From 6a8f8b2234bff52eb85646db7a8b3eea6fa79418 Mon Sep 17 00:00:00 2001 From: Teleo Agents Date: Mon, 23 Mar 2026 04:31:13 +0000 Subject: [PATCH] extract: 2026-02-10-klang-lancet-dh-llm-medical-misinformation Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70> --- ... errors when overriding correct outputs.md | 6 +++++ ...-lancet-dh-llm-medical-misinformation.json | 26 +++++++++++++++++++ ...ng-lancet-dh-llm-medical-misinformation.md | 16 +++++++++++- 3 files changed, 47 insertions(+), 1 deletion(-) create mode 100644 inbox/queue/.extraction-debug/2026-02-10-klang-lancet-dh-llm-medical-misinformation.json diff --git a/domains/health/human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs.md b/domains/health/human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs.md index ecc958e8..986c6c15 100644 --- a/domains/health/human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs.md +++ b/domains/health/human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs.md @@ -38,6 +38,12 @@ OpenEvidence's 1M daily consultations (30M+/month) with 44% of physicians expres The Sutter Health-OpenEvidence EHR integration creates a natural experiment in automation bias: the same tool (OpenEvidence) that was previously used as an external reference is now embedded in primary clinical workflows. Research on in-context vs. external AI shows in-workflow suggestions generate higher adherence, suggesting the integration will increase automation bias independent of model quality changes. +### Additional Evidence (extend) +*Source: [[2026-02-10-klang-lancet-dh-llm-medical-misinformation]] | Added: 2026-03-23* + +The Klang et al. Lancet Digital Health study (February 2026) adds a fourth failure mode to the clinical AI safety catalogue: misinformation propagation at 47% in clinical note format. This creates an upstream failure pathway where physician queries containing false premises (stated in confident clinical language) are accepted by the AI, which then builds its synthesis around the false assumption. Combined with the PMC12033599 finding that OpenEvidence 'reinforces plans' and the NOHARM finding of 76.6% omission rates, this defines a three-layer failure scenario: false premise in query → AI propagates misinformation → AI confirms plan with embedded false premise → physician confidence increases → omission remains in place. + + Relevant Notes: - [[centaur team performance depends on role complementarity not mere human-AI combination]] -- the chess centaur model does NOT generalize to clinical medicine where physician overrides degrade AI performance diff --git a/inbox/queue/.extraction-debug/2026-02-10-klang-lancet-dh-llm-medical-misinformation.json b/inbox/queue/.extraction-debug/2026-02-10-klang-lancet-dh-llm-medical-misinformation.json new file mode 100644 index 00000000..53ede047 --- /dev/null +++ b/inbox/queue/.extraction-debug/2026-02-10-klang-lancet-dh-llm-medical-misinformation.json @@ -0,0 +1,26 @@ +{ + "rejected_claims": [ + { + "filename": "llms-propagate-medical-misinformation-32-percent-average-47-percent-clinical-note-format.md", + "issues": [ + "missing_attribution_extractor" + ] + } + ], + "validation_stats": { + "total": 1, + "kept": 0, + "fixed": 3, + "rejected": 1, + "fixes_applied": [ + "llms-propagate-medical-misinformation-32-percent-average-47-percent-clinical-note-format.md:set_created:2026-03-23", + "llms-propagate-medical-misinformation-32-percent-average-47-percent-clinical-note-format.md:stripped_wiki_link:human-in-the-loop clinical AI degrades to worse-than-AI-alon", + "llms-propagate-medical-misinformation-32-percent-average-47-percent-clinical-note-format.md:stripped_wiki_link:medical LLM benchmark performance does not translate to clin" + ], + "rejections": [ + "llms-propagate-medical-misinformation-32-percent-average-47-percent-clinical-note-format.md:missing_attribution_extractor" + ] + }, + "model": "anthropic/claude-sonnet-4.5", + "date": "2026-03-23" +} \ No newline at end of file diff --git a/inbox/queue/2026-02-10-klang-lancet-dh-llm-medical-misinformation.md b/inbox/queue/2026-02-10-klang-lancet-dh-llm-medical-misinformation.md index ae99eb60..9512c279 100644 --- a/inbox/queue/2026-02-10-klang-lancet-dh-llm-medical-misinformation.md +++ b/inbox/queue/2026-02-10-klang-lancet-dh-llm-medical-misinformation.md @@ -7,9 +7,13 @@ date: 2026-02-10 domain: health secondary_domains: [ai-alignment] format: research paper -status: unprocessed +status: enrichment priority: high tags: [clinical-ai-safety, llm-misinformation, automation-bias, openevidence, lancet, mount-sinai, medical-language, clinical-note, belief-5] +processed_by: vida +processed_date: 2026-03-23 +enrichments_applied: ["human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs.md"] +extraction_model: "anthropic/claude-sonnet-4.5" --- ## Content @@ -58,3 +62,13 @@ Published in The Lancet Digital Health, February 2026. Lead author: Eyal Klang, PRIMARY CONNECTION: "human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs" — the misinformation propagation finding adds a new upstream failure to this chain WHY ARCHIVED: Fourth clinical AI safety failure mode; high KB value as distinct mechanism from the three already documented; the clinical-note format specificity directly implicates OE's use case EXTRACTION HINT: Extract as a new claim about LLM misinformation propagation specifically in clinical contexts. Note the 47% clinical-language amplification as the mechanism that makes this relevant to clinical AI tools (not just general AI assistants). Create a wiki link to the OE "reinforces plans" finding (PMC12033599) — the combination defines a three-layer failure scenario. + + +## Key Facts +- Study tested 1M+ prompts across leading language models +- ChatGPT-4o achieved ~10% misinformation propagation rate (best performer) +- Smaller/less advanced models showed >60% propagation rates +- Study published in The Lancet Digital Health, February 2026 +- Companion editorial titled 'Large language models need immunisation to protect against misinformation' (PIIS2589-7500(25)00160-8) +- Lead author: Eyal Klang, Icahn School of Medicine at Mount Sinai +- Mount Sinai's Klang group also produced the NOHARM framework and the orchestrated multi-agent AI paper (npj Health Systems, March 2026)