Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site’s data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and 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 prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

联邦学习（FL）是一种利用多个来源的数据训练人工智能模型的方法，同时保持数据匿名性，从而消除数据共享的许多障碍。在这里，我们使用来自全球 20 个机构的数据来训练一个 FL 模型，称为 EXAM（电子病历 (EMR) 胸部 X 射线 AI 模型），该模型使用生命体征的输入来预测有症状的 COVID-19 患者未来的氧气需求。体征、实验室数据和胸部 X 光检查。EXAM 的平均曲线下面积 (AUC) >0.92 可以预测从初次到急诊室就诊后 24 小时和 72 小时的结果，并且所有参与中心测得的平均 AUC 提高了 16%，并且平均增加与使用该站点数据在单个站点训练的模型相比，通用性为 38%。对于在最大的独立测试地点预测机械通气治疗或 24 小时死亡，EXAM 的敏感性为 0.950，特异性为 0.882。在这项研究中，FL 促进了无需数据交换的快速数据科学协作，并生成了一个模型，该模型可以跨异构、不统一的数据集进行推广，用于预测 COVID-19 患者的临床结果，为 FL 在医疗保健中更广泛的使用奠定了基础。