A0759
Title: New developments in implementing network science in brain behavior linking
Authors: Selena Wang - Indiana University School of Medicine (United States) [presenting]
Abstract: The aim is to propose a latent space statistical network analysis (LatentSNA) that implements network science in a generative Bayesian framework, preserves the neurologically meaningful brain topology, and improves the statistical power for imaging biomarker detection. LatentSNA (1) addresses the lack of power and inflated Type II errors in current analytic approaches when detecting imaging biomarkers, (2) allows unbiased estimation of biomarkers' influence on behavior variants, (3) quantifies the uncertainty and evaluates the likelihood of the estimated biomarker effects against chance and (4) ultimately improves brain-behavior prediction in novel samples and the clinical utilities of neuroimaging findings. LatentSNA is broadly applicable to multiple neuroimaging landmark studies, imaging modalities, and outcome measures with developing, aging, and transdiagnostic populations, totaling 8,003 to 11,861 participants. In these applications, LatentSNA achieves substantial accuracy gains (averaging 110\% - 150\%) and replicability improvements (averaging 153\% in moderate-to-large datasets. As a result, LatentSNA provides an unprecedented view of how network topology is implicated in brain-behavior relationships.
