A privacy-preserving and computation-efficient federated algorithm for generalized linear mixed models to analyze correlated electronic health records data

• Published in: PloS one Vol. 18; no. 1; p. e0280192
• Main Authors: Yan, Zhiyu, Zachrison, Kori S, Schwamm, Lee H, Estrada, Juan J, Duan, Rui
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 17-01-2023; Public Library of Science (PLoS)
• Subjects: Algorithms; Automation; Collaboration; Communication; Computational efficiency; Computer and Information Sciences; Computer applications; Coronaviruses; COVID-19; Data integration; Data security; Datasets; Electronic data processing; Electronic Health Records; Electronic medical records; Electronic records; Health care facilities; Health facilities; Heterogeneity; Humans; Information management; Linear Models; Management; Medical records; Medicine and Health Sciences; Methods; Mixed-effects models; Numerical experiments; People and Places; Physical Sciences; Population studies; Privacy; Research and Analysis Methods; Sample Size; Statistical models; Technology application; United States
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0280192

Large collaborative research networks provide opportunities to jointly analyze multicenter electronic health record (EHR) data, which can improve the sample size, diversity of the study population, and generalizability of the results. However, there are challenges to analyzing multicenter EHR data including privacy protection, large-scale computation resource requirements, heterogeneity across sites, and correlated observations. In this paper, we propose a federated algorithm for generalized linear mixed models (Fed-GLMM), which can flexibly model multicenter longitudinal or correlated data while accounting for site-level heterogeneity. Fed-GLMM can be applied to both federated and centralized research networks to enable privacy-preserving data integration and improve computational efficiency. By communicating a limited amount of summary statistics, Fed-GLMM can achieve nearly identical results as the gold-standard method where the GLMM is directly fitted to the pooled dataset. We demonstrate the performance of Fed-GLMM in numerical experiments and an application to longitudinal EHR data from multiple healthcare facilities.