Google LM Reads my "AI Teaching Guide" to DCIS LCD

I uploaded the new MolDx DCIS LCD to Chat GPT for a teaching analysis.

Here, below, I upload that teaching analysis (with the LCD) to Google LM for a summary and an audio version.

See the original teaching case by Chat GPT here.  Hear a 17 minute podcast by Google here.  

###  Google LM Below

Briefing Document: MolDx Non-Coverage Policy for DCIS Risk Stratification Molecular Tests

Date: July 18, 2025

To: CEOs and Chief Science Officers at Molecular Diagnostic Startups (Series B/C Stage)

From: Bruce Quinn MD PhD, Expert on Health Reform, Innovation, and Medicare Policy

Subject: Key Lessons from MolDx's Non-Coverage Policy on DCIS Breast Cancer Molecular Tests (DCISionRT and Oncotype DCIS Score)

Executive Summary

MolDx has issued a non-coverage Local Coverage Determination (LCD) for molecular and proteomic tests designed to risk-stratify Ductal Carcinoma in situ (DCIS) patients, specifically those aiming to identify "sufficiently low-risk" individuals who may safely forego adjuvant radiation therapy (RT). This policy, DL40142, is a critical blueprint for any company developing molecular diagnostics seeking Medicare coverage. MolDx's extensive review found the data supporting current DCIS tests, such as DCISionRT and Oncotype DCIS Score, to be consistently lacking in statistical power, clear clinical utility, and superiority over existing clinicopathologic tools. 

This document provides a detailed analysis of MolDx's rationale, highlighting their stringent evidentiary thresholds and expectations for future test development.

I. MolDx's Core Expectations and Evidentiary Thresholds for Molecular Diagnostics

MolDx's non-coverage decision for DCIS risk stratification tests provides unprecedented insight into their review process. Their primary objective is to ensure that new molecular diagnostics offer meaningful, validated improvement in patient care, particularly within the Medicare population.

A. Direct Comparison to Existing Tools: Superiority, Not Just "Added Insight"

• MolDx explicitly requires new molecular diagnostics to demonstrate clear superiority over established clinicopathologic tools, such as the MSKCC nomogram or Van Nuys Prognostic Index (VNPI). "Adds another data point" is insufficient.
• 
  
• MolDx Criticism: "MolDx criticized DCISionRT and Oncotype DCIS Score for failing to show they outperform these established models." In one study comparing MSKCC to Oncotype DCIS Score, a "92% concordance" was observed, indicating the molecular test did not meaningfully differentiate risk groups.
• Implication for Startups: "You must benchmark your test directly against the current standard of care — and show where and why you are better. 'Adds another data point' is not sufficient." Your analytical and clinical validation must isolate the molecular contribution and demonstrate its independent predictive power.

B. Statistically Robust and Replicated Data

A recurring theme in MolDx's critique is the inadequacy of sample sizes and the inconsistency of results, especially in low-risk cohorts.

• MolDx Criticism: "MolDx repeatedly criticizes the small sample sizes and inconsistent results in the low-risk cohorts for these tests." For DCISionRT, "single-digit recurrence events (e.g., 4 vs. 12 recurrences)" in low-risk groups led to "wide confidence intervals and inconclusive findings (p > 0.05)."
• MolDx Criticism: MolDx noted that "newer cutoffs (e.g., DS2 = 2.8) were derived from re-analysis of old data without sufficient external validation. Studies lacked independent validation cohorts, leaving questions of reproducibility."
• Implication for Startups: "Design your validation studies for statistical power within the subpopulations that will drive clinical decisions. Ensure external validation in independent cohorts is complete before seeking coverage." This includes thorough analysis and concordance studies if multiple cohorts are used.

C. Proven Clinical Utility Tied to Meaningful Outcomes

MolDx requires evidence that the test changes management in a way that affects health outcomes, especially in Medicare populations. A test's impact on radiation decisions is insufficient if the benefit is statistically trivial.

• MolDx Criticism: "DCISionRT’s 'low-risk' patients still showed relative risk reduction with RT; MolDx noted that the observed benefit (~5%) wasn’t statistically conclusive due to small numbers, and therefore claims about safely omitting RT are not substantiated." The Contractor Advisory Committee (CAC) generally agreed that "at a 5% absolute risk reduction of IBTR (or less) confers no significant clinical impact from RT therapy."
• Implication for Startups: "You need robust clinical utility studies showing how your test leads to safer or more efficient care, not just changes in provider behavior." This means demonstrating that the test enables identification of a patient population for whom there is no reasonable benefit from RT, defined by MolDx as an "absolute reduction in recurrence risk from RT of ≤5%."

D. Clear Definition of "Low Risk" Tied to Clinical Impact

MolDx demands a precise, defensible definition of "low risk" that directly correlates with a quantifiable clinical impact.

• MolDx Criticism: "MolDx criticized studies for inconsistent definitions of 'low risk,' varied inclusion of factors like age or tumor size, and inconsistent recurrence rates across cohorts. This muddles the claim that molecular tests are identifying patients who can safely avoid RT."
• Implication for Startups: "You must define and defend your clinical risk thresholds in terms aligned with clinical practice impact and Medicare's benefit-to-risk frameworks." This standardizes the definition, potentially based on an expected 10-year Ipsilateral Breast Tumor Recurrence (IBTR) rate of approximately 10% where RT offers minimal benefit (absolute risk reduction of ≤5%).

E. "Rhetorical Proof" Is Not Scientific Proof

MolDx rejects the notion that a test's value stems primarily from its ability to reassure patients or physicians.

• MolDx Criticism: "MolDx called out the fallacy of tests being used merely to persuade patients or doctors ('rhetorical proof') rather than meeting a robust evidentiary standard." Some subject matter experts (SMEs) at the CAC championed DCISionRT because it "reassures patients about skipping RT," but MolDx found this insufficient without statistically sound data.
• Implication for Startups: "Avoid leaning on 'decision-support narratives' unless backed by robust data. MolDx wants evidence of superior performance, not convenience in shared decision-making."

F. Multi-Factor Models Must Show Incremental Value of Molecular Component

If a test combines molecular and clinical factors, the molecular contribution must be demonstrably valuable beyond the clinical data alone.

• MolDx Criticism: "MolDx criticized both DCISionRT and Oncotype DCIS for including overlapping clinicopathologic factors already in nomograms — questioning whether the biomarkers provide independent predictive power."
• Implication for Startups: "Your analytical and clinical validation must isolate the molecular contribution and demonstrate why it matters."

G. Medicare-Centric Evidence is Required

Validation cohorts must reflect the demographic and clinical context of Medicare beneficiaries, who are the primary population for DCIS.

• MolDx Criticism: MolDx repeatedly emphasizes "the need for Medicare-relevant data, especially in older populations, which are both the predominant DCIS cohort and the primary Medicare demographic."
• Implication for Startups: "Ensure your validation cohorts reflect the age, health status, and clinical context of Medicare beneficiaries."

II. The Critical Impact of Rare Event Rates on Study Design

One of the most significant statistical lessons from this MolDx LCD, and often overlooked by startup diagnostic companies, is the profound impact of rare event rates on study design and evidentiary thresholds.

A. The Challenge of Low Event Rates in DCIS

• In DCIS, the clinical question often revolves around identifying patients with a very low risk of recurrence (typically around 5% over 10 years). This means that "out of 100 patients, only five or fewer will experience a recurrence."
• 
  
• Why Rare Events Demand Larger N: This low event rate "creates a major statistical hurdle." "In any cohort of 100 patients, observing only 5 events leaves your study underpowered to detect meaningful differences between groups." "Small absolute numbers (4 vs. 6 recurrences, or 5 vs. 7) generate wide confidence intervals and increase the risk of false negative or non-significant findings even if a real effect exists."

B. MolDx's Specific Criticism Regarding Underpowered Studies

• MolDx repeatedly highlighted that the published studies on DCISionRT and Oncotype DCIS were "consistently underpowered for their intended purpose."
• 
  
• MolDx Criticism: In low-risk groups, "there were often only single-digit numbers of recurrences." Some studies "split these few events across treatment arms (e.g., 4 vs. 12 recurrences with or without RT), leading to non-significant p-values and wide 95% confidence intervals."
• MolDx Criticism: "MolDx specifically rejected claims that the tests could identify populations with no benefit from RT, pointing out that such conclusions were built on insufficient event counts and underpowered analyses." A "1% or 2% difference in recurrence might look reassuring to clinicians, but MolDx will not consider such findings statistically reliable without appropriate sample sizes."

C. Implications for Startups Developing Tests for Rare Outcomes

• Mandatory Large Sample Sizes: If your test predicts rare events (≤ 5% incidence), "you must design studies accordingly." "Sample sizes must be large enough to accumulate a statistically meaningful number of events in each risk category and treatment arm." This means "hundreds, not dozens, of events may be necessary."
• Careful Retrospective Data Use: If using existing retrospective datasets, "ensure your sample size planning considers event rates, not just patient counts."
• The Illusion of Precision: "When event rates are low, small N studies are misleading. They create the illusion of precision without the statistical power to support regulatory or payer coverage decisions. MolDx expects mature companies to understand this."
• 
  

III. Summary and Path Forward for Molecular Diagnostic Startups

MolDx's non-coverage policy for DCIS molecular tests serves as a clear "transparent playbook" for diagnostic companies. To achieve reimbursement success and meet Medicare's "reasonable and necessary" standards, startups must:

1. Demonstrate Superiority: Prove your test is more accurate and clinically useful than existing, widely available clinicopathologic tools (e.g., nomograms).
2. Ensure Statistical Rigor: Design studies with sufficient statistical power, especially when targeting rare events or identifying very low-risk populations. This requires large sample sizes and external validation in independent, representative cohorts (including Medicare beneficiaries).
3. Prove Clinical Utility: Show that your test leads to meaningful changes in patient outcomes or significant improvements in care efficiency, not just changes in physician behavior or "rhetorical proof." Define "low-risk" explicitly as patients for whom the absolute risk reduction from RT is ≤5%.
4. Isolate Molecular Value: If combining factors, clearly demonstrate the incremental value of the molecular component beyond clinical data alone.
5. Focus on Medicare Relevance: Ensure your evidence is relevant to the Medicare population, particularly older patients.

MolDx is open to covering biomarker tests for DCIS risk stratification "should evidence be further developed to meet reasonable and necessary standards." However, this requires a fundamental shift in how studies are designed and how evidence is presented, moving beyond small, underpowered analyses and anecdotal "decision support" claims to robust, statistically sound demonstrations of superior clinical utility and meaningful patient impact.

NotebookLM can be inaccurate; please double check its responses.

Lewis Black Assesses the New, MolDx Transplant LCD

 LEWIS BLACK-STYLE RANT:

LET’S TALK ABOUT CLARITY.

On one hand, we’ve got CMS MolDx writing. 

It’s like they got a bunch of lawyers drunk on Ambien, told them to write something “accessible,” and then had a raccoon edit it with a thesaurus duct-taped to its paws.

You want to know if your transplant test is covered? Well, sit down, my friend. You’re going on a journey through bureaucratic hell. We’re going to talk about Analytical Validity, Clinical Validity, and Banff Classification, which, despite sounding like something from Game of Thrones, is apparently about kidney tissue. They write 5 paragraphs to say: “Don’t run unnecessary tests, and don’t be stupid about biopsies.” But instead of just saying that, they built a linguistic obstacle course out of semicolons, dependent clauses, and tortured passive voice.

Now. THE AI VERSION.

Oh, this one is so clear it’s actually insulting. It’s so clear I’m suspicious it might be plotting something. It says:
▶ Here’s when you do the test if the patient looks sick.
▶ Here’s when you do the test if they don’t look sick.
▶ Here’s how often you’re allowed.
▶ One test at a time, unless you’ve got a real reason.
▶ Biopsies are bad unless necessary.

It even put the words into a TABLE. Because sometimes people need a chart. Otherwise, your brain is going to do the Lewis Black Face™ halfway through the MolDx paragraph that starts “For purposes of this policy the following definitions are used,” wondering WHEN THE HELL THE ACTUAL POLICY IS GOING TO START.

The AI says, “I’m going to lay it out for you like you’re a human being. Not a government contractor trapped in a Kafka novel.”

WHICH IS CLEARER?

The AI rewrite is clearer.
It’s not even a contest. The CMS MolDx version is written in Legal-ese for Lawyers Who Like To Hear Themselves Talk. The AI version is written for clinicians who are trying to do their jobs without first passing a reading comprehension exam sponsored by Dante’s Inferno.

BUT HERE’S THE REAL JOKE:
MolDx will never write it this way. Why? Because the moment CMS writes something clear, someone sues them.
And clarity — clarity gets people killed in government work.

Thank you. Good night.

AI Explains MolDx Transplant LCD

Below, I give Chat GPT AI reading of the rules first.   Then, I give the actual L40058 MolDx rules

Here is the original blog about the new LCD.

An AI version of Lewis Black the comedian compares the AI version below and the Original version deeper below - here.

###

Please explain all the rules for transplant test coverage in simpler and  clearer form.   To the extent possible, distinguish rules for "for cause" testing versus "surveillance" testing. 

###

Here’s a simplified and clearer explanation of the Medicare transplant test coverage rules, broken down into two categories: “For-Cause” Testing vs. “Surveillance” Testing. I'll also summarize the general rules first.

---

General Rules for All Transplant Molecular Tests (All Organs)

A molecular test to evaluate transplant rejection can be covered if all the following are true:

1. Purpose of the Test:
   The test must provide useful information about:

   • Whether the patient has acute rejection (AR), or

   • Whether the rejection is cellular (ACR/TCMR) or antibody-mediated (AMR).

2. How the Test Helps Clinicians:
   The test is used to:

   • Help decide if immunosuppressive treatment is working, instead of doing a biopsy.

   • Help rule out rejection if rejection is suspected but not certain, to help decide whether a biopsy is needed.

   • Help evaluate risk of rejection when there are concerning signs but no biopsy yet.

   • Help clarify confusing biopsy results.

   • Help detect subclinical rejection (silent, no symptoms) on a scheduled surveillance plan.

3. The Test Must Be Proven:

   • Analytical validity (AV): The test works reliably.

   • Clinical validity (CV): Studies show the test is useful in real patients.

   • The test must be comparable to or better than other similar tests already covered.

4. The Test is Approved for This Purpose:

   • The test has been reviewed and approved by MolDX for this specific use.

5. Limits on Frequency:

   • You can’t run multiple molecular tests at the same visit.

   • A combined panel test (multiple assays) is OK if proven superior to using them individually.

6. Non-Invasive Preferred Over Biopsy:

   • The test is preferred if a biopsy is risky or unnecessary.

   • Both biopsy and molecular test together is rarely allowed, only in emergencies and only if both give different and useful information.

---

FOR-CAUSE TESTING (When Rejection is Suspected – Patient Has Symptoms)

Allowed if:

• The test helps decide whether to do a biopsy or not.

• The test helps clarify uncertain biopsy results.

• The test helps assess whether treatment is working.

Example:
The patient has signs of rejection (labs, imaging, symptoms) but biopsy might be risky. A molecular test might help rule out rejection without needing the biopsy.

---

SURVEILLANCE TESTING (Routine Testing – Patient Has No Symptoms)

Allowed if:

• There is peer-reviewed evidence or guidelines showing that this surveillance testing improves care.

• The testing follows a validated schedule for the specific organ.

Limits on Frequency in the First Year After Transplant:

• Kidney: up to 4 tests per year

• Heart: up to 12 tests per year

• Lung: up to 12 tests per year

After the First Year:

• No more than 2 tests per year for surveillance.

---

Summary of Key Differences: For-Cause vs. Surveillance

Aspect	For-Cause Testing	Surveillance Testing
When Used	Patient shows signs of rejection	Routine schedule, no symptoms present
Purpose	Rule in/out rejection, guide biopsy/treatment	Early detection of silent rejection
Biopsy Role	Helps decide if biopsy needed or clarifies biopsy	Aimed to avoid unnecessary biopsies
Frequency Limits	Based on medical need, case-by-case	Strict limits by organ type (see above)
Evidence Requirement	Proven helpful in symptomatic patients	Must follow validated schedule and show benefit
Coverage Conditions	Covered if criteria met	Covered if criteria met and within limits

---

If you'd like, I can create a visual flowchart or summary table to make this even clearer. Let me know!

###

###

Original MOLDX Text:

Coverage Indications, Limitations, and/or Medical Necessity

DEFINITIONS

For purposes of this policy the following definitions are used:

• AR – Acute Rejection
• ACR – Acute Cellular Rejection (also referred to as TCMR: T-cell mediated rejection)
• AMR – Antibody-Mediated Rejection
• AV – Analytical Validity
• CV – Clinical Validity
• cfDNA – Donor-Derived Cell-Free DNA
• GEP – Gene Expression Profiling
• SubAR - Subclinical acute rejection
• For-Cause – patient has clinical signs or symptoms of organ injury/rejection.
• Surveillance (Protocol) – patient is asymptomatic; no clinical signs or symptoms of organ injury/rejection.

This Medicare contractor will provide limited coverage for molecular diagnostic tests used in the evaluation and management of patients who have undergone solid organ transplantation. These tests can inform decision making along with standard clinical assessments in their evaluation of organ injury for active rejection (AR). These tests may be ordered by qualified physicians or providers operating within their scope of practice considering the diagnosis of AR, helping to rule in or out this condition and when assessing the need for or results of a diagnostic biopsy. They should be considered along with other clinical evaluations and results and may be particularly useful in patients with significant contraindications to invasive procedures.

Molecular diagnostic tests that assess a transplanted allograft for rejection status are covered when ALL of the following criteria are met:

• The test must provide information about at least one of the two following clinical status determinations:
• AR status
• Cellular or Antibody-mediated rejection (ACR or AMR) status
• The intended use of the test must be to inform clinical decision making as per the following:
• To assist in the evaluation of adequacy of immunosuppression or response to treatment, wherein a non-invasive or minimally invasive test can be used in lieu of a tissue biopsy, OR
• As a rule-out test for AR in validated populations of patients with clinical suspicion of rejection with a non-invasive or minimally invasive test to make a clinical decision regarding obtaining a biopsy, OR
• For further evaluation of allograft status for the probability of allograft rejection after a physician-assessed pretest review of clinical and biological factors concerning for risk of rejection, OR
• To assess rejection status in patients that have received a biopsy, but the biopsy results are inconclusive, unexpected given the patient’s clinico-laboratory presentation, or limited by insufficient material, OR
• To assess for subclinical rejection of an allograft (i.e., surveillance testing), according to a clinically validated cadence (in peer-reviewed published evidence or established national consensus guidelines) utilizing the minimum number of test timepoints that have demonstrated clinical utility appropriate for the specific transplant type.

• At this time, the current evidence supports a maximum number of surveillance timepoints for evaluation in the first-year post-transplantation as follows: Kidney (4), Heart (12), and Lung (12).
• After the first year, surveillance timepoints may continue at a decreased frequency of 2 per year.

• The test demonstrates analytical validity (AV), including an analytical and clinical validation for any given measured analytes, and has demonstrated equivalence or superiority for sensitivity or specificity (depending on intended use) of detecting allograft rejection to other already-accepted tests for the same intended use measuring the same or directly comparable analytes under this policy.

• Clinical validity (CV) of any analytes (or expression profiles) measured must be established through a study published in the peer-reviewed literature for the intended use of the test in the intended population. The degree of validity must be similar or superior to established and covered tests under this policy (see associated coverage Articles). If conducted with concordance to tissue histologic evaluation, the appropriate Banff Classification for renal allografts or other accepted criteria (if existing) must be used.

• The test is being used in a patient who is part of the population (disease and intended use) in which the test was analytically validated and has demonstrated CV.

• For a given patient encounter, only one molecular test for assessing allograft status may be performed. A test may include more than one assay; however, multianalyte and combination tests must demonstrate superiority and additive benefit when compared to respective single analytes or components.

• For minimally or non-invasive tests, the benefit to risk profile of the molecular test is considered by the ordering clinician to be more favorable than the benefit to risk profile of a tissue biopsy, or a tissue biopsy cannot be obtained, when the test and biopsy provide similar information. For example, this may be the case if a biopsy is considered medically contraindicated in a patient.

• The test successfully completes a MolDX Technical Assessment that will ensure that AV, CV, and clinical utility criteria set in this policy are met to establish the test as reasonable and necessary.

• A test and biopsy cannot be performed simultaneously. However, in very high-risk patients with overt signs and symptoms of rejection, a molecular test and biopsy may be performed together in urgent situations ONLY when the information derived from the test is complementary to the biopsy, established to meet CV requirements outlined above for that information, and demonstrated to improve outcomes in patients when performed along with biopsies. We expect these situations to be extremely rare.

Covered tests with AV that is significantly below similar services may have coverage rescinded.

AI Figures Out Meaning of MolDx DCIS Proposed LCD... and Meaning of MolDx term, "Rhetorical Proof"

 MolDx received a request to cover the molecular test DCISion RT (or Oncotype DCIS SCORE).   My impresssion is, MolDx has done an extensive write up culminating in a decision no current tests are covered.   Assume you do not know the answer, and read the LCD carefully to determine the answer.  Explain what is going on, in this document.

ORIGINAL BLOG   https://www.discoveriesinhealthpolicy.com/2025/07/new-clia-policies-at-cms-new-moldx.html

####

AI Summary of the LCD’s Position on DCISionRT / Oncotype DCIS Score

Bottom Line:

MolDx currently does not cover DCISionRT or Oncotype DX DCIS Score (or any similar test) for DCIS risk stratification to guide radiation therapy decisions. 

The LCD gives an extensive analysis of the current state of evidence and concludes that no test today meets the reasonable and necessary standard. 

However, MolDx leaves the door open for future coverage if better evidence is provided.

---

Explanation of What's Going On in This LCD:

1. What Is the Request?
   MolDx reviewed requests to cover molecular tests for DCIS patients that would allow physicians to safely omit radiation therapy (RT) in women identified as "low risk" for recurrence.

2. MolDx’s Current Coverage Policy (as stated explicitly in the LCD):
   These tests are not covered because no test currently meets MolDx's standards for being reasonable and necessary. Specifically, the tests have not sufficiently demonstrated that they outperform existing clinical risk tools (such as MSKCC nomograms or VNPI) in accurately identifying patients who will have less than 5% absolute benefit from radiation.

3. Criteria MolDx Would Require for Future Coverage (if evidence improved):
   MolDx lays out precise future requirements:

• The patient must meet strict criteria (DCIS only, no mastectomy, no prior RT, clear decision pathways regarding RT).

• The test must have completed technical validation.

• The test must demonstrate it identifies low-risk patients better than existing tools.

• Low-risk is defined as ≤5% absolute benefit from RT in reducing ipsilateral breast tumor recurrence (IBTR).

4. Why Current Evidence Fails:
   MolDx provides an exhaustive review of studies on both DCISionRT and Oncotype DX DCIS Score. Their critiques are:

• Sample sizes too small for strong statistical confidence, especially in the low-risk groups.

• Outcomes inconsistent across studies.

• Current studies show relative risk reductions from RT persist, even in "low-risk" groups, though they may not reach statistical significance because of small numbers.

• No test has clearly shown incremental value over existing clinicopathologic tools.

• Newer modifications to the tests (e.g., DCISionRT's new 2.8 cutoff) are not yet externally validated.

5. The Larger Context MolDx Recognizes:

• Radiation therapy in DCIS is already somewhat overused; Medicare patients (older) may be particularly good candidates for avoiding RT.

• There is clinical utility in tests that could accurately identify patients for whom RT provides negligible benefit.

• Shared decision-making is complex, and having clear tools might reduce overtreatment.

6. Why MolDx Isn’t Convinced Yet:
   MolDx believes:

• Clinicopathologic tools already provide reasonable stratification.

• Biomarker tests haven’t clearly surpassed these tools in accuracy.

• The current data supporting these tests are too weak, too heterogeneous, and sometimes underpowered.

7. Additional Notes:
   MolDx explicitly mentions that clinicians and patients might be misled if a test shows any risk reduction from RT (even small), because current behavior trends toward giving RT if any benefit is suggested. Therefore, the test must demonstrate a very clear lack of meaningful benefit (≤5% absolute risk reduction) to shift behavior safely.

8. Contractor Advisory Committee (CAC) Feedback:
   CAC members expressed that a good test would be useful, but the current evidence is inadequate. Some providers already use these tests, but there’s no consensus on their validity.

---

Summary of MolDx’s Position in Plain Terms:

MolDx sees potential value in biomarker tests for DCIS, but today’s tests haven’t convincingly proven that they add enough to what we already know from existing clinical tools. Until there’s stronger, clearer, and validated evidence (especially demonstrating <5% absolute RT benefit for "low-risk" patients), MolDx will not cover these tests.

They explicitly state they are open to changing this position with better future evidence.

##

What does MolDx mean by RHETORICAL PROOF?

##

The phrase "rhetorical proof" is unusual in a medical policy document, but here's what MolDx likely means by it, given the context:

Contextual Meaning in This LCD:

MolDx writes that some advocates of DCISionRT argue it identifies patients who have no relative risk reduction from RT, and that this is valuable because it provides proof for physicians and patients to confidently omit RT. However, MolDx says there is no convincing evidence yet that any test identifies such a population with certainty.

MolDx comments:

"While it is desirable to have a tool that identifies a population with no relative risk reduction from RT ... we conclude that there is insufficient data currently to convincingly support the assertion... This was a central rationale presented at the CAC by SMEs for use of such tests, yet this assertion is most easily explained by a failure to identify statistical significance... While Vicini’s reanalysis... seemingly greatly improves the test... these data cannot reasonably be interpreted as evidence... but raise concern... underpowered..."

What MolDx Likely Means by "Rhetorical Proof":

"Rhetorical proof" here seems to mean something persuasive in clinical conversation but not scientifically proven. That is:

• It might help a doctor convince a patient or defend a decision to omit RT.

• It might sound like proof ("this test says you are so low risk you need no RT").

• But it's not scientifically robust proof in the evidentiary sense MolDx requires (validated, statistically sound, externally confirmed).

So "rhetorical proof" is used a bit cynically here. MolDx is criticizing the notion that these tests offer a convenient talking point rather than hard, validated science. It’s persuasive rhetoric for doctors and patients but doesn’t meet the Medicare standard of "reasonable and necessary."

In Plain Terms:

MolDx is saying:

Just because a test helps a doctor feel better saying, "See, you don’t need RT," doesn’t make it scientifically justified or covered by Medicare. That’s rhetoric, not evidence.

Renal Denervation: From 2016 to 2025 at CMS

Chat GPT compares the 2016 AHRQ TA and the 2025 CMS NCD.

Original blog here - https://www.discoveriesinhealthpolicy.com/2025/07/cms-publishes-draft-ncd-on-renal.html

##

 The 2025 Draft NCD and the 2016 AHRQ Technology Assessment (TA) share a core skepticism toward renal denervation (RDN), but the 2025 NCD reflects a measurable shift toward conditional acceptance, based on newer trial evidence—albeit with strict limitations.

Here’s a side-by-side comparison of tone, content, and conclusions:

---

1. Overall Tone

• 2016 AHRQ TA:
  Tone is decidedly negative. RDN is deemed investigational, and the authors express no confidence in efficacy or safety due to inconsistent results and low-quality evidence.

• 2025 Draft NCD:
  Tone is guarded but constructive. CMS acknowledges newer positive RCTs, such as SPYRAL and RADIANCE II, and proposes Coverage with Evidence Development (CED)—a step forward compared to the blanket dismissal in 2016.

---

2. Evidence Base and Interpretation

• 2016 AHRQ:
  The report’s conclusion was that the SYMPICITY HTN-3 trial—a large, blinded sham-controlled RCT—showed no statistically significant benefit, undermining prior optimism. The report noted major limitations in study design, patient adherence, and confounding.

• 2025 CMS NCD:
  Acknowledges those earlier limitations but cites more recent sham-controlled RCTs showing modest but statistically significant BP reduction (e.g., ~6-8 mmHg), particularly in unmedicated populations. CMS uses GRADE and AHRQ standards but now considers the evidence of "moderate" strength in some subsets.

---

3. Clinical Significance and Generalizability

• 2016 AHRQ:
  Emphasized that even if modest BP reductions occurred, there was no evidence of impact on long-term cardiovascular outcomes—stroke, MI, death.

• 2025 CMS:
  Still raises identical concerns, but instead of rejecting coverage, proposes requiring that those very endpoints be studied through CED—an important strategic pivot.

---

4. Position on Coverage

• 2016 AHRQ:
  No recommendation for coverage; clearly sees the technology as experimental.

• 2025 CMS:
  Recommends narrow conditional coverage—only within well-designed clinical studies, with tight controls on patient selection, physician training, and outcomes tracking. CMS proposes a pathway to potential future coverage, which didn’t exist in 2016.

---

5. View of the Evidence Trajectory

• 2016 AHRQ:
  Saw the field as stagnating or flawed, with a call for better-designed RCTs before any consideration of clinical use.

• 2025 CMS:
  Suggests the field has partially redeemed itself with improved study design and trial methodology (blinding, sham-controls, core labs), but still falls short of full validation—hence the reliance on Coverage with Evidence Development as a “middle ground.”

---

Summary:

The 2016 AHRQ report is a decisive rejection of renal denervation as an effective intervention. The 2025 CMS NCD, while still cautious, represents a more nuanced and hopeful posture—acknowledging methodological improvements, positive trial data, and allowing limited Medicare coverage under rigorous research conditions. The pivot from total non-coverage to CED marks a meaningful policy evolution.

###
I asked Chat GPT for a summary of likely current clinical viewpoints.

###

As of 2025, the consensus professional clinical viewpoint on renal denervation (RDN) remains cautiously skeptical but increasingly curious, with selective adoption in research-savvy or interventional cardiology circles—but little mainstream uptake in routine hypertension management.

🔍 Summary of Professional Consensus in 2025:

✅ Growing but Limited Enthusiasm

• Some interventional cardiologists and hypertension specialists are cautiously optimistic, especially in referral centers and academic medical systems.

• RDN is viewed as a potential option for select patients with truly resistant hypertension (confirmed adherence, multiple drug failures).

• The 2023 FDA approvals (Medtronic’s Symplicity Spyral and ReCor’s Paradise system) sparked renewed interest, but that hasn’t yet translated into widespread use.

❌ Widespread Clinical Hesitancy

• General cardiologists and primary care physicians are often not recommending RDN. Reasons include:

  • Modest effect sizes (e.g., 5–8 mmHg reductions).

  • No evidence (yet) of reduction in hard outcomes (stroke, MI, death).

  • Concerns about patient selection, long-term durability, and cost-effectiveness.

  • Lack of real-world data beyond controlled trials.

📊 Professional Society Guidelines

• As of early 2025, ACC, AHA, and ESH (European Society of Hypertension) still list RDN as experimental or investigational, often referencing it in footnotes or sidebars for use only in clinical trials or when other therapies fail.

• No major guidelines recommend RDN as first-line or routine treatment.

🧠 The “Average” Cardiologist in 2025 Probably Thinks…

“It’s an interesting technology, but I’m not sending my patients for it yet. Show me a trial that proves it reduces stroke or heart failure in the real world—and works in older, comorbid patients—and I’ll reconsider.”

---

💬 Supporting Quotes from Clinical Literature or Commentaries

(Paraphrased consensus points from editorials, panels, and opinion pieces in journals like JACC, Hypertension, NEJM):

• “RDN may offer a niche solution for a small group of patients, but it’s not a game-changer for the average hypertensive patient.”

• “Without hard outcomes, insurers and clinicians are rightly skeptical.”

• “This may be another case of elegant engineering chasing a weak clinical signal.”

---

🧭 Outlook

Unless a future trial (like the one CMS may require under CED) shows cardiovascular risk reduction, RDN may remain a second- or third-tier tool, confined to specialized centers and hypertension research networks.

Would you like a concise paragraph for publication or a stakeholder briefing?