Classification of major depressive disorder subjects using Pre-rTMS electroencephalography data with support vector machine approach

• Published in: 2014 Science and Information Conference pp. 410 - 414
• Main Authors: Erguzel, Turker, Ozekes, Serhat, Bayram, Ali, Tarhan, Nevzat
• Format: Conference Proceeding Journal Article
• Language: English
• Published: The Science and Information (SAI) Organization 01.08.2014
• Subjects: Antidepressants; Classification; Conferences; cordance; Diseases; Disorders; EEG; Electrodes; Electroencephalography; Magnetic stimulation; Major depressive disorder; Resin transfer molding; Spectra; support vector machine; Support vector machines; Transcranial magnetic stimulation; Vectors
• ISBN: 0989319334; 9780989319331
• DOI: 10.1109/SAI.2014.6918220

The combination of repetitive transcranial magnetic stimulation (rTMS) and electroencephalogram (EEG) is a valuable tool for investigating the functional connectivity in the brain. Using pre-treatment cordance, a relatively new quantitative EEG method combining complementary information from absolute and relative power of EEG spectra, 55 major depression disorder (MDD) subjects were classified into responder or non-responder classes. In order to predict the response of rTMS treatment, support vector machine (SVM) based classification was carried out on pre-treatment cordance and the classification performance was evaluated using 6, 8 and 10-fold cross-validation (CV). Promising findings indicate that it is possible to classify rTMS treatment responders with 85.45% overall accuracy with a sensitivity of 82.35% and 0.925 area under receiver operating characteristics (ROC) curve value.