A privacy-preserving and computation-efficient federated algorithm for generalized linear mixed models to analyze correlated electronic health records data
Yan Z, Zachrison K, Schwamm L, Estrada J, Duan R. A privacy-preserving and computation-efficient federated algorithm for generalized linear mixed models to analyze correlated electronic health records data. PLOS ONE 2023, 18: e0280192. PMID: 36649349, PMCID: PMC9844867, DOI: 10.1371/journal.pone.0280192.Peer-Reviewed Original ResearchConceptsFederated algorithmPrivacy-preserving data integrationEHR dataElectronic health record dataComputation resource requirementsHealth record dataLongitudinal EHR dataPrivacy protectionData integrationResource requirementsMultiple healthcare facilitiesNumerical experimentsComputational efficiencyGeneralized linear mixed modelRecord dataCorrelated dataSite‐level heterogeneityAlgorithmNetworkSummary statisticsResearch NetworkLimited amountDatasetLinear mixed modelsGLMM