MolDx Changes Its Mind (R.A. Tests)

 MolDx converted a draft non coverage LCD on RA GEP tests, to a limited coverage policy.

Blog here:

https://www.discoveriesinhealthpolicy.com/2023/08/busy-day-at-moldx-new-draft-lcd-for.html

The key decision rationale is in the Q&A document A59519 here:

During the comment period, we received many letters supporting a coverage policy for Molecular Biomarker Testing to Guide Targeted Therapy Selection in Rheumatoid Arthritis. 

• Of note, we have acknowledged the need for testing to help physicians and patients avoid a trial-and-error based approach to care. 
• However, we have also acknowledged the limitations of the currently available clinical and laboratory tools to support this effort, as noted in the draft policy that evaluated the data available in the published literature. 
• For example, the molecular biomarker tests had not adequately demonstrated that they can reliably identify responders and/or non-responders to a particular class of therapies beyond what is already known at baseline (i.e. uninformed by the test), given that 
• (a) the overall prevalence of non-response to TNF inhibitors (TNFi), a mainstay of therapy, is so high in this population (~60-70%) and 
• (b) multiple clinical and laboratory data also provide some information regarding the likelihood of response to these therapies. 
• Since then, additional data/newer publications addressing these issues have been published and were provided during the comment period. The policy was therefore modified as an outgrowth of the comments received.

We appreciate the many comments received in support of a coverage policy. We agree that despite the many limitations of predictive biomarker tests, a review of the evidence supports their limited use given their demonstrated validity and utility. 

• Specifically, when a non-response (NR) signature is obtained by the molecular signature response classifier (MSRC), nearly 90% of those patients will prove to not clinically respond to TNFi therapies using multiple validated disease response criteria including the ACR50 and CDAI. 
• For these patients, a change in management would ultimately serve to avoid time on an unnecessary therapy and shorten the time to an appropriate therapy.

However, we also highlight some important points about the evidence regarding these tests to-date: 

1. They have only demonstrated their utility in a subset of the RA population (only half of the TNFi non-responders), 

2. They are only informative about one particular class of therapies (TNFis), 

3. The use of this testing does not guarantee improved disease activity and/or remission outcomes (because many of these patients will also not initially respond to the alternate therapies) and 

4. It is not appropriate that patients continue classes of therapy that they have already failed due to payor preference and/or lack of consideration of national guidelines (that support switching over cycling). 

As a result, it is likely that future tests will add substantially more benefit than the current services offered and reviewed by this contractor, and we will continue to monitor new evidence as it becomes available.

###
AI CORNER
We ask ChatGPT 3.5 about the change of heart shown above.

Regarding specifically the R.A. or rheumatoid arthritis test, MolDx took the unusual (but not impossible) step of converting a draft non coverage policy to a final coverage policy.  They explained their rational in section that we will paste below.   Discuss whether the change of mind was difficult for the author, and what his ongoing reservations are.

The decision by MolDx to convert a draft non-coverage policy for the Molecular Biomarker Testing to Guide Targeted Therapy Selection in Rheumatoid Arthritis to a final coverage policy appears to have been a nuanced and considered process. The rationale provided suggests that the change of mind was driven by a combination of factors, including the receipt of numerous letters supporting coverage during the comment period and the emergence of additional data and newer publications addressing the limitations raised in the initial draft policy.

The change of mind may not have been easy for the author or the organization, as it required reevaluating the evidence, acknowledging new information, and potentially reassessing their initial reservations. The author's ongoing reservations are outlined in the provided section. These reservations seem to revolve around the following points:

• Subset of RA Population: The author notes that the molecular biomarker tests have demonstrated utility only in a subset of the rheumatoid arthritis (RA) population, specifically among non-responders to TNF inhibitors (TNFis). This suggests that the tests might not be universally applicable to all RA patients.
• Specific Class of Therapies: The tests are informative about a particular class of therapies, namely TNFis. This implies that the coverage policy change is not a blanket endorsement for all treatment options but is focused on a specific subset of treatments.
• Uncertain Improvement in Outcomes: The author emphasizes that while the tests can help identify patients who are unlikely to respond to TNFis, their use does not guarantee improved disease activity or remission outcomes. This underscores the complexities of RA treatment and the potential limitations of relying solely on these tests for decision-making.
• Consideration of National Guidelines: The author points out that patients should not continue therapies they have already failed due to payer preference or the lack of consideration of national guidelines. This raises a broader issue of treatment continuity and adherence to established medical guidelines.
• Future Developments: The author acknowledges the potential for future tests to offer greater benefits than the current ones. This implies that the current coverage policy is based on the available evidence and may evolve as more data become available.

In conclusion, the change from a draft non-coverage policy to a final coverage policy for Molecular Biomarker Testing to Guide Targeted Therapy Selection in Rheumatoid Arthritis suggests a careful consideration of the evidence and feedback received during the comment period. The author's ongoing reservations highlight the complexities of implementing such tests in clinical practice and the need for continuous monitoring of emerging evidence to ensure the best possible patient outcomes.