Friday, June 14, 2024

Tempus Up in First-Day Trading; GRAIL Steady

TEMPUS and GRAIL both became publicly-traded entities this week, TEMPUS through an IPO and GRAIL as a spin-out from Illumina.

TEMPUS (TEM) was priced at $37 earlier this week, and open trading on NASDAQ began at noon Friday.   The stock bumped from $37 to  $42 before settling at $38 in mid-afternoon.  According to news sources, the transaction raised $410M.   

One source stated that while Tempus's valuation at $37 would be $6.4B, the firm's highest valuation was in 2022 at $10.2B.   Per Pitchbook, Google bought in at $8B in 2020, and Baillie Gifford holds $350M of the stock.   (Here).

Baillie Gifford, an investment firm based in Edinborough, has a detailed and interesting online article on how evolutionary fitness can be applied to technology investments.  [See also this book.]


GRAIL (GRALV) has now traded for several days in a narrow band, around $14 to $15.50, with a market cap around $450M.  Here.


In other news, Reuters carries a story about a legal case from Guardant versus Tempus relative to DNA-testing patents.


AI Corner.

Chat GPT 4 summarizes the investment article noted above.

The essay explores the concept of "fitness landscapes" from evolutionary biology and applies it to business strategy and growth investing. Key points include:

  1. Complex Systems Commonality: Human brains, cities, cells, ecosystems, and business markets are all complex systems with dynamic interactions between underlying components. They exhibit properties like nonlinearity, emergence, punctuated equilibrium, and path dependence.

  2. Fitness Landscapes: Introduced by geneticist Sewall Wright in 1932, fitness landscapes visualize genetic variations and their survival likelihood. Modern adaptations use three-dimensional models to represent these landscapes.

  3. Dancing Fitness Landscapes: Biophysicist Stuart Kauffman and biologist Sönke Johnsen extended the concept by introducing time variability, highlighting that fitness landscapes are not static but continuously shifting due to interaction dynamics.

  4. Adaptive Strategies in Business: Echoing natural evolutionary processes, businesses are encouraged to be restless, use parallel strategies, and balance short and long strategic moves to adapt and thrive in dynamic markets.

  5. Three Horizons of Growth: McKinsey’s model identifies three strategic horizons: extending existing businesses (short jumps), leveraging the core business to create new opportunities (medium jumps), and creating entirely new businesses (long jumps). Duolingo is presented as a case study, successfully spanning all three horizons.

  6. Founder's Edge: The essay suggests that founder-led companies are often more adaptable and better positioned to make bold strategic decisions necessary for long-term success.

  7. Investment Risks: The document reminds investors of the risks associated with mutual funds, including international investing risks like currency rate changes, political uncertainty, and market volatility.

The essay serves as a guide for investors to understand and navigate the complexities of investing in businesses by learning from evolutionary biology and complex system theory, advising a proactive, diversified approach to business strategy and investment.  [ / end chat gpt 4 ]

Thursday, June 13, 2024

MedPAC Issues Annual June Report: Software in Medicare and Hospital-at-Home

Each June, MedPAC releases a lengthy Report to Congress on a selected list of Medicare policy topics.  The June 2024 edition is out.

Particularly novel or interesting chapters include:

  • Paying for software technologies in Medicare
  • Medicare's Acute Hospital Care-at-Home Program
  • Medicare Advantage: Prior Auth & Narrow Networks
Find the 269-page report here:


AI Corner

I gave the 30-page chapter on software to GPT4 for a summary, as below.  The actual chapter defies such a short summary, with many interesting tables and examples of CMS pricing history and complicated, different evolving policies for software.   MedPAC is always highly in favor of bundling - they never saw a service they didn't think was benefited by bundling rather than paid separately, and this is clear in the last several pages of the software chapter.   But, at a higher level, here's a good AI summary.

This MeddPAC report on CMS payments for software technologies in Medicare is extensive and detailed, focusing on the evolving landscape of software as a medical device (SaMD) in healthcare, particularly how these technologies are integrated, regulated, and reimbursed within the Medicare system. Here is a detailed summary, highlighting dilemmas and key points relevant to diagnostic tests:


The increased reliance on software technologies in healthcare, including AI and machine learning applications, poses new challenges and opportunities for Medicare. Technologies such as clinical decision support software and computer-aided detection (CAD) systems are growing more sophisticated, requiring updated regulatory and payment frameworks.

FDA Approval and Medicare Coverage

Software technologies must receive FDA clearance or approval as SaMD before they are eligible for Medicare coverage. The FDA classifies these technologies based on risk, and there are different pathways for their approval: premarket notification (510(k)), De Novo classification, and premarket approval (PMA).

Medicare Payment Systems

Medicare covers and pays for SaMD under various systems:

  • Part A and Part B services: Coverage depends on the software fitting into a Medicare benefit category and being reasonable and necessary for diagnosis or treatment.
  • Outpatient Prospective Payment System (OPPS) and Physician Fee Schedule (PFS): SaMD can be separately payable or bundled with other services, with specific codes assigned for billing purposes.

Dilemmas in Payment and Coverage

  1. Balancing Innovation and Cost: Medicare must balance the encouragement of innovation with the need to control costs and prevent overpayment for technologies that could be bundled with other services.
  2. Service Integration: Deciding whether a new technology should be paid separately or as part of a bundled payment presents a significant challenge, especially as some software can perform functions independently of hardware devices.

Diagnostic Tests: Specific Insights

  • Software used in radiology, pathology, and genetics, such as CAD systems for diagnostic imaging and AI-driven analysis tools, is critical. These systems analyze medical images and data to assist in diagnosis and management but pose unique challenges for integration into Medicare’s payment frameworks.
  • Technologies like the LumineticsCore for detecting diabetic retinopathy and CAD systems used in radiological assessments are examples where Medicare provides coverage under specific conditions.

Policy Recommendations

The report suggests continued evaluation and adjustment of payment models to accommodate the rapid advancement of medical software technologies. This includes considering the implications of AI and machine skill learning, where software not only supports but potentially replaces human decision-making in clinical settings.

This summary addresses the critical points of integrating new medical software technologies into the Medicare framework, focusing on both the potential benefits and the complexities of ensuring effective coverage and reimbursement without stifling innovation or increasing costs disproportionately. [/end chatgpt 4]

Medicare MACs Finalized LCDs for KidneyIntelX (NGS MAC) and Thyroid Nodule Stratification (MolDx)

 Two new final LCDs have been posted on June 13, 2024.


NGS MAC posts final version of L39726, "KidneyIntelX and KidneyIntelX.dkd Testing."  The process reflects a public meeting (CAC meeting) on August 24, 2023 (17pp; see link within LCD). NGS MAC writes,

  • “The current evidence concerning KidneyIntelX or KidneyIntelX.dkd as a test to identify and stratify patients with T2D and early-stage CKD into low, intermediate, and high risk for near-term rapid progressive decline in kidney function, suggests that the early identification of high-risk patients by the test allows for more intensive patient management, selection of appropriate medications, and appropriate specialty referral or consultation.”
  • “Also, the clinical principles, that more proactive care leads to better health outcomes and improved quality of life for patients, including slowed disease progression, avoidance or delay of kidney failure and need for hemodialysis, were supported by our CAC Subject Matter Experts.”

See LCD L39726 here.  Response to comments A59758 here.  Coding article A59595 here.

The LDT form of the test is "Kidney Intel X" while the FDA-cleared form of the text has the FDA-provided suffix ".dkd".   The text is coded as 0407U, $950.   

  • The code text is, "Nephrology (diabetic chronic kidney disease [ckd]), multiplex electrochemiluminescent immunoassay (eclia) of soluble tumor necrosis factor receptor 1 (stnfr1), soluble tumor necrosis receptor 2 (stnfr2), and kidney injury molecule 1 (kim-1) combined with clinical data, plasma, algorithm reported as risk for progressive decline in kidney function."
Share price for Renalytix has been as high as $32 (2021) and is currently trading around 45 cents, for a market cap of $35M. For the fiscal year ending June 2023, per Yahoo Finance, revenue was $3.4M and operating income negative $44M.  


Palmetto and other MolDx MACs post the final version of L39646, a foundational (general) LCD for thyroid nodule risk stratification,

Find LCD L39646 here.  Response to comments A59734 here.   Coding article A59470 here.

The LCD, effective in August 2024, is based on a request letter from Veracyte dated January 12, 2022.

Updates to the coverage bullet points were minor.  The LCD states somewhat obliquely that "if the patient has multiple nodules, concurrent or reflex testing may be medically necessary."  The Q&A document clarifies that if a nodule is positive for potential malignancy, indicating surgery, then testing of additional nodules on that side are not necessary (which makes sense).


I believe that the Veracyte Afirma test had previously been covered under a general-purpose LCD ("Molecular Diagnostic Tests L35160") and a short billing and coding article which will soon be retired (A54356).   Veracyte's request letter (2022) had been to include the Afirma MTC test as well as creating a broader (open ended or foundational) LCD.  MTC is a test version for medullary thyroid cancer.  In early trading on Thursday, Veracyte (VCYT) was down 2% at $21.62.  Its five-year high was $73 in 2021, low at $15 in late 2022.




It can be difficult to predict a consensus for market demand and market response in diagnostics (e.g. the share price of Renalytix ranges from $32 to <$1 in a couple years, during which, they hit progressive benchmarks like FDA approval).   I found the book "Heart of Innovation" helpful in thinking about utility cases and market response.


AI Corner.

Here is a Chat GPT 4 summary of the 17-page NGS MAC renal transcript.

The CMS transcript presents a detailed Contractor Advisory Committee (CAC) meeting conducted by Dr. Gina Mullen on August 24, 2023, focusing on the KidneyIntelX test, an AI-enabled prognostic testing platform. This test is intended to guide care management for adults with type 2 diabetes and chronic diabetic kidney disease. Key points discussed include:

  1. Overview and Purpose: Dr. Gina Mullen outlined the meeting's purpose—to evaluate medical evidence regarding the KidneyIntelX test as outlined in CMS IOM Publication 100-08, Chapter 13, Section Renalytix introduced two versions of the test, KidneyIntelX and KidneyIntelX.dkd, with the latter distinguished by a suffix and targeted for different CKD-EPI equations used in clinical practice.

  2. Expert Panel: A panel of five experts—Dr. Maryam Gondal, Dr. Jeffrey Rimmer, Dr. Mike Ross, Dr. Charles Jacobs, and Dr. Catherine Kimball—introduced themselves and confirmed no conflicts of interest. They represent diverse institutions and bring significant expertise in nephrology and family practice.

  3. Scientific and Clinical Evaluation: The panel engaged in a structured discussion based on 12 key questions addressing the scientific basis, clinical utility, and potential impact of the KidneyIntelX test. Topics included the adequacy of published evidence, the prognostic capability of the test, and its role in improving health outcomes and clinical management practices.

  4. Evidence Review and Discussion: Highlights from the discussion include:

    • Prognostic Utility: Dr. Gondal supported the test's integration into current practice, highlighting its ability to stratify patients into low, intermediate, and high-risk categories but noted that it should not be used as the sole method for predicting disease progression.
    • Clinical Impact and Utility: Dr. Ross detailed a study indicating that the test led to increased referrals and medication adjustments, suggesting improvements in clinical management but not necessarily in direct health outcomes.
    • Integration Challenges: Concerns were raised about the test’s integration into electronic health records and its dependency on specific clinical variables, which might limit its applicability across diverse health systems.
  5. Future Directions and Considerations: There was a consensus on the need for more randomized controlled trials to conclusively demonstrate the test’s efficacy in improving health outcomes. The discussion also touched upon the test's potential to reduce socioeconomic disparities in CKD management, provided its broader integration into healthcare systems.

  6. Concluding Remarks: Dr. Mullen appreciated the expert inputs, indicating that these would be considered in future deliberations and potential guidelines.

This transcript provides a comprehensive account of expert opinions and discussions regarding the KidneyIntelX test, illustrating the complexity and interdisciplinary approach required to evaluate and potentially integrate new medical technologies into clinical practice.   [ /end ChatGPT4 ]

CMS Updates ADLT Application Instructions - Just Slightly

The 2014  PAMA Medicare legislation updated the lab test pricing system as a whole.  It also created a novel test category, "ADLT," Advanced Diagnostic Laboratory Test, which has special pricing rules.

In June 2024, CMS made a minor update to its application instructions.   CMS continues to state (as per statute) the test must be "covered by Medicare."  However, CMS continues to take as little as "a paid claim" as proof of coverage.

Here's the update.  

  • CMS adds a sentence stating that while "proof" of coverage (such as a paid claim) is needed for ADLT approval, this is NOT the same as "establishment of coverage."  
  • Ongoing future coverage, if any, is dependent on ongoing future LCDs or NCDs.   
    • Creation of an ADLT code is not in itself evidence of any ongoing coverage.


The CMS web page for ADLT information is here:

This includes a list of ADLTs (about 15 since 2014), a 17-page application form, and a 30-page info document.   Both the 17-page application form and 30-page info document have the new inserted text (that ADLT creation isn't "proof" of ongoing coverage.)   Both PDFs have been updated and given a new issue date (6/2024).   Other changes are minor (like changing the issue date everywhere it appeared, to 2024).


I compared the documents with "" which offers some free online resources for PDF comparisons.


I've put the old and new documents in a cloud zip file.

click to enlarge

What's an ADLT?

The ADLT list is here:

In brief, omitting some details, an ADLT test is priced first at the test's list price (it mostly avoids a local pricing or national crosswalk process).  Thereafter the ADLT test is repriced annually at its commercial payor median rate.   

Wednesday, June 12, 2024

CMS Releases Ten Year National Health Expenditure Forecast

On June 12, 2024, CMS released national health expenditure projections which run forward to 2032.   

  • See the press release here.
    • Medicare growth rate, including the large aging population, is 7.4% for 2023-2032.  It's a bit less by 2030, when the last baby boomer will enroll, and the oldest baby boomers are dying off.
    • Medicaid costs, commercial insurance, and physician services all grow circa 5.5%.  
    • By 2032, health care spending as share of the economy will be 19.7% (20%).
  • See downloadable PDFs and charts here.
    • See in particular the PPT summary 14 pages here.
  • See the paired, open-access article at Health Affairs, Fiore et al., here.

  • CMS deck.
    Dalle 3 interprets HA Fiore et al.

CMS Closes Building: REDDIT Says "Legionnaire's"

CMS Lab Meeting Agenda

CMS has 130 total agenda items for its June 25, 2024 annual public comment meeting on new lab test pricing.   Stakeholders submitted 55 separate presentations which will be crammed in from 9 am to 5 pm on the day (6 am to  2 pm PT).    Read the five-page agenda (presenter list) here:

CMS had planned a "hybrid" meeting - on site & video - but the on site meeting is canceled.   The CMS lab website says "The CMS complex is closed due to an unforeseen issue."

Reddit Says "Legionella"

According to Reddit, the CMS site is closed due to Legionairres disease.

I don't have any independent confirmation beyond Reddit, but it's believable enough.  We know from CMS the building is closed, and for an extended time, and there aren't alot of things that will do that.   (Termites?  Carbon monoxide?)

CMS allocates presentation time 9:20-12:00 and 12:45-5;00.  This is 2h40m and 4h15m or 6h55m.   CMS gives each of 53 presenters 10 minutes, which would be 530 minutes or 8h50m.  
Six codes in the 814xx series (comprehensive genomic profiling) are under reconsideration, but don't seem to have any public commenters.   I think I heard at a meeting that if CMS got no public comment on those codes, it would drop them from reconsideration.  Not sure about that.  The codes are also currently in the national gapfill process, based on last year's CMS decisions.   

Gen Eng News: Update on TEMPUS IPO and Financials

Genetic Engineering News publishes an update on the pending IPO at TEMPUS.   It's open access here:

It's a little confusing as it intermingles NVIDIA and TEMPUS news.  The update includes amendment(s) to the initial TEMPUS IPO documents.

Here's some bullet points, pulled from GEN:

  • 11M shares at $35-37, raising ~$400M at a valuation of $6B
    • Veracyte market cap, $1.7B
    • Guardant market cap, $4B
    • Exact Sciences market cap, $8B
    • Natera market cap, $14B
  • Sales history with 7000 physicians, 200 biotech, 19/20 top pharma
  • Data and services 30% of 1Q revenue  (so that leaves 70% genomics)
  • "Tempus expects AI to grow into a third product line"
  • Last year's revenue was $532M (net loss $215M)

Chart by Chat GPT 4.

Sunday, June 9, 2024

Washington Post: Personalized Medicine via "Shadow System" and "Regulatory Vacuums" in Home Testing

Washington Post runs a story on personalized medicine, cryptic diseases and allergies, and a boom in home-based testing that skips your own primary care and specialists.   It's a story that became more multi-faceted the further I got into it.

Nobody comes off too well - not primary care doctors and specialists that are said to sidestep difficult symptoms they can't understand; the lab industry that leapfrogs over primary care to reach frustrated families with sometimes-unusual tests, or the venture capital fueling this part of the US lab industry.  The WaPo authors aren't happy with regulators as well, by describing a "shadow system" that thrives in "regulatory loopholes."

Find the article here (subscription):

This article takes at-home testing and telemedicine in different directions that were probably envisioned a few years ago.   

Written by Elizabeth Dwoskin, Daniel Gilbert, and Tatum Hunter, the article had nearly 3000 comments by Sunday evening.

AI Corner

Here's a very short (intended as non-infringing) AI summary.

  • This narrative underscores a growing trend where individuals, disillusioned by conventional medical systems and empowered by access to information and tools, take health management into their own hands. 
  • The rise of home-testing, catalyzed by the COVID-19 pandemic and driven by a mistrust of established medical authorities, has been bolstered by Silicon Valley start-ups. These companies, supported by significant venture capital, offer a wide range of tests from food sensitivities to complex health conditions, effectively creating a direct-to-consumer health test market.
  • However, this shift raises significant concerns among the medical professionals interviewed.  They doubted the accuracy and efficacy of such tests, often highlighting the potential for misdiagnosis, unnecessary interventions, and increased anxiety among patients. 
  • Regulatory bodies like the FDA are beginning to impose stricter standards on these lab-developed tests to mitigate risk and ensure reliability. 
  • Despite skepticism from parts of the medical community, the demand for personalized, at-home diagnostic tools continues to grow, highlighting a new shift in the public's approach to health management and the pursuit of autonomy in healthcare.

Monday, June 3, 2024

MolDx MACS Draft Non-MolDx LCD: Artificial Intelligence in Coronary Imaging

On Thursday May 30, 2024, there's a new LCD from all the MolDx MACs (WPS, CGS, Noridian, Palmetto), although it's not listed as a "MolDx" LCD.  It's titled:

  • "Artificial Intelligence Enabled CT Based Quantitative Coronary Topography (AI-QCT)/Coronary Plaque Analysis (AI-CPA)"

See the LCD here.  See the 2/2023 request letter here (12pp).  See the draft billing article here.

The LCD notes that it's developed in part from a topical meeting held by the MACs on May 20, 2023.  See a transcript here.

The LCD provides coverage based on patient circumstances that make the test appropriately; a set of Category III codes are provided for billing (0623T-0626T).

In a nutshell, the coverage criteria atop the LCD state:

Artificial Intelligence Enabled CT Based Quantitative Coronary Topography/Coronary Plaque Analysis (AI-QCT/AI-CPA) using coronary computed tomography angiography (CCTA)* is considered reasonable and medically necessary as a diagnostic study when:

  • The patient is eligible for CCTA*, 
  • AND
  • The patient presents with acute chest pain and no known coronary artery disease (CAD)1 and is classified as (1 or both):
    • Intermediate risk** 
    • CAD-RADS 2 and CAD-RADS 3 category on CCTA***, 
  • AND
  • Cardiac evaluation is negative or inconclusive for acute coronary syndrome (ACS).


I haven't researched how the approach used here for coverage compares to the evidence analysis and thinking that went into the Heartflow LCDs for fractional flow reserve (FFR).  See L38238 at Palmetto here.  (Therein find an extensive comments and answers document).

It looks like the comment period on the new LCD runs to July 14, 2024.


Strategic Notes

  • Letter. The 12-page letter from CLEERLY seems well written and could used as an object of study by others.
  • Time.  It took 15 months from the February request to an (almost) June LCD in the next year.
  • MACs. The "MolDx MACS" put out the same LCD, but it's not labeled MolDx in any way.  This suggests the 5 MACs are sharing policies more broadly than just in the MolDx silo.  Interesting.
  • Alternatives.  I'm not up on advanced cardiology so it's hard for me to compare the CLEERLY tech here with other trends in advanced radiology (and AI).
  • Colorado.  It's interesting the company is in Colorado, a Novitas state, but Novitas is absent from the May 2023 public meeting and this draft LCD.
  • APCs.  As Category III codes, the services will be locally priced by MAC medical directors, but nationally priced in "APCs" when billed in a hospital setting.

If of interest, Chat GPT reads the Request, the CAC transcript, and the draft LCD.

AI writes:

To provide an overview and analysis of the materials you've provided regarding the coverage of advanced cardiac testing and the inclusion of AI technologies in Medicare, let's discuss the evolution of coverage for these technologies, focusing on the development and implications of Local Coverage Determinations (LCDs) for AI-enhanced quantitative coronary computed tomography angiography (AI-QCT).

Overview of Key Documents

  1. Request Letter from Cleerly Labs:

    • Cleerly Labs submitted a request for a new LCD to include AI-QCT for patients under evaluation for coronary artery disease (CAD). This request emphasized the limitations of traditional diagnostic tools like coronary angiograms and stress tests, which focus more on stenosis rather than the underlying atherosclerotic disease process. Cleerly Labs argues for the superiority of AI-QCT in providing detailed and actionable diagnostic information, potentially leading to more personalized and effective patient management.
  2. Medicare-Sponsored Conference Transcript:

    • A Contractor Advisory Committee (CAC) meeting discussed the evidence and utility of non-invasive technology for coronary artery plaque analysis. This meeting emphasized the importance of robust scientific evidence in LCD development as mandated by the 21st Century Cures Act. The discussion highlighted the potential of AI-QCT to provide comprehensive assessments of plaque burden and composition, which are crucial for effective CAD management. Various experts expressed support for the inclusion of AI-QCT in routine clinical practice, pending validation of its clinical utility and impact on patient outcomes.
  3. Draft LCD for Public Comment:

    • The draft LCD reflects the considerations and recommendations discussed during the CAC meeting. It outlines specific indications where AI-QCT could be considered medically necessary and reasonable, emphasizing the need for detailed documentation of medical necessity in patient records. The draft also lists various limitations and scenarios where AI-QCT would not be appropriate, ensuring that the use of this technology is well-regulated and targeted.

Analysis and Implications

  • Scientific and Clinical Validation:

    • The inclusion of AI-QCT in Medicare coverage is strongly supported by evidence of its diagnostic accuracy and potential to improve clinical outcomes. The technology allows for a more precise assessment of atherosclerotic plaque, which is crucial for determining the risk of heart attacks and guiding treatment decisions.
  • Policy and Healthcare Impact:

    • The adoption of AI-QCT could lead to significant changes in how CAD is diagnosed and managed, potentially reducing the reliance on invasive procedures and enhancing personalized treatment plans. The coverage of AI-QCT under Medicare would likely increase access to this advanced diagnostic tool, promoting its integration into standard clinical practice.
  • Stakeholder Engagement and Feedback:

    • The process of developing and refining the LCD for AI-QCT involves extensive stakeholder engagement, including feedback from medical experts, industry representatives, and public comments. This collaborative approach helps ensure that the final policy is balanced, evidence-based, and responsive to the needs of both providers and patients.
  • Future Directions:

    • As AI technologies continue to evolve, ongoing research and data collection will be essential to assess their long-term impact on health outcomes and cost-effectiveness. Medicare policies may need to be periodically updated to reflect new evidence and technological advancements.


The evolution of Medicare coverage for AI-enhanced cardiac testing reflects a broader shift towards more precise and personalized healthcare. The inclusion of AI-QCT in the Medicare program, supported by robust evidence and expert consensus, represents a significant step forward in the management of CAD. It highlights the potential of advanced technologies to transform clinical practice and improve patient outcomes in the context of an aging population and rising healthcare costs.

You remark that in the conference transcript, experts were supporting "pending clinical utility validation and impact on patient outcomes." Those seem like two pretty big warnings or caveats. Can you provide more context?

AI writes:

Indeed, the conference transcript does highlight important caveats regarding the clinical utility and impact on patient outcomes of AI-QCT. These concerns are central to determining whether this technology should be widely adopted and covered under Medicare. Here's a deeper look into these aspects based on the discussions captured in the transcript:

Clinical Utility Validation

  1. Definition and Consistency:

    • There was significant discussion about the precise definition of AI-QCT and how it is employed in clinical settings. The term AI-QCT has been used variably, referring to both "Artificial Intelligence-enabled Quantitative Coronary Computed Tomography" and "Atherosclerosis Imaging-Quantitative Computed Tomography." This indicates the necessity for a standardized definition to ensure consistency in its application and evaluation.
  2. Technological Versatility and Accuracy:

    • AI-QCT's ability to analyze plaque composition and burden is recognized, yet the utility hinges on the accuracy and reliability of these analyses. Experts debated the extent to which AI-QCT can replace or augment existing imaging techniques like IVUS (Intravascular Ultrasound) and how it might influence clinical decision-making processes.

Impact on Patient Outcomes

  1. Evidence of Effectiveness:

    • A significant part of the discussion focused on the need for robust evidence demonstrating that AI-QCT not only accurately assesses coronary artery disease but also improves patient outcomes. This includes whether AI-QCT's use in clinical practice leads to better management decisions, reduced rates of cardiac events, or other measurable health benefits.
  2. Comparative Advantages:

    • The panelists explored how AI-QCT compares to traditional methods in terms of outcomes. There's a consideration of whether the technology provides additional benefits over existing diagnostic tools, such as more precise risk stratification or avoidance of unnecessary invasive procedures.

Concerns Raised

  1. Integration into Clinical Guidelines:

    • The discussions highlighted a cautious approach to integrating AI-QCT into clinical guidelines without sufficient evidence. While AI-QCT shows promise, its adoption into routine clinical practice and guidelines should be based on clear proof that it leads to better clinical outcomes.
  2. Research and Validation Needs:

    • There's an emphasis on the need for ongoing research to validate the clinical utility of AI-QCT. This includes randomized controlled trials, longitudinal studies, and real-world evidence that can provide a clearer picture of how AI-QCT influences treatment strategies and patient health over time.
  3. Regulatory and Ethical Considerations:

    • The regulatory approval process for AI-QCT and its ethical use were also discussed, emphasizing the importance of ensuring that the technology is both safe and effective before widespread implementation.


The expert panel's discussion reflects a prudent and evidence-based approach to the adoption of new medical technologies under Medicare. While there is enthusiasm about the potential benefits of AI-QCT, the panelists advocate for a careful validation of its clinical utility and a thorough assessment of its impact on patient outcomes before it is recommended for broad use. This approach ensures that new technologies are not only innovative but also beneficial and safe for patients, aligning with the overarching goal of improving healthcare quality and efficacy.

Saturday, June 1, 2024

CMS Finalizes 130 New Lab CPT Codes for June 25, 2024 Pricing Meeting

In April, CMS set the June 25, 2024 date for this year's public comment meeting on how CMS should price new lab codes.  (Here).  While the public comments, on a CMS powerpoint template, were due May 30, that's about the same day that CMS finalized the agenda of codes, by picking up late-breaking codes from the May 2024 AMA CPT meeting.

Find the code list as a zip file at this CMS page.  Scroll down for meeting announcements and agendas.

The agenda opens with about a dozen reconsidered codes (appealed from last year's pricing).  There follow numbered PLA codes from 420U to 474U.  Not-yet-numbered PLA codes run further, from position 83 to 127.

Noteworthy: Revised Germline Codes; Profusion of New Alzheimer Codes

Among the 130 agenda items, I'd highlight two groups.

Germline Cancer Risk

81432, 18435, 81437 are revisions of three germline cancer risk codes (loosely, one for breast-ovarian, one for Lynch, one for neuroendocrine).   81432 is a decade-old code for heredtiary breast cancer, traditionally paired with 81433 for dup-del analysis.   The code number is struck down from 10 or more to 5 or more (which may block code-stacking of 6 to 9 codes).   The gene list is struck out (it used to be ten genes long including BRCA1-BRCA-2).   If this is priced in the 5-gene range and labs don't bill BRCA inside it, but on another day, it could create a bonus for doing BRCA on a different day (about +$1800).  

81435 continues to say "For Lynch syndrome," but is also rewritten to require only 5 or more genes and the gene list is struck out.   

I don't know if 81433 (dup del) and 81436 (dup del) are deleted because CMS lists only new or modified codes, and does not flag deletions which are not part of the new code pricing meeting.

81437 is a special code for 5 or more genes, neuroendocrine related panel (5 or more genes, no code list).  

Alzheimer Bonanza

Lotsa new Alzheimer codes.

Currently, there's a PLA code for the Fujirebio CSF test (FDA), a Quest blood amyloid test, and a MAAA test that combines ApoE and amyloid.

More neuro codes for 2024/2025:

  1. 0443U, NF light chain
  2. 0445U, Amyloid + tau
  3. 82XX0, Amyloid 40
  4. 82XX1, Amyloid 42
  5. 8X3X0, Tau, phospho (per each phospho position)
  6. 8X3XX, tau, total
  7. XX40U, Amyloid + tau
  8. 83XX0, NF light chain
  9. XX62U, Tau phospho217