Predicting brain stimulation treatment outcomes of depressed patients through the classification of EEG oscillations

Major depressive disorder (MDD) is a mental disorder that is characterized by negative thoughts, mood and behavior. Transcranial direct current stimulation (tDCS) has recently emerged as a promising brain-stimulation treatment for MDD. A standard tDCS treatment involves numerous sessions that run over a few weeks, however, not all participants respond to this type of treatment. This study aims to predict which patients improve in mood and cognition in response to tDCS treatment by analyzing electroencephalography (EEG) of MDD patients that was collected at the start of tDCS treatment. This is achieved through classifying power spectral density (PSD) of resting-state EEG using support vector machine (SVM), linear discriminate analysis (LDA) and extreme learning machine (ELM). Participants were labelled as improved/not improved based on the change in mood and cognitive scores. The obtained classification results of all channel pair combinations are used to identify the most relevant brain regions and channels for this classification task. We found the frontal channels to be particularly informative for the prediction of the clinical outcome of the tDCS treatment. Subject independent results reveal that our proposed method enables the correct identification of the treatment outcome for seven of the ten participants for mood improvement and nine of ten participants for cognitive improvement. This represents an encouraging sign that EEG-based classification may help to tailor the selection of patients for treatment with tDCS brain stimulation.