将临床事件锚定于时间：保留UID的多模态重建与源接地裁决
Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication
浏览论文内容
中文总结 AI 辅助
提出保留UID的多模态框架和GAVEL裁判，将临床事件锚定于时间，提升事件恢复43%，性能与临床注释相当。
中文摘要 AI 辅助
临床时间线支持治疗窗口分析和无泄漏建模，但出院小结常常模糊时间顺序，结构化电子健康记录表仅描述患者病程的一部分。我们提出一个保留UID的框架，将每个叙事事件发生与其源文本片段关联，并通过仅文本估计、结构化证据检索、带时间戳的源行接地和联合修订来保持该身份。我们还提出GAVEL，一个LLM裁判，比较两条UID对齐的时间线与叙事和结构化记录，以增强先前的匹配和时间评估。在六个开放权重模型和40份混合重症监护小结中，GLM 5.2多模态修订，与其仅文本变体相比，提高了时间一致性而未减少事件恢复，并与临床医生注释表现相当，而其他模型修订显示出较小的增益和较低的整体性能。消融研究表明，UID主要保留事件恢复，而源行链接支持时间定位。盲法人工审查支持大多数GAVEL发现，受控裁决偏向于多模态而非仅文本GLM 5.2，但对DeepSeek V3.2并非如此。在开发UID和裁判流程中，我们能够展示事件恢复增加43%，一个与临床医生注释竞争的框架，以及一个在重建和评估中均具有事件级来源的系统。
英文摘要
Clinical timelines support treatment-window analysis and leakage-free modeling, but discharge summaries often obscure chronology and structured EHR tables describe only part of the patient course. We present a UID-preserving framework that links each narrative event occurrence to its source span and retains that identity through text-only estimation, structured-evidence retrieval, timestamped source-row grounding, and joint revision. We also present GAVEL, an LLM judge that compares two UID-aligned timelines against the narrative and structured record, to augment prior matching and temporal assessments. Across six open-weight models and 40 mixed-critical-care summaries, the GLM 5.2 multimodal revision, as compared to its text-only variant, improved temporal agreement without reducing event recovery and performed competitively with clinician annotations, while other model revisions showed smaller gains and lower overall performance. Ablations showed that UIDs primarily preserve event retention, whereas source-row linkage supports temporal placement. Blinded human review upheld most GAVEL findings, and controlled adjudication favored multimodal over text-only GLM 5.2 but did not for DeepSeek V3.2. In developing the UID and judge pipeline, we are able to demonstrate 43\% increased event recovery, a framework competitive with clinician annotations, and a system with occurrence-level provenance for both reconstruction and evaluation.
发表机构
- National Library of Medicine, National Institutes of Health（美国国立医学图书馆，美国国立卫生研究院）
- Princeton University（普林斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。
