Convolutional Neural Network Based Approach for Depression Detection through EEG Signals

This study presents a novel approach for the detection of depression using Convolutional Neural Networks (CNNs) applied to Electroencephalogram (EEG) signals. Leveraging the rich information embedded in EEG data, our CNN architecture is trained and validated using the MDD Patients and Healthy Controls EEG Dataset-a comprehensive and well-established dataset encompassing diverse neurological profiles. Through a meticulous examination of intricate patterns and features within EEG signals, our model demonstrates robust performance in discriminating between Major Depressive Disorder (MDD) patients and healthy controls. The results showcase a high level of accuracy, sensitivity, and specificity, affirming the efficacy of the proposed approach in providing reliable and objective indicators of depression through non-invasive EEG analysis. This research not only advances the field of computational psychiatry but also holds significant promise for the development of precise and accessible tools for early depression detection and monitoring. The obtained accuracy score for the classified category using the referred dataset is 91.3%.