Discriminant EEG analysis for differential diagnosis of schizophrenia. Methodological aspects

Kichuk I.V.; Mitrofanov A.A.; Solovieva N.V.; Chausova S.V.; Rusalova M.N.

doi:https://doi.org/10.17116/jnevro202012008157

Kichuk I.V.

Pirogov Russian National Research Medical University

ORCID: 0000-0002-9625-3912

Mitrofanov A.A.

Mental Health Research Center

Solovieva N.V.

Scientific Center of Personalized Medicine

Chausova S.V.

Pirogov Russian National Research Medical University

ORCID: 0000-0001-5799-5908

Rusalova M.N.

Institute of Higher Nervous Activity and Neurophysiology of the Russian Academy of Sciences

Discriminant EEG analysis for differential diagnosis of schizophrenia. Methodological aspects

Authors:

Kichuk I.V., Mitrofanov A.A., Solovieva N.V., Chausova S.V., Rusalova M.N.

More about the authors

Journal: S.S. Korsakov Journal of Neurology and Psychiatry. 2020;120(8): 57‑63

DOI: 10.17116/jnevro202012008157

Read: 2450 times

Download PDF (RU)

Contact the author

Table of contents

To cite this article:

Kichuk IV, Mitrofanov AA, Solovieva NV, Chausova SV, Rusalova MN. Discriminant EEG analysis for differential diagnosis of schizophrenia. Methodological aspects. S.S. Korsakov Journal of Neurology and Psychiatry. 2020;120(8):57‑63. (In Russ.)
https://doi.org/10.17116/jnevro202012008157

Подписка 2026 Журнал неврологии и психиатрии им. С.С. Корсакова (S.S. Korsakov Journal of Neurology and Psychiatry)

Использование инфографики авторами научных работ

Close metadata

BACKGROUND

A search for accurate linear discriminant function (LDF) allowing the diagnosis of schizophrenia and estimation of treatment effectiveness according to EEG is an urgent problem.

OBJECTIVE

To develop a methodology for discriminant EEG analysis for minimizing the overlearning effect, selection of optimal LDF model and evaluation of its generalizing ability.

MATERIAL AND METHODS

Two hundred and twenty patients with schizophrenia and 1400 people without psychiatric diseases, who were comparable in basic characteristics, were enrolled. EEG was recorded using 16 leads, 10-20 system and aural reference electrodes. EEG was processed by spectral and coherent analysis.

RESULTS

After linear discriminant analysis, LDF was obtained to differentiate people with schizophrenia from healthy subjects and a formula was selected from LDF that included 8 predictors (spectral and coherent parameters of standard EEG ranges theta, alpha and beta) with 90% sensitivity and 80% specificity, significance level for Wilks’ lambda p<3.9E-28 and the Mahalanobis distance between training set centroids 4,6.

CONCLUSION

A method for obtaining optimal LDF models and selection the best one with further LDF generalizing ability assessment is suggested.

Keywords:

electroencephalography (EEG)

schizophrenia

coherence

correlation

LDF (linear discriminant function)

predictors

Authors:

Kichuk I.V.

Pirogov Russian National Research Medical University

ORCID: 0000-0002-9625-3912

Mitrofanov A.A.

Mental Health Research Center

Solovieva N.V.

Scientific Center of Personalized Medicine

Chausova S.V.

Pirogov Russian National Research Medical University

ORCID: 0000-0001-5799-5908

Rusalova M.N.

Institute of Higher Nervous Activity and Neurophysiology of the Russian Academy of Sciences

Received:

26.08.2019

Accepted:

24.04.2020

Close metadata

References:

Mitrofanov AA, Kichuk IV, Solov’eva NV, Kuvshinova YaV, Chausova SV, Vileanov VB, Rusalova MN, Olimpieva SP. Application of discriminant EEG analysis for schizophrenia diagnostics. Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova. 2019;119(1):44-50. (In Russ.) https://doi.org/10.17116/jnevro201911901144
Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. Data Mining, Inference, and Prediction. 2-nd Edition. Springer. 2009.
Vorontsov KV. A combinatorial approach to assessing the quality of learning algorithms. Mathematical Questions of Cybernetics. Ed. OB Lupanov. M.: Fizmatlit; 2004;13:5-36. (In Russ.)
Vapnik V. Statistical Learning Theory. Wiley, New York. 1998.
Lapin IA, Mitrofanov AA. The use of mathematical EEG analysis for differential diagnosis of bipolar and unipolar depressions (using the discriminant analysis of spectral power, coherence and interhemispheric asymmetry as an example). Social and Clinical Psychiatry. 2017;27(2):69-74. (In Russ.)
Klecka WR. Discriminant Analysis. Sage Publications. 1980.
Gevins AS, Rémond A, eds. Handbook of Electroencephalography and Clinical Neurophysiology. (Revised series. Vol. 1). Methods of Analysis of Brain Electrical and Magnetic Signals. Elsevier, Amsterdam—N.Y.—Oxford. 1987.
Anderson TW. An Introduction to Multivariate Statistical Analysis. 3-rd Edition. State Publishing House of physical and mathematical literature. 2003.
Handbook of applicable mathematics. Vol. VI: Statistics. Chief Editor: Walter Ledermann. Edited by Emlyn Lloyd. University of Lancaster. A Wiley Interscience Publication JOHN WILEY & SONS.
Ajvazyan SA, Bukhshtaber VM, Enyukov IS, Meshalkin LD. Finances and Statistics. Ed. SA Ajvazyan. M. 1989.
Nolte G, Bai O, Wheaton L, Mari Z, Vorbach S, Hallett M. Identifying true brain interaction from EEG data using the imaginary part of coherence. Clinical Neurophysiology. 2004;115:2292-2307.
Razumnikova OM, Tarasova IV, Volf NV. Features of cortex activation in individuals with high and low verbal creativity: alpha 1,2-rhythm analysis. Journal of Higher Nervous Activity. 2009;(59)5:581-586. (In Russ.)
Nyuer MR. Quantitative analysis and topographic mapping of EEG: methods, problems, clinical application. Advances in Physiological Sciences. 1992;23(1):20-39. (In Russ.)
Valizadeh SA, Riener R, Elmer S, Jäncke L. Decrypting the electrophysiological individuality of the human brain: Identification of individuals based on resting-state EEG activity. Neuro Image. 2019. https://doi.org/10.1016/j.neuroimage.2019.04.005
Pascual-Marqui RD. Instantaneousand lagged measurements of linear and nonlinear dependence between groups of multivariate time series: frequency decomposition. arXiv:0711.1455 [stat.ME], 2007-November-09. https://arxiv.org/abs/0711.1455