让AI医生和药师协作决策，提升诊疗准确率。
MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
- 设计医生与药师双代理协同机制，动态评估信心并交叉验证
- 诊断与用药准确率均达67.58%，比单代理高7%以上
- 适合远程问诊与日常临床，决策过程可解释
利用大语言模型的自主智能体在孤立医疗任务（如诊断、影像分析）中表现优异，但在连接诊断推理与用药决策的综合临床流程中表现不佳。我们发现核心问题在于现有医疗AI系统各自为战，缺乏临床团队中的交叉验证与知识融合，限制了其在真实医疗场景中的效果。为此，我们提出MedCoAct——一种信心感知的多智能体协作框架，通过整合专科医生与药师代理，模拟临床协作，并构建基准数据集DrugCareQA以评估医疗AI在整合诊断与治疗流程中的能力。实验结果表明，MedCoAct在诊断准确率和药物推荐准确率上分别达到67.58%，较单智能体框架提升7.04%和7.08%。该协作方法在多种医学领域具有良好泛化能力，尤其适用于远程问诊与常规临床场景，同时提供可解释的决策路径。
原文摘要 · Abstract (English)
Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic reasoning and medication decisions. We identify a core limitation: existing medical AI systems process tasks in isolation without the cross-validation and knowledge integration found in clinical teams, reducing their effectiveness in real-world healthcare scenarios. To transform the isolation paradigm into a collaborative approach, we propose MedCoAct, a confidence-aware multi-agent framework that simulates clinical collaboration by integrating specialized doctor and pharmacist agents, and present a benchmark, DrugCareQA, to evaluate medical AI capabilities in integrated diagnosis and treatment workflows. Our results demonstrate that MedCoAct achieves 67.58\% diagnostic accuracy and 67.58\% medication recommendation accuracy, outperforming single agent framework by 7.04\% and 7.08\% respectively. This collaborative approach generalizes well across diverse medical domains, proving especially effective for telemedicine consultations and routine clinical scenarios, while providing interpretable decision-making pathways.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。