Automated Diagnosis of Schizophrenia based on EEG and Spatial–temporal Residual Graph Convolutional Network

Abstract

Schizophrenia (SZ), a psychiatric disorder for which there is no precise diagnosis, has had a serious impact on the quality of human life and social activities for many years. Therefore, an advanced approach for accurate treatment is required. In this study, we provide a classification approach for SZ patients based on a spatial-temporal residual graph convolutional neural network (STRGCN). The model primarily collects spatial frequency features and temporal frequency features by spatial graph convolution and single channel temporal convolution respectively and blends them both for the classification learning, in contrast to traditional approaches that only evaluate temporal frequency information in EEG and disregard spatial features across brain regions. The spatial frequency features are then obtained by single channel temporal convolution, and the processed matrix is flattened after multiple convolutions and input to the classification model. We conducted extensive experiments on the publicly available dataset Zenodo and our own collected dataset. The classification accuracy of the two datasets on our proposed method reached 96.32% and 85.44%, respectively. In the experiment, the dataset using delta has the best performance in the classification results in the sub-bands.