Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate

TL;DR

This paper introduces DxChain, a novel chain-based framework for clinical diagnosis using LLMs, inspired by clinician cognition, incorporating panoramic profiling, strategic planning, and adversarial debate to improve accuracy and consistency.

Contribution

The paper presents DxChain, a new iterative reasoning framework with innovative methods to enhance LLM-based clinical diagnosis, addressing hallucinations and evidence conflicts.

Findings

Achieves state-of-the-art diagnostic accuracy on MIMIC benchmarks.

Improves logical consistency in clinical decision support.

Demonstrates modular architecture for reliable AI in healthcare.

Abstract

The application of large language models (LLMs) in clinical decision support faces significant challenges of "tunnel vision" and diagnostic hallucinations present in their processing unstructured electronic health records (EHRs). To address these challenges, we propose a novel chain-based clinical reasoning framework, called DxChain, which transforms the diagnostic workflow into an iterative process by mirroring a clinician's cognitive trajectory that consists of "Memory Anchoring", "Navigation" and "Verification" phases. DxChain introduces three key methodological innovations to elicit the potential of LLM: (i) a Profile-Then-Plan paradigm to mitigate cold-start hallucinations by establishing a panoramic patient baseline, (ii) a Medical Tree-of-Thoughts (Med-ToT) algorithm for strategic look ahead planning and resource aware navigation, and (iii) a Dialectical Diagnostic Verification procedure utilizing "Angel-Devil" adversarial debates to resolve complex evidence conflicts. Evaluated on two real world benchmarks, MIMIC-IV-Ext Cardiac Disease and MIMIC-IV-Ext CDM, DxChain achieves state-of-the-art performances in both diagnostic accuracy and logical consistency, offering a modular and reliable architecture for next-generation clinical AI. The code is at https://anonymous.4open.science/r/Dx-Chain.