基于一般线性模型和支持向量机的fNIRS精神分裂症患者的自动识别

Schizophrenia is a kind of serious mental illness. Due to the lack of an objective physiological data supporting and a unified data analysis method, doctors can only rely on the subjective experience of the data to distinguish normal people and patients, which easily lead to misdiagnosis. In recent years, functional Near-Infrared Spectroscopy (fNIRS) has been widely used in clinical diagnosis, it can get the hemoglobin concentration through the variation of optical intensity. In this paper, a method is proposed to distinguish patients with schizophrenia based on data measured by fNIRS during a cognitive task. Firstly, general linear model (GLM) was used to extract features based on oxy-Hb signals from 52-channel fNIRS data of schizophrenia and healthy controls. Then, a classier based on Support Vector Machine (SVM) is designed and trained to discriminate schizophrenia from healthy controls. We recruited a sample which contains 34 healthy controls and 42 schizophrenic patients to do the one-back memory task. The hemoglobin response was measured in the prefrontal cortex during the task using a 52-channel fNIRS system.The experimental results indicate that the proposed method can achieve a satisfactory classification with the accuracy of 85.15%, 100% for healthy controls and 78.58% for schizophrenic samples. Also, our results suggested that fNIRS has the potential capacity to be an effective objective biomarker for the diagnosis of schizophrenia.