A Bayesian Nonparametric Approach for Inferring Drug Combination Effects on Mental Health in People with HIV

• Activity Number: 443 - Latent Variables, Causal Inference, Machine Learning and Other Topics in Mental Health Statistics
• Type: Contributed
• Date/Time: Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
• Sponsor: Mental Health Statistics Section
• Author(s): Wei Jin* and Yang Ni and Leah Rubin and Amanda Spence and Yanxun Xu
• Companies: Department of Applied Mathematics and Statistics, Johns Hopkins University and Texas A&M University and Departments of Neurology and Psychiatry, Johns Hopkins University School of Medicine and Department of Medicine, Division of Infectious Disease and Travel Medicine, Georgetown Uni and Department of Applied Mathematics and Statistics, Johns Hopkins University
• Keywords: Antiretroviral therapy; Distance-dependent Chinese restaurant process; Longitudinal cohort study; Precision medicine; Subset-tree kernel

Abstract

Although combination antiretroviral therapy (ART) with three or more drugs is highly effective in suppressing viral load for people with HIV (PWH), many ART agents may exacerbate mental health-related adverse effects. Therefore, understanding the effects of combination ART on mental health can help clinicians personalize medicine to avoid undesirable health outcomes. However, modeling electronic health records data is challenging due to high dimensionality of the drug combination space and the individual heterogeneity. We develop a Bayesian nonparametric approach to learn drug combination effect on mental health in PWH adjusting for demographic, behavioral, and clinical factors. Our method is built upon the subset-tree kernel that represents drug combinations in a way that synthesizes known regimen structure into a single mathematical representation. It utilizes a distance-dependent Chinese restaurant process to cluster heterogeneous population while considering individuals’ treatment histories. We apply the method to a dataset from the Women’s Interagency HIV Study, showing the clinical utility of our model in guiding clinicians to prescribe effective personalized treatment.