Federated Learning for Predicting Clinical Outcomes in COVID-19 Patients

Abstract

Federated learning (FL) is a method for training artificial intelligence (AI) models with data from multiple sources while maintaining the anonymity of the data, thus removing many barriers to data sharing. Here we use data from 20 institutes across the globe to train a FL model, called “EXAM” (EMR CXR AI Model), that predicts future oxygen requirements of symptomatic COVID-19 patients using inputs of vital signs, laboratory data, and chest X-rays. EXAM achieved an average area under the curve (AUC) greater than 0.92 for both 24/72h predictions, and it provided an average improvement in the avg. AUC of 16%, and an average increase in generalizability of 38% when compared to models trained at a single site using the same site’s data (‘local models’). For predicting mechanical ventilation (MV) treatment (or death) at 24h at the independent test site, EXAM achieved a sensitivity of 0.950 and a specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for predicting clinical outcomes in COVID-19 patients, setting the stage for broader use of FL in healthcare.