nudging, home monitoring, caregiver “copilots,” behavioral reinforcement, low-acuity triage, recovery optimization, and medication titration support.

These add up to innumerable of low-intensity interactions happening continuously, outside any formal care setting. This is the long tail in action.

AI reaches populations we've historically failed

Some populations are operationally hard to serve well, such as multimorbid patients, rural patients, elderly and frail individuals living alone, disabled populations, people with behavioral health comorbidities, those with rare diseases, non-English speakers. They all often need coordination, patience, repetition, monitoring, and navigation.

Not to beat a dead horse, but these are all things humans can't scale profitably or with limited human resources but that activities with a high ROI.

Here’s the VBC angle again: AI can redirect attention toward patients and their individual needs that fee-for-service economics couldn’t.

AI cracks healthcare's workflow fragmentation

Healthcare is made up of thousands of workflows, each mostly too small for traditional software vendors to build for.

Infusion scheduling.

Home oxygen paperwork.

SNF transfer coordination.

Pharmacy synchronization.

DME onboarding.

Wound photo monitoring.

Transportation benefit routing.

Building purpose-built tools for each niche workflow required custom development, dedicated training, and more. In addition, there was no logical billing mechanism for these tools to work. The CMMI ACCESS Model is changing this.

The deeper shift is that AI doesn't have to live inside a single application. Much workflow pain is the result of systems living in silos. These are the handoffs between the EHR, the payer portal, the pharmacy system, the SNF, the patient's phone, clinician to clinician, and more.

AI can sit across all of those. Long-tail workflows then finally become addressable.

What This Already Looks Like

Some of this is shipping today. Here are two examples. With ACCESS launching this summer, this will likely become more visible.

Lark runs a 24/7 automated AI health coach for employers and health plans. It’s chat-based, pulling in connected data (weight, activity, sleep, glucose), delivering personalized nudges without clinician review. Published evaluations in diabetes prevention and diabetes care show improvements in engagement and intermediate outcomes like weight loss and A1c. The strongest evidence is on intermediate metrics, not hard endpoints like hospitalizations. But this is the direction.

Withings sells a connected scale, blood pressure cuff, and watch that auto-sync to an app. The app analyzes trends and can trigger nudges or share reports with clinicians or family.

Always-on AI coaching and connected monitoring change behavior between visits, catch deterioration early, and close care gaps before they become expensive. This can lead to fewer preventable ED visits, hospital admissions and readmissions, missed post-discharge follow-ups, and complications from uncontrolled chronic disease. These create medical cost trend improvements and savings that can recur and compound year over year in value-based care structures.

Why AI Succeeds Where Humans Struggle

Some clinicians are worried about how this might reduce the need for human-led healthcare. I see it improving upon the work clinicians can do and allowing their top-of-scope work to carry greater impact on each patient they touch. Might who they touch change? Sure.

Despite challenges scaling this, we've made real progress with things like nurse-led care management and proactive patient outreach. But it depends on a patient's willingness to take phone calls and be transparent with them. It's easy to tell a nurse, "yes, I weighed myself," or "no, I didn't eat the high sodium canned soup."

I can attest to the incredible difficulty in activating most patients in the crucial work of between-visit physical therapist-prescribed care. It’s notoriously hard to impact what patients do when you aren’t in front of them or in their ear.

AI can now become part of the patient's life flow. It can nudge, encourage, course-correct, and be relentlessly consistent in a way no clinical workforce can. It can deliver something that looks a lot like empathy, at a marginal cost that makes it actually deployable.

And AI never gets tired or has a bad day. It doesn’t have a limit to the number of people it can interact with per day. Its reach is hard to wrap your arms around, right?

We're Too Impatient With VBC Transformation

Here's where I push back on the prevailing narrative that says “maybe VBC doesn’t work.”

In the book Same As Ever, Morgan Housel notes that improvements in cardiovascular disease management have prevented something like 25 million deaths, and how he’s struck by this not getting get more attention. He then explains exactly why it doesn't. Slow improvements, especially in things that don't happen, never make news. Look no further than vaccines to see another example of this in action. Countless lives saved with their safety and utility in question by some. Baffling, but explainable in this context.

VBC could be put in the same bucket. I regularly hear from skeptics who expect VBC to have already transformed the system. The truth is, there are massive improvements in pockets, among early adopters, among the practices and risk-bearing organizations willing to learn what success in risk actually requires. Look at advanced primary care practices reducing hospital admissions for Medicare beneficiaries by 40–50%, or reductions in spend and surgical complications inside episode-based acute care.

But we've been at this for less than 15 years. Medical schools aren't teaching VBC patient management in any meaningful way, and neither are most other professional programs.

Healthcare is HARD. It doesn't work like other parts of the economy, either. And its historical doesn't financially reward longitudinal relationships. FFS is baked into the fabric of how we deliver care.

So yes, change takes more than a minute. More than a couple of decades, even. Compounding effects on population health take time inherently. Improving health is not unlike the compounding of improving personal finances: a series of small action steps that build on each other and turn into new habits and behaviors. Another favorite book of Morgan Housel’s, The Psychology of Money, talks about this.

AI Is Arriving Right on Time

And now we have AI to help. I think it's here just in time.

It's going to complement VBC by doing what VBC has needed all along, which is bringing patients themselves into the care team. Newer Medicare models, including the ACCESS Model, lean further into patient engagement and create the financial logic where consumer-facing AI tools actually get rewarded for keeping people healthy.

This is when the head of the trend stops mattering as much, and the tail starts pulling the system in a different direction.

This is also part of why I keep saying this time really is different. The head is loud. The tail is where the long-term win lives.

From Direct Care to “AI-Augmented Practice Operator”

If you are a clinician or manager working on the delivery side of healthcare and want to lead the adoption of tools for your organization, here’s career direction that may emerge.

Instead of fearing automation, forward-thinking leaders looking for career leverage are stepping into roles where they manage the AI tools that handle patient outreach, allowing their staff to operate at the top of their licenses. They are leaning into integrating continuous, longitudinal tech into healthcare clinical settings.

These practice managers and clinical directors are shifting into operations roles dedicated to digital health deployment. They are doing things like designing hybrid models where AI handles the initial patient touchpoints, freeing up the human staff to step in only when complex clinical decisions are required.

The long tail of AI demands a new kind of clinical leader. If you are looking to future-proof your career, moving from direct care to digital practice orchestration might just be the smartest bet you can make right now.

Ultimately, a fragmented healthcare system requires a new kind of operator to run it. The tech is finally arriving, and the roles are right behind it.

If you are already navigating this shift or building a hybrid care model in your own clinic, hit reply and tell me about it. I would love to feature some real-world examples in a future issue.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The Erosion of the Healthcare Moat

Dana Prommel Strauss — Tue, 12 May 2026 03:29:49 +0000

Between meetings, speak your follow-ups. Done before the next one starts.

You have seven minutes between calls. That's enough time to type one email or dictate five.

Wispr Flow turns your voice into clean, professional text inside any app. Walk out of a meeting, speak your action items, follow-ups, and notes — Flow formats everything and you paste it where it needs to go. Email, Slack, Notion, your CRM.

Works on Mac, Windows, and iPhone. 89% of messages sent with zero edits. Used by teams at OpenAI, Vercel, and Clay.

Try Wispr Flow free

“Your Margin Is My Opportunity”—Jeff Bezos

Jeff Bezos originally used this line in 2012 to describe Amazon’s strategy of attacking industries where incumbents protected their own high margins instead of improving efficiency. At that time, these were the retail, publishing, logistics, and cloud computing sectors.

He also believes all companies need to be “young forever,” and that companies should “work to charge less, not more.”

Fast forward to 2026, and AI turns Bezos’ philosophy into a universal law of disruption.

And no sector of the economy is more vulnerable to disruption by AI than healthcare.

But healthcare organization incumbents of all kinds have been generally okay with the status quo, or at least haven’t felt significant risk of disruption. On top of that, they feel “protected” by rules and regulations, complexity, historical stability, and licenses. Remember the failure of Haven Healthcare? Ironically, that was Amazon’s early attempt to disrupt healthcare with Berkshire Hathaway and JP Morgan Chase!

The past attempts failed for explainable reasons when we look back in hindsight. But I think this time is actually different.

The old moats matter less every day, and policy (particularly via CMS and CMMI) is accelerating that.

Artificial intelligence’s ability to disrupt healthcare is being further enabled and accelerated by policy. Organizations moved and innovated before there were payment pathways in place because they anticipated that was a temporary problem.

CMS is pushing on interoperability, digital-first care, digital front doors, risk-bearing and outcomes-based payment, and quality being measured by outcomes data, not manual reporting.

AI-enabled disruptors are aligning with policy initiatives. Disruptors see margin sitting on the table, and they will take it.

Incumbents didn’t ask for AI.

They were stable. They were compliant. But stability is not a strategy.

Denial is the fastest path to irrelevance.

In healthcare, the organizations that will be left standing are the ones that adapt faster than their margin disappears.

Because AI is increasingly

exposing inefficiencies.
automating administrative tasks.
slowly shifting value away from traditional clinical labor.
enabling new entrants to build business models around incumbent friction.

Care Management Is Particularly Vulnerable

There is margin in care coordination and management, and that “manual care management” margin is being absorbed by tech-enabled care navigation companies. AI-enabled outreach platforms can:

stratify risk
automate outreach
escalate only the highest-need cases
run 24/7

Humans alone can’t compete.

Working in Population Health in the 2010s, clinician case managers and navigators could spend 1-2 hours reviewing various EMRs to get a grasp of a patient’s clinical care journey and social and functional factors to understand where they were now and what they needed. It was actually fun! I felt a bit like a sleuth 🕵️‍♀️ But efficient? 🤣

This is becoming a thing of the past. Care management platforms integrate information and surface it in just the right way for care teams to use it to engage meaningfully and build trust with patients and care partners. Here’s an example.

It’s Time to Evolve

The question is “What do you do now if you believe that organizations that survive will be those that get out of “denial mode?”

Denial is not just a river in Egypt.—idiom

1. Build an AI Integration Strategy

Groups need to look at their workflows and find where the costs are high and the value is low.

Audit repetitive tasks like documentation and patient outreach.
Start small pilots for administrative automation.
Teach clinicians how to supervise these systems rather than viewing them as rivals.

2. Double Down on Human-Only Skills

The value of a clinician is shifting.

AI can process data, but it cannot build trust or navigate all the emotional nuances of a patient's journey and the complexity of managing the continuum of care. Focus your talent development on the skills that value-based care actually requires. (See the Career Pulse section for more! 👇️ )

3. Create "AI + Human" Hybrid Models

The goal is probably protecting margins while retaining clinical talent and expertise. One example is implementing AI outreach for low to moderate complexity patient engagement and care management, with humans managing clinical escalation at the right time.

4. Anticipate Policy Acceleration

CMS is making it clear that they see the future as digital and outcomes-based. The policy levers are moving toward more risk, more accountability, and enabled by better interoperability.

Invest in data infrastructure that actually talks to other systems.
Join pilots and communicate through public comment letters to help shape future regulations.
Stay ahead of the shift instead of reacting to it once it becomes a mandate.

(See this May 11, 2026 JAMA Network article by Abe Sutton and Jacob Schiff on tech-enabled care and ACCESS. Note there is a paywall.)

5. Treat AI as a Strategic Asset

The antidotes to denial?

Experiments. Pilots. Persistence.

Find internal champions and measure ROI early.

Champion a mindset of early adoption, and communicate that value clearly to the clinical team.

Remember the uselessness of denial? 🙃

So if disruptors come in and re-imagine healthcare, and the healthcare industry evolves out of necessity, where does that leave the clinicians whose careers have been built on the way we’ve done things for decades?

After all, it’s all they know.

Hone The Skills AI Can’t Replace

Combine clinical and health tech knowledge with these “soft” skills:

Sales/Persuasion

Ever heard the saying “everything is sales?” It’s true. So lean in, because you need this skill in any role. This is more true now than ever.

“Remember that ”sales” means the ability to communicate value, successfully influence decisions, and help people take action.

Storytelling

Practice making the complex simple for others. Help others understand why something matters.

Rejection Tolerance

Resilience is always important, but never more than now. As roles morph, needs change, and expectations evolve, having this skill will help you roll with the punches and persevere. It may be a rocky few years.

Of coures, emotional durability will help you in all parts of your life.

A case study in resilience (while telling a story!) 😄

I clearly remember (while dating myself) in 2001, when the Home Health Prospective Payment System replaced retrospective payment of reasonable costs per visit in home health under Medicare. It coincided exactly with my start date in a Medicare home health agency as one of their first full-time PTs.

So to be fair, I never experienced the “old way,” unless you count commercial visits in non-Medicare agencies via FFS contracts.

The change to PPS created a fixed cost per home health episode, which fundamentally flipped the financial incentives to manage utilization of clinical care within a budgeted amount over 60 days. It was a volume to value play.

The average percentage drop in home health reimbursement per patient episode?

Around 24%! It’s also an important reminder that reimbursement cuts are not “new.”

While managing that reimbursement cut, agencies were also dealing with clinician attrition. Here’s why:

The nurse or therapist performing the home health initial visit now had to complete a new, extensive documentation tool called the Outcome and Assessment Information Set (OASIS) to determine the Home Health Resource Group (HHRG) episodic payment and capture quality, clinical, and functional measurements. Many Medicare home health agencies moved to simple “laptop-like” devices for clinicians starting with the introduction of the OASIS, like our agency did.

For many of the experienced clinicians, this was all too much change at once. Many clinicians left home health or retired early, or moved to non-Medicare home health agencies or certified home care agencies instead. They predicted a doom-and-gloom future for home health, and of course it’s still standing a quarter of a century later.

Staying and adapting to new expectations in their roles while learning new skills required a level of resilience and of flexible thinking. Those clinicians who were able to accept the disruption and still enjoyed the work of home health stayed and evolved. The home health agencies changed their strategies and retrained their care teams and office staff.

Home health is still adapting. Fee-for-service Medicare volumes are lower as a percentage of total Medicare admissions to home health, and this has largely also shrunk margins since FFS reimbursement is the highest.

For what it’s worth, I predict the next step for home health will be value-based contracting with at-risk entities to create and capture more value and corresponding reimbursement per episode of patient management. Let’s see if I’m right and how long it takes to be standardized.

Pair human skills with emerging tools and tech

All indicators are that this time really IS different.

Healthcare professionals are accustomed to relative stability, and that can make it hard to see the present for what’s actually happening.

Regardless of what changes, adaptability is the superstar trait employers, customers, and clients will look for in employees.

I’m a fan of Justin Welsh. I’ve taken other courses of his and am currently taking his Creator MBA course. So I’m passing along this Linked In post (adapted from a Tweet) for you, because he says it best 👇️

100% of successful people are lucky. The catch is they created the luck themselves. Luck shows up for people who keep putting themselves in better situations, around better people, and holding more interesting ideas. You can't guarantee it. But you can engineer way better odds. Every successful person I know runs some version of this: - Read. The cheapest way to collect ideas worth using. - Write. The clearest way to find out what you actually think. - Build. The fastest way to learn what's real and what isn't. - Network. The simplest way to be in the room when something happens. - Introduce. The most generous way to become someone people remember. If you want a system you can run on autopilot, try this: Monday: Read for 30 minutes. Tuesday: Write about something you learned. Wednesday: Code with Claude for 30 minutes. Thursday: Send 5 thoughtful DMs on LinkedIn. Friday: Connect two cool people (double opt-in.) That's 2 hours a week. About one quarter of a workday. In 12 months, your life will look unrecognizable. Job offers, partnerships, ideas, and friendships you didn't see coming will start showing up. People will tell you how lucky you are! And they'll mean it. Or don't run the system. Watch other people pull it off, and chalk it up to good fortune. If you're trying to engineer more luck into your career and your life, I write one short essay every Saturday on exactly how to do that. 5 minutes. No spam. Read by 180,000+ people. Get Saturday's essay: https://buff.ly/fmdmQ8T | 961 comments on LinkedIn

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The End of Hospital Dominance?

Dana Prommel Strauss — Mon, 04 May 2026 01:18:41 +0000

Beyond the Walls, in Brief

Download your free copy of the report 👇️

Beyond the Walls_Policy Pulse_Timeless Autonomy_5.3.26.pdf

2.93 MB • PDF File

Download

What this report will tell you (and why you should care)

If you work anywhere near care delivery, payment policy, or health operations, or you are a leader in healthcare or health tech, 2026 is not a typical year for hospitals. Four structural forces (regulatory, statutory, commercial, and capital) are moving in the same direction for the first time in two decades. The result: billions in hospital‑based revenue are being redirected toward offices, ASCs, and the home.

This report breaks down what changed, why it’s happening now, and what it means for clinicians, operators, and policy pros who need to stay ahead of the slope.

Executive Summary | The 2026 Site‑of‑Service Reset

1. Hospital spending is the biggest and fastest‑growing line in U.S. healthcare.

Hospitals captured $1.6T in 2024 and drove 40% of national spending growth. Prices have outpaced inflation for two straight years.

“Hospitals have been the most protected… That’s the part that’s now changing.”

2. Inpatient volume keeps shrinking while outpatient keeps rising.

Between 2000 and 2023, inpatient admissions dropped by nearly 19%, while outpatient visits surged by 31%.

3. Four forces are converging in 2026

Regulatory: IPO list elimination, ASC list expansion, OPPS site‑neutral expansion, PFS indirect‑PE redistribution.
Statutory: Unique NPI requirement for off‑campus HOPDs, Hospital‑at‑Home extension to 2030.
Commercial: Employers and MA plans steering aggressively to lower‑cost sites.
Capital: Nearly $40B in PE investment into ASCs across 2024–2025.
Together, these forces are structural, not cyclical.

4. CMS moved more in one rulemaking cycle than in the last decade.

285 procedures removed from the IPO list in 2026.
547 procedures added to the ASC list.
Grandfathered HOPDs now paid 40% of OPPS for drug administration.
Facility‑based cardiology projected to see –7% revenue change from PFS redistribution.

5. Home is now a (nearly) permanent, reimbursed site of care.

Hospital‑at‑Home is extended through 2030, with outcomes showing 38% lower cost and 44% lower readmissions. Virtual supervision is permanent. RPM is standard. The home is now part of hospitals’ infrastructure.

6. By 2030, the slope, not the direction, is what’s uncertain.

The optimistic scenario? Maybe it shifts $200B+ in outpatient spend to ASCs, offices, and home. The pessimistic scenario slows federal savings but doesn’t stop commercial migration. The baseline: steady erosion of hospital pricing power and a consolidation wave.

So here’s what you now know

The shift away from hospital‑based care is at least partially the result of a structural realignment of incentives, capital, and clinical capability. That means:

Clinicians should position around outpatient leverage: ASC partnerships, portable case mix, or APM‑aligned work.
Healthcare leaders should track the boring‑but‑foundational infrastructure changes (unique NPIs, site‑neutral scoring, state facility‑fee bans) that set up the next round of reform.
Operators and health tech should build for distributed care—ASC‑grade systems, home‑based diagnostics, and coordination across fragmented sites.

The takeaway:
Care delivery finally moving to the settings where patients prefer to be, and where the system can afford to send them.

Use this report as your briefing for the next phase of the shift. The levers are already pulled. The question now is how you position yourself and how it might impact you and your work.

Two Incentive Layers, And Why You May Feel Stuck

It’s easy to think this as a clinician: If you do good work, the system will reward you.

But healthcare isn’t one system. It’s two incentive layers running on top of each other:

Personal incentives (you): patient outcomes, professional reputation, work-life balance, clinical craft, doing the right thing.
Organizational incentives (your employer): revenue, efficiency metrics, market share, payer leverage, throughput, risk, and optics.

If you don’t separate these two layers, you end up in constant confusion:

“Why is leadership pushing this?” “Why doesn’t this change?” “Why do I feel like I’m compromising?”

The cause of confusion? An incentive mismatch.

Stop trying to “find a better job” before you learn to read the incentive layer you’re standing on.

Because incentives shape what gets measured, funded, staffed, and rewarded—and that shapes your options.

Why this matters in any setting

When you can name the incentive conflict clearly:

You stop internalizing it as personal failure (“I’m not doing enough”)
You reduce moral injury (“I’m trapped in a system that rewards the wrong thing”)
You gain leverage (“I know what language decision-makers respond to”)

Or said differently:

You stop asking “why don’t they just do the right thing?” and start asking:

“What would make the right thing the easy thing?”

The real career unlock: learn which lever you’re holding

Here are a few examples of how incentives quietly steer your day-to-day—and your career ceiling:

Hospital-based practice
If the system earns more from facility-based billing, there can be subtle pressure to keep services in-house. Understanding this helps you advocate for the safest, most appropriate site of care and avoid getting pulled into “keep the volume” politics.
Primary care
If compensation is panel size and RVUs, prevention and coordination get squeezed. Clinicians who understand this often build a niche: complex care management, value-based programs, team-based workflows, quality leadership.
Anywhere you’re asked to do “more” with no resources
“We want better outcomes and happier staff” paired with no staffing change is an incentive mismatch. Naming it is how you ask for the missing input: time, training, tools, staffing.

A simple framework to save and reference later 👇️

Ask these 3 questions about any role you’re in or considering:

What gets paid for?
What gets measured and reported?
Who benefits if we do more of X and less of Y?

If you can answer those, you can predict your future stress points and your future opportunities.

Write 2 short lists:

A) Personal Incentives (Top 5)

What you actually optimize for (even if you haven’t been allowed to say it out loud): outcomes, autonomy, schedule, mastery, relationships, energy, learning, leadership, etc.

B) Organizational Incentives (Top 5)

What your employer optimizes for: volume, RVUs, payer mix, downstream capture, length of stay, star ratings, HEDIS, readmissions, margin, referrals, etc.

Then answer:

Where do these overlap? Where do they clash?

That clash is your burnout risk.

That overlap is your career leverage.

How this helps your career (and makes you feel less powerless)

When you learn incentives, you can:

Make better career decisions: Evaluate jobs by the real drivers, not the brochure.

Negotiate smarter: Ask for what changes outcomes/workload: support staff, visit length, protected time, caseload caps, documentation support, training budget.

Influence more effectively: Frame proposals in access, retention, quality, cost avoidance, risk reduction, patient experience.

This is the difference between being “right” and being effective.

Healthcare runs on incentives. Learn to read them, and you’ll stop feeling stuck or powerless and start making moves that actually work for you.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The One Exercise I Gave (Almost) All My Patients

Dana Prommel Strauss — Mon, 27 Apr 2026 03:16:49 +0000

Fear of Falls Causes Falls: The One Exercise That Changes the Trajectory

Most falls prevention conversations start with the environment.

Yes, remove the throw rugs.

Yes, raise the bed, add grab bars, and help someone order a lift chair.

Those things matter.

But in home health, I kept seeing the same pattern: the real risk often lived inside the person, not just inside the house.

When someone is afraid of falling, they move less.

When they move less, they get weaker, stiffer, and less steady.

And then the fear becomes reality.

This is the loop I want to interrupt.

The invisible driver of falls: fear + immobility

In practice, “fall risk” rarely has a single cause. It is usually a pile-up of factors that make a person feel unsteady, exhausted, and unsafe.

Here are some of the common contributors I saw again and again:

Impaired sensation
Depression
Fear of falls
Not feeling well
Obesity
Very limited endurance
Arthritis
Edema

Many of these are chronic.

Some are hard to change quickly.

And when someone has longstanding ways of doing things?

Building new habits can feel almost impossible.

They need to feel progress.

Because one setback, like an illness or a short hospital stay with immobility, can drop someone right back to “square one.” Weakness is both a side effect and a cause of exacerbations. It can be insidious.

It can even be why patients get labeled “non-compliant,” when what is really happening is that movement has become scary and exhausting!

The one thing I tried to make (almost) everyone do

Over time, I stopped looking for the perfect plan and started looking for the most repeatable plan.

What could someone remember on their hardest day?

What could someone do safely at home without special equipment?

What would actually build strength, balance, and confidence at the same time?

The answer was surprisingly simple:

Sit-to-stand repeats

Stand up from a chair.

Sit back down.

Repeat.

That is it.

And it is powerful.

Why habits matter more than heroics

The biggest challenge was never explaining the exercise. The challenge was adherence.

Most people won’t actually follow another complex program. They will abandon it the moment they have a flare-up, a bad night of sleep, or a week of feeling low.

They need reassurance. They need practice. They need a habit that survives real life.

That is why “success” in falls prevention is less about a single perfect intervention and more about building feedback mechanisms that keep someone going.

Progress has to be noticeable, barriers have to be removed, and support cannot depend on one clinician being a superhero.

The bigger opportunity: prevention embedded in care episodes

Don’t think of falls prevention as a “clinical issue.” It is a system opportunity.

If we take episodes like Resilience and Independence in a Safe Environment (RISE) to Age in Place Episodes seriously, we can build embedded prevention into the moments when risk is highest.

Pull the falls-prevention lever before the next crisis.

Use prevention to avoid another episode, another hospitalization, another stretch of immobility.

Because when we reduce immobility, we reduce weakness.

And when we reduce weakness, we reduce falls.

From CMS-Administered Risk Arrangements (CARA) Factsheet

(Note that CMMI made an update to explicitly include physical therapists in the RISE care team.)

Getting started: the simplest version

If you want to test this approach with yourself, a family member, or a patient, start small.

Pick a stable chair.
Make sure the setup is safe.
Do a number that feels easy.
Repeat it daily.

Then scale up gradually.

The goal is not to “crush a workout.”

The goal is to build a behavior that still happens on the day someone feels tired, stiff, or scared.

The Policy Bottom Line

We can view “sit-to-stand” as a clinical micro-habit, but we can also view it as a risk-mitigation strategy.

Because whether you care about the TEAM Model, an MSSP ACO, the new CJR-X, or even in the Home Health Quality Reporting Program (QRP), Skilled Nursing Facility QRP or Value-Based Purchasing Program, immobility is a liability.

By embedding simple, repeatable habits into care episodes, we can reinforce the financial success of the entire value-based care framework.

Closing thought

Fear of falls causes falls.

But confidence is trainable.

And sometimes the most effective tool is the one a person can do, remember, and repeat day after day until it becomes normal.

Next step: If you are building a falls-prevention program, ask one question: What is the habit we want people to do when life gets hard?

5 Stocks Redefining the Defense Technology Sector

Defense spending is at its highest point in decades, and the companies capturing those dollars have changed. A new class of contractors is winning Pentagon business with AI-driven systems, satellite infrastructure, and advanced aerospace technology. This free research report profiles five of them. You'll find what each company does, why it's winning contracts, and what the growth case looks like from an investor's perspective. These aren't household names yet. That's the point. Download the free report and see why analysts are paying attention to this corner of the market before the rest of Wall Street catches on.

Download the free report

I saw this post last week and it stuck with me.

Here’s a snip from the post:

He was referring to eating well and exercise. But this applies to career growth, too.

You may be doing things on your own time to grow your non-clinical skills and think “Am I wasting my time?” or “How is this going to really help me?” Because when you start out, we are taking a leap of faith. We must believe that this work on our free time will pay off. We may be sacrificing our time with our families and friends, or free time to just relax. The bottom line is we may not know HOW the investments in ourselves will pay off.

Know that they will, in one way or another.

You will have the fresh idea to solve an old problem, or a perspective your peers don’t see.

I have a few friends who are physical therapists in an outpatient PT department of a hospital. They have spent time on their own learning about value-based care and what physicians in ACOs are trying to accomplish. They started taking small steps to contribute to the efforts.

In one example, the rehab manager reached out to a primary care nurse practitioner in the ACO. The NP was receptive to a collaboration on a standardized pathway where therapists helped manage patients with musculoskeletal pain, balance impairments, and movement issues.

But it started with self-educating on how ACOs work and what the levers are success are. Managing patients with musculoskeletal pain, balance impairments, movement impairments and more via physical therapy is a great alternative to higher cost and avoidable interventions. PCPs should know what the PTs’ capabilities are at the top of their scope of practice and feel confident that the therapists can offer prompt access to care.

The takeaway:

If you find a spark of interest in something related to healthcare, learn more, even if you don’t know how you will apply it. The non-clinical self-education we do on our own time will pay dividends, even if you don’t know what that looks like yet.

Here are three pieces of recent content that stuck with me:

From KFF: Affordability is the Issue Now, But Look for the Uninsured to Make a Comeback. Find it here.

Drew Altman emphasizes affordability’s political salience but warns the uninsured, especially the sick, represent a glaring system failure and calls for policy attention to protect vulnerable families and workers.

From McDermott+: Food for thought: Automatic enrollment into Medicare Advantage. Find it here.

CMS recently signaled it’s studying models to automatically enroll newly eligible beneficiaries into Medicare Advantage or into accountable care arrangement in fee-for-service, while allowing opt-outs. Authors Jeffrey Davis, Parashar Patel, Lynn Nonnemaker, and Olivia Gomez examine possible implications. The piece explains current enrollment pathways via Social Security Administration (SSA) and Medicare.gov/plan-compare, considers default assignment mechanics (including impact on access to Special Needs Plans and on future Medigap guaranteed issues), and outlines alternatives such as affirmative choice or expanded seamless enrollment. They explore effects on beneficiaries, providers, MA plans, and federal agencies, noting potential shift in market concentration, administrative burdens, legal risks around assignment criteria, and the need for stronger interagency coordination and funding to implement any change.

From Health Affairs: Levels, Growth, and Semantics: The Role of Prices in Driving Health Care Spending. Find it here.

Michael Chernew examines how price definitions and semantics shape interpretation of recent health spending data, arguing that price growth did not drive the roughly 4 percent inflation-adjusted increase in National Health Expenditures between 2023 and 2024, according to analyses by CMS. He contrasts explanations for spending levels, where high US prices (relative to other countries) are central, with drivers of spending growth, which CMS attributes mainly to volume and mix. He urges policymakers to pursue both price-focused reforms (like caps on high prices and site neutral payments) and measures addressing utilization, mix, and innovation. he notes that fixing persistently high prices remain important even if they aren’t currently the primary source of year-to-year growth.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The False Divide Between Acute and Chronic Care is Diluting Your Strategic Edge

Dana Prommel Strauss — Mon, 13 Apr 2026 00:15:00 +0000

Read online

Silos are Strategic Liabilities

Most people pick a side in value‑based care.
Episodes of care or total cost of care.
As if they’re rival ideologies instead of complementary levers.

That false divide is slowing progress.

Models like BPCI‑Advanced, which overlapped with ACOs (patients can be attributed to an ACO and “fall into” a BPCI-A episode based on their hospital stay final DRG), make the connection impossible to ignore. When a patient sits in both programs, incentives stack. Suddenly, the ROI of devoting resources to managing an acute episode starts to look different.

And that’s where the real leverage is.

Acute episodes create accountability for the post‑discharge trajectory and post-acute throughput of often complex, vulnerable patients.
ACO infrastructure creates accountability for the long‑term trajectory of all attributed patients. Together, they form a feedback loop that improves quality and reduces avoidable spend.

Policy is moving in this direction.
The LEAD model and the IPPS proposal to expand CJR nationwide signal a future where episodic and population‑based models overlap by design.

Clinicians should take note.

Hospitals should take note.

Advanced primary care teams accountability for cost and quality of care should take note.

Then layer on chronic episodes of care, which the LEAD model plans to add in the near future.

Here’s the thing—

Chronic disease management, typically the work of advanced primary care teams, can reduce ED visits and inpatient admissions. But care for some conditions is often driven by clinicians outside the advanced primary care team’s walls. This is the basis of long-term episode types. They create a framework for partnering with providers managing specific conditions that are the drivers of high spend.

Chronic episodes of care payment arrangements, such as those for diabetes, depression, low back pain, and chronic kidney disease, can help reduce the likelihood of a patient presenting to the ER or being admitted to the hospital by aligning incentives between the at-risk providers and/or organization and others in the clinical care ecosystem.

And when a patient in a chronic episode IS admitted to a hospital, the acute episode program structure can function as a part of the continuum of coordinated care.

This is where trust is built with patient.
This is also where goals‑of‑care conversations finally happen. And speaking of goals of care—

Advanced Care Planning Emerges in the 2027 IPPS Proposed Rule

The latest IPPS proposal includes an eCQM advanced care planning measure. CMS understands that patients need to be engaged in conversations that help them understand their options and make informed choices. Yes, advanced care planning must happen regularly in outpatient physician practices. But they belong in the hospital, too. More on that shortly.

The bottom line:

Episodes of care and total cost of care aren’t separate domains.
They’re interlocking gears.
Acute episodes, chronic care management, and population‑level accountability work best when they work together.

That’s how you improve outcomes.
That’s how you reduce avoidable spending.
And that’s how you build a system that finally makes sense for patients.

Why the Overlap Matters Now

Episodes address the “discharge fast, hope for the best” problem.
Hospitals have historically been incentivized to move patients out quickly, not ensure what happens next is in the best interests of the patient given the totality of their needs.
ACOs address the “nobody owns the long‑term outcome” problem.
Primary care teams have a long-term perspective and often focus on population-based levers like preventive testing, annual wellness visits, and patient engagement.
Together, they create shared accountability for the full patient journey and the reality of navigating the health care ecosystem.
Acute → post‑acute → chronic → preventive.
One continuous arc instead of disconnected events.
Policy is aligning the incentives.
More overlap between episodic and population models is growing because we’ve learned how powerful it can be based on model tests.

                ┌──────────────────────────┐
                │      GEAR 1: ACUTE       │
                │        EPISODES          │
                ├──────────────────────────┤
                │ • Manage hospitalization │
                │ • Own post‑discharge     │
                │   trajectory             │
                │ • Reduce complications   │
                │   + readmissions         │
                └─────────────▲────────────┘
                              │
                              │ feeds into
                              │
┌──────────────────────────┐  │   ┌──────────────────────────┐
│   GEAR 3: TOTAL COST     │◄─┘   │     GEAR 2: CHRONIC       │
│        OF CARE           │       │        EPISODES          │
├──────────────────────────┤       ├──────────────────────────┤
│ • Close preventive gaps  │       │ • Stabilize complex pts  │
│ • Manage long‑term risk  │       │ • Engage caregivers       │
│ • Reinforce episode      │       │ • Enable goals‑of‑care    │
│   success                │       │   conversations           │
└─────────────▲────────────┘       └─────────────▲────────────┘
              │                                    │
              └────────────── interconnected ──────┘

What Policymakers Are Signaling

We are entering the phase where learnings from the past 12+ years of value-based care model testing are paying off. Policymakers know more about what works, and they are doubling down on that.

Model overlap is more intentional.

There is an incremental benefit to the patient and there’s a greater chance of improving cost and quality outcomes when patients fall into both program types. The TEAM Model and CJR-X are overlapping with MSSP and LEAD by design. What this means is hospitals must think about their role differently. Their engagement in helping to drive down medical cost trend is non-negotiable.

There’s a greater emphasis on advanced care planning.

It was tested as a quality measure in prior models. In the 2027 IPPS Proposed Rule, we see it emerge as a quality measure for the hospital itself. It’s time to move beyond the acute care excuses of “that’s not my job,” and of physicians in the hospital saying “that’s for their primary care doctor to deal with.”

No.

Primary care must do its part. They must have regular discussions with their patients with chronic and serious illness and make sure they understand their disease trajectory, their goals, and their options. No argument here from me.

But hospital-based clinicians don’t just get to wash their hands of it because of where they interact with patients. It’s easier (and necessary) to access the information needed to have a meaningful conversation about a patient’s advanced care plan while a patient is in the hospital.

And it’s not something that can be punted to a nurse or a social worker—a frustrating push-back I heard for years. Physicians must own this as part of their responsibility. Hospitals will need to put systems in place to ensure this happens. That being said, it’s harder than most think.

But this is the beauty of CMS’ statutory authority to drive care transformation. It’s a requirement for everyone, so everyone will have to figure it out.

CMS is ratcheting up expectations of cross-setting coordination of patient care, and caring for patients with their whole care plan in mind. Not just the plan to discharge them.

A lack of meaningful incentives has yielded fragmented silos of care. Hospitals, primary care, specialty care, post-acute sites—they can’t operate in their own bubbles anymore. Or at least they shouldn’t.

Accountability expectations are changing.

It used to be perfectly acceptable to only be accountable for the actual work you do when in front of a patient or when they are in your building. Soon, we will all see that those were the “bad old days.” Policy changes, including payment incentives, changes to conditions of participation, interoperability requirements, and health tech advancements are accelerating the pace of change.

For hospitals themselves, length of stay is no longer the only metric that counts.

Stop Asking AI for Answers

Most people are using AI incorrectly.

They treat it like a vending machine:
Type a question, get a fact.

But facts aren’t what move your career forward.
Frames do.

The people who win in non‑clinical roles aren’t the ones who know the most.
They’re the ones who can interpret the most.

So here’s my take:

Stop asking AI for information.
Start asking it for orientation.

Ask it to show you:

How experts think
What beginners miss
Where the leverage points are
Which questions matter and which don’t

Because once you understand the shape of a problem, you can generate insights that no one else is thinking about.

And insights are what make you valuable in the modern healthcare economy.

Not credentials, not job titles, not years of experience.

Insights.

AI won’t replace you.
But if you keep using it like Google with better manners, someone who uses it to think will.

Here’s an example prompt and response about the 2027 Inpatient Payment System Proposed Rule that was published Friday late afternoon:

Prompt:
Explain the 2027 IPPS Proposed Rule like I have a Director-level role in a hospital. I want to understand the implications of the rule, including how what is proposed aligns with CMS’ strategic direction.
Focus on what CMS highlights in their press release and fact sheet.
What will hospital leadership have to plan for because of the changes and how will they impact their annual goalsetting and strategic planning?
What is the executive team likely to underestimate and what are the signals through the noise?
Response: (I used the personal pro version of Microsoft Copilot Chat):
1. How the rule aligns with CMS’ strategic direction
CMS is using the 2027 IPPS rule to push three big themes:
Accountability for total episode cost and outcomes via the nationwide, mandatory CJR‑X model for lower extremity joint replacement in both inpatient and outpatient settings.
Acceleration of digital quality measurement through expanded and refined eCQMs, moving hospitals toward real‑time, electronic reporting instead of retrospective chart abstraction.
Consistency and transparency in payment policy with annual IPPS/LTCH updates that reinforce value, equity, and data-driven oversight.
Translation for a Director: CMS is telling you they expect tighter integration across the continuum, cleaner data, and fewer excuses.
2. What hospital leadership will have to plan for
From a planning and goalsetting perspective, leadership will need to:
Bake CJR‑X into service line strategy
Revisit joint replacement volumes, LOS, post‑acute patterns, and readmission risk.
Align orthopedics, therapy, case management, and post‑acute partners around standardized pathways and functional milestones.
Align annual goals with eCQM performance
Set explicit targets for the new and revised eCQMs.
Invest in documentation workflows, EHR builds, and frontline training so data are captured in structured, reportable form.
Tie quality, finance, and operations goals to the same measures instead of running three separate scorecards.
Integrate policy into strategic planning cycles
Move from “IPPS update as a finance event” to “IPPS update as a strategic reset” for care models, staffing, and technology.
Use the rule to pressure-test capital plans (e.g., digital, analytics, post‑acute partnerships) against where CMS is clearly heading.
3. What the executive team is likely to underestimate
Most executive teams will underestimate:
The operational lift of CJR‑X
They’ll focus on projected margins and stop there. The real risk is variation: inconsistent discharge criteria, uneven therapy intensity, and fragmented post‑acute relationships that quietly erode episode performance.
The culture change required for eCQMs
They’ll assume IT and Quality can “handle the measures.” But the real work is behavior change: clinicians documenting differently, managers using real‑time dashboards, and leaders treating data quality as a frontline competency, not a back-office chore.
The compounding effect on strategy
Each rule looks incremental, but together they signal a clear direction: more risk, more transparency, more expectation that hospitals function as integrated systems. Underestimating that arc leads to reactive, year‑to‑year planning instead of a 3–5 year repositioning.
Signals through the noise:
CJR‑X = CMS is comfortable making mandatory, nationwide models the norm, not the exception.
eCQMs = CMS expects digital, near‑real‑time quality data as table stakes.
IPPS updates = annual nudges toward value, not just rate changes.

Here’s how you can use this information:

This kind of prompt and response can help you build a strategic lens to consider “What is CMS really trying to make hospitals become?”

It can also give you an automatic upgrade in conversations with leadership. The response may be what they perhaps should be considering, but that doesn’t mean they are. If a Director has those points in hand, they can bring to executive leadership meetings:

“How are we planning for CJR-X beyond just finance modeling?”

“Which eCQMs are we treating as enterprise priorities, not just quality projects?”

Armed with this AI-assisted analysis, the Director can create a one-pager or a slide or talking points, positioning themselves as someone who can translate policy into operations and strategy promptly.

And that’s the real advantage. AI can help you understand policy. Without a doubt, that’s valuable on its own. But it also helps you show up as the person who can turn policy into action.

Because anyone can read a rule. But few think to translate it into strategy. With AI as your amplifier, you become one of the few.

So much to consume, so little time. But healthcare and health policy content fluency can give you a career edge, so give it a try.

Here are three pieces of content that stuck with me this week:

From KFF: Affordability is the Issue Now, But Look for the Uninsured to Make a Comeback. Find it here.

From McDermott+: Food for thought: Automatic enrollment into Medicare Advantage. Find it here.

From Health Affairs: Levels, Growth, and Semantics: The Role of Prices in Driving Health Care Spending. Find it here.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The LEAD Model and Your Secret Clinical Advantage

Dana Prommel Strauss — Mon, 06 Apr 2026 00:21:19 +0000

Policy Pulse

Read online

The Long-Term Enhanced ACO Design (LEAD) Model’s long-awaited Request for Applications is out. Applications are due May 17th, and CMMI graciously made the application abbreviated for ACOs already participating in ACO REACH!

My initial thoughts when the basics of LEAD were announced in December of 2025 can be found here.

Since I’m not doing a deep dive summary of LEAD today, here’s a super comprehensive and awesome landing page with organized details about the model made by Brad Heywood. Check out the cards that link out to all the relevant areas! 👏 👇️

From Brad Heywood’s LEAD Model Overview | LEAD Model Knowledge Center

Here are two components of LEAD that I’m particularly interested in:

CMS Administered Risk Arrangements
Testing of “AI Inferred Risk”

Let’s dive in:

CMS Administered Risk Arrangements (CARAs)

This model is the first time CMS is testing CARAs. They are a voluntary option for ACOs in Global Risk Arrangements only.

The idea is this:

Some ACOs whose patients overlapped with other CMMI episodic models’ inclusion criteria, like the Bundled Payment for Care Improvement Advanced (BPCI-A) Model, would receive what I called “bundle data” at the time.

From that data, they could (and we did) build longitudinal views of patient journeys. Combine that with access to EMRs along that journey and we were able to identify root causes of avoidable spend and poor patient outcomes and address them. For those patients who overlapped with our ACO patients, the value was actually exponential.

Called out by Premier, Inc. and others, CMMI saw the value in this data and began providing it to ACOs for their attributed patients. So let’s say my patient Mrs. Smith is in my ACO and had a hip fracture with ORIF. If that patient “fell into” a BPCI-A program, that would trigger a “surgical hip and femur fracture treatment” DRG and that would trigger a BPCI-A episode. So CMMI started sharing the same information on that episode with the ACO as if they were also participating in BPCI-A and the patient “fell into” that episode.

Some ACOs have used that data like we did back in the late 20-teens, mapping patient journeys and addressing root causes of potentially avoidable high cost and lower quality care that led to poor outcomes. That information and those insights could be shared with providers in the community along the continuum that provided care to the patient for some portion of time during the episode. It’s a powerful way to help incentivize care transformation!

From the Notioly Collection

Enter the LEAD Model, and CARAs are an embedded part of the model. CMS is offering two options:

Default. ACOs can choose CMS-constructed Episode-Based Cost Measures (EBCMs). They may not be customized for which codes are included or the episode lengths (acute + 30 vs. 90, for example) but can be customized for certain quality measures and discounts. Great starting point.
“Max Flex.” Here’s where it really gets interesting. ACOs can now customize existing EBCMs and can even work with vendors for alternate episode construction! Requires more advanced analytics and experience with episodes. Prior overlap with BPCI-A or the Comprehensive Care for Joint Replacement (CJR) model? Ideal.

It gets even more exciting! 😂

Not only will there be acute medical, surgical and procedural episodes, but CMS will phase in chronic condition episodes! I’m sure I’m not the only one thinking about how beautifully, and likely intentionally, this overlaps with the ACCESS Model.

And enter the Resilience and Independence in a Safe Environment (RISE) to Age in Place falls prevention episode! 🥳 🙌

I spent years working in and then with home health and can’t say enough about how big the opportunity is to improve quality of life, the ability to age in place, and to reduce total cost of care if we can prevent a percentage of falls via addressing balance impairments and home modifications.

CMS establishes Level II HCPCS G-codes for RN and OT services that will be zeroed out. My only beef here is PT should be included. PT at home can be provided under Medicare Part B for medically necessary balance training and other interventions. For my PT friends, it’s a great opportunity to collaborate with your local ACOs on this!

For all the details, find the LEAD RFA here. The resource linked above by Brad Heywood is another great starting point.

Why I Love CARAs:

The overlap of ACOs and Episodes of Care is a powerful one. My past experience taught me the value of managing both total cost of care and embedded episodes of care. Episodes of care, especially the acute care episodes, are often triggered by the most vulnerable of our population.

And it’s a jungle out there!

Transitions of care, competing incentives of post-acute providers, data-sharing challenges, medication reconciliation issues and much more are inherent risks for anyone, but especially our most vulnerable. The outcomes of an episode can influence someone’s life literally forever. There is still so much opportunity to do better. Embedded episodes create an incentive for ACOs to invest in care continuum navigation, post-acute partnerships, strengthening home-based care opportunities, and more.

My biggest fear? ACOs don’t volunteer.

Preferred Providers

I don’t have the data, but ACO REACH entities largely haven’t jumped on the bandwagon to enter into downstream contractual relationships with specialists and other providers like post-acute providers and rehab therapy clinics. Yet we know a high percentage of spend lives right there!

My wish for LEAD: Much greater adoption of Preferred Provider relationships and widespread participation in CARAs.

Testing AI Inferred Risk Adjustment

Risk adjustment in Medicare Advantage and Fee-for-Service value-based care models is the topic of book chapters and out of scope for this article.

Here’s an article by the Commonwealth Fund covering the basic and a visual snippet from the article 👇️

Risk adjustment in Medicare was developed to prevent adverse selection by plans so that CMS pays plans more for beneficiaries with a higher risk of medical spend based on certain diagnoses and demographic information. Diagnoses must be identified by physicians (and advanced practice providers) to determine this component of the risk adjustment factor. ACOs use the same methodology but calculate expected spend a bit differently, and it varies based on the model.

In LEAD, CMMI is actually doing two things with risk adjustment for the first time.

First, they are embedding three different models based on beneficiary category.

Aged and Disabled
End Stage Renal Disease
High Needs (which had its own Track in ACO REACH whose participants were all at-home medical providers like Harmony Cares).

Three different risk adjustment models is exciting in and of itself.

But then, they added a twist.

CMS will test a transition away from provider-identified diagnoses to construct an individual’s risk adjustment factor annually to an artificial intelligence “inferred” risk.

This is not the first time “inferred risk” has come up. Abe Sutton, now Director of the CMS Innovation Center (CMMI), and Gabe Drapos, the COO of Pearl Health, wrote what is now an infamous Health Affairs article in 2024 called “Inferred Risk: Reforming Medicare Risk Scores to Create a Fairer System.”

From Health Affairs Forefront April 24, 2024

Here’s how this will work in LEAD:

In 2027 and 2028, CMMI will calculate benchmarks and reconciliation in LEAD using the standard risk adjustment methodology and the LEAD Model specifics.

In 2028, they will “shadow test” AI-Inferred Risk.

In 2029, the AI weight of risk adjustment will be 33%.

In 2030, the AI weight of risk adjustment will be 67%.

And in 2031, risk adjustment in LEAD will be 100% captured by AI inferred risk.

Here’s my take:

CMMI tests new models and methodologies to incentivizing and paying for care in Medicare and Medicaid.

They are testing inferred risk adjustment in the fifth generation of the advanced ACO model at CMMI (Pioneer ACO → Next Gen ACO → Direct Contracting → ACO REACH → LEAD).

They have been refining and adapting the advanced ACO model with each generation. And for the skeptics out there—it’s incredibly hard to change how care is paid for, incentivized, and especially, delivered. Healthcare is unique in many ways. It makes total sense that research and development through model tests have been needed to get us this far.

If inferred risk is successful, keep this in mind next: CMS has always used the same HCC Model for Medicare Advantage and the ACO Models. We saw that most recently in the move from V24 to V28 of HCC, when CMS finalized a three-year phase in of the new model. They created the same phase-in for MSSP and ACO REACH.

So if successful model tests lead to successful permanent models or model components being adapted in Medicare, and if CMS has always used the same risk adjustment model in MA and FFS ACOs, there’s a more than minimal possibility that inferred risk becomes the model used in MA in the future, too.

No doubt there will be refining of the model over the next few years. CMS as the payer in a CMMI model is more able to manage these refinements than plans are. So it makes sense to test first in LEAD.

More to come on the details of the new AI Inferred Risk Model in the future.

Note: Martin Cech also covered this nicely and in more detail in his “Weekly Health Policy Briefing 04/02/2026” post for Health Tech Nerds.

Health Tech Nerds

Insightful content and vibrant community trusted by over 30,000 healthcare leaders and innovators.

The Hidden Advantage Clinicians Often Don’t Realize They Have

Every non-clinical role I’ve earned was the result of a combination of two main things:

What I learned from years of direct patient care, such as what drives outcomes, what people really need, what gets in the way of that
What I observed happening at the system level. I connected dots most people weren’t looking at.

That was my competitive advantage. Unintentional, maybe. But looking back, it’s clear.

Here’s what you already know

You’ve seen where care breaks down, and these are quality, operations, and product insights
You understand what motivates people vs. what derails them, and these are behavior change and user experience insights
You know what actually improves outcomes vs. what the system assumes improves outcomes

What you’ve learned by paying attention (and if you haven’t been, start today!)

patterns in workflows, documentation, communication gaps, and patient journeys
how policy changes, staffing models, and reimbursement rules played out and impacted care
understood the downstream impacts of decisions made above your pay grade
recognize opportunities before leadership because you were actually closer to the truth

Know this, my clinician friends: the system often trains clinicians to stay in their own lane. And because few clinicians have had education in payment policy or the business of healthcare, they sometimes doubt their own insights. Don’t be one of those clinicians. You can learn most of what you need to on your own time to help make sense of what you observe in the clinic and in the system around you!

You see, leaders in healthcare delivery organizations are often too far removed from the front line to see emerging problems early.

And very few people have actively worked to translate clinical reality into business strategy.

That is your differentiator.

You understand the human side of care and the system side of care and can bridge the two.

You have lived the friction points that product, policy, operations, and other teams are trying to solve.

You can spot risks, opportunities, and unintended consequences before they hit the business’ dashboards.

You bring insight that only comes from being close to patients and close to the system in which they are cared for.

So take this inspiration this week and articulate what you already see. You don’t need another degree for that. Embrace your competitive advantage as a clinician. And do NOT take for granted the skills you think are “just part of the job” because they are the things non-clinical teams struggle with.

Here’s what used to ring in my head on the regular—”Why does no one else notice this?” “This” is the insight you have when you notice how systems awareness intersects with clinical experience in ways that can be improved upon. It can be a pattern, a breakdown, an unintended consequence, and often it’s hiding in plain sight.

That’s your signal.

Here’s an example:

A patient was discharged after a CHF exacerbation with a stack of papers, a rushed medication list, and no real teach‑back. Everyone assumed the discharge was “complete.” But you noticed the pattern: every readmission in that unit involved the same three issues:

inaccurate med rec
no care partner involvement
no confirmation that the patient understood the plan

Here’s what was actually happening:

Medication Chaos: Patients were going home with outdated lists or duplicate meds because no one cross-checked the EMR against the bottles they actually had at home.
The Communication Void: Care partners were left out of the loop, and "teach-back" was skipped, leaving patients nodding along without truly understanding red flags like fluid overload.
The Bridge to Nowhere: Follow-up appointments weren’t booked until the patient was already home, leading to late visits and inevitable ED returns within 10 days.

The solution you came up with:

Verified Med Rec: A two-step process to verify EMR lists against actual home bottles.
Care Partner Bridge: A mandatory phone script for families and a simplified teach-back checklist.
Confirmed Follow-up: A new workflow to ensure the first appointment and transportation were locked in before discharge.

Readmissions for heart failure dropped.

Extra work outside your role? Very likely!

An indirect investment in your career? Absolutely!

So the next time you find yourself asking “Why does no one else see this?” don’t dismiss the thought. It’s gold. That question is the beginning of a strategy. You don’t need a seat at the executive table to connect the dots. Trust that what you see from the front lines is the valuable data the system has but only treating clinicians can see.

Start circulating those insights with something like a “field insight” email to the director or to a team huddle: “I noticed a pattern with our last three CHF discharges. There’s a consistent gap in med rec that seems to be driving the readmission rate. I’ve put together a 3-point checklist that might plug this hole. Who should I send this to for a quick look?”

When you translate what you see at the ground level into a suggestion for the business, you are actually auditioning for your non-clinical role.

This week, I’m listening to and reading a book by my friend Gary Jacobs’ called The Zen Lobbyist.

The book follows Gary’s journey from entrepreneur to lobbyist and offers a framework for transforming the healthcare system through prevention, primary care, and thoughtful policy engagement. He also teaches readers how to stay centered and effective in high-pressure environments, which is an added bonus.

Here’s why I recommend reading it:

It shows how to advocate with compassion and pragmatism, which are skills every “clinician-turned-strategist” needs in their toolkit.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Value-Based Care Has Arrived, and It Lives in Your Patient's Living Room

Dana Prommel Strauss — Mon, 30 Mar 2026 00:15:00 +0000

Policy Pulse
Career Moves
- The Command Center Era: From the Unit-Bound Clinic …
This Week, Try This
- Read about the Kidney Care Choices Model Year Two …

Read online

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Policy Pulse

Your Hospital Isn't Designed to Heal You

Why the shift to care at home is the most important transformation in modern medicine

If you want to know where the biggest dent in American healthcare spending will come from, look no further than the hospital. Specifically, the significant amount of care we provide within its walls that simply doesn't belong there.

The Hospital Was Built to Stabilize You. Not to Heal You.

The case against the hospital as a default care setting starts with a fact most patients would find shocking: the hospital is one of the more dangerous places you can spend time. On any given day, about 1 in 31 hospital patients has at least one healthcare-associated infection. The CDC estimates roughly 687,000 healthcare-associated infections occur in U.S. acute care hospitals annually, with approximately 72,000 patients dying during hospitalizations linked to those infections.

A summary of peer-reviewed research published in the BMJ puts the total at an estimated 250,000 deaths per year from preventable errors and infections in American hospitals. The WHO's 2024 Global Patient Safety Report confirmed that more than one in ten patients globally experience harm in medical care settings — and roughly half of that harm is preventable.

Beyond infection risk, there's the immobility trap. Patients confined to beds for days experience deconditioning. That muscle atrophy, those falls, that functional decline–they have nothing to do with the underlying illness.

In many cases, we are paying premium 'hospital prices' for care that doesn't actually require a hospital's infrastructure. This fiscal waste stems from a deeper misunderstanding of what these buildings are designed to do. While patients come through the doors in some ways expecting a journey toward long-term health optimization, they are entering a high-velocity stabilization hub. The entire institution is engineered around managing crises and clearing beds, a setup that fundamentally prioritizes short-term stability over the slow, intentional work of human flourishing and a return to a state of wellness.

To fix the math of American medicine, we have to move care into environments that are actually capable of prioritizing a patient's quality of life, rather than just their most recent data points.

What We Are — and Aren't — Going to Disrupt

Here is what we are not going to disrupt in the hospital setting: childbirth, the ER, surgery, and the ICU. These belong in hospitals. Acute, emergent, high-acuity situations that require sterile operating environments, immediate life-support technology, and surgical teams on standby — that's exactly what hospitals were built for, and they remain essential for it. In the future, hospitals will function to support what only they can do.

A massive portion of our national healthcare spend is essentially a real estate tax—we are paying premium 'hospital prices' for care that doesn't actually require a hospital's infrastructure. This fiscal waste stems from a deeper misunderstanding of what these buildings are designed to do. While patients walk through the doors expecting a journey toward long-term health optimization, they are entering a high-velocity stabilization hub. The entire institution is engineered around managing crises and clearing beds, a setup that fundamentally prioritizes short-term stability over the slow, intentional work of human flourishing.

The federal government has clearly recognized this mismatch; as of 2026, CMS has expanded the Acute Hospital Care at Home initiative to include over 320 hospitals across 37 states, recently extending the necessary waivers through September 2030. This shift marks the first time Medicare has fundamentally decoupled high-acuity payment from the physical hospital ward, proving that the 'hospital' is increasingly becoming a set of services rather than a specific zip code

The Care-at-Home Continuum Is Already Operational

The vehicle for this shift is "hospital at home.” It includes full inpatient-level care, including IV medications, daily physician visits (hybrid), lab draws, remote monitoring, and more, delivered inside a patient's home. Johns Hopkins, which pioneered the model, reports cost savings of 30% compared to traditional inpatient care, with lower average length of stay and fewer unnecessary diagnostic tests.

Patient use of hospital-at-home programs grew tenfold from 2020 to 2024. By April 2024, CMS had authorized more than 320 hospitals across 133 health systems in 37 states to offer this model. And Massachusetts data shows hospital-at-home patients are more than 14 times less likely to be discharged to a skilled nursing facility than matched inpatient counterparts — which is its own quiet revolution, because SNF stays are miserable, expensive, and often functionally damaging.

The care-at-home spectrum is broader than most people realize.

This shift moves beyond standard primary care into high-acuity medical intervention. Through consolidated platforms like DispatchHealth, which recently merged with Medically Home to form a unified acute-to-transitional continuum, patients now access emergency-level care and inpatient-style monitoring in their own living rooms. This integrated model is already diverting complex cases from overcrowded emergency departments and is projected to free up more than 62,000 hospital bed days annually. From wound care and IV antibiotics to full-scale 'hospital at home' programs, the shift has fundamentally redefined the site of care.

Tech, AI, and Robots Are Making It Possible

Technology is the backbone. Over 68% of Medicare-certified home health agencies now use some form of telemonitoring or virtual care. AI-driven predictive tools in home care are demonstrating the ability to reduce hospitalizations by up to 27%. Remote monitoring devices, AI-generated clinical alerts, tele-rehabilitation, and robotics-assisted care have crossed the line from pilot program to production tool. The infrastructure that didn't exist ten years ago is here, and the question is no longer whether it works. It's how fast the system reorganizes around it.

The financial signals are unambiguous. Home healthcare spending is projected to grow at 7.1% annually — the leading category among all healthcare sectors, outpacing hospitals at 4.7% and nursing homes at 4.8%. The U.S. home healthcare services market, valued at over $100 billion in 2024, is projected to reach $176 billion by 2032. The American Hospital Association's own Sg2 forecasting model projects home health will grow 22% in the coming decade, enabled by virtual care capabilities. The FDA launched its "Home as a Health Care Hub" initiative in April 2024, reimagining the home as a central, integrated health environment.

Payers and Outpatient Providers Want the Same Thing

This truly doesn't get enough attention: there’s so much alignment that can happen between payers and outpatient providers.

In the hospital setting, payers and providers have often been seen as adversaries. Hospitals want to fill beds and bill for services. Insurers want to be sure patients who don’t need hospital-level care are treated in less restrictive and high cost settings. The incentives are structurally opposed.

But in the outpatient and home-based care world, something different is possible and is beginning to happen. Payers and outpatient providers can find common ground, because both benefit from keeping patients out of the hospital. Remember, it’s the hospital and the sequelae of utilization after the hospital that drives the bulk of avoidable and/or preventable healthcare spending.

A primary care practice that proactively manages a diabetic patient's blood sugar (and teaches them to self-manage and provides access when they need help), a home health agency that catches a heart failure exacerbation before it becomes an admission, an AI-powered monitoring platform that flags a medication interaction before it sends someone to the ER…these interventions reduce cost for the insurer and create value for the provider (especially in value-based care payment structures) and for the patient. That's an alignment in American healthcare, and it shouldn't be underestimated.

As value-based care contracts expand, Medicare Advantage plans are increasingly acting as the primary financiers of the home-based shift. While KFF reports that the total share of plans offering in-home support services dipped slightly to 6% in 2025 as insurers recalibrate their margins, the demand for these services continues to act as a flywheel. For outpatient providers, getting paid to keep patients healthy rather than simply treating them when sick makes every successful home-management case a catalyst for further investment.

However, this alignment only works if it directly tackles the primary drivers of hospital over-utilization: affordability and access. KFF reports that more than one-third of U.S. adults (36%) skipped or postponed needed care in 2025 specifically because of the cost. When patients defer care, manageable chronic conditions inevitably spiral into acute crises, forcing them into the very high-cost inpatient settings we are trying to disrupt. By removing the logistical and financial friction of the traditional office visit (where 1 in 6 adults now report cost-related delays) home-based models transform patient behavior from reactive to proactive. They eliminate the price-driven barriers that currently make the emergency room the only 'affordable' option for millions

The Patient Mandate: Preference vs. Infrastructure

Nearly 9 out of 10 seniors say they want to age in place rather than move into institutional settings. The demand isn't just a preference; it’s a demographic inevitability. Yet, there is a stark physical mismatch: while the desire is nearly universal, only 10% of U.S. homes are actually 'aging ready' with the modifications needed to make that stay safe

The hospital isn't going away and never will. It's going to become what it should have always been: a place of last resort, not first instinct. The disruption of healthcare spending — the thing that has eluded three decades of policy ambition — will come from moving care to where it belongs. The data is there. The infrastructure is building. And the business case has never been clearer.

Sources: CDC HAI Data · WHO Global Patient Safety Report 2024 · Leapfrog Group Hospital Safety Grades · Massachusetts HPC Report · Vizient/Sg2 Impact of Change 2024 · CMS Acute Hospital Care at Home Data · DispatchHealth/Medically Home Merger · FDA Home as a Health Care Hub · AARP Home Preferences · KFF Medicare Advantage Benefits Spotlight · McKinsey & Company Healthcare Shift

Career Moves

The Command Center Era: From the Unit-Bound Clinician to the Clinical Architect

The decoupling of medicine from the hospital zip code will fundamentally redefine the "office" for the modern professional. We are entering the era of the Clinical Air Traffic Controller.

For stakeholders like the physician, physical therapist, and health tech innovator, this is a massive invitation to move from a reactive, facility-bound existence to a proactive, environment-agnostic career. Instead of waiting for a patient to arrive at a clinic or a ward, the next generation of leaders will operate from "clinical cockpits," using streams of real-time biometric data to orchestrate high-acuity care across hundreds of living rooms simultaneously.

This evolution is fueled by a projected 23% growth in virtual consultative services and the emergence of nationwide clinical command centers that require a new kind of "virtualist" expertise. The opportunity here is to transition from being a "cog in the facility" to an "architect of the outcome":

For the Physician: The path leads toward the Acute Virtualist. This role trades the "floor walk" for high-level data synthesis, overseeing complex hospital-at-home clusters where you are the invisible hand ensuring stability in a decentralized ward.

For the PT: This is the shift from reactive rehab to Predictive Movement Management. Using remote biometric streams, you become the primary defense against the 'immobility trap,' identifying functional decline in real-time and intervening in the living room—not the clinic

For the Health Tech Innovator: Your "customer" is moving from the hospital IT department to the human environment. The mission is building the "invisible infrastructure.” This includes the sensors, AI-triage layers, and logistics engines that make a living room feel as safe and precise as an ICU.

This is going to make the bedside more scalable. If you are willing to trade the “safety” of the hospital walls for the autonomy of the “clinical cockpit,” the next decade of healthcare can be a professional rebirth.

This Week, Try This

Read about the Kidney Care Choices Model Year Two Results and Celebrate What Good Looks Like

If you care about kidney disease, Medicare payment reform, or simply what it looks like when healthcare policy gets something right, this week's assignment is to read the newly released Kidney Care Choices (KCC) Model Performance Year 2023 Evaluation — and to sit with what it actually means.

First, some context: why this model exists at all.

End-stage renal disease (ESRD) is one of the most expensive, complex, and devastating conditions in the Medicare program. More than 430,000 Medicare fee-for-service beneficiaries with ESRD spend an average of 12 hours a week receiving in-center hemodialysis. It’s a grueling, life-altering regimen that is also, critically, the default. The current Medicare payment system encourages in-center hemodialysis as the default treatment for patients beginning dialysis.

In traditional Medicare fee-for-service, providers get paid per service rendered. A dialysis facility receives a bundled payment every time a patient comes in for in-center hemodialysis which is three times a week, week after week, for hours at a time. It creates a stable, predictable revenue stream built around the patient showing up at the center. Nobody is being villainous. Providers are simply responding rationally to the incentives in front of them.

Home dialysis disrupts that model. If a patient switches to peritoneal dialysis at home, they stop coming to the center. The facility's revenue drops. There's no financial reward built into the traditional system for the care coordination and training work it takes to get a patient successfully doing dialysis at home, even if that patient will have a dramatically better quality of life. Transplants are even more complicated: a successful kidney transplant means the patient no longer needs dialysis at all. From a pure revenue standpoint, a dialysis center loses a patient when a transplant succeeds.

So when we say in-center hemodialysis became the default, what we mean is: the payment system made it the path of least resistance — for providers and for patients who were never given real information about their alternatives. Patients with chronic kidney disease may experience fragmented care and high-cost treatments that do little to slow disease progression. They also receive limited if any education about their disease and treatment options.

Patients are often receiving some of the most intense medical treatment in all of Medicare without being properly educated about what other choices exist. And those choices like home dialysis, preemptive transplant waitlisting, and living donor transplants, can be life-changing.

Meanwhile, in-center hemodialysis patients suffer from poorer health outcomes, such as higher hospitalization and mortality rates, often the result of underlying disease complications and multiple co-morbidities.

This is precisely why CMMI launched the KCC Model — and why you should care.

The CMS Innovation Center (CMMI) is the federal body charged with testing new ways to pay for and deliver care. Congress created it because it recognized that fee-for-service rewards volume over value, and that someone needs to systematically test whether better care designs can produce better outcomes before being scaled nationally.

CMMI is, in essence, the laboratory, the research and development arm, of American healthcare.

The KCC Model's approach is this: rewrite the financial logic so that doing right by the patient is also financially rational for the provider. The KCC Model brings nephrologists and other kidney care providers and practices together to take accountability for patients who have late-stage chronic kidney disease, ESRD, or a kidney transplant, offering coordinated and seamless treatment and care, along with patient education.

Practices receive payments for care coordination, bonuses for successful transplants, and shared savings opportunities when they keep costs down and quality up. Home dialysis stops being a revenue threat and starts being a goal.

The model's three core goals are clear and ambitious: slow the progression of CKD, increase home dialysis, and increase kidney transplantation.

This evaluation is only for year two of the model. The longer models run, the more positive the results.

The results just released cover Performance Year 2023, which is only the second year the model has been running. The first cohort of participants didn't even begin until January 2022. We are watching a new care delivery model find its footing in real time, across 44 states and the District of Columbia, serving patients who represent 51% of Medicare fee-for-service patients with advanced kidney disease. That context matters enormously when you read the findings.

So what did Year 2 actually show? Four things worth celebrating. 🥂

1. More patients on home dialysis. Home dialysis rates increased by 10%, translating to 800 more patients receiving care at home rather than in a center, driven primarily by increased use of peritoneal dialysis. This matters because home dialysis is associated with better quality of life, greater flexibility, and for many patients, better clinical outcomes. Remember: the old payment system gave providers no reason to make this happen. The KCC Model changed that calculus — and 800 more patients are living it.

2. More patients starting dialysis the right way. Optimal ESRD Starts — meaning new dialysis patients who began renal replacement therapy in a planned, coordinated way rather than urgently or in crisis — increased by 31%, reaching 700 more patients. An unplanned start to dialysis is a medical emergency and a signal of care failure. A planned start means the patient was educated, prepared, and supported before the moment of crisis arrived. That's 700 patients who didn't have to experience the chaos and trauma of landing in dialysis without warning.

3. More living donor transplants and earlier waitlisting. While overall transplant rates didn't move yet, living donor transplant rates rose by 22% — 75 more patients. Even more encouraging, preemptive waitlisting (being placed on the transplant list before needing to start dialysis at all) increased by 37%, reaching 128 more patients. These are patients whose care teams are thinking ahead, planning proactively, and giving them the best possible shot at a transplant before dialysis becomes their reality. Under the old model, a successful transplant meant lost revenue. Under KCC, it means a bonus payment. Same providers, different incentives, better outcomes.

4. Better-informed, more activated patients. The KCC Model was associated with more CKD patients receiving information about their treatment options, and KCC patients showed improved patient activation scores. This is a validated measure of a person's ability to understand and manage their own health. This is the foundation everything else is built on. Educated patients ask better questions, make more informed decisions, and are more likely to pursue options like home dialysis or transplant listing. You cannot fix a system that kept patients in the dark without first turning the lights on.

Net Medicare spending increased — and here's how to think about that.

The evaluation found a net increase in Medicare spending of $304.8 million in Year 2, primarily from incentive payments made to participating practices. This is the number that will generate headlines, and it deserves an honest reading. The model did not increase Parts A & B payments, and it did not increase acute care utilization — hospitalizations, readmissions, and emergency department visits were all unchanged. The spending increase came from the model's own payment design: the investments made to reward better behavior.

CMMI models are explicitly designed to test whether upfront investments in better care coordination generate downstream savings and quality improvements. Two years in, the quality signal is real and pointing in the right direction. The financial story is still being written, and it will take time for improved starts, more home dialysis, and more transplants to translate into avoided hospitalizations and reduced total cost of care over a patient's lifetime. Kidney disease is a long game. So is payment reform.

Why does this matter to you?

Because every value-based model, every shared savings arrangement, every effort to move beyond fee-for-service starts here — with real patients and real dollars and real evidence. When a model like KCC shows genuine quality improvement in just its second year of operation, that's not a small thing. It's proof that when you align incentives, coordinate care, and actually tell patients what their options are, better things happen.

The CKCC model option has been extended through December 31, 2027. There is more to learn, more to refine, and more patients to reach. In the meantime, Year 2 gave us something rare in healthcare policy: measurable, meaningful, patient-centered progress — achieved by changing not what providers are capable of, but what the system rewards them for doing.

Full evaluation materials are available here.

Connect with Me

Strategic healthcare trailblazer and systems thinker turning clinical expertise, policy insights, and market intelligence into actionable frameworks..

links.danastrauss.com

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The Tipping Point

Dana Prommel Strauss — Mon, 23 Mar 2026 04:10:10 +0000

Healthcare news for decision-makers

Knowing the healthcare headlines is easy.

Understanding what they mean for the business? That’s the hard part.

Healthcare Brew is a free newsletter breaking down the forces shaping the healthcare industry—from pharmaceutical developments and health startups to policy shifts, regulation, and tech changing how hospitals and providers operate.

No clinical deep dives. No overstuffed jargon. No guessing what actually matters. Just clear, focused coverage built for the people making decisions behind the scenes.

Join 135K+ administrators and healthcare professionals staying informed, for free.

Check it out

Policy Pulse
This Week, Try This

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Policy Pulse

The Moment Has Arrived

The average clinician is going to start feeling it. Not just hearing about it in a conference or reading about it on Linked In, but actually experiencing it in how they care plan, how they interact with patients, and what’s expected of them.

And for healthcare practice owners, this is no longer a future consideration. The pivot is now. Those who don’t transform how they deliver care will not survive the decade.

So what changed? Why now?

Four forces have converged:

More data — more usable, more comprehensive, and more actionable
Data insights built for the end user, not the analyst
Greater interoperability across systems and settings of care
Digital health tools that put real power in the hands of the healthcare consumer

The Only Lever That Bends the Cost Curve

Let’s be honest about where we stand.

CMS drives healthcare policy in this country, particularly since the Affordable Care Act created the CMS Innovation Center and enabled rigorous testing of what actually improves outcomes and lowers cost.

And the headwinds are real: high-cost medications, heavy use of acute care, expensive new treatments, and inflated reimbursement rates for non-time-based procedural services. None of that is going away on its own.

The Innovation Center needs time to test and find solutions that scale. Those who aren’t being realistic about the time this takes are taking the wrong approach to appreciating how enormous the task is.

There are really only two meaningful levers:

Value-based care payment models and care delivery structures
Biosimilar drugs

Biosimilars are relatively straightforward. Value-based care, on the other hand, is all-encompassing. It also often triggers eye-rolls and sighs. I understand the skepticism. But nothing else is capable of bending the cost curve.

What Happens When the Rules Change: A Real Example

The best way to understand value-based care is through how it changes traditional incentives inherent in fee-for-service. When incentives shift, behavior follows.

Take the Transforming Episode Accountability Model (TEAM). Hospitals are held accountable for every healthcare dollar spent in the 30 days after a patient is discharged. When the norm is responsibility for the stay itself (and a readmission hit for certain diagnoses captured in the Hospital Readmission Reduction Program) and essentially nothing starting the day of patient discharge, this is a big deal.

What should a hospital do when their wallet is on the line the moment a patient walks out the door? Here are some big levers if they want to at least prevent owing CMS money.

1. They assess actual, accurate patient function and safety before hospital admission and identify real support systems from day one.

2. They mobilize patients aggressively. Mobility reduces inpatient post-acute stays, the single biggest driver of episode cost overruns. The loss of physical power that happens in acute care stays without a medical necessity for bedrest is almost unforgivable. (It’s one of the hills I’ll die on.)

3. They partner with home health agencies and outpatient PT/OT providers (including OP providers that make home visits) that can begin treatment within 24 hours of discharge.

4. They invest in discharge planning teams who can train patients, communicate across settings, and set expectations with post-acute providers.

5. They scrutinize IRF placements. The cost of inpatient rehab often exceeds the cost of the hospital stay itself. No meaningful functional change? The patient shouldn’t be there.

6. They manage SNF throughput tightly. Many patients can move through a skilled nursing facility in 5–10 days when the episode is closely managed, realistic and appr.

7. They hire care navigators with deep expertise in Medicare payment policy to be the connective tissue across the entire care journey.

My team and I were doing all of this in 2017 and blowing away expectations. We were improving patients’ lives and helping them achieve a long-term successful care journey. We focused on the big picture and insisted everyone who touched our patients did the same.

We were rare then. The difference now is that the tools, the data, and the policy architecture are catching up to make this the standard.

What We Learned Building This in 2017

When my team supported BPCI-A, CJR, and MSSP patients through acute and post-acute episodes, we had something most health systems didn’t: good data, near real-time. ADT feeds. A risk-stratified dashboard. A vendor who integrated multiple data sources into a proprietary risk score that kicked in the moment we identified a patient through concurrent coding. A team of skilled and trained clinicians inside the hospital and embedded in post-acute sites of care working to help successful navigate patients through successful, safe care journeys and help them get back home and remain there.

We stratified. We shared. We did deep dives into patient journeys with stakeholders across the continuum. We saved money for CMS by improving quality, reducing unnecessary post-acute utilization, and setting patients and families up for long-term success. We earned shared savings by reducing avoidable and unnecessary spending. We improved the patient experience and their outcomes.

When I left that health system after 20 years and multiple roles, I realized this:

We were way ahead of the game.

Not because of luck. Because we made major investments in people, data, interoperability, and analytics, and because we had the C-suite buy-in to see it through.

A movement has been building. If you haven’t experienced it yet, that’s likely because of your employer or, if you’re an owner, because you’ve chosen to remain entrenched in fee-for-service. And you yourself may not have made the deliberate decision to learn how the pieces all fit together and how VBC works. It’s not too late!

Straddling fee-for-service and value-based care is genuinely hard. So just expect it. For most, it’s a multi-year transition. But the direction is set. Invest in change or be disrupted.

Digital Health: The Accelerant Few Saw Coming

Digital health tools have mostly existed as employer-sponsored add-ons and parallel to healthcare, not integrated within it. Your employer offers free access to a digital health point solution. A small percentage of employees opt in. Those who need real clinical care hit a wall: the digital tool doesn’t talk to the PT clinic. The PT doesn’t have access to the platform. The consumer experience is fractured.

That’s about to change fundamentally.

Enter the ACCESS Model

For the first time, a digital health vendor will be able to submit to become a Medicare provider and bill under Medicare Part B. CMS is betting that integrating digital health into mainstream medical care (rather than keeping it as an employer add-on) is a game-changer.

CMS isn’t writing blank checks for billing for digital health, however. ACCESS Model participants must demonstrate avoided duplicate care management spending and improved outcomes using well-established measures. Underperform? Receive as little as half the payment.

They’re also requiring data sharing between digital health providers and the patient’s primary medical provider managing their chronic condition, and requiring those providers to ingest and share data back. In return, providers can bill a co-management code for collaborating with the digital health provider and data sharing. It also opens up the option for reducing their own investment in patient engagement tools and care management staff, depending on their partnerships with ACCESS Model participants and clinicians like physical and occupational therapy practices and behavioral health practices.

And here’s the detail that might seem minor but isn’t: CMMI is allowing ACCESS participants to waive the co-pay. For a repeated service like care management, the friction of getting verbal consent for cost-sharing is of a common dealbreaker. Many practices already provide care management without billing for it because of this friction alone.

The End of Healthcare’s Information Monopoly

For decades, healthcare operated on information asymmetry. Providers knew things patients didn’t.

The system was built around that imbalance, and, in many ways, depended on it.

That era is ending.

Patients are done tolerating what they once accepted:

• Months-long waits for an appointment

• Phone-only, 9–5 scheduling

• Urgent care as the default option for everything

• Repeating their medical history at every visit

• Paper forms and faxed records

• Weeks of waiting for test results

• Cookie-cutter advice and treatment plans

• No follow-up, no proactive outreach, no real continuity

The bar is no longer set by healthcare. It’s set by the best consumer and AI experiences people have everywhere else, such as in banking, in travel, in retail. Patients now expect the same in their healthcare.

Data availability, digital health, single-touch data sharing, and easy identification of low-value providers are creating a monumental shift. Good data and value-based care agreements are the tools that allow forward-thinking providers and organizations to get ahead of it.

The Call is Clear

This isn’t doom and gloom. It’s a wake-up call, and there’s still time to answer it on your own terms.

For Clinicians

Understand what value-based care actually requires of you. It’s not just a billing change — it’s a different relationship with your patients, their data, and their care journey. Learn the incentive structures. Know what programs your organization participates in. Understand what metrics matter and why. Your patients will be more engaged, better informed, and less forgiving of experiences that don’t meet modern expectations. That’s not a threat. It’s an opportunity to practice at the top of your capability.

For Owners

The window to lead this transformation is open. Straddling fee-for-service and value-based is the reality for a while. But don’t let that stop you from building toward a future that isn’t entirely dependent on volume. Invest in data infrastructure. Invest in care navigators. Partner with digital health vendors who are entering the Medicare ecosystem. Build the care teams and processes that make your organization indispensable in a value-based world.

The iceberg is visible. The tools to change course exist. The only question is whether you’ll act before or after the collision.

Good Credit Could Save You $200,000 Over Time

Better credit means better rates on mortgages, cars, and more. Cheers Credit Builder is an affordable, AI-powered way to start — no score or hard check required. We report to all three bureaus fast. Many users see 20+ point increases in months. Cancel anytime with no penalties or hidden fees.

Start Building Credit Today

This Week, Try This

Check out this article by my friend Alex Bendersky! 👇️

The Memes Running Physical Therapy

And the Five We Need to Rewrite Before the Profession Falls Behind

medium.com/@sashadpt/the-memes-running-physical-therapy-6c08dfc573e6

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

The Room is Spinning. So is the Billing and Patient Fear

Dana Prommel Strauss — Mon, 16 Mar 2026 00:15:00 +0000

Policy Pulse
- Spinning Its Wheels: How Medicine Keeps Getting Ve …
Career Moves
- What are you doing between now and your next caree …
This Week, Try This

Health Tech Nerds

Insightful content and vibrant community trusted by over 30,000 healthcare leaders and innovators.

Healthcare Huddle

Bridging the clinical trenches and the boardroom. Trusted by 30k+ health professionals for expert takes on business, policy, and tech that impact medicine.

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Policy Pulse

Spinning Its Wheels: How Medicine Keeps Getting Vertigo Wrong

You roll over in bed at 2 a.m. The room lurches. You’re convinced something’s very wrong—like a stroke or something else that feels catastrophic. You head to the ER. Hours and tens of thousands of dollars later, you go home with a diagnosis of "dizziness" or “vertigo” and a prescription for a drug that does absolutely nothing to fix what's wrong (meclizine/Antivert).

I watched this or something similar play out dozens of times as a physical therapist. A patient has a general diagnosis of “dizziness” or “vertigo” after a rule out of something neurological and they are given an oral medication and sent home.

The condition is called Benign Paroxysmal Positional Vertigo (BPPV) and it is almost absurdly treatable. Tiny calcium crystals called otoliths (also known as “otoconia”) drift out of position in the inner ear and trick the brain into thinking the body is spinning. The fix?

A clinician guides your head through a specific repositioning sequence called the Epley maneuver (in the most common presentation of BPPV with a slightly different “maneuver” for the others) and the crystals migrate back where they belong. One visit. Sometimes one treatment. Symptoms gone.

No MRI required. No CT. No overnight admission. No neurologist. No ENT.

I treated BPPV regular in outpatient rehabilitation and even in home health rehabilitation. I’ve since treated multiple family members and friends.

And yet.

It’s the most expensive dizzy spell in medicine.

From Cleveland Clinic’s Page on BPPV

Healthcare costs associated with diagnosing BPPV alone approach $2 billion per year in the United States, with more than 65% of patients undergoing potentially unnecessary diagnostic testing or interventions (and that’s from a 2017 article, so let’s assume it’s a low estimate of dollars spent). Unnecessary diagnostic procedures have been reported in more than 65% of BPPV patients even in advanced countries, including rates of 70% for MRI and 45% for CT.

Why? Some hypotheses:

Because vertigo can feel terrifying, and terror in medicine often defaults to imaging.

Because stroke and BPPV can look similar to an undertrained eye.

Because medical education gives vestibular disorders roughly the attention of a footnote.

And because fee-for-service payment systems reimburse the scan, not the skillful bedside maneuver. That maneuver is commonly perfected by trained physical therapists.

The drug most commonly prescribed for BPPV, meclizine (Antivert), is a particular frustration. It suppresses vestibular signals. It sedates the complaint. It does not and cannot move the otoconia. Patients taking it aren't getting better. Sometimes the crystals drift back to where they belong on their own. Sometimes the crystals remain exactly where they don't belong, and the clock runs out on days the patient could have been functional, working, and not terrified.

Delayed diagnosis and treatment of BPPV is associated with increased rates of anxiety and depression, lost workdays, inappropriate use of emergency resources, and reduced quality of care. These are the kind of outcomes that show up in utilization data, readmission rates, and disability claims.

What we’re not teaching

Ask most ER physicians (or primary care providers in urgent care and primary care) to perform a Dix-Hallpike (the bedside test that can diagnose BPPV in under two minutes) and many will hesitate. It's not complicated. It requires tilting the patient's head at a specific angle and watching for characteristic eye movement. But it takes practice and pattern recognition that a brief residency mention doesn't build.

Physical therapists, by contrast, evaluate and treat BPPV regularly. It is one of the rare conditions in PT where full resolution in a single session is not just possible but common. The irony is that patients often reach us only after exhausting every expensive wrong turn the system sent them on first. Another great reason for PTs to work as the norm in primary care, urgent care, and emergency rooms.

What AI can do right now to help

Here's where it gets interesting. Researchers have developed machine learning models to classify vestibular disorders using patient-reported symptoms alone, achieving 88% accuracy. Why? Because conditions like BPPV can often be diagnosed primarily through what patients describe.

The symptom profile is specific: brief spinning triggered by lying down or turning the head, no hearing loss, no neurological symptoms, no spontaneous vertigo. A dizzy patient describing those features to an ambient listening tool in a busy ER is practically flagging their own diagnosis. A patient saying "the room spins when I roll over, just for a few seconds" is practically self-diagnosing.

Tools that provide ambient AI infrastructure already suggest ICD-10 codes in real time based on what a clinician says aloud. They can hear a patient describe positional vertigo. The technology to flag that pattern and prompt "consider Dix-Hallpike before ordering imaging" is a configuration decision that someone needs to prioritize.

This one is solvable

Value-based care models have an opening here. Treat BPPV as a sentinel condition: high-frequency, low-complexity, wildly over-imaged. Track inappropriate imaging rates. Reimburse the bedside maneuver. Build BPPV recognition into clinical decision support as a default, not an afterthought. Require a Dix-Hallpike before a vertigo-related CT and/or MRI order in low-risk presentations.

Sidenote: The inspiration for this piece was my mother’s visit to the ER this week. They added an MRA to the above-mentioned diagnostic tools employed before someone finally said “we noticed your eye flickering and that’s from BPPV. Here’s meclizine to take.” (That “flickering” is nystagmus.)

That was the treatment provided. No referral to PT for the Hallpike-Dix to evaluate and the Epley maneuver to treat. Just meds after throwing the kitchen sink of imaging at her. I did tell her when she texted me from the hospital that her texted symptoms sounded like BPPV…. 🙃

There are more than four million U.S. ED visits annually for dizziness or vertigo, costing over $4 billion in yearly workup costs. A meaningful percentage of those patients have BPPV. They're not sick. They're otoliths are out of their normal position. But we keep charging them (and the system) a fortune in imaging, overnight stays, and specialist consults, while a frightened patient waits days for an answer a ten-minute bedside test could have given them in the ER.

The otoliths just need repositioning. So does the medical approach to evaluating and treating them.

Career Moves

What are you doing between now and your next career after direct patient care?

For the clinicians who have a gut feeling or even know they will transition away from the bedside “at some point,” take heart! You can start preparing today. Preparing before you want to leave or are ready to leave direct patient care can make it so much easier when it’s time to plan your transition.

Here are a few things you can do right now as a starting point.

Build your professional reputation. Your reputation is one of the most portable assets you have. It travels with you outside the clinic or organization’s walls. Start by showing up consistently and being known for something beyond your clinical role. That might mean volunteering to precept students, joining a committee, presenting at a staff meeting, or contributing to a policy update.
In my case, I was first known for being an expert in managing the throughput of fragile patients from hospital through post-acute settings to home safely. That led to me as the obvious choice to help lead the development and implementation of a transitions of care program and team.
Outside your workplace, think about LinkedIn. If you don't have a profile, create one. If you have one, dust it off. Don't announce anything. Just start connecting with colleagues, sharing the occasional insight from your clinical experience, and engaging with content in spaces you're curious about. Add value to others. Set a cadence for interacting on Linked In. Three times per week is a good starting point.
The goal right now isn't to job hunt. It's to make sure that when opportunities come up, people already know who you are
Unsure what’s valuable to learn about? Start by reading industry journal and blogs. One of the biggest barriers clinicians face when exploring non-bedside roles is not knowing what skills or experience actually translate. The good news is you can start closing that gap just by reading.
Pick one or two journals, newsletters, or blogs in an area that interests you, whether that's health tech, care management, informatics, policy, or something else entirely. Start consuming content. You're getting familiar with the language, the problems people are trying to solve, and the conversations happening in that space.
As you read, you'll start to notice things. You'll recognize gaps that your clinical perspective could speak to. You'll see job titles you've never heard of. You'll come across skills that keep coming up. Start a running list.
This is low-stakes intel gathering that costs nothing but a little time. It’s a great investment.
Here are a bunch of suggestions for journals, publications, and news sources to check out. Check them out and pick a few. If I were choosing three to call mandatory, they would be a., e., and k.:
1. Health Affairs (especially Forefront)
2. NEJM Catalyst
3. JAMA Network, especially health policy and informatics pieces
4. The Commonwealth Fund
5. KFF Health News
6. Stat News
7. Techy Surgeon
8. Andreesen Horowitz (Bio and Health)
9. Advisory Board Daily Briefing
10. Fierce Healthcare
11. CMMI newsletters: sign up for email updates at this link
12. Newsletters I recommended at the top of this article
Start managing what you learn. Reading is only half the equation. What you do with what you read is where the real value builds.
This is where personal knowledge management comes in. In simple terms, it's a system for capturing, organizing, and revisiting what you're learning — so it doesn't just disappear after you close the tab.
Start small: when something you read resonates, write a few sentences about it in your own words and save it somewhere intentional. A notes app, a doc, a dedicated notebook—whatever you'll actually use.
Here's why this matters more than it might seem at first:
When you take notes in your own words, you're not just saving information. In fact, the point is to not just save information. The valuable part is that you're processing it.
You start connecting ideas across different articles. You begin forming opinions. And over time, you develop a point of view that is uniquely yours and shaped by both your clinical experience and your growing knowledge of the industry you want to move into.
That point of view is what makes you valuable outside the clinic. It's what gives you something to say in an interview, something to write about, something to share with a colleague.
It also helps you stand out. When you start the job search for your first non-clinical role, this may be the most important tool in your toolbox. It 100% was for me.
I wrote about personal knowledge management here.

This Week, Try This

I co-host a relatively niche podcast on the “future of physical therapy,” aptly named Future Proof PT. The most recent episode, Episode 27, is about AI in Healthcare. It’s for any clinical or clinically-adjacent audience. My cohost Alex Bendersky and I have a chat with Sergei Polevikov.

Check it out the episode here:

Here’s a “short” from the episode that’s under 60 seconds:

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Paying for Brainpower: The Evolution of Longitudinal Care Reimbursement

Dana Prommel Strauss — Mon, 09 Mar 2026 00:15:00 +0000

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Policy Pulse

The Cognitive Comeback | Reimbursing Brain Power

I was thinking about various policy changes and models rolled out by CMS and the Innovation Center over the past decade.

They’ve created additional codes for cognitive work and coordination of care, such as chronic care management, principal illness navigation, caregiver training, advance care planning, and much more. We have needed to pay for these types of activities for forever. Not paying for them, plus fee-for-service incentives, have led to little longitudinal care and failures of population health in America.

While adoption of advanced primary care is variable, it’s working!

Read this case study

But there’s this other dynamic happening in parallel.

CMS is creating codes like the Advanced Primary Care Management (APCM) codes, which essentially allow practices to simplify care management tracking and bill one monthly code that includes a number of these “cognitive codes.”

APCM Services and Codes on CMS.gov

It can lead to higher overall primary care practice reimbursement and encourage these activities to be performed, especially for practices who aren’t participating in value-based care arrangements.

For practices who have operationalized the various codes and services, it can potentially yield lower revenue by the nature of bundling of the codes.

Of course, those at full financial risk are typically not concerned about code volumes. They are concerned about engaging their attributed population and preventing unnecessary and avoidable healthcare utilization. Their reimbursement isn’t determined by billable units. The administrative time it takes to track and comply with the rules around use of these codes is often determined to be “the juice is not worth the squeeze.”

The “So What”

Policymakers began reimbursing for services that are now seen as valuable and worth paying for. 👏

At the same time, I see them trying to address two other dynamics.

The first is making adoption more widespread by simplifying and bundling related “cognitive” services.

The second is proactively mitigating the risk of the overutilization of the same services by simplifying and bundling related “cognitive” services.

Let’s look at how this applies to two models—one active, one beginning this year.

The GUIDE Model: A Condition-Specific Longitudinal Care Model

Let’s look at the Guiding an Improved Dementia Experience, or GUIDE Model, for dementia and its code for the Dementia Care Management Payment (DCMP). It’s meant to replace all these services below. 👇️

Medicare Physician Fee Schedule Services covered under the Dementia Care Management Payment in the GUIDE Model

Note: this doesn’t stop another provider from billing the above codes for a patient in GUIDE (assuming the other provider is not a GUIDE “Partner Organization”), and the GUIDE Participant isn’t penalized for “substitute spend” if that does happen. (Like in ACCESS, which we’ll talk about next.)

GUIDE is structured in a way that’s not necessarily meant to save money, although CMMI hopes it does. Dementia patients are thought to be under-utilizing upstream services significantly, leading to high downstream costs and high risk of institutionalization.

The Guide Model is meant to improve quality of care and life for patients living with dementia and their unpaid caregivers. It’s a Biden-era model that the Trump Administration’s CMMI Director Abe Sutton retained.

GUIDE aligns patients voluntarily, and patients with ICD.10 coded diagnoses for dementia can be referred ongoing by anyone at any time (think discharge planners, home health agencies, PCPs, therapists, etc). These patients are often not getting the care management and coordination of care they need in fee-for-service. They and their caregivers often end up in ERs and eventually skilled nursing facilities because they don’t know what else to do. The GUIDE Model is meant to address this.

Participants in the model can only “lose” a small amount of their payment based on poor quality performance, so there’s no true, significant risk. CMMI even provides a helpful data dashboard to each Participant so they identify actionable insights and can track their performance, perhaps without needing to secure additional outside analytics solutions .

The ACCESS Model | A Model testing Recurring, Outcome-Aligned Payments for Managing a Patient’s Qualifying Condition

Now let’s look at the Advancing Chronic Care Through Effective, Scalable Solutions (ACCESS) Model. ACCESS participants bill the g-codes to provide monthly support for a bucket of conditions. The same Medicare Part B provider can’t bill any FFS codes for a patient if they are billing the ACCESS code.

ACCESS is the first model to withhold significant reimbursement per patient from the Participant. 50% of reimbursement will be paid retrospectively based on outcomes and the presence or absence of “substitute spend.”

Then CMMI is paying the ACCESS orgs a low annual fee meant to encourage innovation. This will limit the types of organizations who can successfully implement the model, and that’s by design.

Visual from https://www.theaccessmodel.com

Notable Differences

GUIDE and ACCESS both feature monthly payments for managing a condition.

Unlike the approach taken in GUIDE, CMMI is paying the referring and coordinating provider about $100 per patient per year that’s enrolled in ACCESS. The combined payments to the ACCESS org and the referring/coordinating provider are now about on par with the GUIDE payment. There’s nothing like that in GUIDE, but CMMI surely knows it’s hard for primary care practices to effectively manage many patients with dementia and other parts of the healthcare continuum are already looking for places to refer them.

(Note: GUIDE also includes up to $2500 per year reimbursement for respite services for qualifying beneficiaries, but that’s out of scope for this post.)

The coordination payment in ACCESS also addresses something else.

If a provider is billing the coordination fee, they are not permitted to bill the “substitute spend” codes. So this could reduce monthly care management, RPM, and additional code utilization. It also includes PT and OT evaluations in substitute spend codes for the MSK track, and has a similar structure for the Behavioral Health track.

Side note from a PT and VBC expert: Thank you to CMMI for changing the policy and allowing therapists to be the referring providers and bill the co-management fee for the MSK track. It was announced this past week on a webinar. This is a gamechanger for therapists. I Just hope they realize the layers of opportunity here—this is a meaningful inroad into ACO partnerships!

In ACCESS, note CMMI is incentivizing the referring provider to receive and incorporate information from the ACCESS org into the patient’s overall care plan. I see this as an investment so ACCESS orgs have enough patient volume to create a margin with CMMI’s “disciplined” reimbursement rates for what effectively will be digital health access for Medicare beneficiaries.

ACO Primary Care Flex Model | Prospective Primary Care Payments for Certain MSSP ACO Participants

While out of scope for this post, The ACO Primary Care Flex Model is another model that bundles primary care services into a payment for Participants. This is relatively similar to how ACO REACH determines prospective payments for primary care.

This is somewhat different from the APCM, GUIDE, and ACCESS examples because this payment is made as part of participation in the model. Codes billed that overlap are “zeroed out” and not reimbursed. I’m oversimplifying here to give a 30,000 foot view only. There’s lots of information available if you want to dig in.

Here are the codes used to determine the base rate, from the ACO Primary Care Flex RFA:

ACO Primary Care Flex RFA

I wrote about ACO Primary Care Flex in 2024 if you want to check it out👇️

Should you Consider Primary Care Flex?

CMMI's Hybrid Payment Primary Care Model for PCPs in Certain MSSP ACOs

www.timelessautonomy.com/p/primarycareflex

Here’s My Point

CMS post-Affordable Care Act changed direction and began to reimburse for the “cognitive work” of primary care teams.

They have added to the list of available services and codes.

They are also building a primary care “bundle” code, which they may add to further.

Then CMMI creates models that “bundle” codes for cognitive services.

But here’s the thing:

Cognitive services, prevention activities, proactive outreach—these are not services we should be trying to limit, right? They aren’t causing runaway spending.

You know what is? High cost biologics, avoidable and preventable hospitalizations, avoidable surgeries, avoidable imaging….

CMS wants to prevent overuse of codes, but we are focused heavily on the low cost and high-value codes.

Sometimes I wonder—why don’t we just pay primary care more and differently across the board? Yes, it will require reducing reimbursement for other Medicare Part B services. I suppose CMS may think that will just lead to more volume of those services if their reimbursement drops?

They may also be afraid of the backlash after finalizing G2211, which Congress required CMS to hold on implementing for several years because it was going to reduce reimbursement to specialists (it also reduced reimbursement to PT and OT, which is crazy—they are already underpaid 😠 ).

On that note, I’ll leave you with this tidbit I read somewhere this week. If I find the link, I’ll add it to the online post version later. 👇️ 😁

There was so much noise around the add-on complexity code for longitudinal care, G2211.

The predictions of primary care provider utilization of this code were very high. Turns out? Specialists (those who can bill E and M codes) are using the codes more than PCPs. I’m being a cynic and generalizing here, but I don’t know a lot of specialty physicians who own longitudinal care like primary care providers do.

The Future of Primary Care: Team-Based, Higher-Paid, Prospectively-Paid, with Longitudinal Accountability

I’ll venture to say we are realistically 5-10 years away from the widespread norm of paying at least our primary care provider teams prospectively, not just in CMS Innovation Center models. We might see the same for certain specialty care, like for those treating dementia and ESRD patients, also.

The work is heavily overweight on care that requires communication, connection, patient engagement, patient outreach. Figuring out how to price and bill for those services individually seems like an intractable problem.

The X-factor will be what role technology plays outside of human interaction. This is really what ACCESS is testing in my opinion. Put technology in the extended care team and give it wide freedom to innovate. Where it will fit and how it will be reimbursed in the future will surely be informed by the results of ACCESS.

This Week, Try This

Please consider attending the webinar I’m on with Dr. Marc Gruner, Dr. Christian Penn, and Dr. Ben Schwartz on the ACCESS Model on Thursday, March 12th.

Check out Dr. Penn’s Substack article here.

Check out some classics from the Timeless Autonomy archives! 👇️

Should you participate in the Innovation Center's GUIDE Model?

The GUIDE Model (Guiding and Improved Dementia Experience) broken down

www.timelessautonomy.com/p/guide

Beneath the Surface of ACCESS

Plus, the predictor of career success that you can improve on today

www.timelessautonomy.com/p/beneath-the-surface-of-access

OT Potential Blog and VBC Resources

Plus: Intro to Medical Cost Trend

www.timelessautonomy.com/p/ot-potential-blog-and-vbc-resources

Check out my Medbridge webinar on the Transforming Episode Accountability Model (TEAM) for clinicians! 👇️ It’s free with a Medbridge subscription or can be purchased as an individual course from Medbridge.

Not a subscriber? Using my link gives you $106 off your subscription for unlimited CEUs with code DanaStrauss. They have a host of different types of CEUs for various clinicians. The subscription is a must for me since N.J. requires live CEUs and Medbridge adds live webinars monthly.

Medbridge’s CEU platform, where you can find my TEAM webinar

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Screening for Social Needs Changes Patient Outcomes

Dana Prommel Strauss — Mon, 02 Mar 2026 01:15:00 +0000

Medbridge’s CEU platform, where you can find my TEAM webinar

Policy Pulse
Career Moves and This Week, Try This

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Read This Post Online

Policy Pulse

What the Accountable Health Communities Model Tested

From 2017 to 2023, the Centers for Medicare & Medicaid Services ran the Accountable Health Communities (AHC) model across 28 communities nationwide. The question was this: if we screen Medicare and Medicaid patients for social needs in healthcare settings and connect them to community resources, can we improve health outcomes and reduce costs?

The model screened over 1 million patients. Thirty-seven percent had at least one unmet social need. The most common barriers to health were housing instability, food insecurity, transportation problems, utility needs, and interpersonal safety concerns.

The results shouldn’t be surprising. Patients with navigation support had 3-7% lower total healthcare costs, driven by fewer ED visits and hospital admissions. The intervention worked because having someone help navigate resources made a measurable difference in whether patients could show up for care and follow through on treatment plans.

How It Actually Worked: The Camden Coalition Example

To understand how this plays out in practice, look at the Camden Coalition in South Jersey. They're a community-based nonprofit that served as one of the AHC "bridge organizations." Think of that as the connective tissue between healthcare systems and community services.

The structure: The Camden Coalition is funded through a mix of federal demonstration grants (they received CMS funding for AHC), state Medicaid dollars (New Jersey allocated funding to support their Regional Health Hub designation), and shared savings arrangements with managed care organizations.

They partnered with five health systems across Camden, Burlington, and Gloucester counties: Cooper University Health Care, Jefferson Health, Virtua Health, CAMcare, and Oaks Integrated Care.

The model: Unlike traditional CBOs that provide a single service (like a food bank or housing program), the Camden Coalition coordinates the entire ecosystem. They train hospital and clinic staff, manage the screening process, run a referral platform, employ community health workers (CHWs) who navigate patients to services, and maintain relationships with dozens of CBOs that deliver actual assistance.

Over the course of their AHC implementation, they screened over 30,000 patients and demonstrated significantly lower ED utilization rates in the intervention group compared to the control group.

The Workflow: From Screening to Better Outcomes

Here's how it worked:

1. The screening happens A patient comes to Cooper Hospital's emergency department or one of the partner clinics. A staff member (sometimes a medical assistant, sometimes a care coordinator, sometimes a CHW stationed at the site) administers the AHC screening tool. It's a standardized questionnaire with 10 core questions covering five domains: housing, food, transportation, utilities, and safety.

The questions are direct. "Do you have a steady place to live?" "In the past 12 months, have you worried your food would run out before you got money to buy more?" "Has lack of transportation kept you from medical appointments, meetings, work, or from getting things needed for daily living?"

The screening takes about 5-10 minutes. If the patient screens positive for any need, they're offered a tailored referral list through the Camden Coalition's platform called My Resource Pal (powered by Findhelp). Everyone who screens positive gets this list.

2. Navigation kicks in for high-risk patients But not everyone gets navigation support. The model focused resources on patients most likely to benefit. If a patient screened positive for at least one social need AND reported two or more ED visits in the past 12 months AND lived in the community (not in a nursing facility), they were eligible for navigation services.

About 18% of all screened patients met these criteria. Of those eligible, 79% opted in to navigation. An important takeaway is that most people wanted the help when it was offered.

3. The community health worker makes contact A CHW from the Camden Coalition reaches out, often by phone. They don't just confirm the screening results. They dig deeper.

Take Frank, one of the patients the Camden Coalition team described. He screened positive for housing and transportation needs. But when his CHW talked with him, the real issue emerged: employment instability due to a felony record, which meant he couldn't get stable work, which meant he couldn't afford reliable transportation, which affected his housing.

The CHW connected Frank with a job coaching program at Hispanic Family Center—a resource Frank, a Black man, didn't even know would be available to him. The program helped him find employment that included transportation as part of the position. That job stability helped him save for a car and work toward stable housing.

4. The navigation process The CHW uses what the Camden Coalition calls their COACH framework—particularly "observing the normal routine" and "connecting tasks with vision and priorities." This isn't about handing someone a phone number and moving on. It's about understanding what's actually preventing someone from accessing help and troubleshooting those barriers.

Maybe the food pantry has hours when the patient is at work. Maybe the housing assistance application requires documents the patient doesn't have. Maybe the patient tried calling a service before and got lost in voicemail. The CHW helps solve these practical problems.

The Camden Coalition Health Information Exchange plays a role here too. With patient consent, it allows real-time data sharing between hospitals and community providers, so the CHW can see if someone had an ED visit, and the hospital can see if the patient successfully connected with services.

5. The closed-loop referral When the CHW refers a patient to a CBO—say, a food bank or a transportation program—they track whether the patient actually got served. This is the "closed loop" part. They follow up with both the patient and the CBO to confirm the connection happened and the need was addressed.

This is also where the system often breaks down. CBOs are frequently at capacity. They have waitlists. The Camden Coalition has to maintain relationships with multiple providers for each type of need, know which ones have availability, and sometimes get creative when standard resources aren't accessible.

6. The impact on health outcomes Here's how it connects back to healthcare: when Frank got stable employment with transportation, he could make medical appointments. When Jeanette (another patient who screened positive for food insecurity around the holidays and was stressed about caring for her grandkids) got connected to resources, she had fewer crises that might have sent her to the ED.

The model didn't necessarily resolve every social need completely—the evaluation showed mixed results on whether needs were fully met. But navigation demonstrably reduced healthcare utilization and costs. Why? Because having someone actively helping you navigate the system makes it more likely you'll access primary care instead of the emergency department, follow up on referrals, and stay connected to care.

Find more information about case studies of post-model scaling and spreading of innovations from the AHC Model here. Additional examples and resources are in the newsletter’s “Sources and Additional Links” page here.

Why This Model Matters

The AHC model proved several important things:

Screening at scale is possible. A million patients were screened. It can be integrated into clinical workflows in emergency departments, primary care clinics, and specialty settings. Staff can be trained to do it. Patients are generally receptive.

Social needs are prevalent and consequential. Over a third of Medicare and Medicaid patients have at least one unmet social need affecting their health.

Navigation is the critical piece. Just identifying needs and giving people a list doesn't move the needle. Having someone like a CHW, a navigator, a care coordinator who stays with the patient and helps them actually connect to resources is what makes the difference.

Infrastructure requires investment. The Camden Coalition exists because of deliberate funding choices: federal grants, state Medicaid dollars, and payment arrangements that recognize the value of care coordination. Organizations like this don't emerge spontaneously. They need sustained financial support.

CBOs are the rate-limiting factor. The biggest barrier isn't screening. It's not even navigation. It's that community-based organizations providing housing assistance, food support, and transportation programs are chronically underfunded and at capacity. You can't refer people to services that don't exist or can't take more clients.

What Clinicians and Innovators Should Know

For clinicians: Screen. Even if you're worried you can't solve every problem, the data matters. Document the barriers you identify. When you can't address a transportation need or housing instability, write it down. That documentation builds the case for system change.

Know what's available in your community. Build relationships with local CBOs or organizations like the Camden Coalition if they exist in your area. A warm handoff to a specific navigator or program is far more effective than generic information.

For innovators: If you're building tools or solutions for social needs, understand that the workflow requires people. Technology can facilitate screening, referrals, and tracking, but it can't replace navigation. The Camden Coalition used a platform (Findhelp/My Resource Pal) to manage referrals and track outcomes, but that platform worked because CHWs used it to do their jobs better. It was not used as a replacement for human connection.

Focus on interoperability. If your tool doesn't integrate with EHRs and CBO case management systems, you're creating more work, not less. The Camden Coalition's Health Information Exchange enabled data sharing across providers precisely because they invested in making systems talk to each other.

The Funding Reality

Here's what sustaining a model like Accountable Health Communities requires:

Someone has to pay for bridge organizations like the Camden Coalition. That means Medicaid reimbursement for navigation services, state funding for regional health infrastructure, or value-based payment arrangements that recognize preventing an ED visit is worth something.

CBOs need dedicated, stable funding to build capacity. Grants help build infrastructure and are often an important step, but they usually aren’t enough. If we want them to absorb referrals from healthcare systems, they need resources to hire staff and expand services.

Navigation itself needs to be recognized as a reimbursable service. Several states have been moving in this direction through Section 1115 waivers and Medicaid state plan amendments, partly because of what the AHC model demonstrated. However, federal legislation enacted in 2025 imposes stricter budget neutrality requirements on 1115 waivers starting January 1, 2027, which may make it harder for states to get approval for innovative payment approaches that require upfront investment.

Why You Should Believe in This

The AHC model worked because it acknowledged reality: patients live in the world, not in clinical pathways. Meeting clinical needs is necessary but not sufficient. Whether someone can actually get healthier depends on whether they can get to appointments, afford food, and live in stable housing.

Frank didn't need a better diabetes medication. He needed a job that came with transportation so he could get to his medical appointments and work toward stable housing.

Jeanette didn't need a lecture about nutrition. She needed help getting food for her grandkids so she wasn't overwhelmed with stress that kept her from taking care of herself.

The model proved that when we identify these barriers, connect people to someone who can help navigate resources, and invest in the infrastructure to make that happen, patients have better outcomes and use healthcare more appropriately.

This structure is documented, measured, and replicable.

The question now is whether we can actually fund and scale it.

Find all sources and additional context here.

Are you an OT or a PT? Check out my podcast for OT Potential on “How PTs and OTs Get Paid” here:

How OTs and PTs Get Paid • OT Potential

Learn about the 2026 reimbursement landscape with policy expert Dana Strauss. Shift the needle with 3 concrete advocacy efforts and a roadmap for action.

otpotential.com/ceu-podcast-courses/how-ots-and-pts-get-paid

Career Moves and This Week, Try This

Keep it simple. The Timeless Autonomy Resources page has great resources for this week’s newsletter. Learn more about 1115 waivers, CBOs, and the AHC Model by checking out the links I shared there.

New knowledge acquisition is critical to career growth, particularly for those interested in non-clinical career paths.

Career growth is built one educational block after another. If you want non-clinical options, be someone “knowledge rich.” Think of learning non-clinical/clinically-adjacent topics as part of your career growth and development. Each piece of knowledge you acquire is an opportunity to find what “lights you up.” Follow the flickers.

You can become someone whose knowledge and “second brain” has access to solutions when problems come up that you can solve.

You can liken it to investing broadly when you are young in things like total stock market index funds and international index funds, knowing that the compounding of those investments over time will pay you dividends. If you want to be financially independent, you must have invested broadly and diversely over time.

Careers are no different. Gather knowledge and experience. Dig into topics that interest you. Explore different avenues. Make notes about what you learn and store in your personal knowledge management tool.

This is really great news. It means there isn’t a specific “formula” to worry about first. Start learning and exploring. Find what resonates for you. Find what can combine with your clinical knowledge to give you a superpower!

You WILL find ways to apply that knowledge. You WILL find topics that resonate. You WILL find ways to share that. You WILL open doors to opportunities by combining knowledge areas to solve problems, stand out, or become indispensable.

I’m convinced that the willingness to learn about healthcare innovation outside the clinic is the “X” factor that predicts the potential for career growth.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Value Based Care Can't Fix Everything

Dana Prommel Strauss — Mon, 23 Feb 2026 01:15:00 +0000

Medbridge’s CEU platform, where you can find my TEAM webinar

Volume vs. Price Tag

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Read This Post Online

Volume of Services per Beneficiary vs. Costs of Service Units

There’s a lot of finger-pointing in healthcare. That leads to a lot of confusion. And that leads to people thinking they know the problem, or what will solve it, or who’s at fault. It leads to feeling helpless and frustrated.

I am a value-based care expert and advocate. VBC principles are undeniably better for providers and patients. Reward upstream, team-based care that’s structured so long-term patient outcomes improve. That is the nuts and bolts of it. Change incentives, transform how care is delivered.

When done well, which I’ve seen happen in advanced, team-based primary care, managing acute episodes of care, and much more, you get great results for everyone. You reduce the utilization of high-cost settings like inpatient hospital stays and reduce risk of readmissions after a stay, care is coordinated between providers, patient pro-active outreach is prioritized, preventive screenings are done on more patients so high-morbidity and mortality diseases are caught earlier, patients are more directly engaged in their care, they have better access to care, chronic disease progression slows…and the list goes on.

What value-based care can excel at, when structured and executed well, is reducing the volume of high-cost medical interventions.

What it can’t do well is lower unit costs of care outside the primary care setting. There are exceptions, of course. In advanced VBC arrangements, primary care practices can establish downstream relationships with specialists and others, like post-acute providers, to better align incentives and partner with high-value practices and organizations who agree to support the goals of the arrangement.

Spending per enrollee that’s driven by high cost specialty drugs, high hospital prices, new high-cost procedures, device and supply prices, and more is the major force that negatively impacts benefit compression, higher premiums, plan market exits, higher deductibles, co-pays, and co-insurance, and more.

I think sometimes we say value-based care isn’t working because we don’t fully appreciate all the drivers of cost and what can and can’t be controlled by whom. Besides that, transitioning away from transactional, volume-awarded reimbursement is very, very hard. There’s been major progress in the ten years since it became a concept many physicians understand.

As a physical therapist by training, I can say that most non-physician healthcare professionals have little to no understanding of VBC. They have largely been left out and are often struggling to stay afloat even harder than physicians have. It’s hard for them to take the time to learn about it, even if they were exposed to it more. And their buy-in is crucial. For PTs alone, there are several hundred thousand employed in the United States.

Unit Cost and Mix are Difficult to Address

While these are dominant drivers of spending spikes, they are hard to fix.

Here are some concentrated areas of high costs:

Specialty drugs and drug mix make up a high share of Part D spending. Use of new, high-cost agents for oncology, biologics, GLP-1s, cellular therapies, and more and shifts in the mix contribute a lot to the growth. Milliman does a great job covering this here. Here’s a nice visual from their site 👇️
From Milliman’s White Paper “Early 2025 Medicare Part D claims show continued increase in non-low income specialty drugs.”

Hospital prices and intensity remain the largest slice of Medicare goods and services. Per-enrollee spending is increasing as a result of price growth, labor costs, and service intensity. Also, consolidation and market power can amplify negotiated prices. This article in Health Affairs dives deeper into this 👇️
High-cost procedures and supplies—rapid growth in spending for items like skin substitutes (addressed in the 2026 Physician Fee Schedule final rule) has produced dramatic year-over-year jumps.
Higher-priced and high site-of-care imaging modalities—this article published in Radiology in 2021 (FDA Commissioner Dr. Marty Makary is a co-author) looks at commercial negotiated prices for CMS-specific shoppable radiology services. This 2025 article in Health Affairs Scholar. This is directly from the “Results” section, no surprise: “Key findings include greater variation in facility fees compared to professional fees, with facility coefficients of variation often 3 to 6 times higher than professional components.”

Why All Stakeholders Should Understand

Value based care can and should be expanded. It will help blunt future volume growth and improve outcomes. But utilization reductions from VBC can’t offset line items like single drugs or devices or interventions that cost tens to hundreds of thousands of dollars.
Market mechanics amplify the pain. Health system consolidation, transparency limitations, and more allow dominant providers to command higher prices and widen regional price gaps. This makes it harder for payers and policymakers to control spending and for consumers to understand the true costs of their healthcare.

Some Practical Levers to Pull

Double down on VBC to address volume and quality. This includes things like investing in care navigation, chronic care models, addressing social and functional drivers of health, ED diversion, and more. Keep working to scale VBC and reduce avoidable utilization while improving patient experience.
Attack unit costs through formulary design, negotiation biosimilar uptake (besides VBC, this is the major lever to drive lower medical trend), utilization management for specialty drugs that includes patient engagement efforts, and more.
Align payment to evidence. For poorly evidenced, high-cost supplies (like skin substitutes), tighten coverage rules and prior authorization.
Fix healthcare market distortions through hospital price transparency and benchmarking methodology that limits the ability of providers to achieve outsized prices.
Keep fighting fraud, waste, and abuse in the extreme areas. Address unexplained spikes in utilization immediately. Let’s not forget that ACOs blew the foghorn when their claims data started showing urinary catheter spend when patients weren’t receiving it and it wasn’t being ordered!

Here’s the Takeaway

There are many inter-connected factors driving our healthcare affordability problems. When it comes to volume and costs, two truths can coexist. VBC is essential to reduce avoidable volume and improve quality of care, outcomes, and the patient experience. But unit costs and the changing mix of care are a real fiscal problem driving spending per beneficiary in Medicare.

We can make progress with VBC. That being said, expectations for overall results in VBC should take into account the time it takes to get everyone rowing the same direction (we have a long way to go) and the culture and practical changes that have their own associated costs.

But the runaway train is the unit cost and mix of services being used. There are levers to pull to address them, but they are also heavy lifts. Keeping in mind the factors involved in taking action that include: what changes would be needed, who can make the changes, who doesn’t want the changes, and more.

One final thought. Something simple often gets lost when clinicians talk about things like the shrinking conversion factor and reimbursement pressures and when we all rightly lament about the cost of care. I often hear the blame pointed at payers, from CMS to health plans to self-insured employers.

But this is a factor that often gets lost:

There’s a fixed amount of money in a budget every year to cover all expenses that a payer’s population will incur. When unit costs and mix are so high, like we covered here, and the spending trend is up close to double digits in a single year, what are the options to stay in the budget?

They can pay for fewer units of care, increase responsibility on patients, reduce reimbursement levels to clinicians and other providers, raise maximum out of pocket costs, and other cost-control mechanisms. The pie can only be cut so many ways.

Good solutions can only be developed when we recognize there’s no one individual or entity or part of the system to “blame.”

Become An AI Expert In Just 5 Minutes

If you’re a decision maker at your company, you need to be on the bleeding edge of, well, everything. But before you go signing up for seminars, conferences, lunch ‘n learns, and all that jazz, just know there’s a far better (and simpler) way: Subscribing to The Deep View.

This daily newsletter condenses everything you need to know about the latest and greatest AI developments into a 5-minute read. Squeeze it into your morning coffee break and before you know it, you’ll be an expert too.

Subscribe right here. It’s totally free, wildly informative, and trusted by 600,000+ readers at Google, Meta, Microsoft, and beyond.

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Beneath the Surface of ACCESS

Dana Prommel Strauss — Mon, 16 Feb 2026 01:17:26 +0000

Medbridge’s CEU platform, where you can find my TEAM webinar

Policy Pulse
- Follow the Money
  - Follow the Money
  - Timeless Autonomy Resources Page
Career Moves
- Success is Predictable.
This Week, Try This

**Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Policy Pulse

ACCESS Model Updates are Out.

If you are a treating clinician or provide team-based clinical support in primary care, physical therapy, or behavioral health, here’s what you should read between the lines before the model even starts. You have preparing to do!

There so much content online about how ACCESS works and opinions about the model. Before coming to any conclusions, consider doing these two things:

Read CMS’ own documents. Pay special attention to:
1. Who can be an ACCESS organization (NOT providers billing FFS for the same patients)
2. Who can own an ACCESS org (NOT an organization who is at least 5% owned by an organization billing FFS for the same patients)
3. What codes are considered “substitute spend” in each category
4. What outcomes measures will determine the Outcome Aligned Payments.
Read my assessment of what clinicians should be prepared for. I haven’t read this elsewhere yet. I hope it helps. 👇️

As you may have read, clinicians billing the physician fee schedule for a patient population can’t be ACCESS organizations unless they want to stop billing fee-for-service codes. Given the very low reimbursement ($180-$420 per year maximum, depending on outcomes, substitute spend, and ACCESS Track), that is highly unlikely.

CMS established codes for which they consider ACCESS codes to be a substitute. For Tracks 1 and 2, these are a host of care management codes and remote monitoring. The full lists per Track are in the CMS documents.

For the sake of example, let’s look at Track 3, Musculoskeletal Care. The ACCESS code substitutes for PT Evaluation, OT Evaluation, and Remote Therapeutic Monitoring Set Up. These are three non-time-based codes, and all therapy episodes begin with the evaluations, of course.

If a patient is receiving care from an ACCESS organization and seeks a PT or OT evaluation for the same condition, the ACCESS organization will earn less than their full reimbursement because of the “substitute spend” rule. We can only speculate whether patients will be less likely to seek therapy while receiving the digital health care of the ACCESS organization.

For patients who do not receive both the ACCESS services and a PT or OT evaluation, CMS will be able to compare the costs over any longitudinal period between the ACCESS organization and the PT or OT services. They can look for any differences in spend across a longitudinal time period to observe differences in care trajectories.

Does one path or the other, for a similar patient, correlate with lower ED utilization? Lower use of advanced imaging? Lower use of specialty medical visits? Lower use of injections or surgical procedures? CMS will be able to answer these questions as the model progresses.

Are you prepared for CMS to compare the ACCESS org patient trajectory to the traditional care trajectory and the results?

Then let’s look at the outcomes measures CMS is using to determine whether the ACCESS organization providing care for Musculoskeletal conditions has earned their full reimbursement. They focus on patient reported outcomes measures in the MSK Track.

From the ACCESS Model Payment Amounts and Performance Targets

With this information, CMS can analyze spend and the outcomes achieved subsequent to that spend. CMS doesn’t presently have all of this information from OT or PT episodes of care.

I would argue this makes the Outcome Aligned Payment measures the new gold standard for demonstrating value in rehabilitation episodes starting in 2026.

Interestingly, these are not the same measures as are offered in the MIPS Value Pathway (MVP) “Rehabilitation Support for Musculoskeletal Care.”

However, if I was a clinical owner or operator, or an owner or operator in behavioral health or primary care related to the other ACCESS Model Tracks, I would be collecting the OAP measures for your patients starting in July. Even if CMS doesn’t require them, it’s valuable information. Know in real time if you are meeting the targets set for ACCESS organizations.

Find all sources and additional context here.

Career Moves

Success is Predictable.

And it has a name.

The good news and the punchline? It’s plastic. You can improve on it.

It can be grown by aligning your daily actions with a north star goal that excites you.

So what is this crucial ingredient to the recipe of success?

Grit.

Watch Angela Duckworth’s famous, brief, Ted Talk on Grit that has 17 million You Tube videos 👇️

What does it look like to be gritty in the game of career growth?

Clinicians who successfully transition into non-clinical roles and/or leadership positions keep trying when others give up.

They aren’t necessarily the ones who start with good networks, perfect resumes, or have the clearest plan.

Because transitions of any kind are hard. They don’t have a perfect roadmap. Many people quit.

The good news? Grit is a skill. It’s not a personality trait like you might think.

Career grit is just a longitudinal differential diagnosis of your own life

It’s staying the course towards a new life because you want to.

Think about it.

If a patient doesn’t respond to the first treatment, you don’t quit caring for them. You iterate, research, and try the next thing.

Career grit is similar. It’s about getting out of your comfort zone, practicing, and developing rituals that will keep you on track regardless of how you feel on a given day. Consistency is key.

If you’re thinking “but I’m not a gritty person,” STOP. You made it through advanced education that has a built-in attrition rate. You have worked in some of the most physically and emotionally demanding professional roles. You often have incomplete information when you are evaluating a patient and yet you make it work.

We are often conditioned to believe having perseverance in clinical settings as “just doing our jobs,” while viewing the same behavior in career transitions as some special trait that others have.

You objectively can sustain effort towards difficult goals. Give yourself permission to apply that same persistence to your own ambitions instead of towards achieving your license or helping patients achieve their goals.

The perseverance you have been using was already there! In clinical training and roles, you directed it where you needed to because that’s what your training demanded and what felt legitimate.

Grit in career transitions and growth is about mental permission.

You justify endless persistence for clinical work but perhaps feel that dreaded “imposter syndrome” in applying the same tenacity to your own ambitions.

“Success” in this journey is about redirecting the grit you already have. You are strategically building your future.

A “grit framework” for clinician career transitions

Inspired by Angela Duckworth, here’s a framework to apply to your career transitions and growth strategy:

Establish Your “North Star,” or Top-Level Goal

Write down your ultimate concern. Do you want more autonomy? Systemic Impact? Financial Freedom? “Better hours” won’t keep you going in the face of rejection, but something like “changing how one million people access primary care” will.

Seek “Low-Stakes” Failure

Clinician often fear mistakes. Fear of law suits, patient harm, reputational harm, etc. However, in the corporate world, mistakes = data.

“Practice” your transition. Send the cold Linked In message (but not with an “ask,” of course 😃 ). Apply for a job you aren’t too excited about just for the chance to experience the interview.

Build grit by being immune to the sting of being told “no.”

Build a Grit Scaffold

It’s easier to become more gritty when you automate the practice.

Create a non-clinical hour two or three days a week.

Maybe it’s after the kids are in bed, 8-9 PM Tuesdays and Thursdays, or before the house is awake, 6-7 AM. Maybe you skip happy hour on Fridays with the clinical team.

During these hours, you are a career architect. You research, learn, comment on Linked In posts to expand your reach, read a book chapter, or upskill.

(Whatever you do during your career architect hours, make sure you make notes in your personal knowledge management tool, of course!)

The Career Grit Scorecard

I created this to help you audit your transition. It’s purpose? Help you stop guessing and start measuring the three pillars of a successful move: The North Star, Low Stakes Failure, and The Boring Habit.

Here’s how to use it:

Open the Scorecard: Click here to access the Google Doc.
Make a Copy: Go to File > Make a copy to create your own private version.
Audit Your Week: Be brutally honest. Are you actually practicing the skills you're "bad" at, or just reading more articles?
Pick One Metric: Don't try to fix all five pillars at once. Pick the one with the lowest score and commit to one "boring habit" to improve it this week.

Download the Career Grit Scorecard and Reflection Doc Here

This Week, Try This

Read about the ACCESS Model. Start with the facts. Read the RFA, Model Payment Amounts and Performance Targets, and the Technical FAQs
Take this test by Angela Duckworth. It’ her Grit Scale. If you score lower than you like, realize this is NOT diagnostic failure. In fact, for high achievers, it usually indicates “situational fatigue” rather than lack of character. It’s definitely not a “fixed” score! Get a baseline. Read more about what the score means and how to improve your grittiness based on her research in her book, GRIT | The Power of Passion and Perseverance.

Angela Duckworth’s GRIT in paperback on Amazon

*Disclaimer: All opinions and ideas expressed in this article are solely mine and none represent a recommendation or should be viewed as advisement of any kind to anyone to do anything.*

Timeless Autonomy

Can the Medicare Home Health Benefit be a Tool to Accelerate Palliative Care?

Medicare policy runs on two layers.

Which brings me to the confusion that costs patients the most

That invisibility is a money problem and a clinical one.

Take action and provide your comments by the deadline

Here’s my take:

Sources & further reading

Don't Compare It To The Almighty. Compare It To The Alternative

“Better than it is today” is the real baseline for clinical technology

Dr. Bob Wachter on "Healthcare is Hard: A Podcast for Insiders" (hosted by Keith Figlioli)

Eric Larsen on Healthcare’s "Oppenheimer Moment"

What This Means for Your Career

Sources & further reading

Who Decides What You Need?

When it all clicks.

The Need You Were Never Asked About

The options you were never told you had

What "need" actually is

How necessity gets built without an argument

The obvious answer often isn't the evidence

"Medically necessary" and what that was supposed to mean

We are all sharing finite pots of money

What value was always for

What matters to you

Sources & further reading

Patient Safety is the Ultimate Value-Based Care Strategy

AI Is About to Force Healthcare to Confront Patient Harm at Scale

We talk about "quality" constantly.

25%!

What a High Reliability Organization (HRO) journey actually teaches you

Not faster notes. Visible harm.

Here is the connection I keep coming back to.

CMS is already moving

And I don't think the timing is an accident.

The economics finally line up

What this means right now

If you work in a hospital, here's how to bring this up now

Sources & further reading

How to Close the Knowledge Asymmetry Gap in Healthcare

Break the Invisible Ceiling in Healthcare

Attack the informational gap

The mirror

Here's what "systems knowledge" actually is

You need a map

How to future-proof your expertise

Where to start

Value-Based Care Lit the Match. Precision Health Is the Accelerant.

VBC Lit the Match. Personalized Medicine Is the Accelerant.

Why my partner is right that nothing much has changed yet, and why I think he's about to be wrong.

Take the skeptic seriously

VBC has been largely a supply-side project

Does Fixing Healthcare Require a Generational Shift? I Don't Buy It

The near term is already here

The pillar everyone forgets is the patient experience

The long game

Closing the loop

Sources:

How to Bulletproof Your Healthcare Career Against the Risks You Can and Can't See Coming

There are Two Kinds of Risks. Prepare for Them Both.

Black Swan Events

Examples:

The predictable risks?

Black Swan and Predictable Risks Have Implications for Healthcare and Your Career

Managing Both Black Swan and Predictable Risks Requires Preparation

Telehealth, Hospital-at-Home (HAH), and the COVID Pandemic

Section 1135 Waivers

Expiration of Telehealth and Hospital-at-Home is Not Popular

Predictable Risks

Don’t Do This Anymore

Healthcare Will Improve More if Clinicians Push Beyond the Clinical Lane

Compounding Problems Lead to a Perfect Storm for Change

Your Career Barbell

One end of the barbell is the conservative side.

The other end is the offensive side.

Two Risks. Two Sides of the Barbell.

In Policy Pulse, I walked through the career barbell. Two sides. Conservative on one end. Offensive on the other.

1. Financial Runway (note: this is not financial advice, just an example for educational purposes)

2. Licensure That Travels

3. A Network Outside Your Immediate Role