Privacy-preserving construction of generalized linear mixed model for biomedical computation

Abstract

Motivation The generalized linear mixed model (GLMM) is an extension of the generalized linear model (GLM) in which the linear predictor takes random effects into account. Given its power of precisely modeling the mixed effects from multiple sources of random variations, the method has been widely used in biomedical computation, for instance in the genome-wide association studies (GWASs) that aim to detect genetic variance significantly associated with phenotypes such as human diseases. Collaborative GWAS on large cohorts of patients across multiple institutions is often impeded by the privacy concerns of sharing personal genomic and other health data. To address such concerns, we present in this paper a privacy-preserving Expectation–Maximization (EM) algorithm to build GLMM collaboratively when input data are distributed to multiple participating parties and cannot be transferred to a central server. We assume that the data are horizontally partitioned among participating parties: i.e. each party holds a subset of records (including observational values of fixed effect variables and their corresponding outcome), and for all records, the outcome is regulated by the same set of known fixed effects and random effects. Results Our collaborative EM algorithm is mathematically equivalent to the original EM algorithm commonly used in GLMM construction. The algorithm also runs efficiently when tested on simulated and real human genomic data, and thus can be practically used for privacy-preserving GLMM construction. We implemented the algorithm for collaborative GLMM (cGLMM) construction in R. The data communication was implemented using the rsocket package. Availability and implementation The software is released in open source at https://github.com/huthvincent/cGLMM. Supplementary information Supplementary data are available at Bioinformatics online.

Federated Learning Algorithms for Generalized Mixed-effects Model (GLMM) on Horizontally Partitioned Data from Distributed Sources

“…The generalized linear mixed model (GLMM), which takes the heterogeneous factors into consideration, is more amenable to accommodate the heterogeneity across healthcare systems. There have been very few studies in this area and one relevant work is a privacy-preserving Bayesian GLMM model [8], which proposed an Expectation-Maximization (EM) algorithm to fit the model collaboratively on horizontally partitioned data. The convergence process is relatively slow (due to the Metropolis-Hastings sampling in the E-step) and it is also not very stable (likely to be trapped in local optima [9] in high-dimensional data).…”

“…The convergence process is relatively slow (due to the Metropolis-Hastings sampling in the E-step) and it is also not very stable (likely to be trapped in local optima [9] in high-dimensional data). In the experiment, a loose threshold (i.e., 0.08) was used as a convergence condition [8] while typical federated learning algorithms [10] in healthcare use much stringent convergence threshold (i.e., 10 −6 ).…”

“…where a is an arbitrary number. Thus, the global problem of maximizing m i l i can be divided into several local maximization problems (8). Each local site i will update the regression intermediates, and they will be combined to update the iteration status.…”

Fed-GLMM: A Privacy-Preserving and Computation-Efficient Federated Algorithm for Generalized Linear Mixed Models to Analyze Correlated Electronic Health Records Data

“…More recently, a few methods have been developed which consider using site-level random effects to account for heterogeneity across sites. For example, Luo et al proposed a lossless algorithm for the linear mixed model [30], and a few methods have been proposed for GLMM [31][32][33]. However, these approaches only consider site-level random effects, which cannot handle repeated and correlated measures within each site.…”

dPQL: a lossless distributed algorithm for generalized linear mixed model with application to privacy-preserving hospital profiling

“…There are some existing efforts on developing distributed algorithms for fitting GLMM. For example, Zhu, et al 2020 proposed a distributed algorithm based on Expectation–Maximization (EM) algorithm [8]. However, it is well known that the EM algorithm usually takes many iterations to converge.…”