arXiv cs.AI· Leo Y. Li-Han, Chris Varghese, Elizabeth B. Habermann, Mark J. Truty, William R. G. Perry, Cornelius A. Thiels, Hojjat Salehinejad·· 2 天前AI 评分24
GraphBEAT：基于图的时间分桶事件聚合用于胃肠道癌症早期风险分层
GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
AI 导读
GraphBEAT 是一个时序图表示学习框架，将临床事件按时间分桶并转化为患者特异性时序有向图，用于胃肠道癌症早期风险分层。在多站点纵向诊断编码与实验室检测数据上预测胰腺癌、肝癌和肠癌的 12、24、36 个月提前诊断，GraphBEAT 全面优于 GraphSAGE、GAT、GCN 及 Transformer、LSTM 基线。
正文 · 原文
Abstract:Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health. However, irregularity, sparsity, heterogeneity, and incompleteness in documentation complicate EHR modeling. To address the problem, we introduce GraphBEAT (Graph-based Bucketized Event Aggregation over Time), a temporal graph representation learning framework that groups clinical events into time buckets and transforms observed features into patient-specific, temporally directed graphs to enable early risk stratification for gastrointestinal cancers. Each node in an EHR graph encodes feature identity, observed value, and temporal position of clinical events. A context-aware, time-decay message-passing mechanism models transitions between successive buckets, followed by multi-head attention pooling to generate patient-level representations. GraphBEAT was trained and evaluated on multi-site longitudinal diagnosis codes and laboratory tests to predict pancreatic, liver, and intestinal cancer at 12-, 24-, and 36-month diagnostic lead times. In all experimental setups, GraphBEAT consistently outperformed baseline graph neural networks (GraphSAGE, GAT, and GCN) and sequence modeling approaches (Transformer and long short-term memory [LSTM]). GraphBEAT also required over 250x fewer floating-point operations per patient and over 20x fewer parameters than the Transformer and LSTM baselines. These results support GraphBEAT as an accurate and computationally efficient approach for cancer risk stratification from sparse, heterogeneous longitudinal health records.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.22014 [cs.LG] |
| (or arXiv:2610.22014v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22014 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Leo Li-Han [view email]
[v1]
Thu, 15 Oct 2026 14:55:39 UTC (6,590 KB)
来源：arXiv cs.AI · arxiv.org