Federated Learning for Electronic Health Records

被引:39
作者
Dang, Trung Kien [1 ]
Lan, Xiang [1 ]
Weng, Jianshu [2 ]
Feng, Mengling [1 ,3 ]
机构
[1] Natl Univ Singapore, Saw Swee Hock Sch Publ Hlth, Tahir Fdn Bldg,12 Sci Dr 2,10-01, Singapore 117549, Singapore
[2] AI Singapore, Innovat 4-0,3 Res Link,02-05, Singapore 117602, Singapore
[3] Natl Univ Singapore, Inst Data Sci, Innovat 4-0,3 Res Link,04-06, Singapore, Singapore
基金
新加坡国家研究基金会;
关键词
Federated learning; electronic health records; healthcare; neural networks; CLINICAL-RESEARCH; CARE; PRIVACY; MODELS; FEASIBILITY; REGULATIONS; MORTALITY; MULTIPLE; DATABASE; SOCIETY;
D O I
10.1145/3514500
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In data-driven medical research, multi-center studies have long been preferred over single-center ones due to a single institute sometimes not having enough data to obtain sufficient statistical power for certain hypothesis testings as well as predictive and subgroup studies. The wide adoption of electronic health records (EHRs) has made multi-institutional collaboration much more feasible. However, concerns over infrastructures, regulations, privacy, and data standardization present a challenge to data sharing across healthcare institutions. Federated Learning (FL), which allows multiple sites to collaboratively train a global model without directly sharing data, has become a promising paradigm to break the data isolation. In this study, we surveyed existing works on FL applications in EHRs and evaluated the performance of current state-of-the-art FL algorithms on two EHR machine learning tasks of significant clinical importance on a real world multi-center EHR dataset.
引用
收藏
页数:17
相关论文
共 50 条
[21]   Electronic Health Records and Heart Failure [J].
Kao, David P. .
HEART FAILURE CLINICS, 2022, 18 (02) :201-211
[22]   Blockchain Technology for Electronic Health Records [J].
Han, Yujin ;
Zhang, Yawei ;
Vermund, Sten H. .
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2022, 19 (23)
[23]   Safeguarding Confidentiality in Electronic Health Records [J].
Shenoy, Akhil ;
Appel, Jacob M. .
CAMBRIDGE QUARTERLY OF HEALTHCARE ETHICS, 2017, 26 (02) :337-341
[24]   The Move Toward Electronic Health Records [J].
Sobel, Ann E. K. .
COMPUTER, 2012, 45 (11) :22-23
[25]   Security and privacy in electronic health records: A systematic literature review [J].
Luis Fernandez-Aleman, Jose ;
Carrion Senor, Inmaculada ;
Oliver Lozoya, Pedro Angel ;
Toval, Ambrosio .
JOURNAL OF BIOMEDICAL INFORMATICS, 2013, 46 (03) :541-562
[26]   Learning from heterogeneous temporal data in electronic health records [J].
Zhao, Jing ;
Papapetrou, Panagiotis ;
Asker, Lars ;
Bostrom, Henrik .
JOURNAL OF BIOMEDICAL INFORMATICS, 2017, 65 :105-119
[27]   Electronic health records based reinforcement learning for treatment optimizing [J].
Li, Tianhao ;
Wang, Zhishun ;
Lu, Wei ;
Zhang, Qian ;
Li, Dengfeng .
INFORMATION SYSTEMS, 2022, 104
[28]   Subphenotyping depression using machine learning and electronic health records [J].
Xu, Zhenxing ;
Wang, Fei ;
Adekkanattu, Prakash ;
Bose, Budhaditya ;
Vekaria, Veer ;
Brandt, Pascal ;
Jiang, Guoqian ;
Kiefer, Richard C. ;
Luo, Yuan ;
Pacheco, Jennifer A. ;
Rasmussen, Luke V. ;
Xu, Jie ;
Alexopoulos, George ;
Pathak, Jyotishman .
LEARNING HEALTH SYSTEMS, 2020, 4 (04)
[29]   The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data [J].
Ding, Daisy Yi ;
Simpson, Chloe ;
Pfohl, Stephen ;
Kale, Dave C. ;
Jung, Kenneth ;
Shah, Nigam H. .
PACIFIC SYMPOSIUM ON BIOCOMPUTING 2019, 2019, :18-29
[30]   Readmission prediction using deep learning on electronic health records [J].
Ashfaq, Awais ;
Sant'Anna, Anita ;
Lingman, Markus ;
Nowaczyk, Slawomir .
JOURNAL OF BIOMEDICAL INFORMATICS, 2019, 97