DEPRESSION DIAGNOSIS SUPPORT SYSTEM BASED ON EEG SIGNAL ENTROPIES

• Published in: Journal of mechanics in medicine and biology Vol. 14; no. 3; pp. 1450035 - 1-1450035-20
• Main Authors: FAUST, OLIVER, ANG, PENG CHUAN ALVIN, PUTHANKATTIL, SUBHA D., JOSEPH, PAUL K.
• Format: Journal Article
• Language: English
• Published: Singapore World Scientific Publishing Company 01.06.2014; World Scientific Publishing Co. Pte., Ltd
• Subjects: Algorithms; Bayesian analysis; Brain; Classification; Classifiers; Decision trees; Depression; Electroencephalography; Entropy; Entropy (Information theory); Feature extraction; Frequencies; Mental depression; Neural networks; Patients; Probabilistic models; Signal processing; Support systems; Support vector machines; Wavelet analysis; probabilistic neural network; wavelet packet decomposition; sample entropy; Depression; k-nearest neighbor; computer-aided diagnosis; Gaussian mixture model; bispectral phase entropy; decision tree; support vector machine; naive Bayes classification; approximate entropy; fuzzy; Renyi entropy
• ISSN: 0219-5194; 1793-6810
• DOI: 10.1142/S0219519414500353

Electroencephalography (EEG) is a measure which represents the functional activity of the brain. We show that a detailed analysis of EEG measurements provides highly discriminant features which indicate the mental state of patients with clinical depression. Our feature extraction method revolves around a novel processing structure that combines wavelet packet decomposition (WPD) and non-linear algorithms. WPD was used to select appropriate EEG frequency bands. The resulting signals were processed with the non-linear measures of approximate entropy (ApEn), sample entropy (SampEn), renyi entropy (REN) and bispectral phase entropy (Ph). The features were selected using t-test and only discriminative features were fed to various classifiers, namely probabilistic neural network (PNN), support vector machine (SVM), decision tree (DT), k-nearest neighbor algorithm (k-NN), naive bayes classification (NBC), Gaussian mixture model (GMM) and Fuzzy Sugeno Classifier (FSC). Our classification results show that, with a classification accuracy of 99.5%, the PNN classifier performed better than the rest of classifiers in discriminating between normal and depression EEG signals. Hence, the proposed decision support system can be used to diagnose, and monitor the treatment of patients suffering from depression.