A0394
Title: Link prediction problems in functional brain networks
Authors: Panpan Zhang - Vanderbilt University Medical Center (United States) [presenting]
Abstract: Functional magnetic resonance imaging (fMRI) has been widely used to discover the neural underpinnings of cognition decline caused by neurological disorders. Graph-theory-based methods are prevalent for analyzing brain networks constructed from fMRI data. Due to data usability and data noise, the constructed brain networks may contain false positive and/or false negative links. Using graph-based measures extracted from such brain networks as predictors in downstream analyses may cause inference bias. A Bayesian approach is introduced to functional brain network analysis with the presence of false positive and false negative links. The proposed method is applied to investigate the association between functional connectivity and cognitive changes in Alzheimer's disease.
