ENGAGE run · 38c7be064d40

```json [ { "id": 1, "name": "AI Clinical Decision Support, Liability & Care Delivery", "description": "Arguments about AI/ML tools deployed in diagnosis, treatment recommendations, clinical workflows, and care pathways — covering accuracy vs. physician judgment, malpractice liability gaps when AI causes errors, clinician adoption friction, alert fatigue replacement, foundation model

```json [ { "post_index": 5, "cluster_ids": [11, 13], "claim": "Insurance-triggered chargemaster markups obscure actual cost structure and enable price extraction", "argument_type": "empirical_claim", "stance": "challenges_status_quo", "hyde_excerpt": "The divergence between cash-pay and insured pricing for identical services reveals a fundamental asymmetry in healthcare'

```json [ { "post_index": 0, "matched_article_id": 496, "match_confidence": 87, "match_reason": "Tweet describes the specific mechanism of hospice fraud — enrolling beneficiaries, billing Medicare, then disappearing — which directly maps to the article's thesis that the per diem payment structure systemically incentivizes fraudulent enrollment and that Operation Never Say Die / C

What you're seeing is the chargemaster doing its job. The inflated rate isn't a bug in the billing system, it's the product. Insurers need a high list price to negotiate down from, providers need the spread to justify their contracts, and the patient caught in the middle gets a bill that has almost nothing to do with actual cost. The $2,000 figure likely reflects a contracted rate that still sits

The walk-away part is what makes this architecture so durable. The per diem model pays a flat daily rate (currently $230.83 for routine home care days 1-60) regardless of whether any care is actually delivered, so the fraud isn't a workaround of the system, it's the system running exactly as designed for anyone willing to exploit it. That's why one Van Nuys building had 197 registered hospice comp

Skin apps are probably the cleanest real-world test of the mechanism I wrote about in https://www.onhealthcare.tech/p/the-double-edged-algorithm-how-consumer?utm_source=x&utm_medium=reply&utm_content=2050696880040878163&utm_campaign=the-double-edged-algorithm-how-consumer, which is that AI optimized for actionable output will generate utilization regardless of whether outcomes justify it. The Dut

The retinal AI case fits a broader pattern I've been tracing across the referral system: the value isn't in the AI doing the diagnosis, it's in the AI restructuring the decision sequence so the right next step actually happens. That's the piece most people miss. The Ontario eConsult program processed nearly 100,000 cases with a two-day average turnaround, and the volume benchmark matters less th

The VA Whole Health rollout is the cleaner example here. CARA mandated non-opioid pain alternatives across VA facilities, and what followed had nothing to do with whether providers accepted the conceptual framing. Acupuncture, mindfulness, whole-person care pathways, all got absorbed because the legislative mandate created a payment and coding pathway, not because GLP-1 success changed anyone's me

```json [ { "id": 1, "name": "AI Clinical Decision Support, Liability & Care Delivery Transformation", "description": "Arguments about AI/ML tools in diagnosis, treatment recommendations, clinical documentation, and care pathways — covering adoption friction, accuracy vs. physician judgment, malpractice liability gaps when AI causes errors, ambient scribing economics, clinical reason

```json [] ```

```json [ { "post_index": 1, "matched_article_id": 524, "match_confidence": 87, "match_reason": "The tweet reports Trump saying Medicare will soon cover weight-loss drugs, which directly maps to the article's analysis of CMS's BALANCE Model pause and the GLP-1 Bridge extension as the de facto Medicare anti-obesity coverage mechanism for 2027 — the article provides the specific re

The part that gets lost in that framing: "Medicare covering weight-loss drugs" and "Medicare Part D plans covering weight-loss drugs" are two completely different policy problems, and conflating them is exactly how you end up surprised when a model fails. The BALANCE pause happened because CMS tried to get Part D plan sponsors (Humana, UnitedHealth, CVS Aetna, and others) to voluntarily coordinat

Non-hospice spending billed outside the hospice election in California, Nevada, and Arizona jumped from $790M nationally in FY 2020 to over $2.8B in FY 2024. Those three states are already under enhanced CMS oversight, which means the Strike Force prosecutors are walking into a target environment that CMS has been mapping for years. The piece that matters here is the SSVI. CMS just proposed scori

What nobody's answering yet: will a new strike force actually change the structural incentives, or just produce another round of arrests that leave the payment model intact? The enforcement is real. Operation Never Say Die charged 15 defendants and arrested 8 covering $60M in alleged Medicare fraud, and one Van Nuys building alone housed 197 registered hospice companies. But the arrests didn't st

The Strike Force expansion is directionally right, but the prosecution end of the chain is where you're catching fraud that already paid out, sometimes years earlier. The pay-and-chase structure of Medicare fee-for-service means the government is essentially running a credit system with open enrollment for providers, and by the time DOJ indicts, the money has moved through shell companies, across

```json [ {"post_index": 0, "prediction": "reject", "confidence": 72, "reason": "Healthcare fraud scandal reporting without systems analysis. Post announces DOJ strike force but lacks analysis of root causes in healthcare system design, reimbursement incentives, or operational vulnerabilities that

```json [ { "category": "ai_safety_cybersecurity_incident_tangential", "summary": "Posts about AI safety vulnerabilities, hacking incidents, or cybersecurity breaches that lack healthcare systems analysis.", "exclusion_rule": "Exclude posts that report AI safety incidents, cybersecurit