Multi-task learning (MTL) is a machine learning technique aiming to improve model performance by leveraging information across many tasks. It has been used extensively on various data modalities, including electronic health record (EHR) data. However, despite significant use on EHR data, there has been little systematic investigation of the utility of MTL across the diverse set of possible tasks and training schemes of interest in healthcare. In this work, we examine MTL across a battery of tasks on EHR time-series data. We find that while MTL does suffer from common negative transfer, we can realize significant gains via MTL pre-training combined with single-task fine-tuning. We demonstrate that these gains can be achieved in a task-independent manner and offer not only minor improvements under traditional learning, but also notable gains in a few-shot learning context, thereby suggesting this could be a scalable vehicle to offer improved performance in important healthcare contexts.
Transfer Learning in Electronic Health Records through Clinical Concept Embedding
University of Oxford（牛津大学）；NIHR Oxford Biomedical Research Centre（英国国家健康研究所牛津生物医学研究中心）；Oxford University Hospitals NHS Foundation Trust（牛津大学医院国民保健服务基金会信托）
Contrastive Learning on Multimodal Analysis of Electronic Health Records
Harvard T.H. Chan School of Public Health（哈佛T.H. 柏林公共卫生学院）；Harvard Medical School（哈佛医学院）；Rutgers University（罗格斯大学）；National University of Singapore（新加坡国立大学）
Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；Harvard Medical School（哈佛医学院）；Weill Cornell Medicine, Cornell University（康奈尔大学威尔康奈尔医学院）
Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
Simula Metropolitan Center for Digital Engineering（西姆拉大都会数字工程中心）；Oslo Metropolitan University（奥斯陆城市大学）；Swammerdam Institute for Life Sciences, University of Amsterdam（阿姆斯特丹大学斯瓦默丹生命科学研究所）
Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
Peng Cheng Laboratory（鹏城实验室）；Carnegie Mellon University（卡内基梅隆大学）；University of Toronto Mississauga（多伦多大学密西沙加分校）；Peking University（北京大学）
背景资料：电子健康档案（Electronic Health Records，EHR）包含了丰富的患者健康历史信息，通常包括结构化和非结构化数据。已经有许多研究专注于从结构化数据中提取有价值的信息，例如疾病代码，实验室测试结果和治疗方法。然而，单靠结构化数据未必能全面反映病人的数据，而这些数据间中亦可能有错误的纪录。目的：随着机器学习（ML）和深度学习（DL）技术的最新进展，越来越多的研究试图通过合并非结构化自由文本数据来获得更准确的结果。本文回顾了使用多模态数据（即结构化和非结构化数据的组合）的研究，这些数据来自EHR，作为传统ML或DL模型的输入，以解决目标任务。材料与方法：我们在电气和电子工程师协会（IEEE）数字图书馆、PubMed和计算机械协会（ACM）数字图书馆中检索了与基于ML的多模态EHR研究相关的文章。结果和讨论：在最后的94项研究中，我们重点关注来自不同模态的数据如何使用传统的ML和DL技术进行组合和交互，以及这些算法如何应用于EHR相关任务。此外，我们调查这些融合方法的优点和局限性，并指出未来的方向ML为基础的多模态EHR研究。
A Comprehensive Benchmark for COVID-19 Predictive Modeling Using Electronic Health Records in Intensive Care
University of Edinburgh（爱丁堡大学）；Health Data Research UK（英国健康数据研究中心）；Peking University（北京大学）；Peking University Third Hospital（北京大学第三医院）；Kaihong Digital（凯宏数字）
Measuring the Stability of EHR- and EKG-based Predictive Models
Data Science Institute（数据科学研究所）；Columbia University（哥伦比亚大学）；School of Public Health（公共卫生学院）；University of California at Berkeley（加州大学伯克利分校）；Booth School of Business（布斯商学院）；University of Chicago（芝加哥大学）
CAAT-EHR: Cross-Attentional Autoregressive Transformer for Multimodal Electronic Health Record Embeddings
Department of Computer Science and Engineering, University of North Texas（计算机科学与工程系，北卡罗来纳大学达顿分校）；BioDiscovery Institute, University of North Texas（生物发现研究所，北卡罗来纳大学达顿分校）；Center for Computational Life Sciences, University of North Texas（计算生命科学中心，北卡罗来纳大学达顿分校）
Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data
Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Centre for Medical Informatics, University of Edinburgh（爱丁堡大学医学信息学中心）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；National Engineering Research Center for Software Engineering, Peking University（北京大学国家软件工程研究中心）；Health Data Research UK（英国健康数据研究中心）
EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders
Georgia Institute of Technology（佐治亚理工学院）；IBM Research（IBM研究院）；Vanderbilt University（范德堡大学）；Sutter Health（萨特健康）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
