arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.01249cs.LG
收藏

KAT-GNN:一种用于电子健康记录风险预测的知识增强时序图神经网络

KAT-GNN: A Knowledge-Augmented Temporal Graph Neural Network for Risk Prediction in Electronic Health Records

Institute of Computer Science and Engineering, National Yang Ming Chiao Tung University(计算机科学与工程研究所,国立阳明交通大学);School of Medicine, National Tsing Hua University(医学院,国立清华大学);Department of Computer Science, National Yang Ming Chiao Tung University(计算机科学系,国立阳明交通大学);Computational Health Informatics Program, Boston Children’s Hospital(计算健康信息学计划,波士顿儿童医院)

Kun-Wei Lin, Yu-Chen Kuo, Hsin-Yao Wang, Yi-Ju Tseng

AI总结:

针对异构不规则时序电子健康记录建模的挑战,提出KAT-GNN框架,通过构建患者图并结合SNOMED CT本体边与共现先验进行知识增强,利用时间感知transformer捕获纵向动态,在CAD和死亡率预测任务中达到最先进水平。

摘要:

利用电子健康记录(EHRs)进行临床风险预测对于促进及时干预和临床决策支持至关重要。然而,对异构且不规则的时序EHR数据进行建模带来了重大挑战。我们提出了KAT-GNN(Knowledge-Augmented Temporal Graph Neural Network,知识增强时序图神经网络),这是一个基于图的框架,它整合了临床知识和时间动态进行风险预测。KAT-GNN首先从EHRs构建特定模态的患者图。然后使用两个知识源对这些图进行增强:(1)从SNOMED CT导出的本体驱动边和(2)从EHRs提取的共现先验。随后,采用时间感知transformer从图编码的患者表示中捕获纵向动态。KAT-GNN在三个不同的数据集和任务上进行了评估:使用CGRD(Chang Gung Research Database)进行冠状动脉疾病(CAD)预测,以及使用MIMIC-III和MIMIC-IV数据集进行院内死亡率预测。KAT-GNN在CAD预测中实现了最先进的性能(AUROC:0.9269 ± 0.0029),并在MIMIC-III(AUROC:0.9230 ± 0.0070)和MIMIC-IV(AUROC:0.8849 ± 0.0089)的死亡率预测中表现出强劲的结果,持续优于GRASP和RETAIN等既有基线。消融研究证实,基于知识的增强和时间建模组件都是性能提升的重要贡献者。这些发现表明,将临床知识整合到图表示中,再加上时间感知注意力机制,为跨不同临床任务和数据集的风险预测提供了一种有效且通用的方法。

英文摘要:

Clinical risk prediction using electronic health records (EHRs) is vital to facilitate timely interventions and clinical decision support. However, modeling heterogeneous and irregular temporal EHR data presents significant challenges. We propose \textbf{KAT-GNN} (Knowledge-Augmented Temporal Graph Neural Network), a graph-based framework that integrates clinical knowledge and temporal dynamics for risk prediction. KAT-GNN first constructs modality-specific patient graphs from EHRs. These graphs are then augmented using two knowledge sources: (1) ontology-driven edges derived from SNOMED CT and (2) co-occurrence priors extracted from EHRs. Subsequently, a time-aware transformer is employed to capture longitudinal dynamics from the graph-encoded patient representations. KAT-GNN is evaluated on three distinct datasets and tasks: coronary artery disease (CAD) prediction using the Chang Gung Research Database (CGRD) and in-hospital mortality prediction using the MIMIC-III and MIMIC-IV datasets. KAT-GNN achieves state-of-the-art performance in CAD prediction (AUROC: 0.9269 $\pm$ 0.0029) and demonstrated strong results in mortality prediction in MIMIC-III (AUROC: 0.9230 $\pm$ 0.0070) and MIMIC-IV (AUROC: 0.8849 $\pm$ 0.0089), consistently outperforming established baselines such as GRASP and RETAIN. Ablation studies confirm that both knowledge-based augmentation and the temporal modeling component are significant contributors to performance gains. These findings demonstrate that the integration of clinical knowledge into graph representations, coupled with a time-aware attention mechanism, provides an effective and generalizable approach for risk prediction across diverse clinical tasks and datasets.

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。

↑