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.
AI CORNER

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.

Conclusion

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.


ME
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.

Conclusion

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.