EEG-Based Depression Detection: A Temporal Domain Feature-Centric Machine Learning Approach

Depression stands as a significant mental health ailment impacting countless individuals globally. It is a mental condition, but it can harm the physical well-being of an individual. Heart, kidneys, brain and immune system health could all be affected due to depression. Timely and accurate identification of depression holds paramount importance for effective treatment. This research introduces an Electroencephalography (EEG) based approach for detecting depressive metal disorders. EEG has emerged as a promising tool for investigating the neural aspects of depression. It utilizes the publicly accessible Multi-Modal Open Dataset for Mental-Disorder Analysis (MODMA). Correlation-based feature selection technique is applied to extracted features to select the significant features. The selected EEG features are then classified using four distinct classifiers. Remarkably, the Decision Tree achieves the highest classification accuracy of 95.76%. The proposed framework outperforms prior MDD classification methods in electrode count and accuracy. It holds potential for implementation within psychiatric contexts, offering valuable assistance to psychiatrists.