Meeting Banner
Abstract #0837

Nodal centrality of the resting state functional network in the differentiation of schizophrenia using a support vector machine

Hu Cheng 1 , Sharlene Newman 1 , Jerillyn S. Kent 1 , Josselyn Howell 1 , Amanda Bolbecker 1 , Aina Puce 1 , Brian F. O'Donnell 1 , and William P. Hetrick 1

1 Indiana University, Bloomington, IN, United States

Resting state functional networks with 278 cortical and subcortical nodes were constructed on 19 schizophrenics and 29 normal controls. By computing the nodal centrality of the resting state functional network, we show that the two groups can be differentiated using support vector machine based on the order of centrality for a certain number of nodes. The performance of the differentiation is better for the nodes with higher centrality in comparison to the same number of nodes with lower centrality. This finding indicates that change of network hubs may be associated with schizophrenia.

This abstract and the presentation materials are available to members only; a login is required.

Join Here