B0562
Title: Nonparametric group variable selection with multivariate response for connectome-based prediction of cognitive scores
Authors: Arkaprava Roy - University of Florida (United States) [presenting]
Abstract: Possible relations between the structural connectome and cognitive profiles are studied using a multi-response nonparametric regression model under group sparsity. The aim is to identify the brain regions having a significant effect on cognitive functioning. The cognitive profiles are measured in terms of seven cognitive test scores from NIH toolbox of cognitive battery. The structural connectomes are represented by adjacency matrices. Most existing works consider the upper or lower triangular section of these adjacency matrices as predictors. An alternative characterization of the connectivity properties is available in terms of the nodal attributes. We consider nine different attributes for each brain region as our predictors. These nodal graph metrics may naturally be grouped together for each node, motivating us to introduce group sparsity for feature selection. We propose Russian RBF-nets with a novel group sparsity inducing prior to model the unknown mean functions. The covariance structure of the multivariate response is characterized in terms of a linear factor modeling framework. Applying our proposed method to a Human Connectome Project (HCP) dataset, we identify the important brain regions and nodal attributes for cognitive functioning, as well as identify interesting low-dimensional dependency structures among the cognition related test scores.