arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.07569cs.LGcs.AI
收藏

基于电子健康记录的多任务异构图学习

Multi-task Heterogeneous Graph Learning on Electronic Health Records

The University of Hong Kong(香港大学)

Tsai Hor Chan, Guosheng Yin, Kyongtae Bae, Lequan Yu

AI总结:

针对电子健康记录的异质性、稀疏性及现有方法单任务局限的问题,提出融合异构图建模、因果去噪和多任务正则的MulT-EHR框架,在MIMIC系列数据集的四项任务上性能优于现有最优方法。

摘要:

电子健康记录(EHR)学习因能够助力实现精准医疗诊断,正受到越来越多的关注。由于EHR包含丰富的信息,可表征实体间的复杂交互关系,用图对EHR建模已在实践中被证明是有效的。然而,EHR存在高度异质性、稀疏性和复杂性,这会降低大多数应用于其上的模型的性能。此外,现有的EHR建模方法通常专注于学习单个任务的表示,忽略了EHR分析问题的多任务特性,导致模型在不同任务间的泛化能力有限。针对这些局限,我们提出了一种新型EHR建模框架,名为MulT-EHR(多任务EHR),该框架利用异构图挖掘EHR中的复杂关系并对其异质性进行建模。为缓解大量噪声的影响,我们引入了一个基于因果推断框架的去噪模块,以校正严重的混杂效应并减少EHR数据中的噪声。此外,由于我们的模型采用单个图神经网络同时进行多任务预测,我们设计了一个多任务学习模块,利用任务间的知识对训练过程进行正则化。在MIMIC-III和MIMIC-IV数据集上开展的大量实证研究验证了,所提出的方法在四项主流EHR分析任务——药物推荐,以及住院时长、死亡率和再入院率预测——上始终优于当前最优的设计方案。全面的消融实验证明了我们的方法在关键组件和超参数发生变化时仍具备鲁棒性。

英文摘要:

Learning electronic health records (EHRs) has received emerging attention because of its capability to facilitate accurate medical diagnosis. Since the EHRs contain enriched information specifying complex interactions between entities, modeling EHRs with graphs is shown to be effective in practice. The EHRs, however, present a great degree of heterogeneity, sparsity, and complexity, which hamper the performance of most of the models applied to them. Moreover, existing approaches modeling EHRs often focus on learning the representations for a single task, overlooking the multi-task nature of EHR analysis problems and resulting in limited generalizability across different tasks. In view of these limitations, we propose a novel framework for EHR modeling, namely MulT-EHR (Multi-Task EHR), which leverages a heterogeneous graph to mine the complex relations and model the heterogeneity in the EHRs. To mitigate the large degree of noise, we introduce a denoising module based on the causal inference framework to adjust for severe confounding effects and reduce noise in the EHR data. Additionally, since our model adopts a single graph neural network for simultaneous multi-task prediction, we design a multi-task learning module to leverage the inter-task knowledge to regularize the training process. Extensive empirical studies on MIMIC-III and MIMIC-IV datasets validate that the proposed method consistently outperforms the state-of-the-art designs in four popular EHR analysis tasks -- drug recommendation, and predictions of the length of stay, mortality, and readmission. Thorough ablation studies demonstrate the robustness of our method upon variations to key components and hyperparameters.

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。

↑