Friday, July 28, 2023

JAMA x 2: When CMS does NOT Pay for Something: Legalisms

 Most readers of this blog probably wouldn't be amazed at the idea, that CMS may "NOT" pay for something.  New devices and diagnostics are routinely classifed as "not reasonable and necessary."

The Medicare law is written, Medicare can NOT pay for services that are NOT reasonable and necessary.   This use of the double-negative leaves a little vagueness to the opposite concept, what Medicare DOES have to pay for.   Does it have to pay for on-label drugs, for example?  

JAMA Internal Medicine provides a legal memo by Davai and Kesslheim on this topic, accompanied by an Op Ed by  Crosson and Redberg.

Find the article HERE, the Op Ed HERE.

The article is 4700 words, the op ed is 1800.

The article brings out some old favorites, like courts ruling against "least costly alternative" some years ago.  Both articles assert that CMS authority to deny coverage of FDA-approved items is very clear, yet, with rather helter-skelter logic, both then ask that Congress rapidly reaffirm this fact.  I can see the present SCOTUS could find that Congress' instruction to CMS is unacceptably vague and thus gives unacceptable authority to the agency.   Both troop out sky-high sales of Aduhelm as a threat averted but it's highly unclear such a drug with difficult administration and high side effects, would ever had had big sales (see case study: Provenge).  

AI summaries follow.



The Op Ed discusses the need for public recognition and support of the US Centers for Medicare & Medicaid Services (CMS) to make coverage decisions for Medicare beneficiaries. The article highlights concerns regarding FDA-approved drugs and devices with limited evidence of clinical benefit, and the pressure from pharmaceutical and medical device industries influencing approvals. The authors recommend that Congress strengthen CMS's authority to include drug/device cost as part of its reasonable determination. They argue for clear standards on what constitutes "reasonable and necessary" medical products, especially for fast-track and accelerated approvals. Congress should act to protect the health of beneficiaries and the Medicare program by upholding CMS's decision-making authority.



This medical legal essay explores the Centers for Medicare & Medicaid Services' (CMS) authority to limit coverage for FDA-regulated products under Medicare Part B. CMS has employed various strategies, including Coverage with Evidence Development (CED), to condition coverage on patients' participation in clinical trials or registries approved by CMS. 

The essay discusses court rulings upholding CMS's authority to make such coverage decisions, emphasizing the difference between Medicare's coverage criteria and the FDA's approval standards. The authors suggest that Congress may need to clarify CMS's coverage discretion and consider setting appropriate reimbursement rates to prevent exorbitantly priced products from burdening the Medicare budget. As the FDA approves treatments based on surrogate measures, pressure on CMS to cover products with limited evidence will grow, necessitating clearer statutory authorization for CED determinations.

Additional Request:

Discuss how Medicare currently defines "reasonable and necessary," any resulting problems or legal debates, and potential next steps or improvements.  Take as much text as you need.  You are writing for an expert reader.


Medicare currently defines "reasonable and necessary" as a key criterion for determining coverage under Medicare Part B. This term is derived from the Social Security Act, specifically Section 1862(a)(1)(A), which states that Medicare will not pay for any item or service that is not "reasonable and necessary for the diagnosis or treatment of illness or injury." However, the law does not provide a precise definition of what constitutes "reasonable and necessary," leaving room for interpretation and administrative discretion.

The lack of a specific definition has led to significant challenges and legal debates. 

The Centers for Medicare & Medicaid Services (CMS) has the authority to make coverage determinations based on its interpretation of the "reasonable and necessary" requirement, and its decisions have significant implications for patients, providers, and manufacturers. Courts have generally upheld CMS's authority to make these determinations, emphasizing that the agency's expertise in public health and its statutory discretion warrant deference.

One contentious issue arises from the potential inconsistency between FDA approval and CMS coverage. While the FDA evaluates drugs and devices for safety and efficacy, Medicare coverage decisions focus on clinical necessity and cost-effectiveness. As a result, some FDA-approved products may not be covered by Medicare, leading to challenges from industry and beneficiaries seeking broader coverage.

Another area of concern is the use of Coverage with Evidence Development (CED) programs. These programs condition coverage on patients' participation in clinical trials or registries approved by CMS, aiming to generate additional evidence while limiting inappropriate coverage. While CED can be a valuable tool, there have been debates about its scope, with some arguing that it may lead to limitations in access for certain patients.

Furthermore, the lack of explicit consideration of cost in Medicare coverage decisions has been a topic of debate. Medicare is a significant payer in the healthcare system, and its coverage decisions can impact healthcare costs and patient access. Some experts argue that considering cost in coverage decisions could help promote more efficient resource allocation and prevent the potential budgetary strain caused by costly treatments.

Potential next steps and improvements to address these challenges include legislative actions to clarify CMS's coverage discretion and potentially allow the consideration of cost in coverage determinations. Congress could provide clearer statutory authorization for CED programs, validating CMS's approach to incentivize the development of valuable therapies while ensuring appropriate coverage.

Additionally, efforts to improve transparency and public input in the coverage determination process could enhance public trust and understanding of CMS's decisions. Clearer communication about the basis for coverage decisions and the consideration of evidence could help stakeholders better navigate the complex landscape of Medicare coverage.

Furthermore, research and data collection to assess the impact of coverage decisions on patient outcomes, costs, and access to care could inform future policy improvements. Collaboration between CMS, the FDA, and other stakeholders may also facilitate a more integrated approach to coverage decisions, considering both clinical evidence and cost-effectiveness.

In conclusion, defining "reasonable and necessary" in Medicare coverage decisions remains an ongoing challenge, leading to legal debates and potential disparities in access to innovative medical treatments. Addressing these issues requires a balanced approach, ensuring patient access to effective therapies while promoting cost-effectiveness and responsible use of Medicare funds. Legislative clarifications, improved transparency, and evidence-based decision-making are crucial steps toward enhancing the Medicare coverage process for the benefit of patients, providers, and the healthcare system as a whole.

Debates about the scope of CED Coverage with Evidence Development, have gone as far as legal positions that CED is not legal for CMS.  Is this topic discussed?


Yes, the topic of whether Coverage with Evidence Development (CED) is legal for the Centers for Medicare & Medicaid Services (CMS) has been a subject of legal debate. While CMS has implemented CED as a strategy to condition coverage on patients' participation in clinical trials or registries, there have been challenges and legal positions questioning the legality and scope of this approach.

The legal basis for CED is rooted in the Medicare statute, which broadly prohibits payment for items or services that are not "reasonable and necessary" for a medical purpose. However, a narrower provision within the statute prohibits payment for "research conducted" by the Agency for Healthcare Research and Quality (AHRQ) that is not "reasonable and necessary to carry out" its clinical research mission. CMS has relied on this research-based provision to support its CED program, suggesting that payments for research may be appropriate even when clinical benefit is not fully established.

Critics argue that the statutory authority for CED is not explicitly stated and that CMS's use of CED goes beyond its legal boundaries. They contend that conditioning coverage on participation in research studies may lead to limitations on access to certain treatments, and that this approach could result in inequalities in healthcare access for Medicare beneficiaries.

As with many legal issues, there are differing perspectives on the interpretation of the Medicare statute and the scope of CMS's authority. While courts have upheld CMS's ability to limit coverage to research settings, there remains ongoing debate about the appropriateness and legality of CED as a coverage determination strategy.

To address these concerns, potential legislative actions or explicit statutory authorization for CED could provide a clearer legal basis for CMS's approach and help validate the use of CED programs. Moreover, increased transparency and public engagement in the coverage determination process may help to better address potential legal challenges and foster a more informed and inclusive decision-making process.

Very Brief Blog: Cancer Policy Website: "TriageCancer.Org" - State Biomarker Bills & Much More

For a couple years, we've been hearing about state-level biomarker bills, which require insurance coverage for FDA and/or guideline-based biomarkers.  The bills vary; some die in committee, some pass for all biomarkers, some pass for cancer only.   

See diverse types of cancer policy at TriageCancer.Org:

See their detailed table of all the state level biomarker bills:

More Links

See a 2022 article at ACCC here.  See news at ACS here. See news at NantHealth here.  See a PubMed article, Sadigh et al. in "Cancer" 128:2865, 2022, here.

Thursday, July 27, 2023

Journal Club: NEJM Big Review Article on AI in Healthcare

Update:  NEJM the next week published a long article on AI in Medical Education - here.


On July 27, 2023, New England Journal publishes a masterful review article on AI in healthcare - here.

The article is by Sahni and Carrus, at Harvard and at the McKinsey Center for Healthcare Improvement.

Do you want to read it?  NEJM reviews generally don't have abstracts, making an AI summary particularly helpful.  Here's the GPT3.5 summary:


Can you provide a 50 word and a 100 word summary?

50-Word Summary:

The article discusses the slow adoption of artificial intelligence (AI) in U.S. health care delivery and identifies six key challenges hindering its implementation, including proper cost-benefit definition, data management, change management, workflow integration, patient confidence, and regulatory concerns. Overcoming these challenges is crucial to leverage AI's potential for improving patient care and safety.

100-Word Summary:

The article highlights the slow adoption of artificial intelligence (AI) in U.S. health care delivery due to various challenges. These include the need to properly define costs and benefits, data management complexities, change management considerations, seamless workflow integration, addressing patient confidence issues, and navigating regulatory and methodological concerns. Overcoming these challenges is vital for realizing AI's potential to revolutionize health care by improving patient care and safety. Organizations should focus on rigorous evaluation, increased investment, and conducting demonstration projects to identify effective AI use cases and ensure a smooth transition towards AI-driven health care delivery.



The article discusses the adoption of artificial intelligence (AI) in U.S. health care delivery and the challenges associated with its implementation. It is authored by Nikhil R. Sahni and Brandon Carrus and published in the New England Journal of Medicine.

Key Points:

Slow Adoption of AI in Health Care Delivery: Compared to other business sectors, the adoption of AI in health care delivery has been slow. Various factors contribute to this, including the heterogeneity and complexity of health care data, fee-for-service payment models, lack of patient confidence, regulatory issues, and methodological concerns.

Emerging High-Value Uses of AI: AI is being utilized in various domains of health care delivery, including reimbursement, clinical operations, and quality and safety. Examples include using AI to predict and manage sepsis, optimize operating room scheduling, and reduce clinician burnout by automating electronic health record (EHR) updates.

Challenges in AI Adoption: Several challenges need to be addressed for successful AI adoption in health care organizations. These challenges fall into six categories: strategic vision, key enabling factors, data management, change management, workflow integration, and implementation.

Promising Applications: AI shows potential in improving patient safety by predicting adverse events and enabling early intervention. It can also enhance patient experience by analyzing data to identify dissatisfied members and address their issues.

Need for Expanded Evaluation: Despite the potential benefits, the evidence supporting AI applications in health care is still limited. More research and rigorous evaluation, such as randomized controlled trials, are needed to assess the impact of AI on patient outcomes and safety.

Action Points and Next Steps:

Define Costs and Benefits: Health care organizations should consider the nonfinancial factors, such as improved patient safety and experience, when evaluating the costs and benefits of AI adoption.

Address Data Management: Proper data management is critical for successful AI implementation. Organizations should focus on preparing data, addressing biases, and ensuring continuous testing and validation.

Overcome Implementation Challenges: Organizations must address change management and workflow integration to ensure smooth AI adoption. AI should be seen as a supportive tool that enhances clinical judgment rather than a substitute for it.

Conduct Demonstration Projects: Testing AI applications in a few domains through demonstration projects can provide valuable insights and help identify the most effective use cases.

Investment in AI: Higher-performing organizations in AI adoption spend more on AI than lower performers. Continued investment in AI adoption is essential for reaping its benefits fully.

Rigorous Evaluation: As AI is deployed in health care, rigorous evaluation methods, including randomized controlled trials, should be utilized to measure its impact on patient outcomes and safety.

In conclusion, the potential of AI to revolutionize health care delivery is promising, but there are challenges to overcome. By addressing the key factors hindering AI adoption and investing in its implementation, health care organizations can leverage AI to improve patient care, safety, and overall health care delivery. Rigorous evaluation will be essential to understand the true impact of AI in the health care sector.


Can you specifically call out the 6 most important challenges.

The article identifies six important challenges in the adoption of artificial intelligence (AI) in health care delivery:

Properly Defining Costs and Benefits: Organizations need to accurately assess the costs and benefits of deploying AI. Traditionally, the decision to invest in AI has been based on financial return, but the calculation should also include nonfinancial factors, such as improved patient safety and experience.

Data Management: Health care data is heterogeneous and variable, making it more challenging to apply AI compared to other business sectors. Proper data management is crucial, including data preparation, addressing biases, and ensuring continuous testing and validation.

Change Management: Successfully adopting AI within an organization requires addressing change management. Different stakeholders, from hospital administrators to clinicians, may have different perspectives and implications on how AI impacts their workflows and responsibilities.

Workflow Integration: AI in health care delivery is more effective when seamlessly integrated into the clinical workflow. AI should be viewed as a supportive tool to enhance clinical judgment rather than a replacement for it.

Lack of Patient Confidence: Concerns about privacy, trust in AI output, and the potential consequences of AI-based decisions contribute to patient apprehension. Building patient confidence in AI applications is essential for widespread adoption.

Regulatory and Methodological Concerns: Regulatory issues, such as Food and Drug Administration (FDA) approval and reimbursement, need to be addressed. Additionally, concerns about validation and communication of AI-based recommendations or decisions, as well as reporting difficulties, must be overcome for successful AI adoption.

Addressing these challenges is crucial to the successful implementation of AI in health care delivery and realizing the potential benefits it offers for patient care and overall health care outcomes.


I use OpenAI ChatGPT, both the "free" 3.5 and "paid" 4.0.  I find the 3.5 often does better at article summaries.


In 3 Haiku:

AI's promise vast,
Health care's slow embrace revealed,
Challenges must pass.

Data's complexity,
Patient trust and workflow merge,
AI's path to forge.

Six challenges rise,
Adoption's key hurdles faced,
Health care's AI quest.

See 2 minute and 4 minute video scripts here.

Brief Blog: Novitas Issues (Re Issues) Oncology LCD Proposal

Lots going at at Novitas (and First Coast) MACs, re oncology genomics.  They released a draft LCD on this topic in June 2022, and a massively enlarged final version on June 2, 2023.  That version was withdrawn in early July, likely because of protests that the final version was so radically different that the public had never seen or commented on it. [*]

On July 27, Novitas (and First Coast) reissued the large final LCD "as if new" - for public comment as a draft.    Here.

Per the tracking sheet, comment is open til September 9, and there will be a public comment meeting on August 10 and 11 (one for Novitas, one for First Coast).[**] 

The Novitas new proposal is numbered DL39365, the First Coast is DL39367.  Therefore, perhaps confusingly, the numbering 39365 is the same as the proposed/finaled/suspended LCD.

What's New?

In CMS download-PDF version, the new proposal 39365 is 66 pages.  Clipped into a Word document, it is 89 pages and 38481 words.

The June 2 "aborted" version, cut into my Word program, was 68 pages and 30,250 words.  However, I did not include the bibliography in that version.  The newest proposed bibliography is 230 citations.


I used the MS Word "document compare" function to redline the June "final" and July "re proposed" versions, and in overview, I did not notice any differences.

The LCD, from my June review, is sensible in parts but bizarrely written and atypical in other parts.  It was also horrifying complex, with a billing article that was a behometh with 80 confusing sections.   The LCD only briefly touches on important topics like liquid biopsy and minimal residual disease testing, while giving exhaustive review of about 13 specific branded tests, a few of which seem pretty obscure.   

Rather than review that June version, they have simply reissued it for public comment again.    

Novitas: Billion Dollar Fraud Payments Gushing Out as Genomics Claims

During all this, on June 23, OIG released a damning report on the billion dollars plus of OBVIOUSLY bogus claims paid out by Novitas and First Coast in the past couple years.   (I've also pointed out the OBVIOUS insanity in this blog using CMS public records).  Here.


[*] While there are no rules on how much a "final" LCD can be  revised and still be a valid successor to its proposed form, there is some language about this regarding CMS regulations, which must either enumerate the final proposal (among alternatives) or the final proposal must be a "logical outgrowth" of the proposal the public saw.  See SSA 1871.   In current OPPS rulemaking for FY2024, CMS proposes 5 possible ways to revised radiopharmeutical payment, and CMS could settle on no change, one of the 5 methods, or a 6th method that was a natural and similar variant of what was proposed.  Here.

[**] Both the Novitas MAC and First Coast [Florida] MAC are under a complex multi level ownership relationship with Florida BCBS.  

Very Brief Blog: CMS Revises Software for Claims > $999K

CMS issued software instructions to update billing and payment fields to accomodate amounts over $1M (999,999.99).

Very Brief Blog: CMS Posts Advisory Panel Rec's for Pricing New Lab Codes

NUTSHELL:  CMS posts Advisory Panel votes for prices of 85 new lab tests.


Every summer, CMS holds a series of meetings and events regarding the pricing of new lab codes for the next calendar year.  On July 19, 2023, CMS held its panel of expert advisors who voted on a price or alternate prices for every new lab code.

Here's the web page for the panel:

Here's the newly released PDF showing every vote on every code.  Many votes are unanimous but some codes get a variety of voting choices and price choices.

Gapfill Recommendations?

Last fall, CMS sent about 40 of 100 possible codes into the gapfill process (the gapfill process that is active with MACs currently, this year).

The CLFS advisory experts only voted majority-gapfill for about 13 of 85 codes.   Of these, only 8 of 85 codes had a strong majority vote for gapfill (such as 8 votes or 9 votes out of 9 voters).

None of the codes the panel voted for gapfill, were conventional PCR MAAA tests (e.g. mRNA expression for 20 genes).  

A single lone panelist voted for gapfill (1 vote) on 9 codes. 

Event Horizon

June - Public comment meeting (live streamed)

July - Expert panel advisory meeting (live streamed)

1H September - Proposed Prices

2H September - Comments

November - Final Prices

After final prices, an appeal can be filed, but it basically just brings the code back to the same meeting the next summer again.

Wednesday, July 26, 2023

Brief Blog: CMS, Now with FOIA Submission Portal and Info

I've done a dozen FOIA requests over the years, some very successful, others not yielding much.   You may hear response times are "years," but I've often seen "months."   I've learned it can be much more effective to submit a request for MAC documents via the CMS office, because it may be dealt with too casually at the MAC itself.  ("We got nothin', go away.")

I've always submitted FOIA requests via email with a short request letter attached.   Find the CMS home page here:

There's also a FOIA "Reading room," where requests are logged by month.  (CMS gets hundreds.)

And a FOIA portal,

Your FOIA request will be logged and you'll get an email tracking number within a few days (if not, something is wrong).   Like, say, a Fedex letter, your tracking number allows you to see the case status online.

Foia.Gov Portal

Find it here:

When you START, you'll be asked to enter the agency name (CMS, DOD, etc), where you get passed to that agency's page.  You'll see your desired agency's own FOIA reference guide, information like senior FOIA staff by name, and a couple "key performance indicators."  These say that simple requests to CMS were answered in 17 days in 2022, complex requests in 37.   I've rarely seen it go that fast, a few months seems normal, and a year is not remarkable.

If you choose to file by form, rather than email and PDF, there are about a dozen fields (name, city, etc) and the request text box goes to 10,000 characters (probably around 2000 words).


I recently requested a MAC document, and got a prompt letter (30 days) that I couldn't have it.   I then requested the same MAC document via the FOIA central office.  In a few months, I got a letter that CMS FOIA has the document, it is 4 pages long, and they are holding it as a "business secret" (one of the rules for not releasing things.)  I had 90 days to file an appeal, which curiously goes to the deputy director of CMS - which I did.  Just an example of the process at work.

WSJ for CMS Nerds: Why Alzheimer Drugs Bode Well for GE Healthcare; CMS Rulemaking on Tracers


Adoption of Alzheimer drugs could mean a boom in both PET and MRI imaging.  We'll explain why this is, and how CMS payment for radiopharmaceuticals is so different in the Hospital Outpatient vs regular Part B setting.  CMS has also offered to possibly change outpatient pricing rules.


Recent Events

CMS has guaranteed coverage of fully-approved Alzheimer anti-amyloid drugs, as long as patients are enrolled in a basic registry.  CMS has just announced it is dropping its "in research only" coverage of amyloid PET scans, and the drugs will also require patients have regularly monitoring with MRI's to detect adverse brain pathology.   One wild card is how fast the anti-amyloid drugs will be adopted.  Some new biologicals become best-sellers quickly, and others (e.g. Provenge) are launched with high hopes that fizzle.

WSJ and GE Healthcare

See a July 25, 2023, article in WSJ by David Wainer:  "A Surprising Beneficiary of New Alzheimer Drugs: GE Healthcare," here.  Companies as diverse as Lilly - which makes the "Amyvid" tracer - and Philips - which makes imaging equipment.  GE Healthcare (now a standalone stock) makes both the tracer and the PET scanner.

The newspaper can only estimate, but talks about 1.2M extra MRI's, 500K extra PET scans, globally, calling this a "billion dollar market."

CMS Amyloid Imaging Policy

On July 17, 2023, CMS announced it plans to discontinue its roughly ten-year-old NCD, on amyloid PET scans, which covered the scans only under stringent clinical study conditions.  The new policy (to begin in a few months) would leave coverage choices up to the MACs.

I wrote a blog on the initial decision here, and a blog in which I interview AI (GPT3.5) about the new policy, here.   The latter blog also includes an AI-written letter from a stakeholders who urges CMS to make no change, and to keep the current restrictive policy.

Wild World of Payment Policy

In a nutshell, in regular Part B, Medicare pays for the PET scan itself, and separately for the tracer.   This is important because the PET scan may be in the $1500 dollar range while the tracer may be in the $3000 range.

On the other hand, in the hospital outpatient setting (OPPS prospective payment), CMS pays ONE set fee for the scanning and for whatever tracer is chosen for that patient.   That combined payment is in the $1500 range.   The difference is critical, because the least expensive tracers, like FDG, are in the $400 range and the most expensive, for amyloid, may be in the $3000 range. 

This means that amyloid tracer PET will almost always be done in the Part B freestanding centers, not in hospital-based PET centers.   

CMS Proposes Changes in OPPS Radiotracer Policy

In hospital proposed rulemaking released July 13 (here), CMS stated it was happy with its PET tracer bundling policy, but that it receives many complaints.  It listed about five alternatives on which it wants comment (comment til late August).   For example, CMS could make two categories of PET scan coding, one for less-expensive and one for more-expensive tracers.   CMS could bundle tracers, not at any price, but only if they cost less than $500.  (That might lead to a lot of $501 tracers).  CMS could simply pay for the tracer separately (after cutting down the base fee for the scan).  This approach to rulemaking follows instructions in CMS law SSA 1871, which requires that decisions in final rules must be proposed in draft rules, or else, be a natural outgrowth of what was proposed (not a big jump).   

Problems Go Way Back

This HOPPS policy issue also concerns some cancer patients, who get an expensive test tracer prior to certain radioactive anti-cancer therapies.   CMS has bundled the expensive test diagnostic tracer, making it hard for hospitals to buy and offer it.  Scott Gottlieb has complained about this in various Op Eds.   

Another aspect of the story is that it's hard to pay for radiotracers in the same way as regular injectible drugs.  Regular drugs are paid by ASP, average sales price, by surviving the manufacturer (e.g. Pfizer).  But radiotracers have different components at different places - the drug skeleton, the tracer (like F18), the radiobiology center that can combine the two.  The result is there is no simple single price as there is for normal drugs.

I think I recently saw news about 2023 legislation that would REQUIRE CMS to change its OPPS tracer policy, but I haven't got it handy.

Tuesday, July 25, 2023

Carol Blackford Moves from CMS to AdvaMed

Carol Blackford, a long-time respected senior policy expert at CMS, has moved to the private sector.  She is now with AdvaMed as: Executive Vice President of Payment and Health Care Delivery Policy.

See AdvaMed's press release below.


WASHINGTON, D.C. –  July 20, 2023, AdvaMed, the Medtech Association, announced that Carol Blackford has joined the organization as Executive Vice President of Payment and Health Care Delivery Policy. She will lead the AdvaMed team responsible for developing and advocating for policies that expand patient access to medical technologies by improving coverage, coding, and payment processes used by Medicare. The department also oversees research projects on the role and contributions of the medtech industry to the health of patients.

“Carol brings to AdvaMed years of experience and a deep understanding of the reimbursement landscape that will be invaluable in shaping our efforts to ensure medical technology innovations are available to the patients who need them,” said Scott Whitaker, AdvaMed President and CEO. “I am excited to have her join the AdvaMed team, and I look forward to working with her to expand the great work our payment department is doing to advance these life-saving policies.”

Previously, Carol served for 28 years at the U.S. Department of Health and Human Services, including her most recent role as the Director of the Hospital and Ambulatory Policy Group at the Centers for Medicare & Medicaid Services. 

She has also served as Acting Deputy Director of the Center for Medicare and as Deputy Directory of the Chronic Care Policy Group.

Journal Club: CAP TODAY (July 2023): Present Pressures vs Futurism - Dig Path, AI, and NGS Issues

CAP TODAY has excellent, open-access articles, and recently they've been making great using of the "expert roundtable" format.  For July 2023, they have an essay that's great reading but a little cryptically named - "Lab leaders on moving markets and tipping points."  Notably, the article covers Digital Pathology, and AI, and NGS.

Find the article here:

For those who'd like a preview to decide whether to invest in reading it, an AI summary follows.



This article was published in CAP TODAY in July 2023, and discusses key issues surrounding digital pathology, artificial intelligence (AI), and the challenges faced by clinical laboratories in the current healthcare landscape. The conversation involves insights from lab leaders of the Compass Group, an organization of not-for-profit IDN system laboratory leaders.

Digital Pathology Adoption:

Lab leaders from the Cleveland Clinic and Scripps Health share their experiences with digital pathology adoption. While it is being used for subspecialty case review conferences and international consultations, broader implementation is limited by technical staffing constraints and communication challenges in busy clinical environments.

AI in Pathology:

The conversation delves into the hype and reality of AI in pathology. Dr. Henricks expresses skepticism about the speed of AI adoption, emphasizing the importance of data quality and the need for regulatory guidance due to the continuous learning nature of AI algorithms.

Impact of AI on Pathologist Workforce:

Lab leaders discuss the potential impact of AI on the pathology workforce. While AI might improve efficiency in some aspects, it also raises concerns about the need for adequate pathologists for clinical care. There are expectations of a more flexible working environment, with some candidates seeking remote work options.

Financial Pressures on Clinical Laboratories:

The article highlights the financial challenges faced by clinical laboratories. Declining reimbursement rates, competition, and increasing costs for staffing and equipment put labs in a precarious situation, leading to limited margins and stress on resources.

Leadership and Management Development:

Lab leaders emphasize the importance of investing in leadership and management development within laboratories. The lack of competent leadership and management skills, coupled with a shortage of qualified leaders entering the field, poses challenges for labs in the coming years.

Pathology's Role in Healthcare Initiatives:

The article discusses how pathology and the clinical laboratory can be overlooked when grandiose clinical initiatives are planned. Laboratories need to assert their needs and challenges to ensure they are adequately represented in decision-making.

Overall, the article sheds light on the complex issues faced by clinical laboratories in the digital age, from the adoption of new technologies like digital pathology and AI to financial pressures and the need for skilled leadership. It serves as a valuable read for pathologists and medical school professors to understand the current landscape and prepare for the future of pathology practice.   


The article would be of the highest interest and most importance to read for the following potential readers:

Pathologists: Pathologists, both practicing and in training, would find the article highly relevant as it discusses the current challenges and trends in the field of pathology. The insights on digital pathology, AI, and the impact on the pathology workforce can help them stay informed about advancements and potential changes in their profession.

Laboratory Leaders: Leaders of clinical laboratories, including lab directors and administrators, would benefit from reading the article as it addresses financial pressures, staffing challenges, and the need for effective leadership and management development. The article provides valuable perspectives from peers in the Compass Group, offering insights that can guide decision-making and strategic planning within their organizations.

Healthcare Executives and Administrators: Executives and administrators within healthcare organizations would find the article important to understand the challenges faced by clinical laboratories and the potential impact on patient care and overall healthcare operations. It provides an opportunity for them to appreciate the demands and complexities of laboratory services and recognize the significance of supporting the pathology department adequately.

Medical School Professors in Pathology: Professors teaching pathology in medical schools would benefit from the article's insights to keep their curriculum up-to-date with the latest developments in the field. It helps them inform their students about the challenges and opportunities in pathology practice, including the role of technology and AI in shaping the future of the profession.

Researchers and Innovators: Professionals involved in pathology research and innovation, including those working on AI and digital pathology projects, would find the article relevant. It provides valuable context on the current state of digital pathology adoption, the challenges of AI implementation, and the potential impact on the pathology workforce, helping them align their work with real-world needs and priorities.

Overall, anyone involved in the field of pathology, from practicing pathologists to healthcare leaders and educators, would find the article of the highest interest and importance as it addresses critical issues and trends shaping the future of pathology practice.

The content is organized in a way that presents various perspectives and insights from lab leaders on relevant topics, such as digital pathology, AI, financial pressures, leadership challenges, and the role of pathology in healthcare initiatives.

Monday, July 24, 2023

(Not So) Brief Blog: Exclusion Criteria for Leqembi Clinical Trial

Recently, FDA gave full approval to the anti-amyloid Alzheimer's drug LEQEMBI (lecanemab).  I was interested in what the exclusion criteria were, for example, if patients with mixed Alzheimer and Parkinson's disease were excluded.

It was quite a chase to find the exclusion criteria.  Here are some places you can't find it:

The FDA label for LEQEMBI here.

The NEJM pivotal trial (January 2023, Van Dyck et al.) here.

The Supplement to NEJM here.

It's not that the exclusion criteria are trivial.  You DO see, for example, from the Screening & Randomization Flow Chart (van Dyck Fig. 1) that 5967 patients were screened for eligibility, and 3555 failed (60%).   But why did they fail?

Keep looking.

You can find a listing of exclusion criteria at NCT03887455.   With all these exclusions, it's always still a gray area to ask "if the patients are representative of a Medicare population."


Exclusion Criteria

  • Any neurological condition that may be contributing to cognitive impairment above and beyond that caused by the participant's Alzheimer's disease
  • History of transient ischemic attacks (TIA), stroke, or seizures within 12 months of Screening
  • Any psychiatric diagnosis or symptoms (example, hallucinations, major depression, or delusions) that could interfere with study procedures in the participant
  • Geriatric Depression Scale (GDS) score >=8 at Screening
  • Contraindications to MRI scanning, including cardiac pacemaker/defibrillator, ferromagnetic metal implants (example in skull and cardiac devices other than those approved as safe for use in MRI scanners)
  • Evidence of other clinically significant lesions on brain MRI at Screening that could indicate a dementia diagnosis other than Alzheimer's disease
  • Other significant pathological findings on brain MRI at screening, including but not limited to: more than 4 microhemorrhages (defined as 10 millimeter [mm] or less at the greatest diameter); a single macrohemorrhage >10 mm at greatest diameter; an area of superficial siderosis; evidence of vasogenic edema; evidence of cerebral contusion, encephalomalacia, aneurysms, vascular malformations, or infective lesions; evidence of multiple lacunar infarcts or stroke involving a major vascular territory, severe small vessel, or white matter disease; space occupying lesions; or brain tumors (however, lesions diagnosed as meningiomas or arachnoid cysts and <1 centimeter [cm] at their greatest diameter need not be exclusionary)
  • Any immunological disease which is not adequately controlled, or which requires treatment with immunoglobulins, systemic monoclonal antibodies (or derivatives of monoclonal antibodies), systemic immunosuppressants, or plasmapheresis during the study
  • Participants with a bleeding disorder that is not under adequate control (including a platelet count <50,000 or international normalized ratio [INR] >1.5 for participants who are not on anticoagulant treatment, example, warfarin). Participants who are on anticoagulant therapy should have their anticoagulant status optimized and be on a stable dose for 4 weeks before Screening. Participants who are on anticoagulant therapy are not permitted to participate in cerebrospinal fluid (CSF) assessments
  • Any other medical conditions (example, cardiac, respiratory, gastrointestinal, renal disease) which are not stably and adequately controlled, or which in the opinion of the investigator(s) could affect the participant's safety or interfere with the study assessments
  • Participation in a clinical study involving any therapeutic monoclonal antibody, protein derived from a monoclonal antibody, immunoglobulin therapy, or vaccine within 6 months before screening unless it can be documented that the participant was randomized to placebo
  • Participation in a clinical study involving any anti-amyloid therapies (including any monoclonal antibody therapies and any β-site amyloid precursor protein cleaving enzyme [BACE] inhibitor therapies) unless it can be documented that the participant only received placebo
  • Participants who have any known prior exposure to lecanemab
  • Participants who were dosed in a clinical study involving any new chemical entities for AD within 6 months prior to screening unless it can be documented that the participant was in a placebo treatment arm

Extension Phase: Exclusion Criteria

  • Participants who discontinued early from the Core Study
  • Participants who develop the following conditions from the time of Screening for the Core Study to the start of the Extension Phase

    • Any neurological condition that may be contributing to cognitive impairment above and beyond that caused by the participant's AD
    • Any psychiatric diagnosis or symptoms, (example, hallucinations, major depression, or delusions) that could interfere with study procedures in the participant
    • Contraindications to MRI scanning, including cardiac pacemaker/defibrillator, ferromagnetic metal implants (example, in skull and cardiac devices other than those approved as safe for use in MRI scanners)
    • Other significant pathological findings on brain MRI during the Core Study including but not limited to: cerebral contusion, encephalomalacia, aneurysms, vascular malformations, or infective lesions; evidence of multiple lacunar infarcts or stroke involving a major vascular territory, severe small vessel, or white matter disease; space occupying lesions; or brain tumors will be exclusionary if based on the opinion of the investigator, with consultation of medical monitor, these findings may interfere with the study procedures or safety
    • Hypersensitivity to BAN2401 or any of the excipients, or to any monoclonal antibody treatment
    • Any immunological disease which is not adequately controlled, or which requires chronic treatment with immunoglobulins, systemic monoclonal antibodies (or derivatives of monoclonal antibodies), systemic immunosuppressants, or plasmapheresis during the study
    • Any other clinically significant abnormalities in physical examination, vital signs, laboratory tests, or ECG, which in the opinion of the investigator require further investigation or treatment or which may interfere with study procedures or safety.
    • Malignant neoplasms (except for basal or squamous cell carcinoma in situ of the skin, or localized prostate cancer in male participants) that are not stably and adequately controlled or which, based on the opinion of the investigator, may interfere with the participant's safety or participation in the study
    • Any other medical conditions (example, cardiac, respiratory, gastrointestinal, renal disease) which are not stably and adequately controlled, or which in the opinion of the investigator(s) could affect the participant's safety or interfere with the study assessments
    • Severe visual or hearing impairment that would prevent the participant from performing psychometric tests accurately



For a brief blog on male/female differences, here.

There's probably more about exclusion criteria buried in the review dossiers and decks of the June 2023 FDA Ad Comm, here.

AI Corner: AI Assesses, Discusses, CMS Decision to End NCD for Amyloid PET scans.



Chat GPT-3.5 reads and discusses the July 17 CMS proposal to end  NCD-controlled coverage of Amyloid PET scans, and leave this up to MACs.  As always with AI examples, I'm not framing the AI essay as good or bad, but as a work product that might be of interest. 

Not only do we ask ChatGPT to assess the proposed NCD, which would result in the NCD removing itself (reflexive!).  As a final request, we also ask ChatGPT to write an association's letter, asking CMS to keep the NCD in place and not recind it (at bottom). 

Find the proposed decision memo here.

Find my original July 17 blog here.

 Summary of CMS Decision on Amyloid PET Scans:

Chat GPT-3.5

CMS conducted a reconsideration of the national coverage determination (NCD) for beta amyloid PET scans in dementia and neurodegenerative disease. The decision-making process involved a thorough review of evidence, including peer-reviewed literature, external technology assessments, internal technology assessment, and public comments.

Evidence Review:

Peer-Reviewed Literature: CMS reviewed published medical literature, clinical trials, and major studies related to interventions guided by PET Aꞵ imaging to improve health outcomes for patients, including Medicare beneficiaries.

External Technology Assessments: No external technology assessment was requested by CMS on this issue.

Internal Technology Assessment: The literature search was extensive and included databases like Academic Search Premier, CINAHL, Google Scholar, PubMed, Scopus, and more. Reports from various agencies were also considered.

Public Comments: CMS considered public comments received during the 30-day comment period, focusing on the question of whether to remove the current NCD for beta amyloid PET scans.

Decision Justification:

Based on the evidence and stakeholder feedback, CMS determined that the current NCD for beta amyloid PET imaging (NCD 220.6.20) should be revoked, ending the Coverage with Evidence Development (CED) requirement. The decision was justified by several factors:

  • Advances in Medical Care: Since the establishment of the NCD in 2013, there have been significant advances in medical care, including the development of antiamyloid drug treatments. The use of amyloid PET scans has evolved, and now they are used to confirm the presence of brain amyloid to select appropriate patients for these treatments.
  • Individualized Patient Treatment: Patient factors, such as medical comorbidities, concomitant medications, and individual response to treatments, need to be considered when using amyloid PET scans for treatment decisions.
  • Local MAC Discretion: Removing the NCD would allow local Medicare Administrative Contractors (MACs) to make coverage determinations, including covering more than one scan per patient's lifetime and use within or outside the context of a CMS approved study. This would provide flexibility in response to new evidence and developments in medical care.
  • Health Disparities: CMS acknowledges significant disparities in the prevalence of Alzheimer's disease (AD) across racial and ethnic groups. Revoking the NCD may help improve access to amyloid PET scans for underrepresented populations and support better healthcare for all individuals.

In conclusion, CMS has proposed to remove the NCD for beta amyloid PET scans, allowing MACs to make coverage determinations based on individual patient needs and current medical knowledge. The decision reflects the evolving landscape of medical care and the importance of personalized treatment for patients with dementia and neurodegenerative diseases.

In the past, in some CMS decisions like this one, the text rambled and covered miscellaneous topics without clear rationale for their inclusion or relevance to the final decision. Does CMS's discussion here, seem well focused on the purpose of the decision?   The decision was relatively short (14pp not 50 or 70).


Yes, the discussion in this CMS decision appears to be well-focused on the purpose of the decision. The text is relatively concise (14 pages) compared to some previous decisions, which suggests that CMS has made an effort to present the relevant information without unnecessary rambling or inclusion of miscellaneous topics.

The decision starts by providing background information on the NCD reconsideration and the evidence review process. It then proceeds to discuss the key questions addressed in the reconsideration, specifically focusing on whether to revise the current policy or remove the NCD for beta amyloid PET scans. Throughout the discussion, CMS clearly explains the evidence considered, including the peer-reviewed literature, technology assessments, and public comments.

The justification for revoking the NCD is laid out in a clear and logical manner, emphasizing advances in medical care, the importance of individualized patient treatment, and the potential to address health disparities. The decision also highlights the role of local MAC discretion in making coverage determinations, providing flexibility and responsiveness to evolving evidence.

Overall, the text appears to be well-organized and focused on the central purpose of the decision, making it more concise and accessible for expert readers in the field of national health policy.

What criticisms of the NCD might a policy expert have?


A policy expert might have several criticisms of the NCD for beta amyloid PET scans:

Lack of Clarity in Decision-Making: The decision-making process in the NCD may not be entirely transparent, and some aspects of the evidence review and rationale for certain conclusions may not be clearly explained. This lack of clarity can lead to confusion and raise concerns about the validity of the decision.

Inadequate Consideration of Cost-Effectiveness: The NCD may not adequately consider the cost-effectiveness of beta amyloid PET scans, which can be an essential factor in determining whether a medical intervention should be covered by Medicare. Cost-effectiveness analysis is crucial in ensuring the efficient allocation of healthcare resources.

Limited Patient Access: The once-in-a-lifetime limit for PET amyloid scans may restrict patient access to potentially beneficial diagnostic tests. Some experts might argue that this limit should be re-evaluated, especially in light of advances in medical care and the need for individualized treatment approaches.

Inconsistencies with Other CMS Decisions: The NCD might be inconsistent with other CMS decisions or coverage policies, leading to potential disparities in coverage and treatment options for patients with similar conditions. Ensuring consistency across decisions is essential for fair and equitable healthcare coverage.

Addressing Health Disparities: While the NCD mentions health disparities, some experts may argue that it does not go far enough in addressing these disparities. More specific strategies and interventions may be needed to ensure equitable access to diagnostic tests and treatments for underrepresented populations.

Limited Engagement with Stakeholders: Policy experts may criticize the NCD for not fully engaging with all relevant stakeholders, including patient advocacy groups, healthcare providers, and researchers. Involving stakeholders in the decision-making process can lead to more informed and comprehensive policy outcomes.

Scope of Evidence Review: Some experts may question whether the evidence review process considered all relevant studies and data, including potential biases or conflicts of interest in the research presented. Ensuring a comprehensive and unbiased evidence review is crucial for making well-informed policy decisions.

Flexibility and Adaptability: The NCD might be criticized for not being flexible enough to adapt to future developments in medical research and technology. As medical knowledge evolves, policies must remain adaptable to incorporate new evidence and treatment options.

Overall, these criticisms reflect the complexity of making national coverage decisions and the need for continuous improvement and refinement of healthcare policies to best serve patients' interests and promote equitable access to high-quality care.

Based on the CMS discussion, does it foresee or consider any drawbacks to leaving the Amyloid PET decisions in the hands of local contractors?


Based on the CMS discussion provided, there doesn't appear to be any explicit mention of drawbacks to leaving the Amyloid PET decisions in the hands of local contractors (MACs - Medicare Administrative Contractors). The discussion primarily focuses on the advancements in medical care, the development of new treatments for Alzheimer's disease targeting amyloid, and the need to confirm the presence of brain amyloid using PET scans for appropriate patient selection in treatment trials.

The CMS decision proposes to remove the National Coverage Determination (NCD) for beta amyloid PET in dementia and neurodegenerative disease, which would allow local MACs to make coverage determinations regarding the use of PET beta amyloid imaging. The justification provided is that the advances in medical care, standards of practice, and development of proven treatments have altered the application of amyloid PET scans in clinical practice and research. CMS believes that the local MACs can promptly respond to the evidence on proven treatments for individual patients.

While the discussion doesn't explicitly mention drawbacks to leaving the decisions to local contractors, there are potential concerns that could be raised by policy experts:

Inconsistent Coverage: Different MACs might interpret evidence differently, leading to inconsistent coverage decisions across different regions. This could create disparities in patient access to PET beta amyloid imaging and related treatments.

Variable Expertise: Local contractors might not have the same level of expertise or resources to conduct comprehensive evidence reviews and make well-informed coverage decisions, potentially leading to variations in the quality of decision-making.

Burden on Providers: Providers may face administrative burdens in navigating different coverage policies across different regions, leading to additional paperwork and administrative complexities.

Health Disparities: Leaving the decision to local contractors may not fully address health disparities, as certain regions or populations might still face barriers to access amyloid PET scans, leading to potential inequities in healthcare.

It's important to note that while these potential drawbacks are not explicitly discussed in the CMS decision, they are considerations that policy experts might raise when evaluating the proposal to leave the coverage decisions to local contractors. Policymakers need to carefully assess the potential trade-offs and implications of such a decision to ensure equitable access to healthcare services for all beneficiaries.

In that answer, you noted that CMS elaborated on no drawbacks.  However, you chose to add, there ARE potential drawbacks that an expert might have raised.  That was very helpful to add that extra part to your answer.


Thank you for your feedback, and I'm glad you found the additional information helpful. As an AI language model, my aim is to provide comprehensive and insightful responses to your questions. While the CMS discussion may not have explicitly mentioned drawbacks, it's essential to consider potential concerns that policy experts might raise when evaluating such decisions. Including those points can help provide a more well-rounded perspective on the topic. If you have any more questions or need further assistance, feel free to ask!

A stakeholder association wants to write CMS a comment letter opposing the decision and preferring to keep the status quot (under the status quo, amyloid PET is available only in pre-approved clinical trials or registries.)  Please draft such a letter to CMS.   


[Your Association's Letterhead]


Centers for Medicare & Medicaid Services (CMS)

Department of Health and Human Services

Attention: CMS-1753-P

P.O. Box 8016

Baltimore, MD 21244-8016

Subject: Comments on Proposed Decision CMS-1753-P - Amyloid PET Imaging Coverage Determination

Dear Administrator,

[Association Name] is writing to express our strong opposition to the proposed decision (CMS-1753-P) to remove the National Coverage Determination (NCD) for Amyloid PET Imaging (NCD 220.6.20) and to leave coverage determinations to local Medicare Administrative Contractors (MACs). As a stakeholder association representing [state the stakeholders you represent, e.g., patients, caregivers, healthcare providers, etc.], we firmly believe that retaining the status quo, where amyloid PET is available only in pre-approved clinical trials or registries, is in the best interest of Medicare beneficiaries and the healthcare system as a whole.

We acknowledge that CMS has conducted a thorough review of the evidence surrounding amyloid PET imaging and its potential benefits in diagnosing and treating dementia and neurodegenerative diseases. However, we respectfully disagree with the decision to revoke the NCD and here's why:

Lack of Consistency and Access Disparities: Allowing local MACs to make coverage determinations could lead to disparities in access to amyloid PET imaging services across different regions. Inconsistent coverage policies may create confusion for healthcare providers and patients, potentially resulting in delayed or denied access to essential diagnostic tests.

Increased Administrative Burden: The proposed decision to decentralize coverage determinations places an additional administrative burden on both healthcare providers and Medicare beneficiaries. Local MACs may have varying criteria and requirements for coverage, leading to increased paperwork and complexities in the reimbursement process.

Implications for Vulnerable Populations: Disadvantaged and underserved populations may face even greater challenges in obtaining access to amyloid PET imaging under a decentralized coverage system. Racial and ethnic minorities, who are already disproportionately affected by Alzheimer's disease, may face further barriers in obtaining timely and accurate diagnoses.

Potential Conflicts of Interest: Local MACs may face financial pressures and other interests that could influence their coverage decisions. This situation could potentially compromise the objectivity and impartiality of coverage determinations, leading to decisions that prioritize cost-saving measures over patient care.

Uncertain Impact on Clinical Research: The proposed decision may inadvertently deter clinical research in the field of amyloid PET imaging. If local MACs restrict access to amyloid PET scans, researchers may face difficulties in enrolling participants for clinical trials, hindering the advancement of scientific knowledge in this critical area.

Given these concerns, we strongly urge CMS to reconsider the decision and maintain the current NCD (220.6.20) for amyloid PET imaging. By continuing to limit coverage to pre-approved clinical trials and registries, Medicare beneficiaries will have equitable access to this important diagnostic tool, and healthcare providers will be able to make informed treatment decisions based on reliable and standardized criteria.

Furthermore, we recommend that CMS collaborate with stakeholders, including patient advocacy groups, healthcare professionals, and researchers, to develop evidence-based coverage policies that promote equitable access, clinical utility, and patient-centered care.

Thank you for considering our comments on this critical issue. We look forward to continued collaboration and constructive dialogue to ensure the best possible outcomes for Medicare beneficiaries and the healthcare community.


[Your Name]

[Your Title/Position]

[Association Name]

[Contact Information: Address, Phone, Email]

Pair of Papers Shines Light on Mysteries of MRD Test Coverage and Clinical Utility Design


  • We look at the challenges and requirements for obtaining Medicare coverage for minimal residual disease (MRD) testing, particularly in the MolDx program. 
  • MolDx emphasizes the need for MRD tests to meet certain criteria, including identifying molecular recurrence before clinical evidence and demonstrating sensitivity and specificity comparable to standard care methods. 
  • We'll look at two papers in JAMA journals, one on colon cancer MRD testing and the other on HPV biomarkers. Compared, they provide valuable insights for developers aiming to design effective studies for MRD testing. 
  • The Mo et al. paper gets praise from an expert for its systematic approach, while the Ferrandino et al. study is criticized for its less systematic design and frequency of tests. This "RWE" impacts the tightness of statistical conclusions.



One of the most frequent questions I get is what kind of trials must be undertaken to get "minimal residual disease" or MRD coverage from Medicare, e.g. the MolDx program.  The field is moving fast, for sure, as witness a new review article on LBX/MRD by Cohen et al. in Nature (here). 

MolDx has a sort of omnibus LCD for MRD (e.g. L38835) .  It can stretch to cover MRD in hematopoeitic cancers as well as solid cancers, and applications from postsurgical (1 test), to surveilliance (e.g. quarterly for 2 years) to drug response (esp. for I-O cancer drugs).   But MolDx reviews and parcels out each test and indication individually.   

MolDx provides several rules, but most companies find there is a gap between the rules and making actual black-and-white trial decisions.  The MolDx rules for MRD are here:

  1. The test is demonstrated to identify molecular recurrence or progression before there is clinical, biological, or radiographical evidence of recurrence or progression 
    1. AND 
    2. demonstrates sensitivity and specificity of subsequent recurrence or progression comparable with or superior to radiographical or other evidence (as per the standard of care for monitoring a given cancer type) of recurrence or progression.
  2. To be reasonable and necessary, it must also be medically acceptable that the test being utilized precludes other surveillance or monitoring tests intended to provide the same or similar information unless they either (a) are required to follow-up or confirm the findings of this test or (b) are medically required for further assessment and management of the patient.
  3. If the test is to be used for monitoring a specific therapeutic response, it must demonstrate the clinical validity of its results in published literature for the explicit management or therapy indication (allowing for the use of different drugs within the same therapeutic class, so long as they are considered ‘equivalent and interchangeable’ for the purpose of MRD testing, as determined by national or society guidelines).
  4. Clinical validity (CV) of any analytes (or expression profiles) measured must be established through a study published in the peer-reviewed literature 
    1. for the intended use of the test and
    2. in the intended population.
Very often, after reading this, the company is asking, "Whaddawe do next?"

Almost simultaneous papers in JAMA journals provide a guidepost for developers.   

In the first, Mo et al, JAMA Oncol, very systematically assess a fixed 6-biomarker MRD test for MRD in colon cancer.  An Op Ed by Ruiz-Banobre praises the systematic data in 299 patients.   

In the second, Ferrandino et al use real world data (available data) for observational statistics on an HPV biomarker for MRD, in 399 patients (JAMA Otolaryng).  Although this study has more patients, the Op Ed by Lango et al hones right in on the disparate and difficult to study intervals of available tests, both biomarker and imaging.  





Mo et al., JAMA ONC 9:770

Ferrandino et al, JAMA Otolar (July 9)

299 patients, fixed panel of 6 biomethylation markers for MRD, very systematic test schedules

399 patients, high sens HPV in plasma, test or schedules as clinically available



Op Ed:  Ruiz-Banobre, JAMA Oncol 9:763

Op Ed:  Lango, JAMA Otolar (July 9)





Praised the paper for clear results and systematic, carefully followed study disign

Clearly remarked that the test intervals were not systematically timed or repeated, available evidence was used.  (See quotes, bottom of blog).

Take home lesson, if you want a template for a study design that maximizes your key statistical outcome measurements, you'd use Mo et al, not Ferrandino et al., even though both papers were publishable in JAMA journals and the Ferrandino study had "more patients" (399 vs 299).

In a Nutshell

Let's close by looking back at the MolDx standards, for example, showing the test is better than standard of care imaging.  Let's show this as a hypothetical comparison:
  • If SOC imaging picks up cancer at 9 months plus or minus 1 month, and you pick up cancer at 7 months plus or minus 4 months, you haven't shown your test is better.  I mean, c'mon.  
  • If SOC imaging picks up cancer at 9 months plus or minus 1 month, and you pick up cancer at 7 months plus or minus 1 month, you have shown yours is better.   
  • QED, It's not hand-waving and it's not rocket science.

Mo et al. MRD in CRC [systematic evidence collection]
* Noteworthy for strong results using the non-bespoke or non-tumor-informed paradigm
Ruiz Op Ed

Ferrandino et al. MRD in H&N Cancer [available evidence collection]
Lango et al. Op Ed
  (Ferrandino coverage in 360Dx here.)

The summary "In a Nutshell" is adapted from an AI summary of the blog.

I tested both Op Eds in ChatGPT3.5 and it also agreed the CRC editorial was more favorable!  Here:  Overall, both editorials recognize the potential of liquid biopsy tests, but the second editorial (RUIZ BANOBRE) seems more confident in recommending ColonAiQ as a promising tool for managing localized CRC. The first editorial (LANGO) is more cautious in its approach, acknowledging the potential of the NavDx test but highlighting the need for further research and validation before widespread adoption.

As a supplement to this blog, find a detailed AI assessment of the two Op Eds, here.

This is the passage where Longo suggests the Ferrandino study was less systematic:

The reasons for these differences are not entirely clear,
but a comparison of the 2 studies is instructive. 

In the study
by Chera et al,1 patients had frequent blood draws during
and after treatment—10 per patient over the course of the
study. Testing was completed in conjunction with deinten-
sification protocols in which imaging and laboratory sur-
veillance was performed according to a prespecified sched-
ule. All patients with persistently negative tests remained
disease free. The authors determined that 2 positive tests
were suggestive of recurrence, improving the positive pre-
dictive value to 94%.

In contrast, Ferrandino et al2 used data that were col-
lected during the course of routine clinicalcare and at the
discretion of the treating clinician. On average, patients had 1 to
2 TTMV-HPV DNA tests after treatment (591 tests in 290 pa-
tients), and it does not appear that testing was obtained ac-

Furthermore,it is not clear if standardized surveillance
imaging was used,which might have affected
the time at which recurrences were clinically detected.