DxChain uses panoramic patient profiling, Med-ToT planning, and adversarial angel-devil debates to reduce LLM hallucinations in clinical diagnosis, achieving SOTA accuracy and consistency on two MIMIC-IV benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate
DxChain uses panoramic patient profiling, Med-ToT planning, and adversarial angel-devil debates to reduce LLM hallucinations in clinical diagnosis, achieving SOTA accuracy and consistency on two MIMIC-IV benchmarks.