ACIE：基于智能体RAG的可配置临床信息提取--什么有效、什么失效及原因
阅读原文· arxiv.org患者上下文涉及数百份异构文档与数千个结构化数据点，但文档级元数据缺失，标准RAG在处理时间推理、跨文档依赖等任务时表现不佳。为此，研究者在埃森大学医学中心部署了ACIE——一个本地部署的智能体RAG流水线，它可推理完整患者上下文并将每个回答锚定在源段落中供临床医生验证。在一项独立的回顾性淋巴瘤登记研究中，核医学医生对每个提取值与其引用来源进行核对，在7326次判断中接受了96.5%的提取结果，各类型接受率介于80%至99%之间。
Patient contexts span hundreds of heterogeneous documents and thousands of structured data points, yet the document-level metadata that AI systems need for retrieval and triage is absent or incomplete. Standard retrieval-augmented generation fails on this data, mishandling temporal reasoning, cross-document dependencies, and missing metadata. We deploy ACIE (Agentic Clinical Information Extraction) at University Medicine Essen: an on-premise agentic RAG pipeline that reasons over complete patient contexts and grounds every answer in source passages for clinician verification. We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospective lymphoma registry study, in which nuclear-medicine physicians verify every extracted value against its cited sources. Across 7,326 judgments, clinicians accepted 96.5\% of extractions, with per-type acceptance ranging from 80\% to 99\%.