Convolutional Neural Network Driven Electroencephalogram Characterization for Robust and Efficient Schizophrenia Diagnosis

Complex psychiatric disorders such as Schizophrenia show symptoms like disorganized thinking and hallucinations, typically rooted in abnormal brain activity. Early detection of such abnormal brain activity significantly improves diagnosis and subsequent treatment. To that end, Electroencephalogram (EEG), a non-invasive technique that records electrical activity in the brain is often used to record information about these cerebral anomalies. EEG data can be analyzed using various techniques to facilitate Schizophrenia diagnosis. In that respect, traditional machine learning techniques have been extensively used. However, traditional machine learning techniques necessitate pre-processing and extensive feature extraction, which can often considerably vary from one dataset to another. In contrast, deep learning techniques are better suited to classify between normal and schizophrenic cases, owing to their sophisticated network architecture and their ability to resolve complex data. In this work, we leverage a convolutional neural network (CNN) to characterize EEG data from two cohorts to facilitate schizophrenia diagnosis. We report a 96.4% accuracy of classification with fewer network parameters which beats the current gold standard and shows promise for effective and robust detection and subsequent Schizophrenia diagnosis based on EEG data.