Ensemble Approach for Detection of Depression Using EEG Features

被引:31
作者
Avots, Egils [1 ]
Jermakovs, Klavs [1 ]
Bachmann, Maie [2 ]
Paeske, Laura [2 ]
Ozcinar, Cagri [1 ]
Anbarjafari, Gholamreza [1 ,3 ,4 ]
机构
[1] Univ Tartu, Inst Technol, ICV Lab, EE-51009 Tartu, Estonia
[2] Tallinn Univ Technol, Biosignal Proc Lab, EE-19086 Tallinn, Estonia
[3] PwC Advisory, Helsinki 00180, Finland
[4] Hasan Kalyoncu Univ, Fac Engn, TR-27000 Gaziantep, Turkey
关键词
depression; electroencephalogram (EEG); feature extraction and selection; machine learning; ensemble learning; RATING-SCALE; COMPLEXITY; REDUCTION;
D O I
10.3390/e24020211
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Depression is a public health issue that severely affects one's well being and can cause negative social and economic effects to society. To raise awareness of these problems, this research aims at determining whether the long-lasting effects of depression can be determined from electroencephalographic (EEG) signals. The article contains an accuracy comparison for SVM, LDA, NB, kNN, and D3 binary classifiers, which were trained using linear (relative band power, alpha power variability, spectral asymmetry index) and nonlinear (Higuchi fractal dimension, Lempel-Ziv complexity, detrended fluctuation analysis) EEG features. The age- and gender-matched dataset consisted of 10 healthy subjects and 10 subjects diagnosed with depression at some point in their lifetime. Most of the proposed feature selection and classifier combinations achieved accuracy in the range of 80% to 95%, and all the models were evaluated using a 10-fold cross-validation. The results showed that the motioned EEG features used in classifying ongoing depression also work for classifying the long-lasting effects of depression.
引用
收藏
页数:14
相关论文
共 46 条
  • [1] Error reduction through learning multiple descriptions
    Ali, KM
    Pazzani, MJ
    [J]. MACHINE LEARNING, 1996, 24 (03) : 173 - 202
  • [2] Development and psychometric properties of the Emotional State Questionnaire, a self-report questionnaire for depression and anxiety
    Aluoja, A
    Shlik, J
    Vasar, V
    Luuk, K
    Leinsalu, M
    [J]. NORDIC JOURNAL OF PSYCHIATRY, 1999, 53 (06) : 443 - 449
  • [3] [Anonymous], UNIVARIATE FEATURE R
  • [4] Bachmann M., 2014, 13 MED C MED BIOL EN, P694, DOI DOI 10.1007/978-3-319-00846-2_172
  • [5] Methods for classifying depression in single channel EEG using linear and nonlinear signal analysis
    Bachmann, Maie
    Paeske, Laura
    Kalev, Kaia
    Aarma, Katrin
    Lehtmets, Andres
    Oopik, Pille
    Lass, Jaanus
    Hinrikus, Hiie
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2018, 155 : 11 - 17
  • [6] Single channel EEG analysis for detection of depression
    Bachmann, Maie
    Lass, Jaanus
    Hinrikus, Hiie
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2017, 31 : 391 - 397
  • [7] Spectral Asymmetry and Higuchi's Fractal Dimension Measures of Depression Electroencephalogram
    Bachmann, Maie
    Lass, Jaanus
    Suhhova, Anna
    Hinrikus, Hiie
    [J]. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2013, 2013
  • [8] Context Deep Neural Network Model for Predicting Depression Risk Using Multiple Regression
    Baek, Ji-Won
    Chung, Kyungyong
    [J]. IEEE ACCESS, 2020, 8 : 18171 - 18181
  • [9] Beck AT., 1996, MANUAL BECK DEPRESSI
  • [10] Breiman L., 1984, Classification and regression trees