Convolutional neural network propagation on electroencephalographic scalograms for detection of schizophrenia. (July 2022)

• Record Type: Journal Article
• Authors: Korda, A.I.; Ventouras, E.; Asvestas, P.; Toumaian, Maida; Matsopoulos, G.K.; Smyrnis, N.
• Is Part Of: Clinical neurophysiology. Volume 139(2022)
• Page Start: 90
• Page End: 105
• Publication Date: 2022-07
• Subjects: Convolutional neural networks -- Schizophrenia -- EEG -- Layer-wise relevance propagation -- Heatmap -- Transfer learning; Neurophysiology -- Periodicals; Electroencephalography -- Periodicals; Electromyography -- Periodicals; Neurology -- Periodicals; 612.8
• DOI: 10.1016/j.clinph.2022.04.010
• Languages: English
• ISSNs: 1388-2457

Abstract

Highlights: Scalograms of EEG signals were used as potential biomarkers of schizophrenia. Identification of biomarkers in schizophrenia heritability. Low-frequency oscillations might be a general characteristic of patients. Abstract: Objective: Electroencephalographic analysis (EEG) has emerged as a powerful tool for brain state interpretation. Studies have shown distinct deviances of patients with schizophrenia in EEG activation at specific frequency bands. Methods: Evidence is presented for the validation of a Convolutional Neural Network (CNN) model using transfer learning for scalp EEGs of patients and controls during the performance of a speeded sensorimotor task and a working memory task. First, we trained a CNN on EEG data of 41 schizophrenia patients (SCZ) and 31 healthy controls (HC). Secondly, we used a pretrained model for training. Both models were tested in an external validation set of 15 SCZ, 16 HC, and 12 first-degree relatives. Results: Using the layer-wise relevance propagation on the classification decision, a heatmap was produced for each subject, specifying the pixel-wise relevance. The CNN model resulted in the first case in a balanced accuracy of 63.7% and 81.5% in the second case, on the external validation test 64.5% and 83.2%, respectively. Conclusions: The theta and alpha frequency bands of the EEG signals had significant relevance to the CNN classification decision and predict the first-degree relatives indicating potential heritable functional deviances. Significance: The proposed methodology results in important advancements for the identification of biomarkers in schizophrenia heritability.