Nonparametric group variable selection with multivariate response for connectome-based modelling of cognitive scores

Abstract

Abstract We study association between the structural connectivity and cognitive profiles using a multi-response nonparametric regression model. The cognitive profiles are quantified by seven cognitive test scores, and structural connectivity is represented by nine nodal attributes of connectivity graphs. These nodal centralities together encode different connectivity profiles in the brain network. Nodal attributes may be grouped together for each node, motivating us to introduce group sparsity for feature selection, and radial basis function (RBF)-nets are used to quantify the regression effects. An efficient computation algorithm is developed. Applying our proposed method to Human Connectome Project data, we obtain several interesting findings related to cognitive functioning.