A1058
Title: Bayesian estimation of propensity scores for integrating multiple cohorts with high-dimensional covariates
Authors: Yi Li - University of Michigan (United States)
Subharup Guha - University of Florida (United States) [presenting]
Abstract: Comparative meta-analyses of groups of subjects, which integrate multiple observational studies, rely on estimated propensity scores (PSs) to mitigate covariate imbalances. However, PS estimation grapples with the theoretical and practical challenges posed by high-dimensional covariates. Motivated by an integrative analysis of breast cancer patients across seven medical centers, the purpose is to tackle the challenges of integrating multiple observational datasets. The proposed inferential technique, called Bayesian Motif Submatrices for Covariates (B-MSC), addresses the curse of dimensionality by a hybrid of Bayesian and frequentist approaches. B-MSC uses nonparametric Bayesian "Chinese restaurant" processes to eliminate redundancy in the high-dimensional covariates and discover latent motifs or lower-dimensional structures. Standard regression techniques can be utilized with these motifs as potential predictors to accurately infer the PSs and facilitate covariate-balanced group comparisons. Simulations and meta-analysis of the motivating cancer investigation demonstrate the efficacy of the B-MSC approach to accurately estimate the propensity scores and efficiently address covariate imbalance when integrating observational health studies with high-dimensional covariates.
