Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs

2026-08-23

AI Summary

本文提出了一种结构化证据路由方法，通过路由器-预测器-审查者工作流程解决从多模态纵向电子健康记录中预测事件风险的问题。

Abstract

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.

Problem

• incident risk prediction
• longitudinal EHRs
• multimodal signals
• weak signals
• irregular patient histories

Innovation

• structured evidence routing
• multimodal longitudinal EHRs
• router-predictor-reviewer workflow
• evidence-linked risk assessment