Zhaohua Li1, Yuduo Wang1, Wenxiang Quan2, Tongning Wu3, Bin Lv4. 1. School of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing, China. 2. Peking University Sixth Hospital, Beijing, China; Peking University Institute of Mental Health, Beijing, China; Key Laboratory of Mental Health, Ministry of Health (Peking University), Beijing, China. 3. China Academy of Telecommunication Research of Ministry of Industry and Information Technology, Beijing, China. Electronic address: toniwoo@gmail.com. 4. China Academy of Telecommunication Research of Ministry of Industry and Information Technology, Beijing, China. Electronic address: lvbin@catr.cn.
Abstract
BACKGROUND: Based on near-infrared spectroscopy (NIRS), recent converging evidence has been observed that patients with schizophrenia exhibit abnormal functional activities in the prefrontal cortex during a verbal fluency task (VFT). Therefore, some studies have attempted to employ NIRS measurements to differentiate schizophrenia patients from healthy controls with different classification methods. However, no systematic evaluation was conducted to compare their respective classification performances on the same study population. NEW METHOD: In this study, we evaluated the classification performance of four classification methods (including linear discriminant analysis, k-nearest neighbors, Gaussian process classifier, and support vector machines) on an NIRS-aided schizophrenia diagnosis. We recruited a large sample of 120 schizophrenia patients and 120 healthy controls and measured the hemoglobin response in the prefrontal cortex during the VFT using a multichannel NIRS system. Features for classification were extracted from three types of NIRS data in each channel. We subsequently performed a principal component analysis (PCA) for feature selection prior to comparison of the different classification methods. RESULTS: We achieved a maximum accuracy of 85.83% and an overall mean accuracy of 83.37% using a PCA-based feature selection on oxygenated hemoglobin signals and support vector machine classifier. COMPARISON WITH EXISTING METHODS: This is the first comprehensive evaluation of different classification methods for the diagnosis of schizophrenia based on different types of NIRS signals. CONCLUSIONS: Our results suggested that, using the appropriate classification method, NIRS has the potential capacity to be an effective objective biomarker for the diagnosis of schizophrenia.
BACKGROUND: Based on near-infrared spectroscopy (NIRS), recent converging evidence has been observed that patients with schizophrenia exhibit abnormal functional activities in the prefrontal cortex during a verbal fluency task (VFT). Therefore, some studies have attempted to employ NIRS measurements to differentiate schizophreniapatients from healthy controls with different classification methods. However, no systematic evaluation was conducted to compare their respective classification performances on the same study population. NEW METHOD: In this study, we evaluated the classification performance of four classification methods (including linear discriminant analysis, k-nearest neighbors, Gaussian process classifier, and support vector machines) on an NIRS-aided schizophrenia diagnosis. We recruited a large sample of 120 schizophreniapatients and 120 healthy controls and measured the hemoglobin response in the prefrontal cortex during the VFT using a multichannel NIRS system. Features for classification were extracted from three types of NIRS data in each channel. We subsequently performed a principal component analysis (PCA) for feature selection prior to comparison of the different classification methods. RESULTS: We achieved a maximum accuracy of 85.83% and an overall mean accuracy of 83.37% using a PCA-based feature selection on oxygenated hemoglobin signals and support vector machine classifier. COMPARISON WITH EXISTING METHODS: This is the first comprehensive evaluation of different classification methods for the diagnosis of schizophrenia based on different types of NIRS signals. CONCLUSIONS: Our results suggested that, using the appropriate classification method, NIRS has the potential capacity to be an effective objective biomarker for the diagnosis of schizophrenia.
Authors: Lei Yang; Haoyu Jiang; Xiaotong Ding; Zhongcai Liao; Min Wei; Juan Li; Tongning Wu; Congsheng Li; Yanwen Fang Journal: Int J Environ Res Public Health Date: 2022-01-10 Impact factor: 3.390