Study on Feature Selection Methods for Depression Detection Using Three-Electrode EEG Data

The early diagnosis of depression is important to the treatment of this condition, whereas a timely diagnosis can reduce the incidence of mortality caused in patients with depression. In the present study, we collected the EEG signals of Fp2, Fpz and Fp1, compared with 128 channels EEG, a simpler test (3 channels EEG) can make diagnosis more accessible and widespread, researchers can perform more tests on more patients given the same amount of time and money. The difference between the depressed and the non-depressed patients was explored by the linear and non-linear characteristics of these EEG signals. A total of 152 patients with depression and 113 healthy subjects participated in the study. In the current report, the linear features were as follows: peak, variance, inclination, kurtosis and Hjorth parameter. The nonlinear features included C0 complexity, correlation dimension, Shannon entropy, Kolmogorov entropy and power spectrum entropy. With regard to the aforementioned characteristics, the present report utilized four feature selection algorithms, namely WrapperSubsetEval, CorrelationAttributeEval, GainRatioAttributeEval, and PrincipalComponents and five classification algorithms that included Support Vector Machine, K-Nearest Neighbor, Decision Tree, Logistics Regression and Random Forest. The experimental results indicated that the WrapperSubsetEval of the wrapper class exhibited higher performance compared with the other three feature selection algorithms on each classifier, whereas the highest classification accuracy was 76.4. It is suggested that this analysis may be a complementary tool to aid psychiatrists in the diagnosis of depressed patients.

[1]  Bjarne A. Foss,et al.  Applying the unscented Kalman filter for nonlinear state estimation , 2008 .

[2]  Bin Hu,et al.  Pervasive EEG diagnosis of depression using Deep Belief Network with three-electrodes EEG collector , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[3]  Christoph Lehmann,et al.  Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG) , 2007, Journal of Neuroscience Methods.

[4]  Thomas A. Widiger,et al.  Diagnostic and Statistical Manual of Mental Disorders (DSM) , 2011 .

[5]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[6]  Guy W. Mineau,et al.  A simple KNN algorithm for text categorization , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[7]  Hari Singh Dhillon,et al.  A REVIEW ON ELECTROOCULOGRAPHY , 2012 .

[8]  Julius Georgiou,et al.  Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines , 2012, Expert Syst. Appl..

[9]  Shanbao Tong,et al.  More normal EEGs of depression patients during mental arithmetic than rest , 2007, 2007 Joint Meeting of the 6th International Symposium on Noninvasive Functional Source Imaging of the Brain and Heart and the International Conference on Functional Biomedical Imaging.

[10]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[11]  Juri D Kropotov,et al.  EEG Power Spectra at Early Stages of Depressive Disorders , 2009, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[12]  Bilwaj Gaonkar,et al.  Analytic estimation of statistical significance maps for support vector machine based multi-variate image analysis and classification , 2013, NeuroImage.

[13]  Touradj Ebrahimi,et al.  Support vector EEG classification in the Fourier and time-frequency correlation domains , 2003, First International IEEE EMBS Conference on Neural Engineering, 2003. Conference Proceedings..

[14]  Jian Guan,et al.  Weak Target Detection Based on the Average Bandwidth of the Partial Hilbert Spectrum: Weak Target Detection Based on the Average Bandwidth of the Partial Hilbert Spectrum , 2012 .

[15]  M. Arns,et al.  EEG biomarkers in major depressive disorder: Discriminative power and prediction of treatment response , 2013, International review of psychiatry.

[16]  Bin Hu,et al.  Investigation of Chronic Stress Differences between Groups Exposed to Three Stressors and Normal Controls by Analyzing EEG Recordings , 2013, ICONIP.

[17]  William O Tatum,et al.  Artifact and Recording Concepts in EEG , 2011, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[18]  A. Beck,et al.  Psychometric properties of the Beck Depression Inventory: Twenty-five years of evaluation , 1988 .

[19]  U. Rajendra Acharya,et al.  Neural Network Approaches to Grade Adult Depression , 2012, Journal of Medical Systems.

[20]  Belur V. Dasarathy,et al.  Nearest neighbor (NN) norms: NN pattern classification techniques , 1991 .

[21]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[22]  Juri D. Kropotov,et al.  Independent component approach to the analysis of EEG recordings at early stages of depressive disorders , 2010, Clinical Neurophysiology.

[23]  J. Bhattacharya,et al.  Complexity analysis of spontaneous EEG. , 2000, Acta neurobiologiae experimentalis.

[24]  Bin Hu,et al.  EEG-based mild depressive detection using feature selection methods and classifiers , 2016, Comput. Methods Programs Biomed..

[25]  V. Knott,et al.  EEG power, frequency, asymmetry and coherence in male depression , 2001, Psychiatry Research: Neuroimaging.

[26]  Volodymyr I. Ponomaryov,et al.  ABST M-Type K-Nearest Neighbor (ABSTM-KNN) for Image Denoising , 2005, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[27]  Didier Dormont,et al.  Spatial Regularization of Svm for the Detection of Diffusion Alterations Associated with Stroke Outcome , 2022 .

[28]  B. Hjorth.  EEG analysis based on time domain properties. , 1970, Electroencephalography and clinical neurophysiology.

[29]  Reza Rostami,et al.  Classifying depression patients and normal subjects using machine learning techniques , 2011, 2011 19th Iranian Conference on Electrical Engineering.