vida: extract claims from 2026-03-22-cognitive-bias-clinical-llm-npj-digital-medicine

- Source: inbox/queue/2026-03-22-cognitive-bias-clinical-llm-npj-digital-medicine.md
- Domain: health
- Claims: 2, Entities: 1
- Enrichments: 2
- Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5)

Pentagon-Agent: Vida <PIPELINE>

domains/health/llm-anchoring-bias-explains-clinical-ai-plan-reinforcement-mechanism.md

@@ -0,0 +1,17 @@
+---
+type: claim
+domain: health
+description: The cognitive mechanism explaining why clinical AI reinforces rather than corrects physician plans
+confidence: experimental
+source: npj Digital Medicine 2025 (PMC12246145), GPT-4 anchoring studies
+created: 2026-04-04
+title: LLM anchoring bias causes clinical AI to reinforce physician initial assessments rather than challenge them because the physician's plan becomes the anchor that shapes all subsequent AI reasoning
+agent: vida
+scope: causal
+sourcer: npj Digital Medicine research team
+related_claims: ["[[OpenEvidence became the fastest-adopted clinical technology in history reaching 40 percent of US physicians daily within two years]]", "[[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]]"]
+---
+
+# LLM anchoring bias causes clinical AI to reinforce physician initial assessments rather than challenge them because the physician's plan becomes the anchor that shapes all subsequent AI reasoning
+
+The GPT-4 anchoring study finding that 'incorrect initial diagnoses consistently influenced later reasoning' provides a cognitive architecture explanation for the clinical AI reinforcement pattern observed in OpenEvidence adoption. When a physician presents a question with a built-in assumption or initial plan, that framing becomes the anchor for the LLM's reasoning process. Rather than challenging the anchor (as an experienced clinician might), the LLM confirms it through confirmation bias—seeking evidence that supports the initial assessment over evidence against it. This creates a reinforcement loop where the AI validates the physician's cognitive frame rather than providing independent judgment. The mechanism is particularly dangerous because it operates invisibly: the physician experiences the AI as providing 'evidence-based' confirmation when it's actually amplifying their own anchoring and confirmation biases. This explains why clinical AI can simultaneously improve workflow efficiency (by quickly finding supporting evidence) while potentially degrading diagnostic accuracy (by reinforcing incorrect initial assessments).

domains/health/llms-amplify-human-cognitive-biases-through-sequential-processing-and-lack-contextual-resistance.md

@@ -0,0 +1,17 @@
+---
+type: claim
+domain: health
+description: Clinical LLMs exhibit anchoring, framing, and confirmation biases similar to humans but may amplify them through architectural differences
+confidence: experimental
+source: npj Digital Medicine 2025 (PMC12246145), GPT-4 diagnostic studies
+created: 2026-04-04
+title: LLMs amplify rather than merely replicate human cognitive biases because sequential processing creates stronger anchoring effects and lack of clinical experience eliminates contextual resistance
+agent: vida
+scope: causal
+sourcer: npj Digital Medicine research team
+related_claims: ["[[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]]", "[[medical LLM benchmark performance does not translate to clinical impact because physicians with and without AI access achieve similar diagnostic accuracy in randomized trials]]"]
+---
+
+# LLMs amplify rather than merely replicate human cognitive biases because sequential processing creates stronger anchoring effects and lack of clinical experience eliminates contextual resistance
+
+The npj Digital Medicine 2025 paper documents that LLMs exhibit the same cognitive biases that cause human clinical errors—anchoring, framing, and confirmation bias—but with potentially greater severity. In GPT-4 studies, incorrect initial diagnoses 'consistently influenced later reasoning' until a structured multi-agent setup challenged the anchor. This is distinct from human anchoring because LLMs process information sequentially with strong early-context weighting, lacking the ability to resist anchors through clinical experience. Similarly, GPT-4 diagnostic accuracy declined when cases were reframed with 'disruptive behaviors or other salient but irrelevant details,' mirroring human framing effects but potentially amplifying them because LLMs lack the contextual resistance that experienced clinicians develop. The amplification mechanism matters because it means deploying LLMs in clinical settings doesn't just introduce AI-specific failure modes—it systematically amplifies existing human cognitive failure modes at scale. This is more dangerous than simple hallucination because the errors look like clinical judgment errors rather than obvious AI errors, making them harder to detect, especially when automation bias causes physicians to trust AI confirmation of their own cognitive biases.

entities/health/nct07328815-mitigating-automation-bias-llm-behavioral-nudges.md

@@ -0,0 +1,34 @@
+---
+type: entity
+entity_type: research_program
+name: NCT07328815 - Mitigating Automation Bias in Physician-LLM Diagnostic Reasoning
+domain: health
+status: active
+---
+
+# NCT07328815 - Mitigating Automation Bias in Physician-LLM Diagnostic Reasoning
+
+**Type:** Clinical trial  
+**Status:** Registered  
+**Focus:** Testing whether behavioral nudges can reduce automation bias in physician-LLM workflows
+
+## Overview
+
+Registered clinical trial specifically designed to test interventions for reducing automation bias when physicians use LLMs for diagnostic reasoning. The trial tests behavioral nudges as a mitigation strategy.
+
+## Significance
+
+Represents formal recognition that automation bias in clinical AI is a significant enough problem to warrant dedicated RCT investigation. Connects to broader literature on cognitive biases in medical LLMs (npj Digital Medicine 2025) and automation bias findings from NCT06963957.
+
+## Timeline
+
+- **2025** — Trial registered on ClinicalTrials.gov
+
+## Related Research
+
+- [[nct06963957-automation-bias-rct]] — Earlier RCT confirming automation bias in clinical AI
+- Cognitive bias taxonomy in medical LLMs (npj Digital Medicine 2025, PMC12246145)
+
+## Sources
+
+- npj Digital Medicine 2025 paper (PMC12246145)