用100张医学流程图让大模型更准地自我分诊。
Multi-agent Self-triage System with Medical Flowcharts
- 多智能体分工：检索、决策、对话三角色协同工作。
- 流程图匹配准确率达95.29%，导航正确率99.10%。
- 适合想提升AI医疗咨询透明度与可靠性的研究者。
在线健康资源与大型语言模型（LLMs）正日益作为医疗决策的首道入口，但其可靠性受限于准确性低、透明度不足及易受未经验证信息影响。我们提出一个概念验证的对话式自我分诊系统，通过美国医学会提供的100张临床验证流程图引导LLM，构建结构化且可审计的患者决策支持框架。系统采用多智能体架构，包括检索代理、决策代理和聊天代理，分别负责识别最相关流程图、解析患者回答并提供个性化、易懂的建议。在大规模合成对话数据集上评估，系统在2,000条样本中实现95.29%的前3名流程图检索准确率，在37,200条不同对话风格下的流程图导航准确率达99.10%。该方法结合自由文本交互的灵活性与标准化临床指南的严谨性，证明了透明、准确、可泛化的AI辅助自我分诊可行性，有望支持患者自主决策并优化医疗资源配置。
原文摘要 · Abstract (English)
Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.
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。