GraphBEAT：用于胃肠道癌症早期风险分层的基于图的分桶式时间事件聚合方法
GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
AI总结：
本文提出GraphBEAT框架，通过分桶时序图表示学习处理稀疏异质EHR，在多站点数据上预测不同提前期的胃肠道癌症，性能优于基线模型且计算效率更高。
摘要：
纵向电子健康记录（EHR）包含患者健康相关的互补诊断与实验室信息，但记录的不规则性、稀疏性、异质性及不完整性为EHR建模带来挑战。为解决该问题，本文提出GraphBEAT（Graph-based Bucketized Event Aggregation over Time，基于图的分桶式时间事件聚合），这是一种时序图表示学习框架，可将临床事件分组为时间桶，并将观测特征转换为患者特有的时序有向图，以实现胃肠道癌症的早期风险分层。EHR图中的每个节点编码临床事件的特征标识、观测值及时间位置。该框架采用上下文感知的时间衰减消息传递机制对连续时间桶间的转换进行建模，随后通过多头注意力池化生成患者级表示。GraphBEAT在多站点纵向诊断代码与实验室检测数据上进行训练和评估，用于预测12、24及36个月诊断 lead time（提前期）的胰腺癌、肝癌及肠癌。在所有实验设置中，GraphBEAT的性能始终优于基线图神经网络（GraphSAGE、GAT、GCN）及序列建模方法（Transformer、长短期记忆网络[LSTM]）；与Transformer和LSTM基线相比，GraphBEAT每位患者所需的浮点运算量减少250倍以上，参数数量减少20倍以上。这些结果表明，GraphBEAT是一种从稀疏、异质的纵向健康记录中进行癌症风险分层的准确且计算高效的方法。
英文摘要：
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.
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。
