Analysis of Anhedonia disorder using Machine Learning

Depression is the second most common illness which threatens human life, as stated by World Health Organization. Therefore it is significantly necessary to have early detection, diagnosis, and treatment of patients with depression. Depressions are categorized based on their intensity and effects. Major depression disorder (MDD), persistent depressive disorder, seasonal affective, and bipolar disorder are adverse disorders. At the same time, Anhedonia is one of the disorders with very little biological information available in the literature. There are various bio-instruments used for analyzing the said disorder. The EEG signals explicitly help analyze the Anhedonia disorder reported in the literature. The EEG signal data is available in the standard medical repository. In this paper, an attempt has been made to analyze the EEG signal of a depressed patient using machine learning. The classification learning algorithm of male and female neurological disorders has been considered and analyzed in the simulation platform. The results have been achieved differentiating the Major Depression Disorder (MDD) and Anhedonia disorders for both males and females concerning signal characteristics. It can be inferred that the EEG signal in the case of Neurological disorder has distinguishable changes based on the difference of level of depression.