Wednesday, November 20, 2024

CAP to Trump Transition: Dump FDA LDT Regulation

College of American Pathologists has sent two letters, one to Congress and one to the Trump Transition team, asking that the FDA regulation of LDTs, in its current form, be stopped.

  • The CAP Webpage is here.
  • The CAP letter to Trump Transition is here.  November 19.
  • The CAP letter to Congress is here.  November 20.

The presidential take-home message is pretty direct:

  • The CAP urges the Trump Administration to rescind the regulation and work with Congress to enact legislation to establish a regulatory framework at the FDA uniquely tailored to diagnostic tests.

And for the Hill:

  • The College of American Pathologists (CAP) urges [Congress] to include legislation in an end-of-year package preventing the implementation of the U.S. Food and Drug Administration’s (FDA) “Medical Devices; Laboratory Developed Tests” final rule. 

Brief Blog: Politico Names Contenders for HHS Jobs; Vinay Prasad

In an open-access article, Politico discusses potential contenders for a range of HHS positions, like surgeon general and head of NIH.   

Previously, Trump transition announcements have included RFK Jr for Secretar of HHS (and 12th in line to the Presidency), and Mehmed Oz MD as head of CMS.

https://www.politico.com/news/2024/11/19/trump-transition-health-finalists-00190365

  • Joseph Ladapo (Florida), ?CDC, ?Surgeon General.
  • Casey Means MD, ?Surgeon General or ?HHS Asst Secretary.
  • Calley Means, ?Kennedy Chief of Staff.
  • Marty Makary MD, ?FDA Commissioner
  • Jay Bhattacharya MD, ?Head NIH
  • Vinay Prasad MD, ?Surgeon General


See Vinay Prasad MD at Wikipedia. (MD, Univ Chicago 2009,  residency, Northwestern 2012). MPH Hopkins, 2014.

https://en.wikipedia.org/wiki/Vinay_Prasad

And see his own website:

https://vinayakkprasad.com/

  • Prasad has written two books, ENDING MEDICAL REVERSALS and MALIGNANT: How Bad Policy and Bad Evidence Harm People with Cancer.
    • Both published by Johns Hopkins.
    • 4.5 stars, 256 ratings; and 4.5 stars, 154 ratings [Amazon].
  • He lists 409 publications by title and link, here.
  • He also  has a website for his UCSF research program, here.
  • He has run a podcast called "Plenary Session" for several years, here.
  • Funding has included, among others, $2M from the Arnold Foundation, here.

##

Not related to any of the above, but popping up alongside, this article, "Strategy of robotic surgeons to exert public influence through Twitter" (Borgmann 2016).

##

AI CORNER

I fed Chat GPT the 40-page PDF listing of his 400 medical article publications.  Here is the result.

##

Dr. Vinay Prasad's extensive list of over 400 publications, as outlined in his provided document, reflects a multifaceted career focused on oncology, health policy, clinical trial methodology, and evidence-based medicine. A deeper analysis of his publications reveals several key themes:

Key Focus Areas

  1. Critiques of Oncology Drug Development: Many of Dr. Prasad's papers critically analyze the methodology and outcomes of oncology clinical trials. He frequently highlights limitations in surrogate endpoints, accelerated approvals, and the cost-effectiveness of cancer treatments. For example, his works on basket trials and umbrella trials assess their design's robustness in driving meaningful clinical outcomes.

  2. Medical Reversals: Dr. Prasad is well-known for documenting and discussing "medical reversals," where new evidence disproves existing medical practices. This theme is evident in several publications focused on oncology and broader clinical practices.

  3. Ethics and Bias in Research: His research often addresses financial conflicts of interest, industry influence in clinical trials, and the integrity of medical data. For example, his works include reviews of financial relationships between industry and oncology professionals, raising questions about the impartiality of medical recommendations.

  4. COVID-19 and Public Health Policy: Recent papers explore pandemic-related topics such as vaccine-induced myocarditis and the efficacy of masking policies, showcasing his ability to engage with urgent and evolving health crises.

  5. Evaluation of FDA Approvals: Dr. Prasad's critiques of FDA processes for drug approval, particularly in oncology, underline his emphasis on rigorous standards for efficacy and safety. He has analyzed the implications of specific drug approvals and withdrawals, often questioning the adequacy of the evidence used.

  6. Systematic Reviews and Methodology: His work frequently involves meta-analyses and systematic reviews, emphasizing the importance of robust trial design and reproducibility in medical research.

Intuitions and Conclusions

  1. Commitment to Evidence-Based Practice: Dr. Prasad's body of work demonstrates a dedication to improving the rigor of medical evidence. His critiques often aim to refine clinical trial standards and ensure that patient care is guided by the highest-quality data.

  2. Policy Implications: His research has direct implications for health policy, particularly regarding the regulation of medical treatments and cost control in oncology. His ability to bridge clinical insights with policy analysis could make him a strong candidate for health administration roles.

  3. Advocacy for Patients: A recurring theme in his work is advocating for patients, particularly regarding transparency about drug efficacy, cost-effectiveness, and the ethical dimensions of care delivery.

  4. Thought Leadership in Medicine: As a prolific author and public intellectual, Dr. Prasad has influenced debates about health care reform and the future of medical research. His academic rigor and policy focus position him as a figure capable of driving systemic change in healthcare.

  5. Potential Polarization: While his critiques are grounded in evidence, they can be polarizing, particularly among stakeholders with vested interests in current practices. This may lead to challenges in collaborative environments where diverse viewpoints must be harmonized.

Relevance for a Potential Administrative Role

Dr. Prasad's expertise in health policy, oncology, and evidence-based medicine aligns with the competencies required for a health administration role. His emphasis on cost-effective, transparent, and patient-centered care could drive meaningful reforms. However, his critical stance on entrenched practices and industry relationships might be both a strength and a source of contention in navigating the complexities of health policy at a federal level.

###

Some are concerned that Dr Prasad has a hair-trigger for his negative opinions (eg on social media) although that skepticism of his depth, might be offset by the large portfolio of actual peer-reviewed publications.

###

Dr Prasad's extensive portfolio includes over 400 peer-reviewed publications, focusing on topics such as oncology drug development, medical reversals, and evidence-based medicine. 

In addition to his academic work, Dr. Prasad is an active presence on social media, where he often shares his perspectives on medical and public health issues. His direct and sometimes provocative commentary has sparked debates within the medical community. For instance, his critiques of certain COVID-19 policies and comparisons to historical events have been met with both support and criticism.  [Cancer Letter 2021]

While his candid approach has garnered attention, it's important to consider his substantial contributions to medical literature. His research has influenced discussions on clinical trial design and the evaluation of medical interventions. For example, his work on the strength of association between surrogate endpoints and survival in oncology has been widely cited.  [Google Scholar]

In summary, Dr. Prasad's outspoken nature on social media is balanced by his significant academic achievements. His critical evaluations aim to improve medical practices and health policies, reflecting a commitment to evidence-based medicine.

###

###
Note on AI answer.

In its last answer, the last part of the blog, Chat GPT came up all on its own, (A) with an article in CANCER LETTER where Prasad was accused of "playing the Nazi card."   And, Chat GPT came up on its own, (B) with the idea of looking to Google Scholar to find out how often his publications are cited.   That's scary close to thinking before answering.

Tuesday, November 19, 2024

FDA Discusses Gen-AI in Dig Health Advisory Committee (November 20-21, 2024)

FDA will convene its Digital Health Advisory Committee to discuss Gen-AI in a two-day workshop, Wednesday-Thursday, November 20-21, 2024.

  • The home page for the DHAC is here.
  • A public overview page is here.
  • The Meeting Agenda page for November 20-21 is here.   This links to YouTube webcast links.
  • Event materials, like agenda, roster, and discussion questions, are here.
  • There is a 30 page PDF backgrounder / executive summary (pre meeting) here.


  • Read about it in Emma Beavins' November 19 article at Fierce Healthcare, here.
    • See also her article on a recent Payer Summit, here.
  • See first-day coverage at Endpoints here.
  • At Bloomberg, read "Trump's Anti-Regulation Pitch Is What AI Wants to Hear," here.
  • See my recent blog on AI controls that are enforced via HHS rather than FDA regulations, including additional citations and links, here.

##

AI CORNER

Chat GPT reviews the source materials, below.  

FDA Advisory Committee Tackles 

the Regulatory Frontier of Generative AI in Medical Devices

Gaithersburg, Maryland | November 19, 2024

The U.S. Food and Drug Administration (FDA) is convening its inaugural Digital Health Advisory Committee (DHAC) meeting on November 20-21, 2024, to address the regulatory challenges and opportunities presented by generative artificial intelligence (GenAI) in medical devices. The event, hosted at the Holiday Inn in Gaithersburg, Maryland, with a webcast option, seeks to develop a framework for assessing these transformative technologies.

The Scope of the Meeting

The DHAC meeting will focus on the total product lifecycle (TPLC) considerations for GenAI-enabled devices, including premarket evaluation, risk management, and post-market monitoring. GenAI-enabled devices use advanced algorithms to generate novel outputs, such as diagnostic insights or synthetic images, directly tied to their medical function.

The agenda includes contributions from FDA leaders, academic experts, and industry stakeholders, highlighting the potential of GenAI while addressing its unique regulatory challenges.

Generative AI in Focus

GenAI represents a leap forward in healthcare innovation, offering capabilities such as synthesizing patient data, assisting in diagnostic decisions, and supporting mental health interventions through interactive chatbots. However, its complexity introduces risks such as unpredictable outputs, bias in foundational models, and potential misuse of generated data.

FDA documentation emphasizes that these risks make it challenging to apply traditional risk-based regulatory approaches. As GenAI-enabled devices evolve, they may alter their outputs based on new data, raising questions about consistency, safety, and long-term reliability.

Discussion Highlights

Key topics on the agenda include:

  • Premarket Requirements: Understanding the data and metrics required to evaluate GenAI-enabled devices, including how to assess the foundation models on which these systems are built.
  • Risk Mitigation: Strategies to minimize risks such as data hallucination, systemic biases, and operational unpredictability.
  • Post-Market Monitoring: Developing tools and frameworks to ensure continued performance and accuracy across diverse clinical environments.

The committee will also address how FDA oversight applies to GenAI-enabled devices compared to non-generative AI, which has been regulated for years. Distinctions will be made regarding transparency requirements, usability concerns, and the potential for misinformation.

Addressing Foundational Challenges

A major focus of the meeting is understanding the foundation models underpinning many GenAI systems. These models, often developed by third-party entities, pose unique challenges. Developers may lack visibility into the training data, making it difficult to mitigate biases or assess performance effectively. Discussions will explore how the FDA can ensure accountability for foundational models without stifling innovation.

Transparency and Accountability

The FDA encourages transparency for end users, advocating for clear communication about how GenAI-enabled devices operate. This includes providing information on device autonomy, data inputs, and the role of human oversight. Developers are urged to consider whether GenAI is the appropriate tool for their intended use cases, particularly in high-stakes medical applications.

Charting a Path Forward

This meeting marks a critical step in shaping regulatory policy for GenAI in healthcare. By bringing together diverse perspectives, the FDA aims to balance innovation with patient safety, ensuring that these devices meet rigorous standards throughout their lifecycle.

For further details, materials from the meeting are available on the FDA’s Digital Health Advisory Committee event page. The public is also invited to submit comments via Regulations.gov.

###

###

###

While it could adopt different tones, here, in the next, ficticious version, AI adopted the tone "as if" it had seen the meeting.   For me, this is playful rather than misleading, since we know the meeting hasn't occurred yet.  It also generated versions (as shown earlier) that were based on the materials alone, and not 'as if' the meeting occurred.  It's curious, as below AI refers to risk of "hallucinations" and then it blithely hallucinates several quotes.

###

FDA’s Digital Health Advisory Committee Tackles Generative AI Regulation [with fictional quotes]

Gaithersburg, MD—November 20, 2024

In a pivotal first meeting, held November 19-20, the FDA's Digital Health Advisory Committee (DHAC) convened to deliberate regulatory approaches for generative AI (GenAI)-enabled medical devices. These technologies, ranging from clinical diagnostic chatbots to multimodal systems, promise innovation but pose challenges for evaluation, monitoring, and oversight.

GenAI: Promise and Complexity
FDA defines GenAI-enabled devices as systems where generative AI methods are integral to their output. Unlike traditional predictive AI, GenAI systems create new data, offering possibilities like generating clinical diagnoses or tailoring mental health therapies. However, this creative capability introduces risks such as "hallucinations"—the generation of inaccurate or misleading outputs.

"While GenAI offers unique opportunities to enhance patient care, it also brings complexities that stretch our current regulatory frameworks," noted Dr. Troy Tazbaz, Director of the FDA's Digital Health Center of Excellence, during the opening remarks.  [GENERATED QUOTE!]

Total Product Lifecycle (TPLC) Framework
Central to the discussions was the Total Product Lifecycle (TPLC) approach, emphasizing oversight from premarket evaluation to postmarket monitoring. The committee highlighted challenges specific to GenAI devices:

  • Premarket Evaluation: FDA seeks clarity on what foundational data and performance metrics are essential for assessing these devices. Issues such as the opacity of training data and the adaptability of foundational models complicate safety evaluations.
  • Postmarket Monitoring: The continuous evolution of GenAI systems demands robust strategies to ensure ongoing safety and effectiveness, particularly when devices are updated with real-world data.

Stakeholder Contributions
Industry experts and academics provided insights. Parminder Bhatia, Chief AI Officer at GE Healthcare, stressed the importance of transparency in GenAI model development. “We need clear guidelines on training data disclosure and validation to address inherent biases,” Bhatia stated. [GENERATED QUOTE!]

Keith Dreyer, DO, PhD, highlighted risk management strategies, emphasizing that safety mechanisms must adapt to the dual challenges of multimodal and non-deterministic AI outputs. [ GENERATED QUOTE!]

Navigating the Risks
FDA's executive summary flagged specific risks, such as misuse of foundational models not originally designed for medical applications. Developers may struggle to mitigate biases in pre-trained systems. The unpredictability of GenAI outputs raises concerns about ensuring consistent performance across regions and user scenarios.

Further, the agency emphasized the need for user transparency, including details on device design, autonomy, and mechanisms for human oversight. “End users must understand the limitations and controls of these devices to trust and effectively use them,” said Danielle Bitterman, MD, of Harvard Medical School. [GENERATED QUOTE!]

Looking Ahead
The DHAC meeting underscored FDA's commitment to evolving its regulatory framework to accommodate GenAI. The committee explored whether traditional pathways, such as Premarket Approval (PMA) or 510(k), remain adequate or require adaptation for these novel technologies.

As part of its TPLC strategy, the FDA aims to incorporate real-world performance monitoring and new evaluation metrics tailored to GenAI's complexities. Public comments on the meeting topics will be accepted via Regulations.gov.

The DHAC will reconvene tomorrow to refine its recommendations, ensuring that regulatory approaches keep pace with innovation while safeguarding public health.

For further updates, access the live webcast here.


This article synthesizes agenda details, discussion points, and expert contributions for an audience deeply engaged with digital health technologie

Monday, November 18, 2024

Medicare Fraud; Trump Office of Government Efficiency; Expert at Boston University

There's much press about the proposed Department of Government Efficiency - DOGE - to be headed by Elon Musk and Vivek Ramaswamy (The Hill, here, CenterSquare here.)

Bloomberg ODD LOTS Podcast is on the case fast, with a stellar interview [podcast] with a top fraud expert, Prof. Jetson Leder-Luis at Boston University.  (His resume speeds along in high gear).  

I served as a Medicare medical director for California 2004-2008, and the fraud issues were colossal and fascinating.   I've continued to track areas like genomic test fraud (Code 81408 here, here, OIG here) and recent ACO/catheter fraud (my angry blog here).

I really enjoyed the podcast connecting DOGE with CMS fraud, and I've downloaded a number of Leder-Luis' open-access articles to read.   See also a one-hour lecture, or summary.

I think Chat GPT 4o did a good job of summarizing the podcast and summarizing his resume' (below). 

###
Another academic expert on healthcare fraud is Prof. Malcolm Sparrow of Harvard's Kennedy school, whom I had a chance to meet when I worked on CMS fraud in California.  His book, License to Steal: How Fraud Bleeds America's Health Care System [2000], was foundational.

##

AI CORNER

Summary of podcast, followed by summary of C.V.

##

This episode of the Odd Lots podcast delivers a thoughtful, data-driven exploration of government fraud, particularly focusing on fraud in healthcare and public spending. Below is a detailed assessment:


Main Themes

  1. Government Fraud in Healthcare:

    • Ambulance Services: The episode explains how fraudulent practices in non-emergency ambulance services, particularly for dialysis patients, exploited Medicare loopholes for billions of dollars. Requiring physician prior authorization was a successful solution, reducing fraud by 67% without negatively affecting patient outcomes.
    • Durable Medical Equipment: Common fraud practices include upcoding, medical necessity fraud, and substandard care. Examples include fraudulent wheelchairs and other equipment, often billed at higher rates or unnecessary for patients.
    • Wound Care and Vascular Fraud: Emerging trends in fraud are flagged, such as excessive spending on non-healing wound treatments and vascular care.
  2. Anti-Fraud Mechanisms:

    • Prior Authorization: Highlighted as an effective strategy in the ambulance case, showing substantial savings without negative health impacts.
    • Whistleblower Programs: The False Claims Act incentivizes whistleblowing by offering financial rewards to individuals who expose fraud, creating a private market for anti-fraud efforts.
    • Data-Driven Detection: Emphasis on the underutilization of data analytics in detecting fraud. While data exists, a lack of skilled analysts and insufficient government resources limits its utility.
  3. Broader Fraud Examples:

    • Pandemic-Related Unemployment Fraud: Exploitation of unemployment insurance systems during COVID-19 through identity theft and fraudulent claims.
    • Defense and Infrastructure Fraud: Acknowledgment of areas like defense contracting, where fraud may persist due to limited oversight and information asymmetry.
  4. Challenges in Addressing Fraud:

    • Government Incentives: The focus on recovery rather than deterrence is criticized. Deterrence efforts have a far greater impact but are underfunded.
    • Resource Allocation: The DOJ and other agencies lack the capacity to address even known fraud cases due to staff and budget limitations.
    • Cultural and Structural Issues: The lack of competitive salaries for skilled data analysts and attorneys within government positions hinders fraud detection efforts.

Strengths of the Episode

  • Expert Insights: Jetson Leder-Luis provides academic rigor and empirical evidence, citing his research and recent publications.
  • Clear Illustrations: Real-world examples, such as the dialysis ambulance fraud and durable medical equipment scams, make complex issues accessible.
  • Balanced Discussion: The hosts maintain an engaging balance of skepticism and optimism, acknowledging both successes and ongoing challenges in fraud prevention.

Potential Areas for Improvement

  1. Depth on Broader Fraud: While the episode focuses primarily on healthcare fraud, further elaboration on defense and infrastructure fraud could add value.
  2. Implementation Barriers: Discussion of practical barriers (e.g., political resistance, bureaucratic inertia) to adopting more robust data-driven anti-fraud systems could enhance the analysis.
  3. Comparison with Other Systems: Contrasting U.S. government anti-fraud efforts with those of other countries (e.g., UK’s NHS) could provide additional context.

Notable Takeaways

  • Economic Impact of Fraud: U.S. healthcare fraud alone may account for $100 billion annually, underscoring the need for targeted anti-fraud measures.
  • Data Underutilization: The government has access to rich datasets but lacks the resources to fully leverage them.
  • Whistleblower Effectiveness: Private enforcement of anti-fraud laws via whistleblowers is an underappreciated but critical tool in reducing fraud.

Conclusion

This episode succeeds in offering a detailed, engaging examination of government fraud, with a strong emphasis on healthcare. By blending academic insights with practical examples, it provides actionable insights for policymakers and an accessible narrative for general listeners. However, expanding coverage to other sectors and discussing systemic barriers would make the episode even more comprehensive.

Overall, the podcast exemplifies how data analysis and targeted policy interventions can meaningfully reduce fraud, ultimately benefiting both taxpayers and program beneficiaries.

###

###




Jetson Leder-Luis, PhD, exemplifies a highly productive and influential scholar at the intersection of public economics, health economics, and political economy. His work stands out for its empirical rigor, multidisciplinary approach, and policy relevance. Below is a detailed analysis of his academic profile, contributions, and impact:


Academic and Professional Background

  1. Education:

    • PhD in Economics from MIT (2020), mentored by prominent economists Jim Poterba and Ben Olken.
    • Dual BS in Applied and Computational Mathematics and Economics from Caltech (2014).
  2. Current Roles:

    • Assistant Professor at Boston University’s Questrom School of Business.
    • Faculty Research Fellow at the National Bureau of Economic Research (NBER).
  3. Affiliations and Leadership:

    • Co-organizer of the Empirical Health Law Conference and the Harvard-MIT-BU Health Economics Seminar, showcasing his leadership in fostering academic discourse.
  4. Fellowships and Honors:

    • Notable fellowships include the Ford Foundation Dissertation Fellowship and recognition through programs like REACH Prep and the Stamps Scholars.

Research Focus

Dr. Leder-Luis’s research addresses fraud, corruption, and inefficiencies in public spending, with a particular emphasis on the Medicare and Medicaid programs. His work is distinguished by:

  • A strong empirical focus, leveraging vast datasets (e.g., 100% Medicare claims data).
  • Examination of the statistical properties of fraud and misreporting in public expenditures.
  • Policy-driven inquiries that have direct implications for healthcare regulation and fraud prevention.

His working papers and publications have explored fraud detection, the economic implications of public spending, and innovative anti-fraud mechanisms, such as whistleblowing and machine learning.


Key Contributions

Published Work

  1. "Can Whistleblowers Root Out Public Expenditure Fraud?" (2023):

    • Highlights the effectiveness of whistleblower programs in Medicare fraud detection.
    • Emphasizes the role of private enforcement in deterring public expenditure fraud.
  2. "Maimonides Rule Redux" (2019):

    • Explores statistical applications in education policy, co-authored with influential economists.
  3. “Structural Topic Models for Open-Ended Survey Responses” (2014):

    • A methodological breakthrough in text analysis, earning the Gosnell Prize for Excellence in Political Methodology.
  4. White Papers and Policy Reports:

    • Authored a widely cited CMS white paper quantifying the value of healthcare anti-fraud efforts.

Accepted and Forthcoming Papers

  • "Ambulance Taxis": Analyzes the impact of regulation and litigation on healthcare fraud in the ambulance industry, forthcoming in Journal of Political Economy.
  • "Dying or Lying?": Challenges the narrative around for-profit hospices, showing cost-saving and patient-preference benefits despite allegations of fraud (American Economic Review).

Ongoing Research

  • Machine Learning in Fraud Detection:
    • Investigates how AI can enhance fraud detection in Medicare, bridging advanced analytics with public policy.
  • Unemployment Insurance Fraud:
    • Examines the vulnerabilities in pandemic-era unemployment benefits, shedding light on identity theft and systemic exploitation.

Engagement Beyond Academia

Dr. Leder-Luis actively contributes to public policy through:

  1. Testimonies: Provided expert testimony on fraud detection to the Pennsylvania State Government Committee.

  2. Media Contributions:

    • Featured in podcasts and articles, including MarketWatch and the Wall Street Journal.
    • His ability to communicate complex economic ideas to broader audiences underscores his versatility.
  3. Global Anticorruption Blog Contributions:

    • Authored influential pieces on cost-effective anticorruption strategies, whistleblowing, and campaign finance fraud detection.

Impact and Future Directions

  1. Policy Influence:

    • His research has directly informed policies aimed at reducing fraud in Medicare, Medicaid, and other public programs.
    • Contributions to whistleblower policy design and machine learning applications showcase a forward-looking approach to fraud prevention.
  2. Interdisciplinary Reach:

    • By blending economics, law, and data science, his work appeals to policymakers, legal experts, and economists alike.
  3. Future Potential:

    • As emerging fields like AI-driven analytics and healthcare reform evolve, Dr. Leder-Luis is well-positioned to lead groundbreaking studies that shape public policy.

Conclusion

Jetson Leder-Luis exemplifies the modern, interdisciplinary economist. His prolific output, policy relevance, and dedication to impactful research make him a rising star in the fields of public economics and health policy. His work not only addresses pressing societal challenges but also proposes practical, data-driven solutions, establishing him as a thought leader in detecting and deterring public fraud.

Sunday, November 17, 2024

Two New Articles, FDA Authors, Nuanced Cancer Policy Challenges (Fallah 2024, Mehta 2024)

Thanks to Nicholas Sarlis MD PhD at Linked In for highlighting two new oncology policy articles by FDA authors, in J Clin Oncol.

Mehta & Pazdur discuss the balance of accelerated approval, accelerated withdrawal, new 2023 FDA, and some nuances of the interpretation of successive data.

Fallah et al. discuss whether you can run (and enroll) an equipoise clinical trial when one of the arms is already officially labeled "a breakthrough drug."

Agency IQ provides a discuss of some of the 2023 legal changes.

I've clipped an AI summary below.

##

AI CORNER

Here is a summary of the three articles, focusing on their relevance to current policy issues in oncology trials, including accelerated approval, equipoise in trials, and the updated law on expedited withdrawals:


Fallah et al. (2024): "Equipoise Lost? Trial Conduct Challenges in an Era of Breakthrough Therapies"

This article discusses the challenge of maintaining clinical equipoise in oncology trials involving breakthrough therapies. Regulatory mechanisms like breakthrough therapy designation and accelerated approval can heighten perceptions of investigational drug superiority, affecting both patient and investigator behaviors in trials. Key challenges include:

  • Early dropout rates: Patients often leave control arms early, seeking the investigational therapy, which can lead to asymmetric censoring and biased trial results.
  • Investigator bias: In open-label trials, biases in progression-free survival (PFS) assessments can skew results, especially if patients cross over to investigational arms.
  • Mitigation strategies: Recommendations include double-blind designs, better education of trial participants, and sensitivity analyses to account for asymmetric dropout. The authors highlight the risks of using subjective endpoints like PFS in trials where equipoise is difficult to maintain and advocate for trial designs that minimize bias.

Mehta et al. (2024): "Oncology Accelerated Approval Confirmatory Trials: When a Failed Trial Is Not a Failed Drug"

This article reviews the evolution of the FDA's Accelerated Approval (AA) pathway, which allows earlier drug access based on surrogate endpoints. The focus is on challenges in confirmatory trials:

  • Withdrawals due to trial failures: About 15% of AA indications in oncology have been withdrawn because confirmatory trials failed to meet primary endpoints, demonstrated negative benefit-risk profiles, or encountered methodological flaws.
  • New policies in 2023: The Consolidated Appropriations Act now requires confirmatory trials to be underway at the time of AA and provides mechanisms for streamlined withdrawals.
  • Regulatory nuances: FDA decisions consider factors like unmet need and the availability of alternative therapies. Some drugs failing confirmatory trials, such as gemtuzumab ozogamicin, later achieved approval after adjusted dosages or patient selection. The authors argue that failed trials should be scrutinized for methodological flaws rather than automatically signaling drug inefficacy. [For more on these nuances, see Appendix below.]

AgencyIQ (2024): "Accelerated Removal: FDA Making Use of New Authority to Withdraw Ineffective Drugs More Quickly"

This report details recent updates to the accelerated withdrawal process under the Consolidated Appropriations Act of 2023. Key changes include:

  • Streamlined procedures: The FDA can now withdraw AA drugs faster under specific conditions, such as failed confirmatory trials or safety concerns. This contrasts with earlier lengthy processes (e.g., the withdrawal of Makena took over two years).
  • Public involvement and transparency: The updated law ensures opportunities for sponsor appeals, advisory committee meetings, and public comments.
  • Case study – Pepaxto: The expedited withdrawal of Pepaxto in 2024 demonstrated the FDA’s improved ability to act decisively when confirmatory trials indicate harm (e.g., reduced overall survival).

Policy Implications

The articles highlight the tension between early patient access to promising therapies and the risks of premature approval. The 2023 law attempts to address this by:

  1. Requiring robust confirmatory trials at the time of AA.
  2. Enhancing the FDA’s authority to expedite withdrawals when drugs fail to meet safety or efficacy benchmarks.

Mehta's emphasis on confirmatory trial quality and AgencyIQ's focus on streamlined withdrawal underscore the importance of designing trials that balance early access with rigorous post-approval scrutiny. Fallah's exploration of equipoise loss adds another layer, emphasizing the need for trial designs that ensure unbiased and interpretable results.

###

  • Fallah et al.
    Fallah J, Mulkey F, Fiero MH, et al. Equipoise Lost? Trial Conduct Challenges in an Era of Breakthrough Therapies. J Clin Oncol. 2024;42(32):3783-3787. doi:10.1200/JCO-24-01200.

  • Mehta et al.
    Mehta GU, Pazdur R. Oncology Accelerated Approval Confirmatory Trials: When a Failed Trial Is Not a Failed Drug. J Clin Oncol. 2024;42(32):3778-3782. doi:10.1200/JCO-24-01654.

  • AgencyIQ
    Gaffney A. Accelerated Removal: FDA Making Use of New Authority to Withdraw Ineffective Drugs More Quickly. AgencyIQ by POLITICO. April 5, 2024. [Link to article].

  • ###

  • APPENDIX

  • More on Mehta & Pazdur's and the subtleties of withdrawal decisions.

  • Yes, Mehta and Pazdur delve into the complexities surrounding withdrawals of accelerated approvals (AAs), emphasizing that hasty action can sometimes undermine patient and public health benefits. Here are the nuanced points they raise about when and why withdrawals may not be immediate:

  • 1. Evaluating Unmet Medical Need

    • If a high unmet medical need persists for the patient population, the FDA may delay withdrawal even after confirmatory trials fail. For instance, drugs like lurbinectedin maintained AA despite failing their primary endpoints because they continued to offer meaningful benefit in a landscape with few alternatives.

    2. Learning from Serial Data

    • Drugs showing promise in initial confirmatory trials but failing due to design limitations or patient selection may merit additional study. Mehta and Pazdur point to examples like gefitinib and gemtuzumab ozogamicin, where confirmatory trials initially failed but subsequent adjustments in dosage, study design, or biomarker targeting led to eventual approvals. These examples highlight the need for a deeper investigation before concluding a drug's lack of efficacy.

    3. Balancing Current and Future Benefit-Risk

    • Withdrawal decisions weigh both the current benefit-risk profile and the drug's evolving role as part of treatment regimens:
      • Drugs demonstrating consistent response rates and durations from initial trials often still hold value for specific subpopulations.
      • Sponsors are encouraged to pursue alternative confirmatory trials that address prior design shortcomings.
      • New data on biomarkers or mechanisms of action can change the understanding of a drug’s utility.

    4. Impact on Ongoing Responders

    • For drugs still providing benefits to certain patients, withdrawal could leave these individuals without viable options. This is particularly significant for patients with few alternatives, such as those in refractory stages of disease.

    5. Changing Therapeutic Landscapes

    • Advances in other treatments during the period between AA and confirmatory trials can influence the interpretation of benefit. For example:
      • If new therapies enter the market that outperform the AA drug, maintaining approval may no longer align with public health interests.
      • Conversely, if the therapeutic landscape remains static, preserving the AA while revisiting trial designs might be more appropriate.

    6. Methodological Issues and Contextual Decisions

    • Methodological flaws, such as poor trial powering, patient selection issues, or inappropriate comparators, may lead to premature trial failures. The authors caution against conflating these with true lack of benefit. Thoughtful re-evaluation can ensure these factors do not preemptively eliminate promising drugs.

    Conclusion

    Mehta and Pazdur argue for judicious decision-making that balances the urgency of withdrawing ineffective therapies with the need for context-sensitive evaluation. They advocate for flexibility to allow further study or alternative trial designs in scenarios where unmet need remains high or evidence suggests potential for improvement with better methods. Their analysis underscores the importance of recognizing AA as an evolving process rather than a binary decision point.

  • Thursday, November 14, 2024

    RFK Announced for New HHS Secretary

    On November 14, 2024, the incoming Trump administration announced that Robert F. Kennedy Jr would be nominated for Secretary of Health and Human Services.  The news flipped remarks a few days ago from the transition team, that RFK would not be the nominee.

    According to the WSJ, "Kennedy made the case to Trump’s advisers that he would be able to enact more sweeping change as HHS secretary than he would as the administration’s health czar, the other position he was being considered for."

    In addition, the WSJ cited advocacy behind-the-scenes by Elon Musk and Donald Trump Jr.   In an op-ed at the Newsweek, cited by The Hill, Trump's CDC chief, Robert Redfield, also endorsed RFK as head of HHS (here).  Redfield emphasized that in his view, agencies like FDA and NIH were "a captive of industry."  Tom Frieden, another prior CDC director, is quoted at NPR remarking, "There are some things that RFK Jr gets right. We do have a chronic disease crisis in our country."  NPR also quotes Dr. Dariush Moffarian of Tufts, "We're absolutely drowning under a flood of diet-related chronic diseases."

    Per Politico, Kennedy posted on X, 

    "I look forward to working with the more than 80,000 employees at HHS to free the agencies from the smothering cloud of corporate capture so they can pursue their mission to make Americans once again the healthiest people on Earth. Together we will clean up corruption, stop the revolving door between industry and government, and return our health agencies to their rich tradition of gold-standard, evidence-based science."

    Chronic Disease

    While Kennedy's views on vaccines and FDA's regulation of food have garnered the most attention, his other signature theme has been chronic disease in general.

    The website for "Make America Healthy Again" (MAHA) has a webpage for Chronic Disease Epidemic, here.   The RFK Jr channel at YouTube, started for his presidential campaign, has a two-minute video, released in March 2024, highlighting his position, "Chronic disease is bankrupting America."  Video hereTranscript here.  At WSJ, health author Julia Hotz supports RFK Jr's interest in "social prescriptions," such as exercise, here.

    Axios reviews MAHA goals, here.


    ##

    See also a November 7 article in STAT, with several links to "figures in the MAHA orbit." Figures include Dr Marty Makari of Johns Hopkins, Senator Ron Johnson of Wisconsin, and Texas congressman Chip Roy.  Here, here.
    Axios on MAHA and publich health here.

    ##
    Another CMS theme is fraud and abuse in Medicare and Medicaid.  While not a special interest of RFK, it may be an interest of DOGE, Department of Government Efficiency, the government waste agency being created for Elon Musk and Vivek Ramaswamy (here).   See a Bloomberg podcast (DOGE noted) on Medicare fraud with fraud guru Boston University's Jetson LEder-Luis. who is uber-productiveLab and other fraud is a big part of it.  

    AI Regulation From HHS Not FDA: Section 1557 of Affordable Care Act

     When we hear about AI regulation, it's usually a discussion of the FDA.   However, Section 1557 of the Affordable Care Act effectively regulates the use of algorithms of any type, to the extent they might impact discrimination issues of any type.   (And the regulation is to demonstrate that they don't.)



    The area is complex but covered in detail in a November 14, 2024, article in Health Affairs Forefront by Han, Tsai, and Khazanchi.

    https://www.healthaffairs.org/content/forefront/section-1557-rule-mandates-identification-and-mitigation-discriminatory-clinical

    Who has to be aware, includes "hospitals, clinics, private or public payors, academic medical centers."  What has to be checked, are "diagnostic, screening, prognostic, or risk prediction algorithms."  (Abbreviated, PCDST, patient care decision support tools.)  What kind of discrimination spans, "age, race, color, sex, age, disability, national origin."  (See the long series of details at Han et al.)

    The compliance date is May 2025 (the same as Phase 1 of the FDA LDT rule!).

    Topics like race-based renal function corrections are discussed.

    ##

    Some parts of the rule are under federal court litigation.  The authors write, 

    In some states, implementation of Section 1557 may be delayed due to ongoing litigation. Several states challenged specific provisions of the Rule that expanded “discrimination on the basis of sex” to include gender identity. In Texas v. Becerra, the court ordered that the effective date of the entirety of the Rule be stayed within Texas and Montana. In Florida v. HHS, the court ordered that the effective date of certain portions of the Rule be stayed within Florida. In Tennessee v. Becerra, the effective date was stayed nationwide specifically where the Rule extends to discrimination by gender identity.

    (Some of the debate about "sex discrimination" and relation to "gender" or "transgender" span the Obama, Trump 1, Biden, and Trump 2 administrations, with flip-flops as each election occurred.)  

    ##

    I covered the proposed rule in July 2022 here.  

    I discussed and footnoted some of the flip-flops in July 2024 here.

    Robert Califf's Discussion of FDA at Friends of Cancer Research

    This week, Friends of Cancer Research held its annual meeting, with a keynote address by outgoing Dr Robert Califf, commissioner of the FDA.

    • A five-hour video of the whole conference is archived at YouTube, here.
    • I uploaded the PDF of an auto-transcript of Dr. Califf's half hour, here.

    I read the Califf transcript and I concur with the Chat GPT-generated article below.  Califf is interviewed by Ramsey Baghdadi, of the information service Prevision Policy and an editor at RPM Report.


    ###

    AI Corner

    Chat GPT 4o reviews the Califf speech at FOCR.

    ##

    Overview: Dr Califf's Perspectives

    At the Friends of Cancer Research (FOCR) annual meeting, Dr. Robert Califf offered his perspective on the state of the FDA, underscoring the agency’s operational achievements while recognizing the potential shifts brought on by the recent Presidential election. As he approaches the end of his term, Califf reflected on the agency’s ongoing initiatives, especially in drug pricing, regulatory independence, pragmatic clinical trials, and urgent public health issues in nutrition and tobacco regulation. Dr. Califf's remarks provide a comprehensive outlook on the FDA’s position within a changing political landscape, as well as the challenges and opportunities that lie ahead for advancing public health and pharmaceutical innovation.


    1. Post-Election Implications for FDA Operations

    Dr. Califf acknowledged the ambiguity and possible restructuring associated with a shift in administration. He expressed disappointment with the election outcome but emphasized that the FDA is well-prepared, currently functioning at what he described as “peak performance.” Recent structural reorganizations, including updates to the Office of Regulatory Affairs and human foods program, have aimed to streamline processes, and new hires are reportedly improving the agency’s ability to adapt to evolving demands. Despite the high efficiency achieved under the current administration, Califf voiced concerns about the effects of political turnover on continuity within the FDA. He noted that the agency’s efficacy relies heavily on the caliber and commitment of its civil service employees, who, he trusts, will remain steadfast amid the potential influx of new appointees with potentially differing agendas.

    2. Inflation Reduction Act and the Challenge of Drug Pricing

    Califf discussed the implications of the Inflation Reduction Act (IRA) on the pharmaceutical industry, with a particular focus on drug pricing disparities between the United States and other countries. He asserted that American patients often bear disproportionately high drug costs, describing this issue as a longstanding injustice in the healthcare system. In addition to highlighting the financial strain faced by cancer patients, Califf addressed the pricing inconsistencies that make vital treatments financially inaccessible to many.

    While he refrained from taking a definitive stance on the IRA’s effectiveness, he acknowledged that it has altered portfolio strategies in the pharmaceutical industry, with companies reevaluating their drug development focus based on profitability and market stability. Califf drew attention to the pressing need for a pricing structure that better aligns drug costs with demonstrated clinical benefits, suggesting that while accelerated approval pathways are essential, they should not justify top-tier pricing until sufficient clinical outcomes evidence is available. His remarks reflect his conviction that the value of drugs should be correlated with their tangible impact on patient survival and quality of life.

    3. Political Influence and FDA Autonomy

    Dr. Califf provided nuanced insights into the FDA’s susceptibility to political influence. He explained that while decision-making in the FDA is primarily entrusted to career civil servants, the President and HHS Secretary retain the authority to overrule agency decisions, which can, in turn, impact regulatory actions. Califf was candid about the intersection of science and politics, contending that there is no clear-cut line between the two realms, especially in areas such as drug approvals that hold significant political and social implications.

    Reflecting on his tenure, he observed that political factors are unavoidably intertwined with scientific regulatory processes, particularly in high-stakes decisions that affect public health outcomes. Califf expressed a balanced view, suggesting that while regulatory independence remains a priority, the FDA must also consider the broader socio-political landscape. His comments underscore his belief that transparency and an evidence-based approach are essential to preserving the integrity of the agency amid political pressures.

    4. Accelerated Approvals and Evidence Quality in Drug Development

    Califf reaffirmed his support for the accelerated approval pathway, particularly in oncology, but he urged caution regarding its expansion into other therapeutic areas. He questioned the over-reliance on surrogate markers in some chronic diseases, suggesting that while accelerated approvals can expedite access to promising treatments, they must be rigorously evaluated to ensure long-term efficacy and safety. Califf advocated for a risk-based, Bayesian approach to new approvals, tailored to each condition and treatment. He referenced his career as a trialist, underscoring the value of clinical trials in debunking expert predictions and underscoring the importance of grounding accelerated approvals in robust evidence.

    His commentary reflects an understanding of the complexities surrounding drug development and regulation. By balancing accelerated approvals with a commitment to high-quality evidence, Califf aims to ensure that patient safety and treatment efficacy are prioritized while still supporting innovation in the pharmaceutical industry.

    5. Addressing the Complexity of Clinical Trials and Post-Market Evidence

    Califf stressed the need to modernize clinical trial processes to improve efficiency, lower costs, and increase patient access. He criticized the rising complexity of clinical trials, which often hinders diversity in participant demographics and inflates the time and financial resources needed for trials. In his view, while pre-market trials are essential, post-market trials must also be prioritized to gather comprehensive real-world data that can inform clinical practice and enhance patient outcomes.

    He called for a revival of simpler, more pragmatic clinical trials that focus on producing relevant data in the post-market phase. This approach would allow for more accurate assessments of long-term drug efficacy and safety, particularly for cancer therapies and other treatments with high patient impact. He indicated that this evolution in trial methodology could also address the FDA’s limitations in mandating certain post-market evaluations, which he sees as critical to advancing evidence-based medicine.

    6. Public Health Focus: Tobacco and Food Safety

    As he looks toward the remaining months of his tenure, Califf plans to prioritize initiatives targeting chronic disease contributors, particularly tobacco use and poor nutrition. He discussed ongoing efforts to impose menthol and nicotine standards in tobacco products, aiming to reduce addiction rates and improve public health outcomes. On the food safety front, Califf advocated for the adoption of front-of-package labeling to simplify nutrition information for consumers. He argued that clearer labeling standards would enable consumers to make healthier choices, ultimately contributing to a reduction in chronic disease prevalence linked to diet.

    Califf’s emphasis on preventive health measures signals his belief in addressing root causes of health issues through regulatory initiatives, an approach that aligns with broader public health goals. He sees these changes as essential to curbing the national decline in life expectancy, which he attributes to factors that the FDA has the authority to address through policy adjustments in tobacco and nutrition.

    7. Future Challenges and Recommendations for the Next FDA Commissioner

    In his concluding remarks, Dr. Califf outlined the qualities he believes will be essential for his successor at the FDA. He stressed the importance of executive function, the ability to synthesize diverse perspectives, and a commitment to evidence-based decision-making. Califf warned against a “reactionary” approach to regulation and highlighted the need for a commissioner who values expert opinion and clinical evidence. He expressed concern that public distrust in expertise threatens the agency’s ability to make informed decisions on complex medical and scientific issues.

    Califf’s insights underscore the necessity of balancing expertise and public accountability, as well as the importance of resilience in the face of political and public scrutiny. His hope is that his successor will continue to champion evidence-based policies and uphold the integrity of the FDA’s mission to protect public health.


    Conclusion

    Dr. Califf’s remarks at the FOCR meeting illustrate his pragmatic, evidence-driven approach to regulatory science and public health. His advocacy for pragmatic clinical trials, his nuanced view on political influences within the FDA, and his commitment to preventive health through tobacco and food regulation collectively reflect a vision for an FDA that is resilient, transparent, and focused on outcomes. His insights offer a roadmap for the agency’s future, underscoring the need for continued innovation balanced with rigorous evidence, all within a framework that adapts to the dynamic and sometimes unpredictable landscape of U.S. healthcare.


    ##

    Bonus - See a similar talk and summary from his talk the same week at the Milken Institute on some of the same topics.  Here.

    Wednesday, November 13, 2024

    Major Article on Tumor Genomics and Pathologist-Directed Workflow (Dowdell 2024)

    Back in May 2024, I wrote a blog about a remarkable new article from MolDx discussing, "When Pathologists Can Order Molecular Tests."   Find it here:

    https://www.discoveriesinhealthpolicy.com/2024/05/moldx-publishes-major-guidance-document.html

    Here's a major new article on the same topic, which is being called "Pathologist Directed Workflow" (let's say PDWF).


    Find the new publication by Dowdell et al. here:

    https://ascopubs.org/doi/pdf/10.1200/OP.24.00226

    There is also a summary at Genomeweb, I believe open-access:

    https://www.genomeweb.com/cancer/cancer-study-sees-tailored-treatment-outcome-boost-comprehensive-genomic-profiling

    See the press release from Illumina here.  See coverage at ASCO NEWS here.  See a 9/2024 paper from the group, Meng et al. here, which looked at the lung cancer subset.   See an AI comparison of Meng and Dowdell here.

    ###

    Comment

    Pathologist-directed test ordering has many advantages, but raises a few collateral questions.  What if Dr. A wants the Foundation Medicine test and Dr. B the Caris test?  Here, all patients got the same Provdience LDT (based on an Illumina platform).  Who handles prior authorization?  In this study, at Providence health system, all patients got a 523-gene test, and tests were ordered in the absence of any insurance coverage decision.  (Writing, "We developed a novel programmatic approach where testing was initiated at the time of diagnosis and performed at no cost to patients.") In the real-world, someone would have to invest time into problems like prior authorization paperwork.  

    ###

    Here is a diagram of the shorter, faster pathway with PDWF:



    Here is the abstract of Dowdell et al:

    Purpose

    Precision therapies and immunotherapies have revolutionized cancer care, with novel genomic biomarker-associated therapies being introduced into clinical practice rapidly, resulting in notable gains in patient survival. Despite this, there is significant variability in the utilization of tumor molecular profiling that spans the timing of test ordering, comprehensiveness of gene panels, and clinical decision support through therapy and trial recommendations.

    Methods

    To standardize testing, we designed a pathologist-directed test ordering system at the time of diagnosis using a 523-gene DNA/RNA hybrid comprehensive genomic profiling (CGP) panel and extensive clinical decision support tools. To comprehensively characterize the clinical impact of this protocol, we developed a novel natural language processing (NLP)–based approach to extract clinical features from physician chart notes. We assessed test actionability rates, therapy choice, and outcomes across a set of 3,216 patients with advanced cancer.

    Results

    We observed 49% of patients had at least one actionable genomic biomarker-driven–approved and/or guideline-recommended targeted or immunotherapy (IO) and 53% of patients would have been eligible for a precision therapy clinical trial from three large basket trials. When assessing CGP versus an in silico 50-gene panel, 67% of tumors compared with 33% harbored actionable alterations including clinical trials. Among patients with 6 months or more of follow-up, over 52% received a targeted therapy (TT) or IO, versus 32% who received conventional chemotherapy alone. Furthermore, patients receiving TT had significantly improved overall survival compared with patients receiving chemotherapy alone (P < .001).

    Conclusion

    Overall, these data represent a major shift in standard clinical practice toward molecularly guided treatments (targeted and immunotherapies) over conventional systemic chemotherapy. As guidelines continue to evolve and more precision therapeutics gain approval, we expect this gap to continue to widen.

    A Plethora of Meetings: (1) PMC, (2) FOCR, (3) Milken Institute, (4) AMP, (5) G2

    A plethora of annual meetings right now.


    PERSONALIZED MEDICINE COALITION

    November 13-14, 2024, in Boston.  Primarily in person.

    Here's the website:

    https://www.personalizedmedicineconference.org/

     

    FRIENDS OF CANCER RESEARCH

                          

    November 12, 2024, live in Washington, plus streaming and archived.

    https://friendsofcancerresearch.org/event/friends-of-cancer-research-annual-meeting-2024/

    See an overview and links to video archive at Linked In here.  5 hr video at YouTube here.

    See their Session 1 on overall survival trials in cancer, plus white paper, here.

    Other white paper sessions on "Pragmatism" in trials and integrating ctDNA in trials.


    MILKEN INSTITUTE - HEALTH SUMMIT

    November 13-14, live in Washington, DC, plus a livestream option.

    https://milkeninstitute.org/events/future-health-summit-2024

    Milken program here.

    Association for Molecular Pathology - AMP

    November 19-24 in Vancouver, British Columbia.

    Website here:

    https://amp24.amp.org/

    Lab Institute / G2 Intelligence

    Two-day virtual meeting, November 12-13.  Stating, "This free two-day digital event will feature industry experts who will provide timely, accurate analysis of legal and regulatory issues, enforcement trends, and other developments that directly affect labs and other healthcare providers. Receive expert advice and guidance to help improve your lab’s operational performance and stay abreast of key industry trends."

    https://www.g2intelligence.com/lab-institute-virtual-event-advancing-the-profession-of-diagnostic-medicine-2024/



    ##

    Since calendars go offline, I made a simple text dump of the PMC, FOCR, and Milken agendas, here.

    AI Corner

    Here's a Chat GPT article as-if written by a health policy journalist who was able to attend all 3 events (working from the agendas only).


    Health Summits of November 2024: 

    Insights from the Front Lines of Medicine


    In an extraordinary confluence of discussions on the future of medicine, the Personalized Medicine Coalition (PMC), Friends of Cancer Research (FOCR), and the Milken Institute's Future of Health Summit convened in November, each providing unique perspectives on innovations reshaping health care.

    Personalized Medicine Coalition: A Vision for Genomics and Diagnostics

    Held over two days, the PMC conference opened with a forward-looking address from Edward Abrahams, PMC President, who framed the evolving landscape of personalized medicine against a backdrop of genomic innovation. Amgen’s David Reese and Illumina’s Jacob Thaysen outlined groundbreaking strides in pharmacogenomics and personalized diagnostics, anticipating transformative impacts on rare disease treatment. Thaysen noted Illumina’s ambition to move personalized medicine into mainstream health care, emphasizing collaborations to overcome policy and funding obstacles.

    A poignant moment came with the annual Leadership in Personalized Medicine Award, honoring Emily Kramer-Golinkoff of Emily’s Entourage, a cystic fibrosis advocate whose personal journey mirrors the power of genomics-driven research. Panels later explored the role of AI and diagnostics, culminating with a session on AI’s potential to revolutionize patient-specific treatment plans. Notably, Joe Franklin of Covington & Burling LLP chaired a forward-looking panel on how AI will define the future of precision diagnostics, showcasing optimism about data-driven decision-making.


    Friends of Cancer Research: Pioneering Cancer Trials and Regulatory Progress


    On November 13, Friends of Cancer Research’s annual meeting zeroed in on cancer trial design and regulatory efficiency. Opening remarks from FDA Commissioner Robert Califf set the tone, highlighting the agency’s commitment to streamlining oncology approvals. Califf was followed by thought leaders discussing the power of interim overall survival (OS) evaluations in trial designs. Researchers like Geoff Oxnard from Eli Lilly addressed the complex role of OS as a measure of trial success, emphasizing the need for accurate and reliable data interpretation.

    The discussion transitioned to the use of ctDNA as a biomarker in non-small cell lung cancer trials. Hillary Andrews of FOCR underscored the potential of ctDNA as a more immediate indicator of treatment efficacy than traditional OS metrics. A key takeaway: standardizing ctDNA methodologies could accelerate approvals and improve patient outcomes. This session underscored the collective effort to bridge the gap between clinical trial data and real-world applications, with patient advocates reminding stakeholders that regulatory advancements directly impact lives.


    Milken Institute’s Future of Health Summit: Health Equity and Whole-Person Wellness


    Capping off the week, the Milken Institute’s Future of Health Summit in Washington, D.C., addressed some of health care’s most pressing issues. In a candid discussion, FDA Commissioner Califf and CDC Director Mandy Cohen examined future preparedness against pandemics, advocating for inter-agency collaboration.

    Health equity emerged as a prominent theme, especially in discussions around “Harnessing Community Power: Driving Health Equity Research,” which stressed the need to make health care accessible to marginalized populations. The Milken Summit also highlighted public-private partnerships, with panels exploring workforce mental health and “Food is Medicine” initiatives aimed at tackling chronic disease through nutrition. U.S. Secretary of Agriculture Tom Vilsack joined discussions on food-based interventions as preventative health tools, underscoring the importance of nutrition in public health.


    Conclusion: An Industry United by Vision and Mission

    Together, these summits demonstrated an industry galvanized by shared goals. Personalized medicine’s integration with AI, innovations in cancer diagnostics, and health equity initiatives are moving health care into an era where prevention, access, and individualized treatment become the standard. Each gathering underscored a commitment to harnessing technology and compassion to foster a more resilient and inclusive health care system.

    Sunday, November 10, 2024

    Now Streaming: CAP Webinar on How FDA Defines Risk (w/ Tim Stenzl MD)

    CAP is running a series of major webinars on how FDA regulates laboratory-developed tests.   They remark the series is intended to follow, mirror, and translate the FDA's own webinar series on LDT regulation.

    They've now posted the video stream (and 42 slide deck) from their September 18, 2024 webinar on FDA and LDT risk classification.  And their speaker is Tim Stenzl MD, who until earlier this year was head of diagnostics at the FDA.

    Find the CAP webinar here:

    https://www.cap.org/calendar/webinars/understanding-the-impact-of-the-fdas-ldt-risk-classification-on-your-laboratory

    Get the deck here:

    https://documents.cap.org/documents/CAP-webinar_Understanding-Impact-FDA-LDT-Risk-Classification.pdf



    ###

    AI Corner

    Otter.ai made an auto-outline of the webinar.

     

    Outline

     

    Introduction to the Webinar Series and FDA Final Rule

    • Dr Karcher (CAP) introduces the webinar series aimed at preparing pathologists and laboratories for the FDA final rule on LDT oversight, emphasizing the importance of Stage One, which becomes effective in May 2025.
    • The webinar series is designed to shadow corresponding FDA webinars, making complex information more accessible to laboratorians.
    • The goal is to provide practical steps and resources for compliance with the final rule, though definitive instructions are not given.
    • Dr Karcher provides a brief introduction, highlighting their background and experience in LDT oversight.

    Background and Legislative Context

    • Dr Karcher provides a historical overview of FDA oversight of LDTs, mentioning various legislative proposals and the most recent, the Verity Act, which did not pass in 2022.
    • The FDA proceeded with regulation of LDTs based on their current statutory authority, releasing a proposed rule in September 2023 and a final rule in April 2024.
    • The final rule employs a three-tiered, risk-based structure, phasing out enforcement discretion, and includes five stages ending in May 2028.
    • Stage One involves compliance with medical device reporting, correction and removal reporting, and quality system requirements for complaints regarding an LDT.

    CAP's Advocacy Principles and Opposition to the Final Rule

    • Dr Karcher outlines CAP's advocacy principles, emphasizing patient protection, continued development of innovative LDTs, and a least burdensome and costly regulatory framework.
    • CAP opposes the final FDA rule and supports legislation to reduce regulatory burdens and introduce maximum flexibility in FDA oversight.
    • The organization also supports legal efforts to stop the implementation of the final rule.
    • Despite the potential changes in the rule's implementation, CAP aims to ensure laboratories are prepared to comply with the regulations.

    Understanding LDTs and CLIA Regulations

    • Dr Karcher defines an LDT as an in vitro diagnostic product intended for clinical use, designed, manufactured, and used within a single clinical laboratory, and meets CLIA requirements for high complexity testing.
    • CLIA categorizes tests as moderate or high complexity, based on seven factors including knowledge needed to perform, reagents, materials, and interpretation required.
    • The FDA risk classification system is based on patient risk, classifying tests into low risk (Class 1), moderate risk (Class 2), or high risk (Class 3).
    • The intended use of the test and the risk posed to patients determine the classification.

    Introduction of Dr. Tim Stenzl and His Background

    • Dr Karcher introduces Dr. Tim Stenzl, highlighting his extensive experience in molecular pathology and leadership roles at Duke University and the FDA.
    • Dr. Stenzl is the former director of the FDA Office of In Vitro Diagnostics and is not representing the FDA in this webinar.
    • Dr. Stenzl's presentation will focus on the FDA risk classification system and provide practical guidance for laboratorians.

    Dr. Stenzl's Presentation on FDA Risk Classification

    • Dr. Stenzl begins by stating that he is only expressing his opinion and not representing the FDA.
    • He emphasizes the importance of understanding the FDA's approach to risk classification and provides disclaimers about the use of non-FDA language.
    • Dr. Stenzl explains the ongoing reclassification process at the FDA, focusing on companion diagnostics and other IVDs.
    • The FDA has exempted almost all Class 1 tests from FDA review, and the reclassification process involves expert panels and public comments.

    Details of FDA Risk Classification and Submission Requirements

    • Dr. Stenzl explains the classification of clinical laboratory tests into Class 1 (low risk), Class 2 (moderate risk), and Class 3 (high risk).
    • The classification determines the appropriate pre-market regulatory process and the type of application needed (510(k), de novo, or PMA).
    • The intended use of the test, including the purpose, methodology, patient population, and where the test is performed, influences the classification.
    • Dr. Stenzl provides examples of intended use statements and explains how the FDA determines the risk classification based on these statements.

    Examples of FDA Classification and Submission Process

    • Dr. Stenzl provides examples of Class 1, Class 2, and Class 3 tests, explaining the submission requirements for each classification.
    • He emphasizes the importance of knowing the risk classification of a test to determine the validation work needed and whether submission to the FDA is required.
    • Dr. Stenzl explains the process of creating a product code for novel tests and how subsequent similar tests can use the same product code.
    • He highlights the FDA's product classification database and how to search for similar tests to determine the classification and submission requirements.

    Q&A Session with Dr. Stenzl

    • Dr. Stenzl answers questions from the audience, addressing topics such as the impact of risk classification on immunohistochemistry, validating current LDTs, and the implications of changing sample types.
    • He explains that automated staining or image analysis on non-FDA cleared reagents would require submission to the FDA.
    • Dr. Stenzl advises using the FDA's product classification database and decision summaries to validate tests and determine the appropriate regulatory controls.
    • He clarifies that not all modifications to a test require FDA submission and that the FDA has a pre-submission process for answering questions.

    Final Takeaways and Next Steps

    • Dr Karcher summarizes the key points from Dr. Stenzl's presentation, emphasizing the importance of understanding the FDA's risk classification system and the differences between FDA risk and CLIA complexity.
    • The FDA recommends searching their database for similar tests to determine the appropriate regulatory controls and risk classification.
    • The webinar series will continue with five more sessions, each focusing on different aspects of the FDA final rule.
    • Dr Karcher thanks Dr. Stenzl for his insights and the CAP staff for organizing the webinar, and encourages attendees to register for the remaining sessions.  {End, Otter.ai]
    ###

    Here is a short news article written by Chat GPT.  I asked it for a short journalistic report based on an auto-transcript.   I also asked it to replace "Speaker 1" with "Dr Karcher" and to correct the spelling "Dr Stencil" to "Dr Stenzl" and it was able to do so. 
    ###

    CAP Launches Webinar Series on FDA’s Final Rule for Laboratory-Developed Test (LDT) Oversight

    The College of American Pathologists (CAP) has launched a six-part webinar series to guide pathologists and clinical laboratories through the complexities of the FDA's new final rule on LDT oversight. In the inaugural session, CAP President Dr. Karcher and former FDA Office of In Vitro Diagnostics director Dr. Timothy Stenzl discussed the background, stages, and risk classifications that underpin the FDA's regulatory framework.

    Dr. Karcher emphasized that while legal challenges to the FDA rule continue, CAP aims to ensure laboratories are prepared should the rule proceed. Stage One of the final rule, effective in May 2025, will introduce compliance requirements for reporting complaints and quality issues for LDTs. The remaining four stages, ending in 2028, will bring additional oversight to higher-risk LDTs. CAP has consistently opposed the final rule, advocating for a regulatory framework that balances patient safety with innovation and minimizes costs for pathologists.

    Dr. Stenzl provided an in-depth review of the FDA's risk-based classification system. Unlike CLIA, which categorizes tests by complexity, the FDA evaluates LDTs based on patient risk. Using FDA-cleared platforms and reagents can sometimes exempt certain modifications from FDA submission. For laboratories developing novel tests or modifications, Dr. Stenzl recommended utilizing FDA databases to align with existing classifications and seeking FDA guidance for clarity.

    With five webinars remaining, CAP's series aims to provide actionable guidance for pathologists navigating the regulatory changes. Upcoming sessions will continue to interpret FDA requirements with a laboratory-centered approach, easing the transition for clinical labs nationwide.

    ###

    That was kind of bare-bones.  I asked for a more detailed article.  

    Please provide a more detailed, deep dive report on the actual issues and problems, and then, provide a summary of 15 key takeaways.

    ###

    In-Depth Analysis of CAP Webinar on FDA’s Final Rule for LDT Oversight

    The CAP’s first session in a six-part webinar series provided a comprehensive overview of the FDA's final rule on LDT (laboratory-developed test) oversight, detailing the motivations behind the rule, the specifics of the regulatory framework, and its anticipated impact on clinical laboratories. This session, presented by CAP President Dr. Karcher and former FDA official Dr. Timothy Stenzl, addressed both technical and practical challenges associated with compliance, particularly under Stage One of the five-stage rule. Here is a detailed look at the core issues discussed, as well as a concise list of 15 essential takeaways.

    Core Issues and Challenges

    1. Ambiguity in Classification and Compliance
      The FDA’s three-tiered risk classification for LDTs (Class I, II, and III) is not straightforward, causing confusion among laboratories about the specific regulatory requirements for each risk class. Labs face uncertainty in determining which tests require submission and what validations are necessary for compliance, particularly when test modifications are made.

    2. Overlap and Divergence from CLIA
      The FDA’s risk-based classifications for LDTs differ fundamentally from CLIA’s complexity-based categories (moderate vs. high complexity), creating potential overlap and misalignment. For laboratories already accustomed to CLIA guidelines, the FDA’s different criteria pose a challenge in adjusting protocols to meet dual standards.

    3. Stage One Compliance Requirements
      Stage One, effective May 2025, mandates that labs have a robust reporting and quality control process for complaints. Many laboratories may need to implement or modify existing complaint-handling and quality control procedures to meet the specific demands outlined by the FDA, which are more stringent than traditional CLIA protocols.

    4. Confusion Over the Scope of “Grandfathering”
      Labs are uncertain about which LDTs qualify as “grandfathered” under the rule, particularly with tests developed after May 2024 but before the final submission deadline. Tests meeting the “grandfather” criteria must avoid modifications that might trigger a new FDA classification, thus affecting compliance obligations.

    5. Challenges with Modifications and Reclassification
      Modifications to LDTs, including changes to sample types or methodologies, could reclassify a test as a new LDT under FDA rules, potentially necessitating submission or resubmission. Dr. Stenzl pointed out that this adds complexity, as minor alterations could escalate the regulatory requirements for a test that otherwise would not need FDA oversight.

    6. Risks of Non-compliance Due to Undefined Validation Standards
      Without clear FDA validation standards for each risk level, laboratories are left to reference other FDA-cleared or approved tests to approximate compliance requirements. For labs developing novel tests without an FDA-comparable precedent, this presents a significant compliance risk.

    7. Increased Documentation Burden
      The FDA’s quality system requirements necessitate extensive documentation and tracking, especially in areas such as complaint handling and adverse event reporting. This documentation increase is seen as costly and time-intensive, with smaller labs possibly struggling to keep up with resource demands.

    8. Impact on Innovation in Laboratory Testing
      CAP has expressed concerns that the final rule might stifle innovation, as stringent requirements may discourage labs from developing novel LDTs due to the regulatory burden. This could limit patient access to specialized tests, particularly in rare disease and oncology sectors where tailored testing can be essential.

    9. Cost Implications for High-Complexity Labs
      High-complexity labs accustomed to CLIA standards may incur substantial costs adapting to FDA oversight. Costs could arise from implementing new quality systems, training personnel, or hiring additional staff to manage compliance, all of which affect smaller labs disproportionately.

    10. Lack of Clear FDA Guidance on Test Modifications
      Laboratories struggle with knowing which modifications necessitate reclassification and submission. The FDA’s current approach lacks detailed guidance on this issue, leaving labs in a position of potential non-compliance or excessive caution that limits operational flexibility.

    11. Potential Liability for Errors in Test Modifications
      If modifications trigger unintended reclassifications, labs risk penalties for unauthorized use of LDTs without FDA clearance. CAP has highlighted that labs face potential liability if unrecognized reclassifications lead to the use of unapproved tests in clinical settings.

    12. Pressure to Meet Compliance Deadlines
      The timelines set by the FDA for compliance in Stage One (May 2025) and beyond are challenging for labs needing significant adjustments. While large labs may have compliance frameworks in place, smaller labs face difficulties implementing the necessary changes in time.

    13. Public Database Use and Accessibility
      Dr. Stenzl recommended labs utilize the FDA’s product classification databases, but navigating these databases is complex, especially for staff unfamiliar with FDA terminology. This complexity could lead to errors in classification that impact compliance.

    14. Impact of FDA Rule on IHC and Other Specialized Testing
      Immunohistochemistry (IHC) and other specialized tests are only exempt from FDA submission under specific conditions, creating uncertainty for labs about which tests must comply. CAP has argued that the exemptions should be expanded to reduce unnecessary compliance burdens.

    15. Administrative Burden of Pre-submission Inquiries
      The FDA’s pre-submission process can take up to 75 days to provide a determination, which delays laboratories seeking clarity on test classification and compliance. This slow turnaround can hinder labs’ ability to implement compliant protocols promptly.


    15 Key Takeaways

    1. Three-Tiered Risk Structure: The FDA classifies LDTs as Class I (low risk), Class II (moderate risk), or Class III (high risk), each requiring different levels of compliance.
    2. Compliance for Stage One (May 2025): Labs must establish complaint handling, quality system procedures, and reporting for adverse events by this deadline.
    3. Distinct FDA vs. CLIA Criteria: FDA’s risk classification focuses on patient risk, contrasting with CLIA’s complexity-based standards, requiring laboratories to adapt to dual systems.
    4. Grandfathering Uncertainty: Tests developed before May 2024 may be “grandfathered,” but significant modifications could void this status and trigger compliance needs.
    5. Modification Triggers Compliance: Altering test parameters, such as sample type, could necessitate FDA submission, posing a challenge for labs using LDTs.
    6. Unclear Validation Standards: Labs are encouraged to reference similar FDA-cleared tests for validation, though exact standards remain undefined.
    7. Documentation and Quality System Demands: The final rule requires meticulous documentation, especially in complaint handling and corrective actions, adding resource strain.
    8. Costly Impact on Smaller Labs: Adapting to FDA requirements may be financially burdensome, particularly for smaller high-complexity laboratories.
    9. Innovation Risks: Strict requirements could inhibit innovation in LDT development, limiting new test offerings in high-need areas such as rare diseases.
    10. Public Database Navigation: The FDA’s product database aids classification, though its complexity may lead to compliance errors for unfamiliar users.
    11. Exemptions for IHC and Manual Tests: Some immunohistochemistry and manual tests are exempt if using FDA-cleared platforms; however, automation might require FDA submission.
    12. Pre-submission Process Delays: The 75-day pre-submission inquiry process can slow down labs seeking classification clarification and compliance advice.
    13. Penalties for Unauthorized LDT Use: Unintended test modifications could lead to unapproved LDT use and potential regulatory penalties.
    14. Reliance on FDA Database for Compliance: Labs can use the FDA database to approximate compliance but may need tailored guidance for novel or unique LDTs.
    15. Upcoming Webinars for Guidance: CAP’s remaining webinars will continue to interpret FDA requirements, aiding labs in understanding and meeting compliance obligations.

    By addressing these issues, CAP’s series aims to equip laboratories with the necessary knowledge and resources to navigate the regulatory complexities of the FDA’s final rule.