|
Abstract:
|
Our goal is to model clinical outcomes using high-dimensional brain networks, motivated by a posttraumatic stress disorder (PTSD) study, where brain network interacts with environmental exposures in complex ways to drive disease progression. Existing approaches using the full edge set cannot tackle such interactions and may select inflated models leading to inaccurate results. We develop a novel two stage Bayesian framework to first find a lower dimensional node-specific representation for the networks, and then embed these representations in a flexible Gaussian process regression framework along with environmental exposures to predict the clinical outcome. Moving from edge level analysis to node level model allows us to scale up to high-dimensional networks, and enables node selection via an extension of the Gaussian process framework that involves spike-and-slab priors on the length-scale parameters. Extensive simulations show a distinct advantage of the proposed approach in terms of prediction, coverage, and node selection. When modeling PTSD resilience, the proposed model results in significant reduction in prediction error and increased coverage and identifies nodes in cingul
|
