FEATURE SELECTION OF ELECTROENCEPHALOGRAPHY (EEG) BIOMARKERS FOR UNIPOLAR MAJOR DEPRESSIVE DISORDER (MDD)

Major Depressive Disorder (MDD), a leading cause of functional disability worldwide, is a mental illness and commonly known as unipolar depression. The clinical management of MDD patients has been challenging that includes an early diagnosis and antidepressant’s treatment selection. The electroencephalography (EEG)-based studies for diagnosis and treatment selection have shown less clear clinical utilities and warrant further investigations. This research advocates the use of EEG as a biomarker for early diagnosis and antidepressant’s treatment selection for unipolar MDD patients. More specifically, the study has presented an improved feature selection and classification system involving pre-treatment EEG data termed as Intelligent Treatment Management System (ITMS) for unipolar depression. The ITMS involved an integration of the most significant EEG features as input data. The study hypothesized that the MDD patients and healthy controls could be discriminated based on integrating the EEG alpha asymmetry and synchronization likelihood (the EEG measure to quantify the brain functional connectivity). The method helped during diagnosis of MDD patients and was termed asITMS for diagnosis (ITMS�diagnosis). In addition, the study hypothesized that the integration of the time and frequency information involving wavelet transform (WT) analysis and EEG signal complexity measures (composite permutation entropy index, sample entropy, and fractal dimension) could discriminate the antidepressants treatment response and non�response. The method helped during antidepressant’s treatment selection such as classifying MDD patients as either respondents or non-respondents to treatment with selective serotonin re-uptake inhibitors (SSRIs): Escitalopram (E), Fluvoxamine (F), Sertraline (S), Fluoxetine (Fl), and was termed as the ITMS for treatment selection (ITMS-treatment selection). The proposed ITMS for depression includes a general machine learning (ML) framework for EEG feature extraction, the selection of most noteworthy features that could give high-performance classification models such as the logistic regression (LR), support vector machine (SVM) and naïve bayesian (NB) classifiers