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

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

doi:10.3389/fninf.2020.00040

Abstract

Functional near-infrared spectroscopy (fNIRS) has been widely employed in the objective diagnosis of patients with schizophrenia during a verbal fluency task (VFT). Most of the available methods 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 from an individual channel. The data measured 100 patients with schizophrenia and 100 healthy controls, who were used to train the classifiers and to evaluate their performance. Different classifiers were evaluated, and support machine vector achieved the best performance. In order to reduce the dimensional complexity of the feature domain, principal component analysis (PCA) was applied. The classification results by using an individual channel, a combination of several channels, and 52 ensemble channels with and without the dimensional reduced technique were compared. It provided a new approach to identify schizophrenia, improving the objective diagnosis of this mental disorder. FCS from three channels on the medial prefrontal and left ventrolateral prefrontal cortices rendered accuracy as high as 84.67%, sensitivity at 92.00%, and specificity at 70%. The neurophysiological significance of the change at these regions was consistence with the major syndromes of schizophrenia.

Highlights

IntroductionSchizophrenia is a kind of psychiatric disorder characterized by a series of positive/psychotic (e.g., hallucinations and delusions), negative/deficit (e.g., insufficiency of thought and loss of motivation), and cognitive (e.g., impairment of memory and attention) symptoms (Buckley et al, 2009)
Schizophrenia is a kind of psychiatric disorder characterized by a series of positive/psychotic, negative/deficit, and cognitive symptoms (Buckley et al, 2009)
Classification using functional connectivity strength (FCS) from three channels can achieve accuracy at 85.00% (LOOCV), sensitivity at 87.00% (LOOCV), and specificity at 83.00% (LOOCV)

Summary

Introduction

Schizophrenia is a kind of psychiatric disorder characterized by a series of positive/psychotic (e.g., hallucinations and delusions), negative/deficit (e.g., insufficiency of thought and loss of motivation), and cognitive (e.g., impairment of memory and attention) symptoms (Buckley et al, 2009). FNIRS is a noninvasive hemodynamic imaging technique used to assess functional activities in the human brain (Hoshi, 2003) It detects the concentration of oxygenated hemoglobin (OxyHb) and deoxygenated hemoglobin (Deoxy-Hb) by measuring the absorption and reflection of specific near infrared spectrums in the cortices during tasks. Compared to other neuroimaging instruments, fNIRS has the benefit of being low cost with a high portability These advantages have enabled its application in the diagnosis of schizophrenia, which was mainly based on the effect of hypofrontality (reduced activation around the bilateral prefrontal cortex) during various verbal fluency tasks (VFTs; Suto et al, 2004; Ehlis et al, 2007; Takizawa et al, 2008; Ji et al, 2020). Diverse machine learning classifiers (Li et al, 2015) were trained and distinguished the patients with schizophrenia from the healthy subjects

Methods

Results

Conclusion