Friday, September 5, 2025

Van Calster (2025) Why Adoption of Clinical Predictors Is So Low

 Annual Reviews of Statistics just released a paper with an interesting title:

The Enemies of Reliable and Useful Clinical Prediction Models: A Review of Statistical and Scientific Challenges.  Here.

Writing,

The current status of applied clinical prediction modeling is poor. Many models are developed with suboptimal methods and are not evaluated, and hence have little impact on clinical care. We review 12 challenges—provocatively labeled enemies—that jeopardize the creation of prediction models that make it to clinical practice to improve treatment decisions and clinical outcomes for individual patients.

##

While the focus is on prediction algorithms, many of the challenges map easily onto the adoption, or disappearance, of diagnostic tests as well (e.g. MAAA predictors).   The need for impact assessment and implementation studies is highlighted, topics close to genomics.


Their summary figure is worth highlighting (from Royen):


##
Van Calster discuss use of AI-ML in Banff transplant classification (p. 10), citing Farris 2023.

Bipartisan Policy Center: Report: Rise of AI in Federal Health Agencies

 On August 10, 2025, the Bipartisan Health Center released a detailed report, with numerous graphics, on "Mapping the Rise of AI in Federal Health Agencies."

It's cited in the briefing memo for the September 3, 2025, House Health hearing on AI in healthcare.

Find the full report here:

https://bipartisanpolicy.org/blog/mapping-the-rise-of-ai-in-federal-health-agencies/


AI Corner

Federal health agencies are rapidly expanding their use of artificial intelligence, moving from pilot projects to core operations in areas like fraud detection, outbreak surveillance, and regulatory review. Under new White House and HHS mandates, agencies such as CDC, CMS, and FDA now track and disclose hundreds of AI use cases, with applications ranging from internal workforce support to high-impact public services. While tools like FDA’s new generative AI assistant Elsa promise major efficiency gains, they also raise questions about transparency, safeguards, and the role of AI in sensitive regulatory decisions.

##

Here’s a TL;DR of the Bipartisan Policy Center report Mapping the Rise of AI in Federal Health Agencies (Aug 10, 2025):


Federal AI Expansion

  • FDA launched Elsa (June 2025), a secure generative AI chatbot for staff productivity.

  • HHS has tracked AI use since 1996, with cases quadrupling between 2022–2024 (270 cases across nine agencies).

  • Growth accelerated after generative AI tools (e.g., ChatGPT) emerged.

Policy & Oversight

  • 2020 executive order required agencies to inventory AI uses.

  • April 2025 OMB memoranda mandated Chief AI Officers, transparency, and standardized evaluation.

  • Agencies must now report AI tools’ purposes, safeguards, and metrics.

Agency Highlights

  • CDC: Uses AI for literature reviews, outbreak prediction, and internal operations (ChatCDC).

  • CMS: Applies AI to fraud detection, claims monitoring, and customer complaints; recent AI-supported fraud takedown blocked $4B in false claims.

  • FDA: Uses AI for data extraction from submissions and document review. Elsa supports writing and summarization but raises concerns about reviewer influence and legal liability. FDA also launched two AI councils: one for regulating AI-enabled products, another for internal oversight.

Key Applications (6 categories):

  1. Education & Workforce (training, chatbots).

  2. Emergency Management (social media monitoring, outbreak tracking).

  3. Government Services (benefits delivery, adverse event monitoring).

  4. Health & Medical (surveillance, real-world data).

  5. Law & Justice (fraud detection, case routing).

  6. Mission-Enabling (internal workflows like drug labeling review).

Takeaway
AI adoption in federal health agencies is accelerating, with a focus on transparency, fraud prevention, regulatory review, and workforce support. Success will depend on governance, safeguards, and clarity around AI’s role in high-stakes regulatory decisions.


 

Chat GPT 5 Reviews House Hearing on AI in Healthcare

Overshadowed by the 3-hour RFK Jr Senate hearing, don't lose track of the 3-hour "AI in Healthcare" hearing in the House.

  • Find the Youtube site here.  (Includes auto transcript).
  • Find coverage at MedCityNews here.  Healthcare Dive here.
  • Find Congr. Griffith's opening statement here.
  • Find the full agenda (scroll for September 3) here.  And the 7-page Hearing Memo here.

Witnesses - 

TJ Parker, Lead Investor, General Medicine
Andrew Toy, Chief Executive Officer, Clover Health
Dr. Andrew Ibrahim, MD, MSc, Chief Clinical Officer, Viz.ai
Dr. Michelle Mello, JD, PhD, MPhil, Professor of Law, Stanford Law School, and Professor of Health Policy, Stanford University School of Medicine
Dr. C. Vaile Wright, PhD, Senior Director, Health Care Innovation, American Psychological Association

###

AI CORNER

  • Direct output from Chat GPT 5.  
    • Do not quote without checking.
  • For a good example of alternative AI output on the same hearing, from Google Notebook LM - here.  

###

Here is a detailed report on the September 3, 2025 House Subcommittee on Health hearing on Artificial Intelligence in Healthcare, integrating the 3-hour transcript, witness testimonies, and the 7-page committee memo. I’ve written it for an expert audience in health policy and diagnostics, at the depth of the Wall Street Journal or Financial Times.


Report:
House Hearing on AI in Healthcare –
September 3, 2025

Introduction

On September 3, 2025, the House Energy and Commerce Subcommittee on Health convened a three-hour hearing titled “Examining Opportunities to Advance American Health Care through the Use of Artificial Intelligence Technologies.” The session brought together lawmakers from both parties and five witnesses representing the provider, payer, technology, and academic perspectives:

  • TJ Parker (General Medicine, former Amazon Pharmacy executive)

  • Andrew Toy (CEO, Clover Health)

  • Dr. Andrew Ibrahim (Chief Clinical Officer, Viz.ai)

  • Dr. Michelle Mello (Professor of Law and Health Policy, Stanford University)

  • Dr. Vaile Wright (American Psychological Association).

The discussion highlighted AI’s promise to reduce administrative burdens, accelerate diagnosis, and improve patient outcomes—but also underscored risks around safety, trust, bias, and regulatory gaps.


Partisan Context and Opening Statements

The hearing unfolded against a backdrop of political tension. Republicans emphasized AI as a tool to “empower, not replace” clinicians, streamline documentation, improve rural access, and strengthen U.S. competitiveness. Democrats, however, repeatedly connected AI oversight to what they called the Trump administration’s “war on science,” citing recent CDC leadership upheavals and HHS layoffs as undermining trust in federal health governance.

Both sides agreed that AI adoption is accelerating, citing GAO data that HHS reported 271 AI use cases in 2024, up from 157 in 2023 and that FDA approvals of AI-enabled devices had surged from six in 2015 to 223 in 2023. The challenge, as framed by the committee, is to harness this momentum responsibly.


Key Themes from Witness Testimony

1. Clinical Impact and Diagnostics

  • Viz.ai’s Dr. Ibrahim described how AI now supports patient care “every five seconds” in more than 1,800 hospitals. Their stroke detection platform reduces time-to-treatment by 30 minutes, shortens length of stay by three days, and lowers mortality. Similar platforms now cover pulmonary embolism, aneurysms, and hypertrophic cardiomyopathy. Ibrahim stressed that integration into workflow—not algorithms in isolation—drives clinical value.

  • The testimony resonates strongly for pathology and radiology, as Viz.ai represents a new class of FDA-cleared, reimbursed, imaging-adjacent diagnostic AI. Ibrahim urged Congress to align FDA pathways, reimbursement with outcomes, and interoperability to accelerate safe adoption.

2. Administrative Simplification and Patient Experience

  • TJ Parker (General Medicine) argued that Americans want healthcare to be “as easy to shop as anything else.” His company uses large language models to parse insurance benefit PDFs and combine them with hospital transparency files to generate real-time, upfront pricing.

  • He also highlighted AI-enabled “comprehensive care plans” that integrate preventive services and follow-ups into a single actionable dashboard for patients. For diagnostics, this signals a push toward AI tools that not only interpret tests but embed them in longitudinal care pathways.

3. Payer Integration and Equity

  • Andrew Toy (Clover Health) framed AI as physician enablement, not denial-of-care. Clover Assistant aggregates fragmented data from EHRs and national networks (TEFCA, CommonWell) to deliver real-time, in-workflow decision support.

  • Toy, who lives with Marfan syndrome, described his personal mission to prevent missed diagnoses. He insisted AI should never be used to replace clinicians or ration care but instead to democratize access to high-quality insights—even in paper-based practices.

4. Trust, Governance, and Regulatory Gaps

  • Dr. Michelle Mello stressed that the bottleneck is not innovation but low adoption due to a trust deficit. She outlined four needed policy moves:

    1. Require AI developers and healthcare organizations to disclose and mitigate risks.

    2. Fund independent research on real-world AI performance.

    3. Adjust reimbursement policies so monitoring costs don’t deter adoption.

    4. Modernize FDA’s statutory framework, which remains ill-suited to adaptive algorithms.

Her warning—that hospitals often adopt AI based on sales pitches, with little monitoring—was one of the sharpest critiques of the day.

5. Psychological and Equity Considerations

  • Dr. Vaile Wright (APA) focused on behavioral health. She noted both opportunities (AI-powered scribes reducing burnout; chatbots expanding access) and risks (unregulated DTC mental health bots that encourage harmful behaviors; bias in algorithms measuring illness by cost of care rather than severity).

  • APA urged Congress to legislate guardrails, age-appropriate protections, equity testing, federal privacy laws (including “mental privacy”), and AI literacy programs.


Issues Raised by Lawmakers

Oversight and Guardrails

Members repeatedly pressed on whether AI prior authorization tools might delay care—especially in Medicare pilots allowing nonprofits to use AI for utilization review. Democrats worried about AI being used to deny coverage; Republicans saw potential for fraud detection and efficiency.

Data Privacy and Security

Concerns were voiced that AI’s reliance on large datasets could erode patient privacy. Calls for federal privacy legislation—particularly covering biometric and neural data—were prominent.

Workforce and Role of Clinicians

Both sides agreed: AI should augment, not replace clinicians. Yet witnesses acknowledged that adoption could redistribute roles, particularly in radiology and pathology, where AI interpretation tools are most advanced.

Mental Health and Youth

Members highlighted tragedies where teens interacting with AI chatbots were encouraged toward self-harm. Wright’s testimony sharpened calls for FTC/CPSC oversight of unregulated behavioral AI products.


Implications for Diagnostics (Pathology and Radiology)

The hearing provided unusually direct relevance for diagnostics:

  • Viz.ai exemplifies how FDA-cleared, reimbursed AI is reshaping acute care radiology workflows.

  • General Medicine’s pricing and care plan AI underscores how diagnostic services (labs, imaging) will increasingly be bundled into consumer-facing platforms.

  • Clover Health’s approach to synthesizing fragmented diagnostic data highlights how payers may become central nodes in AI-enabled diagnosis.

  • Policy debates on FDA frameworks, reimbursement models, and trust will be decisive in shaping whether diagnostic AI scales beyond pilots into mainstream clinical practice.


Conclusion

The September 3 hearing revealed both bipartisan enthusiasm for AI’s potential and sharp partisan divides over federal leadership in science and health policy. For the diagnostics community, the key takeaways are:

  • AI is moving rapidly from hype to FDA-approved, reimbursed, clinical reality (particularly in imaging).

  • Adoption lags innovation, driven by governance gaps, reimbursement misalignment, and lack of trust.

  • Congress is being urged to act: modernize FDA authorities, legislate privacy, support independent evaluation, and build patient/clinician trust.

For pathology and radiology stakeholders, the path forward will hinge not just on technological advances, but on how Congress and regulators balance innovation, safety, and equity in the next 12–24 months.


Would you like me to also prepare a 2–3 page policy implications memo (similar to what you circulated after Senate hearings) that translates this into actionable insights for diagnostics and medtech clients? That could serve as a client-facing briefing.

 


Policy Implications Memo

House Subcommittee on Health Hearing: Artificial Intelligence in Healthcare (September 3, 2025)

Audience: Diagnostics, Radiology, and Medtech Stakeholders


Executive Summary

On September 3, 2025, the House Energy & Commerce Subcommittee on Health held a three-hour hearing on AI in healthcare. The session underscored bipartisan enthusiasm for AI’s potential to improve efficiency and outcomes, but also revealed sharp divides on governance, trust, and federal leadership.

For the diagnostics community, the hearing matters because:

  • FDA-approved and CMS-reimbursed AI tools in radiology and pathology (e.g., Viz.ai) are now frontline use cases.

  • Lawmakers are weighing policies that could either accelerate adoption (via streamlined FDA pathways and reimbursement reform) or constrain it (via privacy mandates, new governance burdens).

  • Trust and oversight will drive adoption as much as technical performance.


Key Themes Relevant to Diagnostics

1. FDA and Regulatory Pathways

  • Growth trajectory: FDA approved 223 AI-enabled medical devices in 2023, up from 160 in 2022 and only 6 in 2015.

  • Challenge: Current FDA statutory framework is mismatched to adaptive algorithms. Witnesses (Mello, Ibrahim) urged Congress to modernize oversight so innovation and adoption are not stalled.

  • Implication: Expect renewed FDA rulemaking or legislation in 2026 to define “continuous learning” AI standards, with diagnostics first in line.

2. Reimbursement and Payment Alignment

  • Viz.ai testimony emphasized that reimbursement must align with outcomes — AI can cut treatment times, reduce length of stay, and lower mortality.

  • Mello noted that many AI tools do not save hospitals money; monitoring costs can be substantial.

  • Implication: Diagnostics companies must prepare economic evidence dossiers that link AI-enabled interpretation to clinical outcomes and system savings — not just algorithmic accuracy.

3. Trust, Transparency, and Governance

  • Mello highlighted a “trust deficit” as the main barrier to adoption: hospitals often adopt AI on sales pitches with minimal monitoring.

  • APA warned of unregulated mental health bots and biased algorithms in coverage determinations.

  • Implication: Diagnostics vendors should expect mandatory disclosure requirements (risk documentation, independent validation, governance processes) in the next legislative cycle.

4. Privacy and Data Use

  • Multiple members raised concerns that AI’s reliance on massive datasets threatens patient privacy.

  • APA urged Congress to legislate “mental privacy” protections, extending to biometric and neural data.

  • Implication: Companies handling imaging, pathology slides, or genomic data must prepare for federal privacy legislation that could narrow secondary use and require new consent models.

5. Clinical Role of AI

  • Lawmakers stressed: AI must augment, not replace clinicians.

  • In radiology/pathology, this means AI adoption will be positioned as triage and support, not replacement.

  • Implication: Messaging to policymakers, providers, and payers should consistently frame diagnostic AI as a partner to clinicians.


Strategic Takeaways for Diagnostics & Medtech Clients

  1. Position AI as workflow-embedded, outcome-driven
    — Emphasize integration into care pathways (stroke, cancer, pathology) rather than stand-alone algorithms.

  2. Build the reimbursement case early
    — Develop clinical utility and economic evidence packages anticipating CMS and private payer scrutiny.

  3. Prepare for regulatory tightening
    — FDA, FTC, and potentially Congress will impose stricter disclosure, monitoring, and safety guardrails.

  4. Adopt proactive governance
    — Demonstrating risk assessment, monitoring, and bias audits will differentiate credible companies from opportunistic entrants.

  5. Shape privacy debates
    — Engage in Washington discussions about federal health data privacy legislation, ensuring diagnostic datasets remain usable for innovation.


Outlook

The September 3 hearing signals that Congress sees AI in healthcare as both opportunity and risk. For diagnostics, the landscape will favor companies that:

  • Deliver clinically validated, workflow-integrated solutions,

  • Build payer-aligned economic cases, and

  • Demonstrate trustworthy governance.

As with past digital health regulation cycles, diagnostics and imaging will be the test case for broader health AI policy.


 


Thursday, September 4, 2025

Chat GPT 5 reviews the RFK Senate Hearing (September 4, 2025)

This is an unedited Chat GPT 5 review of the 9/4/2025 Senate hearing on HHS.  Based on a YouTube auto-transcript.  The essays below are direct AI output and should not be quoted unless fact-checked.

##


NYT "5 Takeaways."

##

Here is a detailed expert-level summary of the Senate Finance Committee hearing with HHS Secretary Robert F. Kennedy Jr. regarding President Trump’s 2026 healthcare agenda, based on the transcript you provided.


Overview and Context

The hearing was one of the most contentious health policy sessions in recent memory, reflecting deep partisan divides. Secretary Kennedy appeared before the Senate Finance Committee to defend the administration’s record, outline reforms, and respond to severe criticisms. The central issues included the administration’s handling of vaccines, chronic disease prevention, rural health investment, program integrity in Medicare/Medicaid, and the restructuring of CDC and other health agencies.


Republican Framing and Priorities

  • Shift to Prevention and Chronic Disease: Republicans emphasized that HHS is moving from “sick care” to tackling root causes of chronic conditions (processed food, inactivity, chemical exposures, over-medicalization). The administration’s Make America Healthy Again (MA) report and forthcoming strategy were cited as roadmaps.

  • Fraud and Abuse Control: CMS identified 2.8 million people dually enrolled in Medicaid and ACA plans, projecting $14B in annual savings by fixing duplications. Eligibility verification (including immigration checks) was highlighted as essential for program sustainability.

  • Rural Health Transformation: The One Big Beautiful Bill (OBBA) authorized $50B for rural hospitals over five years—a >50% boost in federal rural funding. Senators stressed this was the largest rural health investment in decades.

  • Regulatory Realignment: Kennedy touted initiatives on drug pricing, prior authorization reform, interoperability, eliminating gain-of-function research, and addressing screen-time and nutrition in schools.

  • CDC Shakeup: Firings at CDC were described as necessary corrective measures after failures during COVID. Kennedy argued for “depoliticized, evidence-based science,” contrasting with what he portrayed as conflicts of interest under prior leadership.


Democratic Criticism

  • Vaccine Policy and Credibility: Ranking Member Wyden and others accused Kennedy of:

    • Firing all 17 members of the CDC’s ACIP vaccine advisory committee and replacing them with skeptics.

    • Threatening doctors who diverge from administration guidelines.

    • Creating confusion that is directly reducing vaccine access (COVID, RSV, MMR, Hepatitis B).

  • Conflicts of Interest: Senators charged that Kennedy installed advisors with histories as paid expert witnesses against vaccine makers, undermining scientific independence.

  • Healthcare Cuts: Democrats argued Trump-era legislation imposed the largest healthcare cuts in U.S. history, destabilizing Medicaid, ACA coverage, and rural hospitals. They cited closures (e.g., Providence Seaside, Oregon) as early fallout.

  • Corruption and Chaos: Kennedy was accused of enriching allies via lawsuits, promoting conspiracy theorists, and mishandling refugee children at ORR facilities (including alleged deportations under questionable circumstances).

  • Scientific Denial: Democrats pressed Kennedy on COVID mortality data, mRNA vaccines, and epidemiological basics. His refusal to affirm that vaccines reduced mortality drew sharp criticism.


Flashpoints During the Hearing

  1. Swearing-In Request: Democrats sought to have Kennedy sworn under oath, citing false or misleading testimony on vaccines. Chairman Crapo (R) rejected this.

  2. Transparency Dispute: Wyden demanded advance disclosure of evidence underpinning vaccine panel recommendations. Kennedy countered that, for the first time, the evidence was transparent and free of pharma influence.

  3. mRNA Platform Funding: Democrats criticized Kennedy for canceling $500M in mRNA research contracts, framing it as a retreat from global scientific leadership. Kennedy argued these projects were wasteful or captured by pharma.

  4. Operation Warp Speed: Both Kennedy and Republicans praised Trump’s leadership; however, Democrats noted the inconsistency of praising Warp Speed while restricting vaccine access.

  5. Organ Procurement Scandal: Grassley raised organ transplant oversight failures, citing cases of attempted harvesting from patients showing signs of life. Kennedy pledged reforms and contract terminations.

  6. PBM Reform: Senators from both parties emphasized PBM transparency and direct-to-consumer drug distribution. Kennedy stated the White House treats PBM reform as a weekly priority.


Policy Tensions

  • Chronic Disease vs. Acute Care: Kennedy consistently reframed debates around his chronic disease agenda, arguing that focusing on food, chemicals, and lifestyle would save trillions and improve national security. Democrats dismissed this as a deflection from vaccine policy and immediate care access.

  • Data and Trustworthiness: Kennedy claimed CDC and FDA under prior administrations fabricated or politicized COVID data, while Democrats countered that Kennedy himself was undermining science and public trust.

  • Coverage Policy: Kennedy denied Medicaid “cuts,” framing recent actions as program integrity measures. Democrats insisted coverage reductions are inevitable from enacted policy changes.

  • International Competitiveness: Democrats warned that retreating from mRNA innovation cedes leadership to other countries, undermining U.S. preparedness for future pandemics.


Key Takeaways for Experts

  1. Vaccine Access is the Central Political Battleground: Kennedy’s overhaul of vaccine advisory committees is viewed by Republicans as “depoliticization,” and by Democrats as an existential threat to scientific credibility.

  2. Chronic Disease Narrative as Counterweight: Kennedy is repositioning HHS policy around lifestyle and environmental determinants of health, framing vaccines and acute interventions as distractions.

  3. Structural Changes at CDC/FDA/NIH: The hearing confirmed that the administration is intent on reorganizing major agencies, with firings justified by alleged conflicts of interest and COVID-era failures.

  4. Legislative Outlook: Expect bipartisan movement on PBM reform, rural hospital funding deployment, and possibly organ transplant oversight. Vaccine governance, Medicaid funding, and mRNA R&D will remain partisan flashpoints.

  5. Strategic Political Context: The hearing doubled as a campaign proxy war—Republicans showcasing disruption and fiscal discipline, Democrats portraying chaos, corruption, and anti-science governance.


Would you like me to prepare a policy implications memo (2–3 pages) that translates this hearing into actionable insights for healthcare industry stakeholders (insurers, hospital systems, and biotech companies)? That would turn this summary into something you could circulate with clients or use in briefings.

###

Were there any moments that could be described as lighter or humorous?

###

Yes — although the hearing was dominated by sharp exchanges and accusations, there were a few moments where the temperature briefly shifted toward the lighter or even unintentionally humorous. Based on the transcript:


1. The “gentle tap of the gavel”

At the outset, the chair tried to keep order by warning senators that he would “gently tap the gavel” if they ran over their five-minute limit. Given the deeply hostile tone that followed, the image of a “gentle tap” to rein in fiery senators came across as almost comic understatement.


2. Audience outburst

During Kennedy’s testimony listing dozens of initiatives (“food dyes, baby formula contamination, fluoride in water, gas station heroin…”), someone in the audience shouted out. The chair had to pause proceedings, apologize, and warn that police would restore order if it happened again. The interruption injected a bit of live-theater absurdity into an otherwise heavy policy recitation.


3. The “One Big Beautiful Bill” branding

Both sides, even while disagreeing about the bill’s consequences, repeatedly used its official nickname — “the One Big Beautiful Bill.” The repetition of such a Trumpian phrase in a formal Senate transcript, alongside discussions of Medicaid integrity and rural hospital finance, carried an almost satirical edge.


4. The “mailbag contest”

When pressed by Senator Wyden on whether experts supported his advisory panel changes, Kennedy retorted:

“I will put my mailbag against your mailbag.”
That folksy phrasing, dropped into an otherwise bruising exchange about vaccine science, drew chuckles in the room.


5. Senators breaking character

Several senators — notably Senator Cassidy — tried to “restore calm” and frame questions “as a doctor, not a senator.” The tonal shift, almost like stepping out of character in a play, momentarily lightened the mood before returning to confrontation.


6. Verbal collisions

At points, the transcript reads almost like a comedy of interruptions: senators insisting “I’m asking the questions here,” Kennedy pressing “Are these questions or statements?” and exchanges dissolving into overlapping accusations. The sheer procedural chaos, though serious in content, had the rhythm of dark humor.


✅ So, while this hearing was overwhelmingly bitter, experts reading between the lines would note these moments of levity, irony, or absurdity that broke up the tension.

Would you like me to highlight clips that could be used in media coverage (i.e., the sound-bite-worthy “lighter” moments) — or keep it at this analytical level?


##

##

POLICY MEMO

##

##

Got it — here’s a policy implications memo in briefing format, written for healthcare industry stakeholders. I’ve structured it in about the equivalent of 2–3 pages of content (executive memo style), focusing on implications rather than rehashing the hearing itself.


Policy Implications Memo

Subject: Senate Finance Committee Hearing with HHS Secretary Robert F. Kennedy Jr. (September 2025)
Prepared for: Healthcare Industry Stakeholders — Insurers, Hospital Systems, Biotech and Diagnostics Companies


Executive Summary

The Senate Finance Committee hearing with HHS Secretary Robert F. Kennedy Jr. underscored the sharp partisan divide over the Trump administration’s healthcare agenda. While the administration champions prevention, chronic disease reduction, program integrity, and rural investment, Democrats attacked what they see as anti-science policymaking, destabilization of Medicaid and ACA programs, and the politicization of vaccine governance.

For healthcare stakeholders, the key takeaway is that policy risk is rising across multiple dimensions simultaneously: vaccines and public health infrastructure, Medicaid integrity rules, rural hospital stabilization, PBM reform, and R&D priorities (notably mRNA). Companies need to prepare for volatility in both regulatory execution and market perception, with opportunities in rural health funding and PBM reform, and risks in vaccine markets, Medicaid coverage, and research funding.


Key Policy Domains and Implications

1. Vaccine Policy and Public Health Infrastructure

  • Issue: Wholesale replacement of the CDC’s vaccine advisory panel with vaccine skeptics; restrictions on COVID and RSV vaccine recommendations.

  • Industry Implication:

    • Insurers & Hospitals: Confusion over vaccine eligibility rules may increase liability exposure and administrative costs, especially in pharmacy and outpatient settings. Expect uneven uptake and potential regional coverage disputes.

    • Biotech & Pharma: Investment in vaccines — especially mRNA — faces reputational and regulatory headwinds. Advisory committee credibility is eroding, raising questions for global markets about U.S. scientific leadership.

    • Strategic Note: Stakeholders should emphasize transparency, evidence generation, and depoliticized science in external messaging to preserve trust with providers and patients.


2. Medicaid and Program Integrity

  • Issue: CMS highlighted 2.8M duplicate Medicaid/ACA enrollments, projecting $14B in savings from tighter eligibility verification. Democrats countered that cuts and redeterminations are already destabilizing coverage.

  • Industry Implication:

    • Insurers: ACA marketplace plans may see significant churn as duplicate enrollees are purged. Medicaid managed care plans risk coverage losses, offset by compliance burdens on states.

    • Hospitals: Safety-net hospitals should brace for uncompensated care increases if disenrollment accelerates, particularly in rural areas.

    • Strategic Note: Position compliance and technology services (eligibility verification, data integrity) as growth areas. Align advocacy with “coverage continuity” to avoid backlash narratives.


3. Rural Health Transformation

  • Issue: OBBA allocated $50B (over five years) for rural hospitals — a 50% boost in Medicaid-related rural funding. Both parties publicly support implementation, though Democrats warn broader Medicaid pressures undercut it.

  • Industry Implication:

    • Hospitals: Critical Access and rural facilities stand to benefit from targeted stabilization funding and wage index adjustments. Hospitals should prepare project proposals early to capture grant flows.

    • Insurers: Medicare Advantage and rural managed care organizations may see contract opportunities tied to new rural delivery models.

    • Biotech: Enhanced funding creates opportunities for decentralized clinical trials and rural telehealth expansion.

    • Strategic Note: Companies should align product offerings with rural transformation pilots (telehealth platforms, decentralized testing, workforce support).


4. PBM Reform and Drug Pricing

  • Issue: Both parties and the White House are prioritizing PBM transparency and direct-to-consumer alternatives. Kennedy stated President Trump raises the issue “weekly.”

  • Industry Implication:

    • Insurers: PBM contracts will face new disclosure and transparency requirements. Margins could compress as spread pricing comes under scrutiny.

    • Hospitals/Health Systems: Potential for lower drug acquisition costs if direct distribution bypasses PBMs, but contract negotiations may become more volatile.

    • Biotech/Pharma: PBM reforms could accelerate value-based contracting and require manufacturers to rethink channel strategies.

    • Strategic Note: Prepare for PBM legislation in 2026 with bipartisan momentum. Position as constructive partner in transparency reforms.


5. Research & Development Policy

  • Issue: Cancellation of $500M in mRNA platform contracts; emphasis on “ending gain-of-function research” and expanding non-mRNA drug approvals. Democrats framed this as ceding scientific leadership to other countries.

  • Industry Implication:

    • Biotech: Federal R&D funding may shift toward small-molecule drugs, chronic disease research, and safety-focused agendas, away from pandemic-preparedness platforms.

    • Insurers & Hospitals: Downstream implications include fewer new vaccines, slower preparedness for emerging infectious diseases, but greater focus on chronic disease therapeutics.

    • Strategic Note: Biotech firms dependent on federal R&D should hedge by diversifying into chronic disease and lifestyle-linked areas aligned with administration priorities.


Political and Strategic Considerations

  • Partisan Polarization: Expect volatility. Republicans frame reforms as “depoliticization,” while Democrats warn of anti-science chaos. Market messaging must anticipate both narratives.

  • Regulatory Execution Risk: Administrative upheaval at CDC, FDA, and NIH creates operational uncertainty — approval timelines, clinical trial oversight, and advisory committee reliability may all shift unpredictably.

  • Coverage Dynamics: Medicaid integrity efforts could shrink enrollment; rural funding may partially offset but will not fully stabilize vulnerable providers.

  • Public Trust: The credibility of HHS as a scientific authority is under strain. Hospitals and biotech firms may need to step into a quasi-public health role to reassure patients and providers.


Recommendations for Stakeholders

  1. Insurers: Prepare for higher churn in Medicaid and ACA markets. Develop patient retention strategies tied to eligibility verification. Engage early on PBM transparency legislation.

  2. Hospitals: Position aggressively for rural health transformation funds. Expand advocacy around uncompensated care impacts from disenrollment. Build internal compliance around organ transplant and patient safety reforms.

  3. Biotech & Pharma: Diversify R&D portfolios beyond mRNA, while publicly emphasizing commitment to transparent science. Prepare advocacy strategies that highlight U.S. competitiveness risks if funding priorities shift abroad.

  4. Cross-Sector: Maintain bipartisan credibility by focusing on access, transparency, and trust. Anticipate public messaging battles, and ensure alignment with both “prevention-first” and “science-first” narratives.


Conclusion

This hearing signals a high-stakes reset of health policy priorities under the Trump–Kennedy HHS. Opportunities exist — especially in rural investment and PBM reform — but stakeholders must navigate heightened political risk around vaccines, coverage, and research funding. Strategic positioning should emphasize adaptability, transparency, and readiness to engage across partisan divides.


Would you like me to also condense this into a 1-page client-facing slide deck outline (bulletized, with talking points per stakeholder group)? That could serve as a quick-turn deliverable for investor or board meetings.

##

##
Were there direct comments on A.I. or on med tech innovation?

##

##

From the hearing transcript, there were no direct, substantive references to Artificial Intelligence (AI) or to CMS’s role in fostering medtech innovation in the way stakeholders might expect (e.g., AI-driven diagnostics, digital health reimbursement, or FDA/CMS coordination on innovation).

Here’s what does emerge:


Innovation Mentions in Passing

  • Interoperability & Information Blocking: Kennedy highlighted work on prior authorization and healthcare interoperability. While these issues are foundational to digital health and could eventually overlap with AI-enabled systems, AI itself was not explicitly named.

  • Drug Approvals at FDA: Kennedy claimed FDA was on track to approve more drugs than at any point in history. This was presented as evidence of efficiency and innovation, but without tying it to novel technologies (e.g., AI-assisted trials, computational drug design).

  • Organ Procurement Oversight: Senators raised serious misconduct concerns in organ transplant networks. Kennedy pledged reforms and industry reorganization, but again, no mention of AI-driven monitoring or analytics.

  • PBM Reform: The discussions around transparency and direct-to-consumer models could eventually intersect with AI in pricing/claims analysis, but AI wasn’t part of the framing.


Noticeable Absence

  • Unlike other recent congressional hearings (e.g., on FDA regulation of digital health, or CMS pilot models involving AI), this session did not address AI explicitly.

  • Similarly, there was no extended discussion of CMS Innovation Center (CMMI) pilots or regulatory sandboxes for medtech. The CMS focus was limited to fraud, duplicate enrollments, and rural health transformation funding.


Implication for Stakeholders

  • AI & Medtech Firms: The absence is notable — it signals that under current leadership, HHS’s political bandwidth is consumed by vaccines, chronic disease framing, Medicaid integrity, and rural health, rather than new technology adoption.

  • CMS Innovation: With no mention of AI pilots or CMMI’s role, stakeholders should not expect near-term, high-level political support for AI reimbursement models. The focus is on compliance and cost control, not innovation.


✅ So in short: No direct mentions of AI or CMS-led medtech innovation. The closest touchpoints were interoperability reforms, drug approvals, and PBM transparency.

Would you like me to draft a short client alert (1 page) specifically on this absence of AI/medtech discussion — framing it as a gap that innovators can leverage in upcoming policy conversations with CMS and HHS?

##

##


WSJ Article on Spin-offs: Insights to the Becton Dickinson-Waters Deal (AI)

In mid-July, it was  announced that Waters would expand its clinical  footprint via a $17.5B acquisition of Becton Dickinson’s diagnostics business.  

Six weeks later, there's a relevant headline in today's WSJ:  "The Year's Buzziest Deals are Corporate Breakups.  Companies are splitting themselves up to appease frustrated investors.  Thomas & Glickman, 9/4/2025."

##

Here are some sources:

WSJ - review of break-ups and spin-offs.  Here.

The Waters-BD deal.  In WSJ July 14 here.  In Reuters here.  In 360Dx on August 28 here (Waters CEO). 

I understand it's likely a "Reverse Morris" deal - Chat GPT explains here.

Chat GPT 5 quick take on BD-Waters.  Here.   "BD concentrates on medical devices..." here.

##

 AI CORNER

##

Chat GPT 5 provides a guided summary (prompt at bottom).

##

Here’s a composite article that weaves together the BD–Waters deal, the broader boom in corporate breakups, and the mechanics of a Reverse Morris Trust, written at a WSJ/FT level.


Waters’ $17.5 Billion Bet on BD’s Labs: A Deal Born of Breakups

Becton Dickinson’s decision to shed its biosciences and diagnostics division in a $17.5 billion combination with Waters Corp. captures two converging trends: the remaking of U.S. healthcare conglomerates and the resurgence of corporate breakups as Wall Street’s deal du jour.

The Transaction

Announced in July, the transaction will spin out BD’s Biosciences & Diagnostics Solutions business and merge it with Waters, the Massachusetts-based maker of analytical instruments. Structured as a Reverse Morris Trust, the deal allows BD to divest tax-free while handing its shareholders a 39% stake in the enlarged Waters. BD will also pocket $4 billion in cash, while Waters assumes $4 billion of new debt.

For BD, the deal represents a strategic narrowing. Chief Executive Tom Polen has signaled a sharper focus on core medical technologies, from pre-filled syringes to vascular devices, while moving away from the volatile world of molecular diagnostics. BD is simultaneously investing in initiatives like community screening for peripheral artery disease, underscoring its pivot toward patient-facing medtech.

For Waters, under CEO Udit Batra, the deal is transformative. It doubles the company’s addressable market to roughly $40 billion, enhances its presence in clinical diagnostics, and brings access to BD’s deep installed base of molecular and microbiology systems. Waters expects cost savings of $200 million within three years and sees longer-term upside from marrying its mass spectrometry know-how with BD’s platforms.

A Reverse Morris Trust Explained

The Reverse Morris Trust is a favored Wall Street tool for these situations. The mechanics are deceptively simple: BD spins off its diagnostics arm into a standalone entity, which then merges with Waters. To qualify for tax-free treatment, BD shareholders must own more than 50% of the combined company at the moment of closing. Once the ink is dry, those shareholders can sell immediately—the IRS cares only about ownership at closing, not after.

The attraction is clear. BD avoids a hefty capital gains bill, shareholders retain upside through stock in both companies, and Waters acquires a business at an effective discount. Indeed, the unit is being valued at about five times projected 2025 revenue—20% below the multiple fetched by peer Danaher.

Risks and Rewards

The deal is not without hazards. Waters, valued at about $21 billion before the announcement, is taking on substantial debt and complexity, more than doubling its revenue base. Nearly half of BD’s divested unit’s sales come from biosciences, a segment exposed to U.S. government cuts in research funding. Investors reacted warily: Waters shares fell by double digits on the news, reflecting fears the company may have bitten off more than it can chew.

Yet analysts note that BD’s diagnostics assets provide a counterweight: recurring revenue from clinical platforms like BD MAX and BD COR, as well as dense customer relationships across specialty and hospital labs. Waters is betting that these distribution channels can accelerate the adoption of mass spectrometry in clinical practice, a field where rivals from Thermo Fisher to Roche have struggled to crack the automation puzzle.

Part of a Bigger Story

The Waters–BD tie-up fits squarely within a broader boom in divestitures and spin-offs. As the Wall Street Journal noted this month, corporate breakups have become some of the year’s buzziest deals—from Warner Bros. Discovery’s decision to unwind its $43 billion megamerger to Kraft Heinz’s plan to split a decade after Warren Buffett orchestrated its union. The rationale is consistent: investors have grown weary of conglomerates trading at discounts, and activist shareholders are pushing management teams to simplify portfolios.

In BD’s case, activist fund Starboard Value pressed for the separation earlier this year, valuing the diagnostics unit at $33–35 billion. While the final transaction came in lower, BD achieved its goal: a cleaner profile, immediate cash for buybacks and debt reduction, and the ability to tell investors a more focused growth story.

The Outlook

If the transaction clears regulators, closing is expected by the end of Q1 2026. Waters will emerge as a markedly larger and riskier player—one with twice the scale, greater exposure to recurring diagnostic revenues, and a hefty debt load. For BD, the divestiture sharpens its medtech identity and aligns with a wider investor-driven trend: simplifying sprawling empires into leaner, more transparent businesses.

In that sense, the deal is not just about two companies. It is a case study in how Wall Street’s current enthusiasm for corporate breakups is reshaping the healthcare landscape—one Reverse Morris Trust at a time.


 

Prompt.

[For article above] Write a composite article about the Becton Dickinson spinoff to Waters. Include a special focus on the WSJ article on why there's a boom in spinoffs and divestures, and the other articles fit in that frame. inform readers what a reverse morris trust is. You're writing at the WSJ or Financial Times level.

###

[For clipping below.]  I don't quite get a key point, from WSJ, why do these spinouts raise shareholder value? 1 + 1 = 3? or 2-1 = something bigger than "1"? Does the stock market have to be irrational for the spinouts to be worth more than the original sum?

Great question — and it goes to the heart of why investors (and activists) push for breakups. The WSJ (“The Year’s Buzziest Deals Are Corporate Breakups”) makes the case that the stock market isn’t being “irrational” so much as re-rating the pieces once they’re no longer trapped inside a conglomerate.

Here’s the logic, in WSJ/FT terms:


The “Conglomerate Discount”

Large diversified companies often trade at a discount to the sum of their parts. Investors don’t always give full credit to a high-growth or high-margin division if it is bundled inside a slower, more cyclical group. Think of BD: its diagnostics business was growing high-single digits, but the market valued all of BD more like a mature medtech player with recalls and pricing headwinds.

So the spin is like 2 – 1 = more than 1. You remove the drag, and the remaining company re-rates higher. Meanwhile, the spun-out or merged unit can get valued in line with its faster-growing peers.


Sharper Narratives for Investors

Post-split, each company can tell a clearer story. Investors want to “put their money into something where they’re clear what it does,” as one M&A lawyer told the WSJ.

  • BD becomes a pure-play medical technology company, easier to compare with peers like Medtronic or Edwards.

  • Waters, meanwhile, doubles its market and gains a recurring diagnostics revenue stream. Investors who want the diagnostics growth story can now buy Waters directly.

Clarity matters in markets. A “simpler” stock can attract a broader base of investors, especially growth or income funds that screen out conglomerates.


Incentives and Focus

Breakups can also improve operating performance. Management teams no longer fight for capital across unrelated units; incentives align more closely with each business’s strategy. That can unlock productivity or M&A optionality that was stifled before.


Does 1 + 1 = 3?

It’s not that value is magically created. Instead:

  • 1 (BD as a whole) traded below its potential.

  • Split into 2, and each is valued on more favorable peer multiples.

  • The “extra” comes from removing the conglomerate discount and from investors pricing the pieces more optimistically once they stand alone.

The stock market doesn’t have to be irrational. It just needs to believe that separate companies are easier to understand, benchmark, and invest in than a sprawling, mixed-growth conglomerate.


📊 Think of it less as “1 + 1 = 3,” and more as “2 – 1 = worth more than 1,” because the leftover pieces are finally valued on their own merits.


Would you like me to build a numerical worked example (e.g. applying different EBITDA multiples to BD’s diagnostics vs. medtech units, showing how the sum of parts > consolidated valuation) to make this concrete?

##

##

See the same sources collated by Google Notebook LM here.

CMS Releases Part B Utilization by CPT Code for CY2024

HEADER: If you love Medicare Part B utilization data, the agency has released its summary 2024 data files in Excel.

###

CMS releases Part B  data annual in two different forms.   Sometime in the fall, it releases Part B data for the prior year (for us, CY2024) in Excel spreadsheets.  Find these here:

 https://www.cms.gov/data-research/statistics-trends-and-reports/part-b-national-summary-data-file

(I believe they've belatedly released the 2023 data along with 2024.)

This is simple data - CPT code, volume of national utilization, volume of dollars paid per code.

##

At a longer delay, CMS releases an awesome cloud database of CPT code utilization by provider.  (E.g. Dr. Alvin Smith had 1,100 92114 office visits and 800 92115 office visits.)  Find that here, for CY2023:

https://data.cms.gov/provider-summary-by-type-of-service/medicare-physician-other-practitioners/medicare-physician-other-practitioners-by-provider-and-service


##

Quick Look - PLA Codes

In Cy2024 data, there are PLA codes up to 0503U.  Together with"M" codes, these PLA codes were paid $682M dollars.   But the distribution among the 500 codes was highly skewed, with the top 15 codes paid 86% of the money, and the  top 4 codes paid 52% of the money. Click to enlarge.


The top two PLA codes, 0242U, 0326Ul, are Guardant's, garnering about $200M for about 40,000 services.

##

Thanks to Jack Meehan at Nephron for flagging the data release.

##

The CPT utilization files provide code numbers, but not descriptors.  Skilled Excel jockeys should be able to merge the code + descriptor tables found in the CLFS itself, with the CPT codes of the annual data, and get a spreadsheet with code + descriptor + dollars paid.  

##

If you're still reading, you might enjoy an article about using Excel "PivotCharts" rather than "PivotTables" - at MakeUseOf here.  And you might enjoy a detailed automatic AI anaysis (via Chat GPT 5) of CMS new test pricing data - here.




Wednesday, September 3, 2025

CMS Publishes Expert Panel Lab Pricing Votes (From July 23, 2025 Mtg)

CMS is required to hold an advisory expert panel to help it price new laboratory tests.  This year, the panel brought together 10 members on July 23, 2025, and worked through 90 agenda items in one televised workday.

Find the panel results here (PDF, 27pp):

https://www.cms.gov/files/document/clfs-advisory-panel-recommendations-2025.pdf

Find the home page for the panel here:

https://www.cms.gov/medicare/payment/fee-schedules/clinical-laboratory-fee-schedule-clfs/clfs-advisory-panel

(You find the PDF by scrolling down to, "Panel Recommendations.")

##

What happened?

The panelists vote individually, and there can be several pricing options to vote on per code.  Most of the votes are either 10/10 (unanimous for one pricing option) or 9/10 (one member varies, or one member abstains).  There were a couple codes where no single option got more than 5 or 6 votes of 10.

About 70 of the votes were for "crosswalk" pricing and about 20 for gapfill pricing.  About 90% of the crosswalk votes are for a single crosswalk price x1.   (A few votes were for multiples or fractions).  

##

What happens next?  

CMS is required to "consult with an expert outside advisory panel."  However, when CMS releases its proposed federal prices for 2026, it's under no obligation to match the panel vote on any particular code, and often its prefered choices vary from where the panelists settled.

Look for CMS proposed prices sometime in the first half of September, followed by a comment period, and final prices in the second half of November.

Example

One of the more complex votes was for item #9, code X159U, transplantation medicine.  All 10 panelists voted, 1 for "gapfill," 3 for 0018U x 85%, and 6 for crosswalk to 0069U.

##
AI CORNER

I asked Chat GPT to see what it could make of the 27 page, 92-item PDF.  I can't or haven't checked all these numbers, so the AI discussion is presented "as is."

###

Big picture. 

The panel favored crosswalk over gapfill by roughly 4:1. In 90 items, 19 winners were gapfill (21%), while 71 winners were crosswalks (79%). Of those crosswalk wins, 63 (70% of all items) were single-code, straight crosswalks (e.g., 0538U → 81459), and only 8 (9%) used fractions/multiples (e.g., 87185 × 3; 87811 + 87804 × 2). Unanimity was common: 49 items (54%) were 10-0 wins—broken down as 36 straight crosswalks, 1 composite crosswalk, and 12 unanimous gapfills. The median winning vote count was 10, with a tight distribution (only four items won with ≤6 votes—the narrowest was 5 votes). Abstentions occurred on 12 items (13%), typically on less familiar or edge-case tests.

Gapfill—when did it prevail? 

Gapfill was the majority (≥6 votes) and top choice in 19 items and accounted for ~23% of all individual votes cast across the day. It dominated where novel analytic paradigms or poorly comparable predecessors made crosswalks awkward—especially infectious-disease NGS and new biomarkers:
Unanimous gapfill for plasma metagenomic ID sequencing (0531U), urine NGS for 44 organisms (X177U), sepsis marker PSP (X182U), and TB CFP-10 (0574U).
• In neurology, pTau217 (0551U) was 10–0 gapfill.
• Oncology had at least one notable gapfill: 0569U (ctDNA methylation) was 10–0 gapfill, while most other oncology codes crosswalked (see below).

Crosswalks—how “clean” vs composite? 

When crosswalks won, they were usually clean. Only 8 winners used fractions/multiples (11% of crosswalk wins), and across all crosswalk votes (not just winners), ~11% were for composite options. Typical composite winners included:
871XX → 87185 × 3 (9–1) and 871X1 → 87150 × 5 (8–2) (phenotypic/genotypic resistance assays).
8XXXX (COVID/Flu antigen) → 87811 + 87804 × 2 (8–1–1).
0550U (prostate algorithm) → 81539 × 0.5 (10–0).
0420U (urothelial RNA+ddPCR signature) → 0012M + 0356U × 0.35 (9–1).
X184U (APOE peptides) was the day’s closest call: 5 votes for 0412U × 0.33, with 2 for “0412U” and 2 for gapfill.

How fractured were crosswalk preferences? 

Not very. In 64 items, all crosswalk votes went to a single comparator; only 22 items split crosswalk votes across ≥2 options, and just one item split across three composite variants (0567U, constitutional WGS). Net: when panelists chose to crosswalk, they converged on one target most of the time.

By content area (illustrative patterns).

  • Oncology. Consistent alignment with the NGS families: tissue CGP to 81459 (e.g., 0538U, 0543U), plasma CGP to 81464 (0539U, 0530U), MRD setup/follow-up to 0306U/0307U (0560U/0561U). Protein/RNA signatures commonly crosswalked to established algorithm codes (81525, 81539, 81503). An outlier: 0569U (ctDNA methylation) was 10–0 gapfill. Unanimity was frequent in this cluster.

  • Infectious disease. Gapfill swept the novel ID NGS and new biomarker entries (see above), while common modalities crosswalked cleanly: respiratory NAAT panels to 87633 (e.g., 0563U, 0564U), joint-space multiplex to 0505U, and HSV/VZV NAAT to 87631. The COVID/Flu combo antigen used a composite crosswalk (87811 + 87804 × 2). Lyme IgG (X166U) was 10–0 gapfill.

  • Transplantation. Donor-derived cfDNA tests 0540U and 0544U crosswalked to 0493U; the combined cfDNA + expression test X160U crosswalked to 81558 (with 1 vote for adding 0118U). The liver miRNA rejection test (X159U) gives a good snapshot of how the panel weighs comparators: 0069U won (6 votes) over a fractional crosswalk to 0018U × 0.85 (3) and gapfill (1).

  • Neurology. pTau217 (0551U) was 10–0 gapfill; NfL and GFAP single-analyte assays crosswalked to 0361U; a TBI panel crosswalked to 0358U. The APOE prototype (X184U) was the most divided item (noted above).

What a payer or submitter should take from this.

  • If there’s a clear incumbent analog, expect a straight crosswalk. The panel rarely resorted to arithmetic constructions; composites were exceptions, not the rule.

  • Use gapfill arguments when the analytic paradigm is genuinely new (e.g., broad untargeted ID NGS, emerging protein biomarkers, or methylome approaches without obvious cousins). That’s where the panel repeatedly embraced gapfill—often with 10–0 calls.

  • Consensus was strong (median 10 votes for the winner). If you anticipate a crosswalk, aligning your dossier to the dominant comparator the panel tends to pick (e.g., 81459/81464 families; 0306U/0307U; 0493U) is a defensible strategy. If you need composite pricing, be prepared: only ~11% of all crosswalk votes—and 8 winners—went that route.

A few precise stats for your slide:

  • Winners: 19 gapfill (21%); 63 single-code crosswalk (70%); 8 composite crosswalk (9%).

  • Unanimous (10–0): 49 items (36 single-code CW, 1 composite CW, 12 gapfill).

  • Gapfill share of all panelist votes: ~22.7% (204 of 900 votes, including abstentions).

  • Crosswalk vote consolidation: 64 items had all crosswalk votes on one target; 22 items split across ≥2 targets.

  • Closest call: X184U (APOE peptides): 0412U × 0.33 won 5–2–2 over gapfill and straight 0412U.

 

###

Prompt.  

These pages show the votes of the CMS laboratory advisory expert panel, for pricing of new lab codes for 2026. The panel met on July 23, 2025, and reviewed 92 agenda items. The items generally had 10 respones from 10 unique participants. (Occassionally one panelist abstained). Panelists could vote for "gapfill" pricing, or for crosswalk to a particular code or fractional code or multiple codes. For example, on agenda item 9, which is 0159U, transplantation medicine, we see that 1 panelist voted for gapfill, 3 for a crosswalk to 85% of 0018U, and 6 for a crosswalk to the price of 0069U. Please conduct a carefully analytical assessment of the panelist results and discuss in illuminating and insightful ways. For example, a reader might want to know how often "Gapfill" was the majority vote, or how often panelists voted for a single crosswalk as opposed to some sort of fraction or multiple. Take your time.

Items 22, 61, were numbered at one time but not shown on the final output (skips from 21 to 23, from 60 to 62).