CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis
This addresses interpretability for medical diagnosis applications, but it appears incremental as it builds on existing LLM frameworks.
The study tackled the problem of interpretability in LLM-based medical diagnostics by introducing Chain-of-Diagnosis (CoD), which transforms the diagnostic process into a transparent reasoning pathway and outputs disease confidence distributions, resulting in DiagnosisGPT outperforming other LLMs on diagnostic benchmarks.
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.