I asked Chat GPT to try a re write for clarity, while preserving each LCD's coverage criteria.
Here's the original blog June 12 on the two new LCDs.
https://www.discoveriesinhealthpolicy.com/2025/06/moldx-releases-two-cardiac-genetic-lcds.html
##
🔹 LCD L39950 – Hereditary Transthyretin Amyloidosis (hATTR)
Rewritten Coverage Criteria:
Molecular genetic testing for hereditary transthyretin amyloidosis (hATTR) is covered when all the following criteria are met:
-
Patient Presentation
The patient meets either of the following:
-
Has a clinical diagnosis of ATTR (wild-type or hereditary), or
-
Has cardiac signs or symptoms suggestive of ATTR cardiomyopathy (e.g., unexplained heart failure, arrhythmias),
and at least one of the following:
-
African ancestry
-
A first-degree relative with a confirmed hATTR diagnosis
-
Clinical features aligned with published expert consensus (e.g., bilateral carpal tunnel syndrome, lumbar spinal stenosis)
-
Neuropathy Variant
Alternatively, if the patient presents with progressive sensorimotor and/or autonomic neuropathy, then either of the following must also apply:
-
Test Utilization and Counseling
-
The patient has received pre-test counseling about the implications of the test.
-
The test results will be used to inform clinical management, such as therapy initiation.
-
Test Design and Validity
-
The test includes only the minimum validated gene content required for clinical decision-making (e.g., TTR) or a known familial variant.
-
The test does not include unvalidated or non-actionable genes that could mislead care.
-
The test must have passed MolDX Technical Assessment (TA) confirming its clinical validity and utility.
🔹 LCD L39946 – Heritable Thoracic Aortic Disease (HTAD)
Rewritten Coverage Criteria:
Genetic testing for Heritable Thoracic Aortic Disease (HTAD) is covered when all the following criteria are satisfied:
-
Clinical Indication
The patient has a diagnosis of aortic root or ascending aortic dilation, aneurysm, or dissection (per national guidelines),
and at least one of the following applies:
-
Onset or presentation before age 60
-
Syndromic features suggestive of a connective tissue disorder (e.g., Marfan syndrome, Loeys-Dietz, vascular Ehlers-Danlos)
-
A first- or second-degree relative with:
-
Thoracic aortic disease, or
-
Aneurysms (peripheral or intracranial), or
-
Unexplained sudden death at a relatively young age
-
Test Design and Content
-
The patient has received genetic counseling on the risks and implications of testing.
-
The test includes only clinically validated genes with definitive or well-established evidence per ACC/AHA and ClinGen guidelines.
-
The panel must exclude genes of uncertain significance or poor validation that might lead to inappropriate clinical decisions.
-
Regulatory Requirements
-
The test has passed MolDX Technical Assessment (TA)
-
The test is compliant with related MolDX policies, such as restrictions on repeat germline testing (L38353)
####
#
I then asked Chat GPT to provide constructive criticism for the LCD author.
##
Yes — both LCDs (L39950 and L39946) are generally well-aligned with clinical guidelines and thoughtfully written, but they do suffer from some recurring issues that may hinder clarity, consistent application, and efficient use by labs, clinicians, and payers. Here's a structured critique:
⚠️ Common Issues Across Both LCDs
1. Overly Verbose and Redundant Language
Both LCDs repeat ideas in multiple places, especially in the coverage sections. For example:
The need for counseling, minimum gene content, and test utility appears multiple times, sometimes with slightly different phrasing.
They mix clinical eligibility, test design requirements, and regulatory compliance into a single list, when they could be cleanly separated.
Impact: Slows comprehension and increases the risk that clinicians or test developers misinterpret which criteria are patient-facing vs lab-facing.
2. Vague Terms Without Operational Definitions
Both LCDs use terms like:
"Features consistent with expert consensus"
"Genes with definitive or well-established evidence"
"Properly validated" or "unclear clinical utility"
These phrases are not anchored to a specific source, leaving ambiguity:
Impact: Creates interpretive flexibility that could lead to coverage disputes or inconsistent TA approvals.
3. Lack of Clarity About Single-Gene Testing vs Panel Testing
While both LCDs permit single-variant testing when a familial mutation is known, they don’t:
Clarify if this applies to duo/trio testing or reflex testing.
Clarify if limited panels (e.g. just TTR, or just FBN1/ACTA2) are acceptable for patients without known familial variants.
Impact: Labs may be uncertain whether they can offer targeted panels unless a family mutation is already known, potentially discouraging cost-effective testing.
4. Limited Guidance on Cascade or Family Testing
Both LCDs imply support for familial risk assessment, but do not clearly state:
This is particularly relevant in L39946 (HTAD), where early detection in relatives can be life-saving.
Impact: May deter cascade testing or lead to unnecessary denials.
5. Technical Assessment (TA) Language Is Ambiguous
Both LCDs require that a test:
“has successfully completed a technical assessment (TA)...”
However, they don’t:
Define what the TA evaluates (analytical validity, clinical validity, or both?)
Link to a checklist or reference document explaining TA criteria
Distinguish between new and grandfathered tests
Impact: Adds friction for test developers seeking coverage, particularly new market entrants.
🔍 LCD-Specific Observations
📄 L39950 (hATTR)
The clinical phenotypes of hATTR-CM and hATTR-PN are mixed together in one long bulleted list. It would be clearer to break them into two distinct diagnostic pathways.
There's an overemphasis on detailed drug mechanisms and trials (tafamidis, acoramidis, RNAi agents). This may be more appropriate in a background article, not an LCD.
📄 L39946 (HTAD)
The LCD refers to ACC/AHA and ClinGen guidelines, but doesn’t specify a minimum list of genes (though it hints at 11 validated genes). A table of “required core genes” would enhance usability.
While it’s based on high-quality data, the gene–phenotype correlations are buried in long paragraphs that make it hard to parse actionable coverage implications.
✅ What They Do Well
Align with current guidelines (especially 2022 ACC/AHA for aortopathies and hATTR diagnosis).
Emphasize clinical utility, not just analytic validity — a good signal for payers and clinicians.
Include appropriate flexibility for new evidence or guideline changes.
🛠️ Suggested Fixes
Help the reader - Streamline coverage criteria into 3 buckets: (1) Patient eligibility, (2) Test design, (3) Compliance.
Provide an appendix or hyperlink to required gene lists (ClinGen, ACC/AHA)
Clarify whether family member testing is covered when a proband has a known mutation
Offer TA submission guidance in a separate MolDX companion article
Would you like a suggested redraft of the coverage criteria section using these structural improvements?
