通过分步路由证据，提升长期病历中事件风险预测的准确性与可解释性。
Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs
- 设计路由器-预测器-评审者三阶段流程，分离全局信息与疾病特异性评估。
- 在5个1年期诊断任务中，AUROC达到基准水平，且保持良好精确率。
- 可生成患者级证据路径，适合需要可解释性的临床风险预测场景。
从长期电子健康记录（EHR）中进行事件风险预测极具挑战性，因相关信号具有多模态特性，单个信号弱且分散于不规则的患者病史中。本文提出结构化证据路由机制，采用路由器-预测器-评审者工作流，将完整病历访问与疾病特定评估相分离。路由器将预索引的全量EHR组织为紧凑摘要与目标证据片段；预测器基于这些证据生成关联风险评估，由评审者进行反馈修正。为与监督式EHRSHOT基线对比，将路由所得证据摘要输入监督分类器输出。在五个1年期事件诊断任务中，本方法实现与现有监督式EHRSHOT基线相当的AUROC表现，并在AUPRC上保持竞争力，同时揭示患者级别的证据链条。内部消融实验进一步表明，路由机制、检验指标证据、任务引导和评审环节均对性能有贡献。
原文摘要 · Abstract (English)
Incident risk prediction from longitudinal electronic health records (EHRs) is challenging because relevant signals are multimodal, weak in isolation, and distributed across irregular patient histories. We propose structured evidence routing, a router-predictor-reviewer workflow that separates full-record access from disease-specific assessment. The router organizes the complete pre-index EHR into a compact summary and targeted evidence slices; the predictor uses this evidence to form an evidence-linked risk assessment, which the reviewer critiques. For comparison with supervised EHRSHOT baselines, we pair the routed evidence summaries with a supervised classifier readout. Across five 1-year incident diagnosis tasks, our method reaches the AUROC range of established supervised EHRSHOT baselines and remains competitive on AUPRC, while exposing a patient-specific evidence trail. Internal pre-readout ablations further suggest that routing, laboratory evidence, task guidance, and review each contribute to performance.
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。