面向公共卫生数据采集的智能体AI方法探索
原标题:Toward an Agentic AI Approach to Public Health Data Collection
AI 摘要
弗吉尼亚大学与RAND的研究者提出一种面向公共卫生数据采集的智能体AI工作流,由编排智能体将监测目标转化为共享任务规范,多个专用智能体协同完成来源发现、治理、证据结构化、事件关联与验证。该工作流在2026年汉坦病毒疫情、2025年加拿大麻疹和塞拉利昂猴痘三个场景中应用:汉坦病毒场景重建了专家基准中全部13例病例,关联85个发布者域名(基准为28个),但可评估字段正确率为67.8%,低于人工基准的85.1%。研究认为该方法可减少人工重复适配,同时保留专家监督与证据可追溯性。
正文节选
Toward an Agentic AI Approach to Public Health Data Collection Xueyi Zhanga, Hongru Dua,*, Ensheng Dongb,* aDepartment of Systems and Information Engineering, University of Virginia, Charlottesville, USA bEngineering and Applied Sciences Department, RAND, Arlington, USA *Corresponding author: hongrudu@virginia.edu, edong@rand.org Disease surveillance is essential to the prevention and control of infectious diseases 1, 2, and the collection of outbreak information has evolved from manual investig