CoD：面向基于诊断链的可解释医疗智能体的研究
CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis
- Shenzhen Research Institute of Big Data（深圳大数据研究院）
- The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对大语言模型医学诊断可解释性不足的问题，本研究提出诊断链（CoD）方法，模拟医师思维提供透明推理路径与疾病置信度，据此开发的DiagnosisGPT可诊断9604种疾病，在基准测试中表现优于其他大模型，兼具可解释性与诊断严谨性可控性。
AI中文摘要：
大语言模型（LLM）的出现为医学诊断领域带来了重大变革，但这类模型的可解释性挑战仍未得到充分解决。本研究提出诊断链（Chain-of-Diagnosis, CoD）方法，以提升基于LLM的医学诊断的可解释性。CoD将诊断过程转化为契合医师思维过程的诊断链，提供透明的推理路径；此外还输出疾病置信度分布，确保决策透明度。这种可解释性让模型诊断具备可控性，还能通过置信度的熵减识别需询问的关键症状。基于CoD，我们开发了可诊断9604种疾病的DiagnosisGPT。实验结果表明，DiagnosisGPT在诊断基准上的表现优于其他LLM，且在保证诊断严谨性可控的同时提供了可解释性。
英文摘要：
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.
