CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis

2024/07/18 by Junying Chen, Chen, Junying, Anningzhe Gao +9 · 14 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2407.13301

openalex publication_date 2024/07/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The field of medical diagnosis has undergone a significant transformation with the advent of large language models (LLMs), yet the challenges of interpretability within these models remain largely unaddressed. This study introduces Chain-of-Diagnosis (CoD) to enhance the interpretability of LLM-based medical diagnostics. CoD transforms the diagnostic process into a diagnostic chain that mirrors a physician's thought process, providing a transparent reasoning pathway. Additionally, CoD outputs the disease confidence distribution to ensure transparency in decision-making. This interpretability makes model diagnostics controllable and aids in identifying critical symptoms for inquiry through the entropy reduction of confidences. With CoD, we developed DiagnosisGPT, capable of diagnosing 9604 diseases. Experimental results demonstrate that DiagnosisGPT outperforms other LLMs on diagnostic benchmarks. Moreover, DiagnosisGPT provides interpretability while ensuring controllability in diagnostic rigor.

Cited by

• Socratic Students: Teaching Language Models to Learn by Asking Questions
• CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare
• Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
• Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs
• Medical Interpretability and Knowledge Maps of Large Language Models
• Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
• MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning
• CLARITY: Clinical Assistant for Routing, Inference, and Triage
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
• End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
• Reasoning LLMs in the Medical Domain: A Literature Survey
• MedRepBench: A Comprehensive Benchmark for Medical Report Interpretation
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications
• ControlMed: Adding Reasoning Control to Medical Language Model

Related

• Large Language Models Perform Diagnostic Reasoning
• Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine
• DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
• Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis
• DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models