临床意图提取：FHIR对齐的表示与CIRCA基准
Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark
浏览论文内容
中文总结 AI 辅助
提出临床意图提取任务及FHIR对齐的表示CIR，构建含10,011个意图的CIRCA基准，揭示现有模型在完整结构化意图提取上的不足。
中文摘要 AI 辅助
前瞻性临床行动，即决定患者下一步会发生什么的随访、医嘱、转诊和指示，目前以碎片化的形式标注在各种不兼容的语料库中：每个语料库仅记录一个文本片段和一个粗略类别。我们引入了临床意图提取（CIE）任务，即将这些行动恢复为完整的结构化记录，并提出了临床意图表示（CIR），该表示将每个行动分解为其动词、类型、编码目标、时间和条件，并增加了先前数据集未共同表示的两个轴：请求意图，即行动背后的权威（提议、计划、医嘱或选项，与HL7 FHIR对齐），以及模态，即临床强度的七级量表。将五个异构语料库（CLIP、MedDec、ap_parsing、PaniniQA、SIMORD）重新表示为CIR，得到CIRCA：涵盖两种笔记分布的10,011个统一意图，并包含人工验证的子集、源到CIR的交叉映射，以及确定性的FHIR R4映射器。CIRCA通过三模型共识构建，自动接受高一致性意图，并将其余意图交由人工审查；经审计的一致性层级与人工决策的匹配率为88.4%。对五个现有模型进行无任务特定训练的基准测试，揭示了CIRCA所针对的差距：给定片段，它们能很好地标注类型（85%至91%），但四个封闭字段全部正确的概率仅为18%至35%。所有工件均已发布，其中MIMIC衍生的层以独立标注的形式共享，需通过PhysioNet凭证访问。
英文摘要
Prospective clinical actions, the follow-ups, orders, referrals, and instructions that deter-mine what happens to a patient next, are annotated today in thin fragments across incom-patible corpora: each records a text span and one coarse category. We introduce Clinical Intent Extraction (CIE), the task of recovering these actions as complete structured rec-ords, and the Clinical Intent Representation (CIR), which decomposes each action into its verb, type, coded target, timing, and condition, and adds two axes prior datasets do not jointly represent: request-intent, the authority behind the action (proposal, plan, order, or option, aligned to HL7 FHIR), and modality, a seven-valued scale of clinical strength. Re-expressing five heterogeneous corpora (CLIP, MedDec, ap_parsing, PaniniQA, SIMORD) in the CIR yields CIRCA: 10,011 harmonized intents spanning two note distributions, with a human-validated subset, source-to-CIR crosswalks, and a deterministic FHIR R4 mapper. CIRCA is built by three-model consensus that auto-accepts high-agreement in-tents and routes the rest to human review; the audited agreement stratum matches human decisions 88.4% of the time. Benchmarking five existing models without task-specific training exposes the gap CIRCA targets: given the span, they label type well (85 to 91%) but get all four closed fields right only 18 to 35% of the time. All artifacts are released, with MIMIC-derived layers shared as stand-off annotations under PhysioNet credentialed access.
发表机构
- Holon Institute of Technology（霍隆理工学院）
- Afeka College of Engineering（阿费卡工程学院）
机构由 AI 辅助整理，请以论文原文为准。
