arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.09288cs.AI

MIPO：患者旅程与医学本体的相互整合用于医疗表示学习

MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning

Australian AI Institute, Faculty of Engineering and IT, University of Technology Sydney（澳大利亚人工智能研究所，工程与信息技术学院，悉尼技术大学）；School of Information Technology and Electrical Engineering, The University of Queensland（信息科技与电气工程学院，昆士兰大学）；Department of Data Science and AI, The Hong Kong Polytechnic University（数据科学与人工智能学院，香港理工大学）；Health Economics and Research Division, Department of Health and Aged Care（健康经济学与研究部，健康与老龄化部）

Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Chengqi Zhang, Allison Clarke, Clement Schlegel

备注：
9 pages, 4 figures, accepted for IJCNN 2025
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

MIPO通过整合患者旅程与医学本体，提升医疗表示学习的鲁棒性和可解释性。

摘要：

电子健康记录（EHRs）上的表示学习在下游医疗预测任务中起着至关重要的作用。尽管自然语言处理技术，如循环神经网络和自注意力机制，已被用于从分层、时间戳化的EHR数据中学习医学表示，但当通用或任务特定的数据有限时，它们往往难以应对。最近的努力试图通过将医学本体（即知识图谱）纳入自监督任务如诊断预测中来缓解这一挑战。然而，仍然存在两个主要问题：（1）小而统一的本体缺乏多样性，不利于鲁棒学习；（2）对患者旅程背后关键上下文或依赖关系的注意力不足，这可能进一步增强基于本体的学习。为了解决这些差距，我们提出了MIPO（患者旅程与医学本体的相互整合），一个稳健的端到端框架，采用基于Transformer的架构进行表示学习。MIPO通过顺序诊断预测任务强调任务特定的表示学习，同时纳入基于本体的疾病分类任务。引入了一个图嵌入模块，以整合患者就诊记录的信息，从而缓解数据不足的问题。这种设置创建了一个相互促进的循环，其中患者旅程嵌入和本体嵌入都从彼此中受益。我们验证了MIPO在两个真实世界基准数据集上的表现，证明其在数据充足和有限的情况下均优于基线方法。此外，所产生的诊断嵌入提供了改进的可解释性，突显了MIPO在实际医疗应用中的前景。

英文摘要：

Representation learning on electronic health records (EHRs) plays a vital role in downstream medical prediction tasks. Although natural language processing techniques, such as recurrent neural networks, and self-attention, have been adapted for learning medical representations from hierarchical, time-stamped EHR data, they often struggle when either general or task-specific data are limited. Recent efforts have attempted to mitigate this challenge by incorporating medical ontologies (i.e., knowledge graphs) into self-supervised tasks like diagnosis prediction. However, two main issues remain: (1) small and uniform ontologies that lack diversity for robust learning, and (2) insufficient attention to the critical contexts or dependencies underlying patient journeys, which could further enhance ontology-based learning. To address these gaps, we propose MIPO (Mutual Integration of Patient Journey and Medical Ontology), a robust end-to-end framework that employs a Transformer-based architecture for representation learning. MIPO emphasizes task-specific representation learning through a sequential diagnosis prediction task, while also incorporating an ontology-based disease-typing task. A graph-embedding module is introduced to integrate information from patient visit records, thus alleviating data insufficiency. This setup creates a mutually reinforcing loop, where both patient-journey embedding and ontology embedding benefit from each other. We validate MIPO on two real-world benchmark datasets, showing that it consistently outperforms baseline methods under both sufficient and limited data conditions. Furthermore, the resulting diagnosis embeddings offer improved interpretability, underscoring the promise of MIPO for real-world healthcare applications.

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。

↑