Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach (Preprint)
Authors:
- Akhil VaidAVAkhil Vaid
- Suraj K JaladankiSJSuraj K Jaladanki
- Jie XuJie Xu
- Shelly TengSTShelly Teng
- Arvind KumarAKArvind Kumar
- Samuel LeeSLSamuel Lee
- Sulaiman SomaniSSSulaiman Somani
- Ishan ParanjpeIPIshan Paranjpe
- Jessica K De FreitasJFJessica K De Freitas
- Tingyi WanyanTWTingyi Wanyan
- Kipp W JohnsonKJKipp W Johnson
- Mesude BicakMBMesude Bicak
Preprint
- 9 September 2020
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
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.Keywords
All Related Versions
- Published version: JMIR Medical Informatics, 9 (1), e24207.
This publication has 16 references indexed in Scilit:
- Sampling the host response to SARS-CoV-2 in hospitals under siegeNature Medicine, 2020
- Association of Treatment Dose Anticoagulation With In-Hospital Survival Among Hospitalized Patients With COVID-19JACC, 2020
- Coronavirus 2019 and People Living With Human Immunodeficiency Virus: Outcomes for Hospitalized Patients in New York CityClinical Infectious Diseases, 2020
- Artificial intelligence–enabled rapid diagnosis of patients with COVID-19Nature Medicine, 2020
- COVID-19 and Cardiovascular DiseaseCirculation, 2020
- The Incubation Period of Coronavirus Disease 2019 (COVID-19) From Publicly Reported Confirmed Cases: Estimation and ApplicationAnnals of Internal Medicine, 2020
- An interactive web-based dashboard to track COVID-19 in real timeThe Lancet Infectious Diseases, 2020
- International Electronic Health Record-Derived COVID-19 Clinical Course Profiles: The 4CE ConsortiummedRxiv, 2020
- Characteristics of and Important Lessons From the Coronavirus Disease 2019 (COVID-19) Outbreak in ChinaJAMA, 2020
- Pathological findings of COVID-19 associated with acute respiratory distress syndromeThe Lancet Respiratory Medicine, 2020