基于纵向电子健康记录的图增强疾病轨迹发现与时间终点预测
Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records
AI总结：
该研究提出基于MIMIC-IV v3.1的图增强框架，结合分支基序与时间感知Transformer，在EHR的疾病时间终点预测中提升了AUPRC并降低事件时间MAE，证实分支基序的核心价值为长程时间支持。
摘要：
纵向电子健康记录（EHR）可揭示疾病进展结构，而有效的预测需满足泄漏控制的发现、审查感知的结局以及可检查的轨迹证据。我们开发了一个基于MIMIC-IV v3.1的图增强框架，该框架在图构建前对患者进行划分，学习仅在训练集中的连续入院转换，并冻结在验证数据上选择的终点特定分支基序策略。最终目录包含99527个基序，时间感知Transformer通过终点特定交叉注意力为每个终点检索最多24个患者兼容基序。在5个训练种子下，微平均AUPRC从0.9330提升至0.9357，而事件时间平均绝对误差（MAE）从676.9天降至657.7天（减少19.2天；95%配对患者集群自举置信区间为13.8-24.8）。时间效应存在异质性：730天内事件的MAE恶化，但730天后发生的事件MAE改善58.9天。在探索性内部时间划分中，分支条件使条件事件时间MAE减少26.9天（95%置信区间为23.0-30.8），但未显示微平均AUPRC的改善。在支持的0-2555天区间内的校正生存评估，未确立宏观C指数或综合Brier评分优于匹配的仅历史离散风险模型。有向、度匹配的GNN修复显著改善了未见边的发现，但在固定基序身份内替换GNN衍生评分未改善下游预测。这些结果表明，分支基序是结构化轨迹上下文，其主要价值在于长程时间支持，而非统一更强的终点判别、生存预测或因果解释。
英文摘要：
Longitudinal electronic health records (EHRs) can reveal disease-progression structure, while useful forecasting requires leakage-controlled discovery, censor-aware outcomes, and inspectable trajectory evidence. We developed a graph-enhanced framework in MIMIC-IV v3.1 that splits patients before graph construction, learns train-only consecutive-admission transitions, and freezes endpoint-specific branching-motif policies selected on validation data. The final catalog contained 99,527 motifs, and a time-aware Transformer retrieved at most 24 patient-compatible motifs per endpoint through endpoint-specific cross-attention. Across five training seeds, micro-AUPRC increased from 0.9330 to 0.9357, while event-time MAE decreased from 676.9 to 657.7 days (reduction 19.2 days; 95% paired patient-cluster bootstrap CI, 13.8-24.8). Timing effects were heterogeneous: MAE worsened for events within 730 days but improved by 58.9 days for events occurring after 730 days. In an exploratory internal temporal split, branch conditioning reduced conditional event-time MAE by 26.9 days (95% CI, 23.0-30.8) without evidence of better micro-AUPRC. Corrected survival evaluation over the supported 0-2,555-day interval did not establish macro C-index or integrated Brier score superiority over a matched history-only discrete-hazard model. A directed, degree-matched GNN repair substantially improved unseen-edge discovery, yet replacing GNN-derived scores within fixed motif identities did not improve downstream forecasting. These results position branching motifs as structured trajectory context whose main value is long-range timing support rather than uniformly stronger endpoint discrimination, survival prediction, or causal explanation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
