Jaladanki Suraj K, Vaid Akhil, Sawant Ashwin S, Xu Jie, Shah Kush, Dellepiane Sergio, Paranjpe Ishan, Chan Lili, Kovatch Patricia, Charney Alexander W, Wang Fei, Glicksberg Benjamin S, Singh Karandeep, Nadkarni Girish N
The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
The Mount Sinai Clinical Intelligence Center (MSCIC), New York, New York, USA.
medRxiv. 2021 Jul 28:2021.07.25.21261105. doi: 10.1101/2021.07.25.21261105.
Federated learning is a technique for training predictive models without sharing patient-level data, thus maintaining data security while allowing inter-institutional collaboration. We used federated learning to predict acute kidney injury within three and seven days of admission, using demographics, comorbidities, vital signs, and laboratory values, in 4029 adults hospitalized with COVID-19 at five sociodemographically diverse New York City hospitals, between March-October 2020. Prediction performance of federated models was generally higher than single-hospital models and was comparable to pooled-data models. In the first use-case in kidney disease, federated learning improved prediction of a common complication of COVID-19, while preserving data privacy.
联邦学习是一种在不共享患者层面数据的情况下训练预测模型的技术，从而在允许机构间合作的同时维护数据安全。2020年3月至10月期间，我们在纽约市五家社会人口统计学特征各异的医院中，对4029名因新冠肺炎住院的成年人，利用人口统计学、合并症、生命体征和实验室值，采用联邦学习来预测入院后三天和七天内的急性肾损伤。联邦模型的预测性能总体上高于单医院模型，且与汇总数据模型相当。在肾病的首个应用案例中，联邦学习在保护数据隐私的同时，改善了对新冠肺炎常见并发症的预测。
