MEDDxAgent：面向可解释自动鉴别诊断的统一模块化智能体框架
MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
AI总结：
针对现有大语言模型辅助鉴别诊断方法的局限，提出交互式模块化可解释框架MEDDxAgent，通过多组件迭代推理实现诊断，构建多疾病综合基准，实验显示其在不同规模LLM下准确率提升超10%且具备可解释性。
摘要：
鉴别诊断（Differential Diagnosis，DDx）是临床决策中基础且复杂的环节，医生会根据症状、既往病史和医学知识，迭代优化可能疾病的排序列表。尽管大语言模型（Large Language Models，LLMs）的最新进展在辅助鉴别诊断方面展现出潜力，但现有方法存在关键局限：仅在单一数据集上评估、组件优化相互孤立、对完整患者档案存在不切实际的假设、仅进行单次诊断尝试。\n我们提出了面向交互式鉴别诊断的模块化可解释鉴别诊断智能体（Modular Explainable DDx Agent，MEDDxAgent）框架，其诊断推理通过迭代学习逐步推进，而非假设一开始就能获取完整的患者档案。MEDDxAgent整合了三个模块化组件：（1）协调器（DDxDriver）；（2）病史采集模拟器；（3）两个分别负责知识检索和诊断策略的专用智能体。为保证评估的可靠性，我们构建了一个涵盖呼吸系统疾病、皮肤病和罕见病的综合鉴别诊断基准。\n我们分析了单轮诊断方法，证明了在初始阶段无完整患者档案时，迭代优化的重要性。全面评估显示，无论基于大尺寸还是小尺寸LLM，MEDDxAgent在交互式鉴别诊断任务中的准确率均提升了10%以上，同时能为其诊断推理过程提供关键的可解释性。
英文摘要：
Differential Diagnosis (DDx) is a fundamental yet complex aspect of clinical decision-making, in which physicians iteratively refine a ranked list of possible diseases based on symptoms, antecedents, and medical knowledge. While recent advances in large language models (LLMs) have shown promise in supporting DDx, existing approaches face key limitations, including single-dataset evaluations, isolated optimization of components, unrealistic assumptions about complete patient profiles, and single-attempt diagnosis. We introduce a Modular Explainable DDx Agent (MEDDxAgent) framework designed for interactive DDx, where diagnostic reasoning evolves through iterative learning, rather than assuming a complete patient profile is accessible. MEDDxAgent integrates three modular components: (1) an orchestrator (DDxDriver), (2) a history taking simulator, and (3) two specialized agents for knowledge retrieval and diagnosis strategy. To ensure robust evaluation, we introduce a comprehensive DDx benchmark covering respiratory, skin, and rare diseases. We analyze single-turn diagnostic approaches and demonstrate the importance of iterative refinement when patient profiles are not available at the outset. Our broad evaluation demonstrates that MEDDxAgent achieves over 10% accuracy improvements in interactive DDx across both large and small LLMs, while offering critical explainability into its diagnostic reasoning process.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
