EEG signaling of major depressive disorder a review on detection with artificial intelligence applications

Öz

Major depression is a common mental health disorder, and in recent years, combating depres-sion has become a significant global issue. Experts diagnose the condition through psychometric questionnaires and interviews with patients. However, the lack of concrete symptoms, along with the patients' descriptions and undefined symptoms, severely impacts the accuracy of the diagno-sis. This situation underscores the importance of the expert's experience. Developing an objecti-ve method is crucial for aiding experts in making early and accurate diagnoses, as well as posi-tively contributing to the treatment process. This study presents a detailed literature review of artificial intelligence applications and other methods for diagnosing Major Depressive Disorder using Electroencephalography signals. The analysis includes a comparative table of the methods used in signal processing and feature extraction, as well as the classifiers applied. Additionally, based on the studies reviewed, detailed information is provided regarding datasets and methods for future research, aiming to achieve higher accuracy rates and make a positive contribution to the literature.

Anahtar Kelimeler

• Major Depressive
• Disorder Electroencephalography
• Artificial Intelligence
• Signal Processing

EEG sinyallerinden majör depresif bozukluğun yapay zeka uygulamaları ile tespiti üzerine bir inceleme

Öz

Majör depresyon yaygın görülen bir ruh sağlığı bozukluğudur ve son yıllarda depresyonla mücadele önemli bir küresel sorun haline gelmiştir. Uzman, hastalık teşhisini psikometrik anketler ve kişiyle yaptığı görüşmeler neticesinde yapmaktadır. Fakat depresyon belirtilerinin somut olmaması, uzmanın tecrübesi, hastanın söylemleri ve tanımlanamayan semptomlar teşhisin doğruluğunu ciddi derecede etkilemektedir. Bu nedenle objektif bir yöntemin geliştirilmesi teşhis sürecinde uzmana yardımcı olmak ve tedavi sürecine de olumlu katkıda bulunmak açısından önem arz etmektedir. Bu çalışmada Elektroensefalografi sinyallerinin kullanılarak Majör Depresif Bozukluk tanısında Yapay Zekâ uygulamalarına dayalı ayrıntılı literatür taraması verilmiştir. Yapılan bu inceleme sonucunda sinyal işleme ve öznitelik çıkarımında kullanılan yöntemler, uygulanan sınıflandırıcılar tablo halinde verilmiş olup, daha yüksek doğrulukla analiz elde edebilmek için ileriye yönelik yapılacak çalışmalara ve literatüre katkı sağlamak amaçlanmıştır.

Anahtar Kelimeler

• Majör Depresif Bozukluk
• Elektroensefalografi
• Yapay Zeka
• Sinyal İşleme

Kaynakça

1. E. Keleş ve E. Kol, «An Overview of the Brain Imaging Techniques from the,» Elementary Education Online, cilt 14, no. 1, p. 349‐363, 2015.
2. P. A. Young, P. H. Young ve D. L. Tolbert, Basic Clinical Neuroscience, Lippincott Williams & Wilkins, 2008.
3. N. V. Thakor ve S. Tong, «Advances in Quantitative Electroencephalogram Analysis Methods,» Annual Review of Biomedical Engineering, no. 6, pp. 453-495, 2004.
4. «Mayfield Brain & Spine,» [Çevrimiçi]. Available: https://mayfieldclinic.com/pe-anatbrain.htm. [Erişildi: Temmuz 2024].
5. M. Teplan, «Fundamentals Of Eeg Measurement,» Measurement in Biomedicine, cilt 2, no. 2, 2002.
6. J. S. Kumar ve P. Bhuvaneswari, «Analysis of Electroencephalography (EEG) Signals and Its Categorization–A Study,» Procedia Engineering, no. 38, pp. 2525-2536, 2012.
7. P. L. Nunez ve R. Srinivasan, «Electroencephalogram,» 2007. [Çevrimiçi]. Available: http://www.scholarpedia.org/article/Electroencephalogram. [Erişildi: Eylül 2024].
8. M. Khazi, A. Kumar ve V. M J, «Analysis of EEG Using 10:20 Electrode System,» International Journal of Innovative Research in Science, Engineering and Technology, cilt 2, no. 1, 2012.

9. D. Silverman, «The Rationale and History of the 10-20 System of the International Federation,» American Journal of EEG Technology , cilt 1, no. 3, pp. 17-22, 2015.
10. D. L. Schomer ve F. H. Lopes da Silva, Niedermeyer's Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, Lippincott Williams & Wilkins, 2011.
11. L. Heimer, The Human Brain and Spinal Cord: Functional Neuroanatomy and Dissection Guide, Springer Science & Business Media, 2012.
12. W. H. Organization, «World Health Organization,» 31 Mart 2023. [Çevrimiçi]. Available: https://www.who.int/news-room/fact-sheets/detail/depression. [Erişildi: Eylül 2024].
13. P. Gorwood, E. Corruble ve B. Falissard, «Toxic Effects of Depression on Brain Function: Impairment of Delayed Recall and the Cumulative Length of Depressive Disorder in a Large Sample of Depressed Outpatients,» American Journal of Psychiatry, cilt 6, no. 165, 2008.
14. S. Salık, Soner Çakmak ve Şükrü Uğuz, «Tedavi almamış major depresyon hastalarında erken dönemde bilişsel işlevler,» Klinik Psikiyatri Dergisi, no. 22, pp. 408-415, 2019.
15. P. A. Young, Paul Henry Young ve D. L. Tolbert, Basic Clinical Neuroscience, Lippincott Williams & Wilkins, 2008.
16. M. D. Lezak, Neuropsychological Assessment, Oxford University Press, 2004.
17. E. Mtui, G. Gruener ve P. Dockery, Fitzgerald's Clinical Neuroanatomy and Neuroscience E-Book, Elsevier Health Sciences, 2020.
18. V. Knott, C. Mahoney, S. Kennedy ve K. Evans, «EEG power, frequency, asymmetry and coherence in male depression,» Psychiatry Research: Neuroimaging Section, no. 106, pp. 123-140, 2001.
19. H. Hinrikus, A. Suhhova ve M. Bachmann, «Electroencephalographic spectral asymmetry index for detection of depression,» Med Biol Eng Comput, no. 47, pp. 1291-1299, 2009.
20. S. D. Puthankattıl ve P. K. Joseph, «Classıfıcatıon Of Eeg Sıgnals In Normal And Depressıon Condıtıons By Ann Usıng Rwe And Sıgnal Entropy,» Journal of Mechanics in Medicine and Biology, cilt 12, no. 4, 2012.
21. B. Hosseinifard, M. H. Moradi ve R. Rostami, «Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal,» computer methods and programs in biomedicine, no. 109, pp. 339-345, 2013.
22. O. Faust, P. C. Alvın Ang ve S. D. Puthankattıl, «Depressıon Dıagnosıs Support System Based On Eeg Sıgnal Entropıes,» Journal of Mechanics in Medicine and Biology, cilt 3, no. 14, 2014.
23. U. R. Acharya, V. K. Sudarshan ve H. Adeli, «Computer-Aided Diagnosis of Depression Using EEG Signals,» Europan Neurology, no. 73, 2015.
24. X. Li, B. Hu, S. Sun ve H. Cai, «EEG-based mild depressive detection using feature selection methods and classifiers,» computer methods and programs in biomedicine, no. 136, pp. 151-161, 2016.
25. Y. Mohan, S. S. Chee ve D. K. Pei Xin, «Artificial Neural Network for Classification of Depressive and Normal in EEG,» %1 içinde 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences, 2016.
26. S.-C. Liao, C.-T. Wu ve H.-C. Huang, «Major Depression Detection from EEG Signals Using Kernel Eigen-Filter-Bank Common Spatial Patterns,» Sensors, no. 17, 2017.
27. W. Mumtaz, L. Xia ve S. S. Azhar Ali, «Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD),» Biomedical Signal Processing and Control, no. 31, pp. 108-115, 2017.
28. U. R. Acharya, S. Lih Oh ve Y. Hagiwara, «Automated EEG-based screening of depression using deep convolutional neural network,» Computer Methods and Programs in Biomedicine, no. 161, pp. 103-113, 2018.
29. S. Mahato ve S. Paul, «Classification of Depression Patients and Normal Subjects Based on Electroencephalogram (EEG) Signal Using Alpha Power and Theta Asymmetry,» Journal of Medical Systems, cilt 28, no. 44, 2020.
30. H. Cai, J. Han ve Y. Chen, «A Pervasive Approach to EEG-Based Depression Detection,» Hindawi Complexity, 2018.
31. B. Ay, O. Yildirim ve M. Talo, «Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals,» Journal of Medical Systems, cilt 43, no. 205, 2019.
32. L. Duan, H. Duan ve Y. Qiao, «Machine Learning Approaches for MDD Detection and Emotion Decoding Using EEG Signals,» Frontiers in Human Neuroscience, cilt 284, no. 14, 2020.
33. M. Saeedi, A. Saeedi ve A. Maghsoud, «Major depressive disorder assessment via enhanced k nearest neighbor method and EEG signals,» Physical and Engineering Sciences in Medicine, no. 43, pp. 1007-1018, 2020.
34. E. İzci, . M. A. Özdemir ve A. Akan, «Majör Depresif Bozukluğun Tespiti için EEG ve Makine Öğrenmesi Tabanlı Bir Yöntem,» ResearchGate, 2021.
35. U. Raghavendra, A. Gudigar ve Y. Chakole, «Automated detection and screening of depression using continuous wavelet transform with electroencephalogram signals,» Wiley Expert Systems, pp. 1-20, 2021.
36. X. Sun, Chao Ma ve P. Chen, «A Novel Complex Network-Based Graph Convolutional Network in Major Depressive Disorder Detection,» Ieee Transactıons On Instrumentatıon And Measurement, no. 71, 2022.
37. J. Zhu, C. Jiang ve J. Chen, «EEG based depression recognition using improved graph convolutional neural network,» Computers in Biology and Medicine, no. 148, 2022.
38. Y. Chen, X. Hu ve L. Xia, «A Local-Global Graph Convolutional Network for Depression Recognition using EEG Signals,» International Journal of Advanced Computer Science and Applications, cilt 7, no. 14, 2023.
39. B. Zhang, D. Wei ve G. Yan, «Spatial–Temporal EEG Fusion Based on Neural Network for Major Depressive Disorder Detection,» Interdisciplinary Sciences: Computational Life Sciences, 2023.
40. HanshuCai, Z. Yuan, Y. Gao ve S. Sun, «A multi-modal open dataset for mental-disorder analysis,» Scientific Data |, cilt 9, no. 178, 2022.
41. F. Cong, T. Ristaniemi ve H. Lyytinen, Advanced Signal Processing On Brain Event-related Potentials: Filtering Erps In Time, Frequency And Space Domains Sequentially And Simultaneously, World Scientific, 2015.
42. F. Çifçi, C. Kaleli ve S. Günal, «Öznitelik Seçme ve Makine Öğrenmesi Yöntemleriyle Eğitmen Performansının Tahmin Edilmesi,» Anadolu Journal of Educational Sciences International, cilt 8, no. 2, pp. 419-440, 2018.
43. S. B. Maind ve P. Wankar, «Research Paper on Basic of Artificial Neural Network,» International Journal on Recent and Innovation Trends in Computing and Communication, cilt 1, no. 2, 2014.
44. S. Gunn, Support Vector Machines, Image Speech and Intelligent Systems Group, 1997.
45. V. Podgorelec, P. Kokol ve B. Stiglic, «Decision Trees: An Overview and Their Use in Medicine,» Journal of Medical Systems, no. 26, pp. 445-463, 2002.
46. A.-M. Šimundić, «Measures of Diagnostic Accuracy: Basic Definitions,» Ejıfcc, cilt 19, no. 4, pp. 203-211, 2009.