Bayesian pathway analysis over brain network mediators for survival data

TL;DR

This paper introduces a Bayesian framework for analyzing how brain connectivity mediates the relationship between genetic factors and disease onset, preserving network information and improving interpretability in survival data analysis.

Contribution

It develops a novel structural modeling approach that incorporates sparsity and shrinkage to identify informative brain network configurations affecting disease progression.

Findings

Method outperforms existing approaches in simulations.

Provides neurobiologically plausible insights into Alzheimer's disease.

Identifies key brain network mediators linked to disease onset.

Abstract

Technological advancements in noninvasive imaging facilitate the construction of whole brain interconnected networks, known as brain connectivity. Existing approaches to analyze brain connectivity frequently disaggregate the entire network into a vector of unique edges or summary measures, leading to a substantial loss of information. Motivated by the need to explore the effect mechanism among genetic exposure, brain connectivity and time to disease onset, we propose an integrative Bayesian framework to model the effect pathway between each of these components while quantifying the mediating role of brain networks. To accommodate the biological architectures of brain connectivity constructed along white matter fiber tracts, we develop a structural modeling framework that includes a symmetric matrix-variate accelerated failure time model and a symmetric matrix response regression to characterize the effect paths. We further impose within-graph sparsity and between-graph shrinkage to identify informative network configurations and eliminate the interference of noisy components. Extensive simulations confirm the superiority of our method compared with existing alternatives. By applying the proposed method to the landmark Alzheimer's Disease Neuroimaging Initiative study, we obtain neurobiologically plausible insights that may inform future intervention strategies.