AI助手自动分诊，精准推荐专科，效率超人类医生三倍。
CLARITY: Clinical Assistant for Routing, Inference, and Triage
- 用状态机+大模型协同，结构化对话实现智能问诊。
- 两月完成5.5万次对话，首诊分诊准确率超真人，耗时缩短三分之二。
- 适合医院跨机构协作系统，可快速集成现有医疗信息平台。
我们提出CLARITY（临床助理：分诊、推断与分级），一个由AI驱动的平台，用于患者到专科医生的路由、临床咨询及病情严重程度评估。其混合架构结合有限状态机（FSM）以实现结构化对话流程，以及采用大语言模型（LLM）的协作代理，用于症状分析和向合适专科的优先转诊。基于模块化微服务框架构建，确保安全、高效且稳健的性能，具备灵活性和可扩展性，可适应现有医疗工作流与信息系统需求。我们在国家级跨院平台中集成该临床助手，部署两个月内完成超过55,000次内容丰富的用户对话，其中2,500次经专家标注用于后续验证。验证结果显示，CLARITY在首次尝试分诊精度上超越人类水平，咨询时间最多缩短至人类的三分之一。
原文摘要 · Abstract (English)
We present CLARITY (Clinical Assistant for Routing, Inference and Triage), an AI-driven platform designed to facilitate patient-to-specialist routing, clinical consultations, and severity assessment of patient conditions. Its hybrid architecture combines a Finite State Machine (FSM) for structured dialogue flows with collaborative agents that employ Large Language Model (LLM) to analyze symptoms and prioritize referrals to appropriate specialists. Built on a modular microservices framework, CLARITY ensures safe, efficient, and robust performance, flexible and readily scalable to meet the demands of existing workflows and IT solutions in healthcare. We report integration of our clinical assistant into a large-scale national interhospital platform, with more than 55,000 content-rich user dialogues completed within the two months of deployment, 2,500 of which were expert-annotated for subsequent validation. The validation results show that CLARITY surpasses human-level performance in terms of the first-attempt routing precision, naturally requiring up to 3 times shorter duration of the consultation than with a human.
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。