A Novel Depression Diagnosis Index Using Nonlinear Features in EEG Signals

被引:245
作者
Acharya, U. Rajendra [1 ,2 ,3 ]
Sudarshan, Vidya K. [1 ]
Adeli, Hojjat [4 ,5 ,6 ,7 ,8 ,9 ]
Santhosh, Jayasree [3 ]
Koh, Joel E. W. [1 ]
Puthankatti, Subha D. [10 ]
Adeli, Amir [9 ]
机构
[1] Ngee Ann Polytech, Dept Elect & Comp Engn, Singapore 599489, Singapore
[2] SIM Univ, Sch Sci & Technol, Dept Biomed Engn, Singapore, Singapore
[3] Univ Malaya, Dept Biomed Engn, Kuala Lumpur, Malaysia
[4] Ohio State Univ, Dept Biomed Engn, Columbus, OH 43210 USA
[5] Ohio State Univ, Dept Biomed Informat, Columbus, OH 43210 USA
[6] Ohio State Univ, Dept Civil Environm & Geodet Engn, Columbus, OH 43210 USA
[7] Ohio State Univ, Dept Elect & Comp Engn, Columbus, OH 43210 USA
[8] Ohio State Univ, Dept Neurosci, Columbus, OH 43210 USA
[9] Ohio State Univ, Dept Neurol, Columbus, OH 43210 USA
[10] Natl Inst Technol Calicut, Dept Elect Engn, Calicut, Kerala, India
关键词
Depression; Electroencephalogram signal; Nonlinear analysis; Recurrence quantification analysis; Higher order spectra; Classifiers; Sample entropy; Largest Lyapunov exponent; Detrended fluctuation analysis; Hurst's exponent; FRACTALITY;
D O I
10.1159/000438457
中图分类号
R74 [神经病学与精神病学];
学科分类号
100204 [神经病学];
摘要
Depression is a mental disorder characterized by persistent occurrences of lower mood states in the affected person. The electroencephalogram (EEG) signals are highly complex, nonlinear, and nonstationary in nature. The characteristics of the signal vary with the age and mental state of the subject. The signs of abnormality may be invisible to the naked eyes. Even when they are visible, deciphering the minute changes indicating abnormality is tedious and time consuming for the clinicians. This paper presents a novel method for automated EEG-based diagnosis of depression using nonlinear methods: fractal dimension, largest Lyapunov exponent, sample entropy, detrended fluctuation analysis, Hurst's exponent, higher order spectra, and recurrence quantification analysis. A novel Depression Diagnosis Index (DDI) is presented through judicious combination of the nonlinear features. The DDI calculated automatically based on the EEG recordings can be used to diagnose depression objectively using just one numeric value. Also, these features extracted from nonlinear methods are ranked using the t value and fed to the support vector machine (SVM) classifier. The SVM classifier yielded the highest classification performance with an average accuracy of about 98%, sensitivity of about 97%, and specificity of about 98.5%. (C) 2015 S. Karger AG, Basel
引用
收藏
页码:79 / 83
页数:5
相关论文
共 24 条
[1]
Computer-Aided Diagnosis of Depression Using EEG Signals [J].
Acharya, U. Rajendra ;
Sudarshan, Vidya K. ;
Adeli, Hojjat ;
Santhosh, Jayasree ;
Koh, Joel E. W. ;
Adeli, Amir .
EUROPEAN NEUROLOGY, 2015, 73 (5-6) :329-336
[2]
A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy [J].
Adeli, Hojjat ;
Ghosh-Dastidar, Samanwoy ;
Dadmehr, Nahid .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (02) :205-211
[3]
Spatiotemporal Analysis of Relative Convergence of EEGs Reveals Differences Between Brain Dynamics of Depressive Women and Men [J].
Ahmadlou, Mehran ;
Adeli, Hojjat ;
Adeli, Amir .
CLINICAL EEG AND NEUROSCIENCE, 2013, 44 (03) :175-181
[4]
Fractality analysis of frontal brain in major depressive disorder [J].
Ahmadlou, Mehran ;
Adeli, Hojjat ;
Adeli, Amir .
INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY, 2012, 85 (02) :206-211
[5]
Improved visibility graph fractality with application for the diagnosis of Autism Spectrum Disorder [J].
Ahmadlou, Mehran ;
Adeli, Hojjat ;
Adeli, Amir .
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2012, 391 (20) :4720-4726
[6]
[Anonymous], 1999, Comput Assist Phys
[7]
[Anonymous], 2005, Data Mining: Concepts and Techniques
[8]
[Anonymous], 2012, WORLD SUIC PREV DAY
[9]
PATTERN-RECOGNITION USING INVARIANTS DEFINED FROM HIGHER-ORDER SPECTRA - ONE-DIMENSIONAL INPUTS [J].
CHANDRAN, V ;
ELGAR, SL .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1993, 41 (01) :205-212
[10]
Computer-based analysis of cardiac state using entropies, recurrence plots and Poincare geometry [J].
Chua, K.C. ;
Chandran, V. ;
Acharya, U.R. ;
Lim, C.M. .
Journal of Medical Engineering and Technology, 2008, 32 (04) :263-272