Abstract
Depression is a psychiatric disorder that has a negative impact on a person’s development, such as how they think, feel, and behave. Electroencephalogram (EEG) signal can act as biomarker for detection of depression. In this study, analysis is carried out on EEG signals to identify in which region of the brain depression affects so that high accuracy with low number of EEG channels could be obtained.
For this purpose the brain is divided basically into six regions. Four EEG band power features - delta, theta, alpha and beta band power and non-linear features - Approximate Entropy (ApEn), Sample Entropy (SampEn), Correlation Dimension (CD) and Detrended Fluctuation Analysis (DFA) are extracted from all the channels. Based on different regions of the brain and different features, classifiers - Linear Discriminant Analysis (LDA), Naïve Bayesian (NB), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and Bagging have been used.
Results show non-linear feature SampEn and DFA showed comparatively higher accuracy compared to 4 EEG band power features, CD and ApEn. Highest classification accuracy of 95.23% was attained using SVM along with ReliefF. Results also show that depression effects the temporal region of the brain.
Thus a portable device with lesser number of channels specifically placed in temporal region would be able to detect depression with high accuracy which could act as an adjunct tool for detection of depression.
Similar content being viewed by others
Data availability
Data used is a Publicly available dataset [9].
Code availability
Authors would make the code available whenever required for evaluation by the editors and reviewers.
References
American Psychiatric Association (2013) Diagnostic and Statistical Manual of Mental Disorders. 5th edition. American Psychiatric Association Washington, DC. World Health Organization (2017) Depression and Other Common Mental Disorders Global Health Estimates, WHO Document Production Services, Geneva, Switzerland
Asif R, Saleem S, Hassan SA, Alharbi SA, Kamboh AM (2020) Epileptic Seizure Detection With a Reduced Montage: A Way Forward or Ambulatory EEG Devices. IEEE Access 8:65880–65890. https://doi.org/10.1109/ACCESS.2020.2983917
Beck AT (1994) “Depression: Causes and treatment.”, University of Pennsylvania Press, Philadelphia, pp 3–42, 1967 American Psychiatric Association, Diagnostic and statistical manual of mental disorders, 4th edn. American Psychiatric Association, Washington, DC, pp. 339–345
Bouallegue G, Djemal R, Alshebeili SA, Aldhalaan H (2020) A Dynamic Filtering DF-RNN Deep-Learning-Based Approach for EEG-Based Neurological Disorders Diagnosis. IEEE Access 8:206992–207007. https://doi.org/10.1109/ACCESS.2020.3037995
Cai H, Han J, Chen Y, Sha X, Wang Z, Hu B, Yang J, Feng L, Ding Z, Chen Y, Gutknecht J (2018) A Pervasive Approach to EEG-Based Depression Detection. Complexity, Hindawi:1–13. https://doi.org/10.1155/2018/5238028
Cai H, Zhang X, Zhang Y, Wang Z, Hu B A Case-Based Reasoning Model for Depression Based on Three-Electrode EEG Data. In IEEE Trans Affect Comput 11(3):383–392. https://doi.org/10.1109/TAFFC.2018.2801289
Chen Z, Lu G, Xie Z, Shang W (2020) A Unified Framework and Method for EEG-Based Early Epileptic Seizure Detection and Epilepsy Diagnosis. IEEE Access 8:20080–20092. https://doi.org/10.1109/ACCESS.2020.2969055
Cortes C, Vapnik V Support-Vector Networks. Mach Learn 20(3):273–297. https://doi.org/10.1023/A:1022627411411
Dataset: https://figshare.com/articles/dataset/EEG_Data_New/4244171 (last accessed 27/07/2022)
Delorme A, Makeig S EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134(1):9–21. https://doi.org/10.1016/j.jneumeth.2003.10.009
Delorme T, Sejnowski S, Makeig S (2007) Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis. Neuroimage 34(4):1443–1449. https://doi.org/10.1016/j.neuroimage.2006.11.004
Dien J (1998) Issues in the application of the average reference: review, critiques and recommendations. Behav Res Methods Instrum Comput 30(1):34–43. https://doi.org/10.3758/BF03209414
Ding C, Peng H (2003) Minimum redundancy feature selection from microarray gene expression data. Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference, CSB2003, Stanford, CA, USA, pp. 523–528, https://doi.org/10.1109/CSB.2003.1227396
Gandhi V (2014) Brain computer interfacing for assistive robotics. Electroencephalograms, recurrent quantum neural networks, and user-centric graphical interfaces, 1st edn. Academic Press, Cambridge, pp 21–29
Grassberger P, Procaccia I (1983) Measuring the strangeness of strange attractors. Physica 9D 9(1–2):189–208. https://doi.org/10.1016/0167-2789(83)90298-1
Han J, Kamber K, Pei J (2012) Data Mining: Concepts and Techniques, 3rd edn. Morgan Kaufmann, Elsevier, USA, pp 327–413
Hasanzadeh F, Mohebbi M, Rostami R (2021) Single Channel EEG Classification: A Case Study on Prediction of Major Depressive Disorder Treatment Outcome. IEEE Access 9:3417–3427. https://doi.org/10.1109/ACCESS.2020.3046993
Hosseinifard B, Moradi MH, Rostami R (2011) Classifying depression patients and normal subjects using machine learning techniques. 2011 19th Iranian Conference on Electrical Engineering, Tehran, pp. 1–4
James G, Witten D, Hastie T, Tibshirani R (2017) In: Casella G, Fienberg S, Olkin I (eds) An introduction to statistical learning with applications in R. Springer, New York, pp 138–150
Jernajczyk W, Gosek P, Latka M, Kozlowska K, Święcicki L, West BJ (2017) Alpha Wavelet Power as a Biomarker of Antidepressant Treatment Response in Bipolar Depression. Adv Exp Med Biol 968. https://doi.org/10.1007/5584_2016_180
Jung TP, Makeig S, Humphries C, Lee TW, McKeown ML, Iragui V, Sejnowski TJ (2000) Removing electroencephalographic artefacts by blind source separation. Psychophysiology 37(2):163–178. https://doi.org/10.1111/1469-8986.3720163
Khan AI, Alsolami F, Alqurashi F, Abushark YB, Sarker IH (2022) Novel energy management scheme in IoT enabled smart irrigation system using optimized intelligence methods. Eng Appl Artif Intell 114(June)
Kira K, Rendell LA (1992) The feature selection problem: traditional methods and a new algorithm", In: Proceedings of the tenth national conference on Artificial intelligence AAAI'92, San Jose, California, pp. 129–134
Kononenko I (1994) Estimating attributes: Analysis and extensions of Relief. In L. De Raedt & F. Bergadano (Eds.), Machine Learning: ECML-94, vol.784, pp. 171–182, Springer Verlag
Kutner MH, Nachtsheim CJ, Neter J. Applied Linear Statistical Models. 5th Edition, McGraw-Hill, New York, pp. 555–603
Levy WJ (1987) Effect of epoch length on power spectrum analysis of the EEG. Anesthesiology 66(4):489–495. https://doi.org/10.1097/00000542-198704000-0000
Liao SC, Wu CT, Huang HC, Cheng WT, Liu YH (2017) Major Depression Detection from EEG Signals Using Kernel Eigen-Filter-Bank Common Spatial Patterns. Sensors 17(6):1385. https://doi.org/10.3390/s17061385
Mahato S, Paul S (2019) Electroencephalogram (EEG) Signal Analysis for Diagnosis of Major Depressive Disorder (MDD): A Review. In: Nath V, Mandal J (eds) Nanoelectronics, Circuits and Communication Systems, Lecture Notes in Electrical Engineering, vol 511. Springer, Singapore, pp 323–336. https://doi.org/10.1007/978-981-13-0776-8_30
Mahato S, Paul S (2019) Detection of major depressive disorder using linear and non-linear features from EEG signals. Microsyst Technol 25(3):1065–1076. https://doi.org/10.1007/s00542-018-4075-z
Mahato S, Paul S (2020) Classification of Depression Patients and Normal Subjects Based on Electroencephalogram (EEG) Signal Using Alpha Power and Theta Asymmetry, pp. 1–8
Mohammadi M, Al-Azab F, Raahemi B, Richards G, Jaworska N, Smith D, Salle SDL, Blier P, Knott V (2015) Data mining EEG signals in depression for their diagnostic value. BMC Med Inform Dec Making 15(1):1–14. https://doi.org/10.1186/s12911-015-0227-6
Mumtaz W, Malik AS (2018) A Comparative Study of Different EEG Reference Choices for Diagnosing Unipolar Depression. Brain Topogr 31(5):875–885. https://doi.org/10.1007/s10548-018-0651-x
Mumtaz W, Xia L, Yasin MAM, Ali SSA, Malik AS (2017) A wavelet-based technique to predict treatment outcome for Major Depressive Disorder. PLOS ONE:1–30. https://doi.org/10.1371/journal.pone.0171409
Myung J (2003) Tutorial on maximum likelihood estimation. J Math Psychol 47(1):90–100. https://doi.org/10.1016/S0022-2496(02)00028-7
Niemiec J, Lithgow BJ (2005) Alpha-band characteristics in EEG spectrum indicate reliability of frontal brain asymmetry measures in diagnosis of depression. 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, 2005, pp. 7517–7520. https://doi.org/10.1109/IEMBS.2005.1616251
Paul J, Puthankattil SD (2014) Analysis of EEG signals using wavelet entropy and approximate entropy: a case study on depression patients. World Acad Sci, Engin Technol Int J Bioengin Life Sci 8(7)
Peng CK, Havlin S, Stanley HE, Goldberger AL (1995) Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos 5(1). https://doi.org/10.1063/1.166141
Pincus SM (1991) Approximate entropy as a measure of system complexity. Proc Natl Acad Sci 88(6):2297–2301. https://doi.org/10.1073/pnas.88.6.2297
Richman J, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol 278(6). https://doi.org/10.1152/ajpheart.2000.278.6.H2039
Richman JS, Lake DE, Moorman JR (2004) Sample Entropy. Methods Enzymol 384:172–184. https://doi.org/10.1016/S0076-6879(04)84011-4
Robnik-Sikonja M, Kononenko I (2003) Theoretical and Empirical Analysis of ReliefF and RReliefF. Mach Learn 53(1–2):23–69. https://doi.org/10.1023/A:1025667309714
Rodriguez-Bermudez G, Garcia-Laencina PJ (2015) Analysis of EEG Signals using Nonlinear Dynamics and Chaos: A review. App Mathema Inform Sci 9(5):2309–2321. https://doi.org/10.12785/amis/090512
Sarker IH, Khan AI, Abushark YB, et al. Internet of Things (IoT) Security Intelligence: A Comprehensive Overview, Machine Learning Solutions and Research Directions. Mobile Netw Appl
Sternberg RJ, Sternberg K (2012) Cognitive Psychology, 6th edn. Wadsworth, Cengage Learning, Belmont, USA, pp 52–56
Tharwat A (2016) Linear vs. quadratic discriminant analysis classifier: a tutorial. Int J Appl, Pattern Recogn 3(2):145–180. https://doi.org/10.1504/IJAPR.2016.079050
Tharwat A Independent component analysis: An introduction. Appl ComputInform 17(2):222–249. https://doi.org/10.1016/j.aci.2018.08.006
Theodoridis S, Koutroumbas K (2009) Pattern Recognition, 4th edn. Academic Press, Burlington, USA, pp 215–219
Tortora GJ, Derrickson BH (2012) Principles of Anatomy and Physiology, 11th edn. John Wiley and Sons, USA, pp 495–499
World Health Organization (2017) Depression and other common mental disorders global health estimates. WHO Document Production Services, Geneva, Switzerland
Acknowledgments
The authors would like to thank Mumtaz et al. for the dataset contribution [33]. The authors would also like to thank Dr. Rakesh Kumar Sinha, Professor and Head, Bioengineering and Biotechnology, Birla Institute of Technology (BIT), Mesra, India for always supporting us with his immense knowledge and expertise.
Funding
No funds, grants, or other support was received.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Ethics approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Consent to participate
Informed consent was obtained from all individual participants included in the study.
Consent for publication
The authors give the consent for the publication of identifiable details, which can include photograph(s), tables and other details to be published in the Journal.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Mahato, S., Paul, S. Analysis of region of interest (RoI) of brain for detection of depression using EEG signal. Multimed Tools Appl 83, 763–786 (2024). https://doi.org/10.1007/s11042-023-15827-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15827-7