Classification of Major Depressive Disorder Subjects using Pre-rTMS Electroencephalography Data with Support Vector Machine Approach

Erguzel T., Ozekes S., BAYRAM A., Tarhan N.

Science and Information Conference (SAI), London, Kanada, 27 - 29 Ağustos 2014, ss.410-414 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/sai.2014.6918220
  • Basıldığı Şehir: London
  • Basıldığı Ülke: Kanada
  • Sayfa Sayıları: ss.410-414
  • Anahtar Kelimeler: Major depressive disorder, EEG, transcranial magnetic stimulation, cordance, support vector machine, TRANSCRANIAL MAGNETIC STIMULATION, TREATMENT RESPONSE, PREDICTOR, ANTIDEPRESSANTS
  • Marmara Üniversitesi Adresli: Hayır

Özet

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.