@Article{info:doi/10.2196/24207,
author="Vaid, Akhil
and Jaladanki, Suraj K
and Xu, Jie
and Teng, Shelly
and Kumar, Arvind
and Lee, Samuel
and Somani, Sulaiman
and Paranjpe, Ishan
and De Freitas, Jessica K
and Wanyan, Tingyi
and Johnson, Kipp W
and Bicak, Mesude
and Klang, Eyal
and Kwon, Young Joon
and Costa, Anthony
and Zhao, Shan
and Miotto, Riccardo
and Charney, Alexander W
and B{\"o}ttinger, Erwin
and Fayad, Zahi A
and Nadkarni, Girish N
and Wang, Fei
and Glicksberg, Benjamin S",
title="Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach",
journal="JMIR Med Inform",
year="2021",
month="Jan",
day="27",
volume="9",
number="1",
pages="e24207",
keywords="federated learning; COVID-19; machine learning; electronic health records",
abstract="Background: Machine learning models require large datasets that may be siloed across different health care institutions. Machine learning studies that focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. Objective: We aimed to use federated learning, a machine learning technique that avoids locally aggregating raw clinical data across multiple institutions, to predict mortality in hospitalized patients with COVID-19 within 7 days. Methods: Patient data were collected from the electronic health records of 5 hospitals within the Mount Sinai Health System. Logistic regression with L1 regularization/least absolute shrinkage and selection operator (LASSO) and multilayer perceptron (MLP) models were trained by using local data at each site. We developed a pooled model with combined data from all 5 sites, and a federated model that only shared parameters with a central aggregator. Results: The LASSOfederated model outperformed the LASSOlocal model at 3 hospitals, and the MLPfederated model performed better than the MLPlocal model at all 5 hospitals, as determined by the area under the receiver operating characteristic curve. The LASSOpooled model outperformed the LASSOfederated model at all hospitals, and the MLPfederated model outperformed the MLPpooled model at 2 hospitals. Conclusions: The federated learning of COVID-19 electronic health record data shows promise in developing robust predictive models without compromising patient privacy. ",
issn="2291-9694",
doi="10.2196/24207",
url="http://medinform.jmir.org/2021/1/e24207/",
url="https://doi.org/10.2196/24207",
url="http://www.ncbi.nlm.nih.gov/pubmed/33400679"
}