Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques

Schizophrenia is a severe mental disorder that has adverse effects on the behavior of an individual such as disorganized speech and delusions. Electroencephalography (EEG) signals are widely used for its identification as they are non-invasive and have high temporal resolution. EEG signals may be captured using wearable devices but transmission of complete data from all channels is both battery and data consuming. Several studies on Schizophrenia have either used all channels or relied on sophisticated feature extraction algorithms to find the most relevant EEG channels for further processing. That too, however, needs data from all channels beforehand to identify the most relevant features. In this study, a publicly available multi-channel EEG signals dataset from the institute of Psychiatry and Neurology in Warsaw, Poland is studied for an automated identification of Schizophrenia using only a subset of data from selected channels. To achieve this, we device a channel selection mechanism based on a rigorous performance analysis of the Convolutional Neural Network (CNN) while considering the individual EEG channels at different brain regions. The selected channels are combined, and we use a fusion of CNN and different machine learning (ML) classifiers to train the classification model. Our ex-periments show that a combination of three channels namely, T4, T3, and Cz achieves 90% and 98% accuracies on subject-based and non-subject based testing, respectively, using a hybridization of CNN and logistic regression (LR).

Automated summary

Schizophrenia, a severe mental disorder characterized by disorganized speech and delusions, can be identified using non-invasive and high temporal resolution EEG signals. In this study, a publicly available multi-channel EEG signals dataset is utilized to automatically identify Schizophrenia using a subset of data from selected channels. The combination of three specific channels achieved high accuracies of 90% and 98% on subject-based and non-subject based testing, respectively, using a fusion of CNN and LR.