A Bayesian Additive Regression Trees Model for zero and one inflated data for Predicting Individual Treatment Effects in Alcohol Use Disorder Trials

2025-07-26

AI Summary

Alcohol Use Disorder (AUD) treatment exhibits substantial inter-individual heterogeneity, and drinking outcomes follow a zero-one-inflated semi-continuous distribution—posing significant challenges for personalized treatment effect prediction and decision-making. To address this, we propose HOBZ-BART: a novel hierarchical Bayesian model that decomposes outcomes into three mutually exclusive components—zero, positive continuous, and one—via a tripartite hurdle structure. It jointly models nonlinear main effects, covariate interactions, and personalized treatment effects (PITE) by integrating Beta-likelihood approximation within a shared Bayesian Additive Regression Trees (BART) framework. The model supports full Bayesian posterior inference, ensuring both high predictive accuracy and intrinsic interpretability. Evaluated on the MATCH clinical trial dataset, HOBZ-BART significantly outperforms benchmark models—including zero-one-inflated beta (ZOIB)—in estimating heterogeneous treatment effects across psychological interventions. It delivers actionable, interpretable insights for tailoring AUD interventions to individual patients.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Bayesian Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Alcohol Use Disorder (AUD) treatment presents high individual-level heterogeneity, with outcomes ranging from complete abstinence to persistent heavy drinking. This variability-driven by complex behavioral, social, and environmental factors-poses major challenges for treatment evaluation and individualized decision-making. In particular, accurately modeling bounded semicontinuous outcomes and estimating predictive individual treatment effects (PITEs) remains methodologically demanding. For the pre-registered PITE analysis of Project MATCH, we developed HOBZ-BART, a novel Bayesian nonparametric model tailored for semicontinuous outcomes concentrated at clinically meaningful boundary values (0 and 1). The model decomposes the outcome into three components-abstinence, partial drinking, and persistent use-via a sequential hurdle structure, offering interpretability aligned with clinical reasoning. A shared Bayesian Additive Regression Tree (BART) ensemble captures nonlinear effects and covariate interactions across components, while a scalable Beta-likelihood approximation enables efficient, conjugate-friendly posterior computation. Through extensive simulations we demonstrate that HOBZ-BART outperforms traditional zero-one inflated Beta (ZOIB) model in predictive accuracy, computational efficiency, and PITE estimation. We then present the primary PITE analysis of the MATCH trial using HOBZ-BART which enables clinically meaningful comparisons of Cognitive Behavioral Therapy (CBT), Motivational Enhancement Therapy (MET), and Twelve Step Facilitation (TSF), offering personalized treatment insights. HOBZ-BART combines statistical rigor with clinical interpretability, addressing a critical need in addiction research for models that support individualized, data-driven care.

Problem

• Modeling zero and one inflated data for AUD treatment outcomes
• Estimating predictive individual treatment effects (PITEs) accurately
• Comparing CBT, MET, and TSF therapies for personalized insights

Innovation

• Bayesian Additive Regression Trees for semicontinuous data
• Sequential hurdle structure for clinical interpretability
• Scalable Beta-likelihood approximation for efficient computation