A sex-dependent functional-effective connectivity model for diagnostic classification of Autism Spectrum Disorder using resting-state fMRI

Abstract

Autism spectrum disorder (ASD) is a neurodevelopmental disorder associated with deficits in social interactions. Currently, its diagnosis is done by behavioral tests. Previous studies have shown that connections between brain regions can be a suitable biomarker for the diagnosis of ASD from normal control (NC). Also, differences in the connections of the brain regions of ASD individuals have been shown between male and female groups. This study, proposed a sex-dependent functional-effective connectivity model for the diagnostic classification of ASD using resting-state fMRI (rs-fMRI).After preprocessing, dual regression independent component analysis (ICA) was applied to obtain the time course of each resting state network (RSN) for each subject. To investigate the role of sex, two male and female groups were considered. Functional connectivity (FC) between time series of RSNs were extracted using full and partial correlation. Also, effective connectivity (EC) was extracted using bivariate granger causality. Two feature selection approacheswere proposedbased on different modes of combining FC and EC features. Finally, the classification accuracy was obtained using thirteen different classifiers for each sex group.The highest classification accuracy of 96.6% in the male group was achieved by using the combination of partial correlation (FC) and granger causality (EC) features, while in the female group, the highest classification accuracy of 93.3% was obtained by all the combinations that used full correlation (FC) features.The results have shown the combination of features obtained from FC and EC can lead to improved classification accuracy in male and female groups.