Chronologically Arranged Convolutional Gated Recurrent Network for EEG-Based Schizophrenia Detection

Schizophrenia is a severe brain disorder having disruptive effects on human behavior, which can progressively turn out to be worst if left undiagnosed and untreated in its early stages. Therefore, early detection of schizophrenia is crucial for effective treatment and limiting the extent of its effects. Electroencephalogram (EEG) is a widely used method for measuring brain activity in order to investigate the presence of any brain disorders such as schizophrenia. This paper aims to identify the cases of Schizophrenia by applying deep learning techniques to electrical signals recorded through the human brain. Here, chronologically arranged stacks of convolutional modules are used to learn features for further analyzing the temporal dynamics of EEG signals associated with schizophrenia. This hybrid deep learning architecture composed of multiple 1D convolution layers followed by deep gated recurrent units (GRU), achieves a classification score of 99.44% during experimental execution. The performance analysis demonstrates the potential of the proposed architecture for identifying schizophrenia using the EEG recordings of the affected subjects. Following similar footsteps, this study might also be of great help to clinicians in detecting other mental disorders as well.