In our recent study, scalograms of EEG signals were used to identify potential biomarkers in schizophrenia heritability. This study presented evidence 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. It was shown that the theta and alpha frequency bands of the EEG signals are significantly relevant to the CNN classification decision and predict the first-degree relatives indicating potential heritable functional deviances. The proposed methodology results in important advancements for the identification of biomarkers in schizophrenia heritability.
Check out the publication here:
Korda, A. I., Ventouras, E., Asvestas, P., Toumaian, M., Matsopoulos, G. K., Smyrnis, N. (2022). Convolutional neural network propagation on electroencephalographic scalograms for detection of schizophrenia. Clinical Neurophysiology, 139, 90-105. https://doi.org/10.1016/j.clinph.2022.04.010