Classification of schizophrenia using general linear model and support vector machine via fNIRS
- PDF / 1,603,065 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 94 Downloads / 170 Views
SCIENTIFIC PAPER
Classification of schizophrenia using general linear model and support vector machine via fNIRS Lei Chen1 · Qiang Li1 · Hong Song1 · Ruiqi Gao1 · Jian Yang2 · Wentian Dong3 · Weimin Dang3 Received: 29 August 2019 / Accepted: 21 July 2020 © Australasian College of Physical Scientists and Engineers in Medicine 2020
Abstract Schizophrenia is a type of serious mental illness. In clinical practice, it is still a challenging problem to identify schizophreniarelated brain patterns due to the lack of objective physiological data support and a unified data analysis method, physicians can only use the subjective experience to distinguish schizophrenia patients and healthy people, which may easily lead to misdiagnosis. In this study, we designed an optimized data-preprocessing method accompanied with techniques of general linear model feature extraction, independent sample t-test feature selection and support vector machine to identify a set of robust fNIRS pattern features as a biomarker to discriminate schizophrenia patients and healthy people. Experimental results demonstrated that the proposed combination way of data preprocessing, feature extraction, feature selection and support vector machine classification can effectively identify schizophrenia patients and the healthy people with a leave-one-outcross-validation classification accuracy of 89.5%. Keywords Functional near-infrared spectroscopy · Schizophrenia discrimination · General linear model · Support vector machine
Introduction Schizophrenia is a serious mental disorder in which the pathogen has still not been fully ascertained until now. Patients with schizophrenia usually characterize significant behavioral abnormalities and accompanied by a series of typical * Hong Song [email protected] Lei Chen [email protected] Qiang Li [email protected] Ruiqi Gao [email protected] Jian Yang [email protected] 1
School of Computer Science & Technology, Beijing Institute of Technology, Beijing, China
2
School of Optics and Electronics, Beijing Institute of Technology, Beijing, China
3
Peking University Sixth Hospital, Peking University Institute of Mental Health, Key Laboratory of Mental Health, Ministry of Health (Peking University), Beijing, China
symptoms such as delusions and hallucinations, which significantly affect the patient’s daily life and compose a potential danger to the safety of himself and people around him [1, 2]. The modern clinical diagnostic criteria for schizophrenia are mainly based on observing the behavioral symptoms of patients, which is very subjective and limited by the professional knowledge of doctors. What’s more, the diagnosis results of different doctors may also vary from each other, which may easily lead to misdiagnosis. Recently, some neuroimaging studies have demonstrated that brain structure and function between schizophrenia patients and normal people have distinctive abnormalities [3, 4]. And researchers have used these imaging techniques and several pattern recognition methods to develop syste
Data Loading...
