Electroencephalographic Spectral Analysis to Help Detect Depressive Disorder

The increasing prevalence of depressive disorder (also known as major depressive disorder or MDD), especially in the younger generations, has brought urgency upon the importance of good mental health. Moreover, depression has proven to increase the risk of cardiovascular diseases, along with the severity of those diseases. Depressive disorders are oftentimes not diagnosed or misdiagnosed, because some of the symptoms are similar to those of other illnesses. Therefore, an electroencephalography-based system that could help diagnose this illness using a more quantitative approach is necessary to be developed. The goal of this study is to make a machine learning-based classification program using EEG signals to aid for the diagnostics of depression. EEG data of 19 channels were obtained from two data sources, Hospital Universiti Sains Malaysia and Leipzig Study of Mind, Body, and Emotion. The EEG data consisted of 31 depressed subjects and 30 healthy controls during resting conditions. These signals were processed using two different methods, which were wavelet transformation and Power Spectral Density (PSD). Relative power ratio and average alpha asymmetry were calculated for feature extraction. The classifier used was a feedforward neural network with cross validation. The highest achieved results were 83,6% accuracy using the wavelet method and 77,5% accuracy using the PSD method.