A Bayesian Integrative Mixed Modeling Framework for Analysis of the Adolescent Brain and Cognitive Development Study

TL;DR

This paper introduces BIPmixed, a Bayesian framework that integrates multi-view neuroimaging and adversity data to identify features and predict behavioral outcomes in hierarchical adolescent studies.

Contribution

It extends Bayesian analysis to handle nested hierarchical data with simultaneous feature selection and prediction, applied to the ABCD study.

Findings

BIPmixed effectively integrates multi-view data.

It accounts for nested random effects.

It demonstrates robustness in simulation studies.

Abstract

Integrating high-dimensional, heterogeneous data from multi-site cohort studies with complex hierarchical structures poses significant feature selection and prediction challenges. We extend the Bayesian Integrative Analysis and Prediction (BIP) framework to enable simultaneous feature selection and outcome modeling in data of nested hierarchical structure. We apply the proposed Bayesian Integrative Mixed Modeling (BIPmixed) framework to the Adolescent Brain Cognitive Development (ABCD) Study, leveraging multi-view data, including structural and functional MRI and early life adversity (ELA) metrics, to identify relevant features and predict the behavioral outcome. BIPmixed incorporates 2-level nested random effects, to enhance interpretability and make predictions in hierarchical data settings. Simulation studies illustrate BIPmixed's robustness in distinct random effect settings, highlighting its use for complex study designs. Our findings suggest that BIPmixed effectively integrates multi-view data while accounting for nested sampling, making it a valuable tool for analyzing large-scale studies with hierarchical data.