AUTHOR=Yang Jiayi , Ji Xiaoyu , Quan Wenxiang , Liu Yunshan , Wei Bowen , Wu Tongning 

TITLE=Classification of Schizophrenia by Functional Connectivity Strength Using Functional Near Infrared Spectroscopy

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2020.00040

DOI=10.3389/fninf.2020.00040

ISSN=1662-5196

ABSTRACT=Functional near-infrared spectroscopy (fNIRS) has been widely employed in objective diagnosis of patients with schizophrenia during a verbal fluent task (VFT). Most of the available method depended on the time-domain features extracted from the data of single or multiple channels. The present study proposed an alternative method based on the functional connectivity strength (FCS) derived on individual channel. The data measured from 100 patients with schizophrenia and 100 healthy controls were used in to train the classifiers and to evaluate their performance. Different classifiers were evaluated and support machine vector achieve the best performance. In order to reduce the dimensional complexity of the feature domain, principal component analysis has been applied. The classification results by using individual channel, combination of several channels, ensemble 52 channels with and without the dimensional reduced technique were compared. It provided a new approach to identify schizophrenia, benefiting the objective diagnosis of this mental disorder. FCS from three channels on medial prefrontal and left ventrolateral prefrontal cortices rendered accuracy as 84.67%, sensitivity as 92.00% and specificity as 70%. The neurophysiplogical significance of the change at these regions was consistence with the major syndromes of schizophrenia.