arXiv：cs.LG· Jin-Jia Zheng, Vincent S. Tseng·· 4 小时前
基于图增强的纵向EHR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 导读
研究团队在 MIMIC-IV v3.1 上开发了一个图增强框架，通过先拆分患者再构建图、仅用训练集学习连续入院转移并冻结终点特异性分支模体策略，最终构建了包含 99,527 个模体的目录。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20502 [cs.LG] |
| (or arXiv:2610.20502v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20502 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Vincent S. Tseng [view email]
[v1]
Wed, 14 Oct 2026 17:08:50 UTC (963 KB)
来源：arXiv：cs.LG · arxiv.org