Tendencias y perspectivas en la detección de depresión mediante el análisis de  señales Electroencefalográficas (EEG): una Revisión Sistemática de la Literatura.

Teofilo Habiram Obispo Bustillos; Nimrod González Franco; Juan Gabriel González Serna; Dante Mújica Vargas; Noé Alejandro Castro Sánchez

doi:10.29057/xikua.v11i22.10561

Teofilo Habiram Obispo Bustillos Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0002-9955-7428
Nimrod González Franco Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0002-1051-1379
Juan Gabriel González Serna Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0002-1874-9402
Dante Mújica Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0001-8665-4096
Noé Castro Centro Nacional de Investigación y Desarrollo Tecnológico https://orcid.org/0000-0002-8083-3891

DOI: https://doi.org/10.29057/xikua.v11i22.10561

Keywords: Depression, EEG, Machine Learning, Deep Learning

Abstract

Currently, the diagnosis of depression is carried out through clinical interviews; taking into account the information provided by the patient, questionnaires or tests are used which help us have an approximation of the severity of the illness. To avoid human intervention in this type of diagnosis, one could resort to the analysis of electroencephalographic (EEG) signals using different machine learning techniques. This Systematic Literature Review (SLR) aims to synthesize current trends in the detection of depression through EEG signals and machine learning models. A search was conducted in PubMed, IEEExplore, ScienceDirect, and SpringerLink where 41 works were obtained in databases and 50 works were obtained through other sources, of which 20 articles published between 2020 and 2022 were selected, which present a comparison between different processing and classification methods. In the vast majority of the works, the accuracy rate is more than 80% in a binary classification (Depression/No Depression), as a result of the study of different methodologies and machine learning models. This work aims to review the literature to offer a useful cross-section to determine the most widely used classification methods.

Downloads

Download data is not yet available.

References

Avots, E., Jermakovs, K., Bachmann, M., Päeske, L., Ozcinar, C., and Anbarjafari (2022). Ensemble approach for detection of depression using EEG features. Entropy, 24.

Berger, H. (1929). Über das elektroenkephalogramm des menschen. Archiv für psychiatrie und nervenkrankheiten, 87(1):527–570.

Cahn, B. (2006). Meditation states and traits: EEG, ERP, and neuroimaging studies. Psychological Bulletin.

Collell, G. (2015). Brain activity and cognition: a connection from thermodynamics and information theory. frontiers in psychology.

Camacho, M., Katherine, M., Rani, P., James, C., and James, J. (2018). Next generation machine learning for biological networks. Cell, 173:1581–1592.

Čukić, M., López, V., and Pavón, J. (2020a). Classification of depression through resting-state electroencephalogram as a novel practice in psychiatry: Review.

Duan, L., Duan, H., Qiao, Y., Sha, S., Qi, S., Zhang, X., Huang, J., Huang, X., and Wang, C. (2020). Machine learning approaches for mdd detection and emotion decoding using EEG signals. Frontiers in Human Neuroscience, 14.

Friston, K. (2009). Causal modelling and brain connectivity in functional magnetic resonance imaging.

Friston, K. (2002). Bayesian estimation of dynamical systems: an application to fmri. Neuroimage.

Gilson, M., Deco, G., Friston, J., Hagmann, P., Mantini, D., Betti, V., Romani, G., and Corbetta, M. (2018). Effective connectivity inferred from fmri transition dynamics during movie viewing points to a balanced reconfiguration of cortical interactions. neuroimage.

Gilson, M., Moreno-Bote, R., Ponce-Alvarez, A., Ritter, P., and Deco, G. (2016). Estimation of directed effective connectivity from fmri functional connectivity hints at asymmetries of cortical connectome. PLOS Computational Biology, 12:1–30

Hughes, J. R. (2008). Gamma, fast, and ultrafast waves of the brain: Their relationships with epilepsy and behavior. Epilepsy Behavior, 13(1):25–31.

Hobson, J. (2002). The cognitive neuroscience of sleep: neuronal systems, consciousness and learning.

Jaworska, N., Blier, P., Fusee, W., and Knott, V. (2012). Alpha power, alpha asymmetry and anterior cingulate cortex activity in depressed males and females.

Jang, K., Kim, S., Lee, C., and Chae, J. (2021a). Machine learning based electroencephalographic phenotypes of schizophrenia and major depressive disorder. Frontiers in Psychiatry, 12.

Jang, K., Kim, S., Lee, C., and Chae, J. (2021b). Machine learning based electroencephalographic phenotypes of schizophrenia and major depressive disorder.

Kaur, C., Singh, P., and Sahni, S. (2021). Eeg artifact removal system for depression using a hybrid denoising approach. Basic and Clinical Neuroscience, 12.

Li, Y., Shen, Y., Fan, X., Huang, X., Yu, H., Zhao, G., and Ma, W. (2022). A novel EEG-based major depressive disorder detection framework with two-stage feature selection. BMC Medical Informatics and Decision Making, 22.

Liu, W., Jia, K., Wang, Z., and Ma, Z. (2022b). A depression prediction algorithm based on spatiotemporal feature of EEG signal. Brain Sciences, 12.

Liu, B., Chang, H., Peng, K., and Wang, X. (2022a). An end-to-end depression recognition method based on eegnet. Frontiers in Psychiatry, 13.

Mahato, S., Goyal, N., Ram, D. et al., Detection of Depression and Scaling of Severity Using Six Channel EEG Data., J Med Syst 44, 118 (2020). https://doi.org/10.1007/s10916-020-01573-y.

Movahed, R. A., Jahromi, G. P., Shahyad, S., and Meftahi, G. H. (2021). A major depressive disorder classification framework based on EEG signals using statistical, spectral, wavelet, functional connectivity, and nonlinear analysis. Journal of Neuroscience Methods, 358.

Marreiros, A., Kiebel, S., and Friston, K. (2008). Dynamic causal modelling for fmri: A two-state model. NeuroImage, 39(1):269–278.

Nyström, C., Matousek, M., and Hällström, T. (1986). Relationships between EEG and clinical characteristics in major depressive disorder.

Pfurtscheller, G., Stancák, A., and Neuper, C. (1996). Event-related synchronization (ers) in the alpha band — an electrophysiological correlate of cortical idling: A review. International Journal of Psychophysiology, 24(1):39–46. New Advances in EEG and cognition.

Ramsey N., M. R. (2020). Handbook of clinical neurology, vol. 168 (3rd series) brain-computer interfaces.

Saeedi, M., Saeedi, A., and Maghsoudi, A. (2020). Major depressive disorder assessment via enhanced k-nearest neighbor method and EEG signals. Physical and Engineering Sciences in Medicine, 43:1007–1018.

Sadat Shahabi, M., Shalbaf, A., and Maghsoudi, A. (2021). Prediction of drug response in major depressive disorder using ensemble of transfer learning with convolutional neural network based on eeg. Biocybernetics and Biomedical Engineering, 41(3):946–959.

Saeedi, A., Saeedi, M., Maghsoudi, A., and Shalbaf, A. (2021). Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach. Cognitive Neurodynamics, 15:239–252.

Thoduparambil, P. P., Dominic, A., and Varghese, S. M. (2020). EEG based deep learning model for the automatic detection of clinical depression. Physical and Engineering Sciences in Medicine, 43:1349– 1360.

Uyulan, C., Ergüzel, T. T., Unubol, H., Cebi, M., Sayar, G. H., Asad, M. N., and Tarhan, N. (2021). Major depressive disorder classification based on different convolutional neural network models: Deep learning approach. Clinical EEG and Neuroscience, 52:38–51.

Uyulan, C., de la Salle, S., Erguzel, T. T., Lynn, E., Blier, P., Knott, V., Adamson, M. M., Zelka, M., and Tarhan, N. (2022). Depression diagnosis modeling with advanced computational methods: Frequency domain emvar and deep learning. Clinical EEG and Neuroscience, 53:24–36

World Health Organization, Depression and Other Common Mental Disorders: Global Health Estimates., Geneva; (2017). Licence: CC BY NC-SA 3.0 IGO.

Wang, B., Kang, Y., Huo, D., Feng, G., Zhang, J., and Li, J. (2022). Eeg diagnosis of depression based on multi-channel data fusion and clipping augmentation and convolutional neural network. Frontiers in Physiology, 13.

Xin, D., Xufeng, F., Xiangwei, L., and Kaiwei, S. (2022). Sparnet: A convolutional neural network for EEG space-frequency feature learning and depression discrimination. Frontiers in Neuroinformatics, 16.

Zhu, J., Wang, Z., Gong, T., Zeng, S., and Li, X. (2020). An improved classification model for depression detection using eeg and eye tracking data. IEEE Trans Nanobioscience.