Ayrık Dalgacık Dönüşüm Lideri ve Topluluk Öğrenme Yöntemleri Kullanılarak EEG Kayıtlarından Hafif Bilişsel Bozukluğun Otomatik Tespiti

Öz

Hafif Bilişsel Bozukluk (MCI), yaygın olarak normal biliş ile demans arasında bir geçiş aşaması olarak adlandırılan bir bilişsel gerileme riskidir. MCI'lı hastalar tipik olarak, düşünme yeteneklerinin bozulması gibi bilişsel eksikliklere neden olan Alzheimer hastalığına (AD) ilerlemektedir. Bu çalışma, elektroensefalografi (EEG) sinyallerini kullanarak MCI hastalarını saptamayı amaçlamaktadır. Bu çalışmada kullanılan EEG veri seti, 18 MCI ve 16 kontrol gruplarından kaydedilen EEG sinyallerinden oluşmaktadır. Çalışmada, öncelikle çok ölçekli temel bileşenler analizi (çok ölçekli PCA) kullanılarak, EEG sinyallerinden gürültüler temizlenmiştir. Daha sonra ayrık dalgacık dönüşüm lideri (DWT lideri) özellik çıkarma yöntemi kullanılarak, EEG sinyallerinden 36 öznitelik çıkarılmıştır. Son olarak bu öznitelik vektörleri ile topluluk öğrenme algoritmaları kullanılarak kontrol ve MCI grupları sınıflandırılmıştır. Sonuç olarak AdaBoostM1 algoritması %93,50 doğruluk, %93,27 duyarlılık, %93,75 özgüllük, %94,38 kesinlik, %93,82 f1 skoru ve %86,97 Matthews korelasyon katsayısı (MCC) ile en yüksek başarıya sahiptir. Bu çalışma, oldukça tatmin edici doğruluk elde ederek, topluluk öğrenme algoritmasının MCI tespiti için kullanılabileceğini kanıtlamaktadır.

Anahtar Kelimeler

• Ayrık dalgacık dönüşüm lideri
• EEG
• topluluk öğrenme
• MCI
• otomatik tanı

Automatic Detection of Mild Cognitive Impairment from EEG Recordings Using Discrete Wavelet Transform Leader and Ensemble Learning Methods

Abstract

Mild Cognitive Impairment (MCI) is a risk of cognitive decline, commonly referred to as a transitional stage between normal cognition and dementia. Patients with MCI typically progress to Alzheimer's disease (AD), which causes cognitive deficits such as deterioration of their thinking abilities. This study aims to detect MCI patients using electroencephalography (EEG) signals. The EEG dataset used in this study consists of EEG signals recorded from 18 MCI and 16 control groups. Firstly, EEG signals were denoised using multiscale principal component analysis (multiscale PCA). Then, 36 features were extracted from the EEG signals using the discrete wavelet transform leader (DWT leader) feature extraction method. Finally, using the extracted feature vectors, control groups, and MCI groups were classified by ensemble learning algorithms. As a result, AdaBoostM1 algorithm has the highest success with 93.50% accuracy, 93.27% sensitivity, 93.75% specificity, 94.38% precision, 93.82% f1-score, and 86.97% Matthews correlation coefficient (MCC). By achieving quite satisfactory accuracy, this study proves that the ensemble learning algorithm can also be used for MCI detection.

Keywords

• Discrete wavelet transform leader
• EEG
• ensemble learning
• MCI
• automatic detection

Kaynakça

1. [1] Y. Tao, Y. Han, L. Yu, Q. Wang, S.X. Leng, and H. Zhang, “The predicted key molecules, functions, and pathways that bridge mild cognitive impairment (MCI) and Alzheimer's disease (AD),” Frontiers in Neurology, vol. 11, p. 233, 2020.
2. [2] S. J. Lim, Z. Lee, L. N. Kwon, and H. W. Chun, “Medical health records-based Mild Cognitive Impairment (MCI) prediction for effective dementia care,” International Journal of Environmental Research and Public Health, vol. 18, no. 17, p. 9223, 2021.
3. [3] M. N. Sabbagh, M. Boada, S. Borson, M. Chilukuri, P. M. Doraiswamy, B. Dubois, and H. Hampel, “Rationale for early diagnosis of mild cognitive impairment (MCI) supported by emerging digital technologies,” The Journal of Prevention of Alzheimer's Disease, vol. 7, no.3, pp. 158-164, 2020.
4. [4] N. T. Lautenschlager, K. L. Cox, and K. A. Ellis, “Physical activity for cognitive health: what advice can we give to older adults with subjective cognitive decline and mild cognitive impairment?” Dialogues in Clinical Neuroscience, 2022.
5. [5] R. Baschi, A. Luca, A. Nicoletti, M. Caccamo, C. E. Cicero, C. D'Agate, and R. Monastero, “Changes in motor, cognitive, and behavioral symptoms in Parkinson's disease and mild cognitive impairment during the COVID-19 lockdown,” Frontiers in Psychiatry, vol. 11, p. 590134, 2020.
6. [6] M. Maruta, H. Makizako, Y. Ikeda, H. Miyata, A. Nakamura, G. Han, and T. Tabira, “Association between apathy and satisfaction with meaningful activities in older adults with mild cognitive impairment: A population‐based cross‐sectional study,” International Journal of Geriatric Psychiatry, vol. 36, no.7, pp. 1065-1074, 2021.
7. [7] K. Ritchie, “Mild cognitive impairment: an epidemiological perspective,” Dialogues in Clinical Neuroscience, 2022.
8. [8] M. Kashefpoor, H. Rabbani, and M. Barekatain, “Supervised dictionary learning of EEG signals for mild cognitive impairment diagnosis,” Biomedical Signal Processing and Control, vol. 53, p. 101559, 2019.

9. [9] A. M. Alvi, S. Siuly, H. Wang, K. Wang, and F. Whittaker, “A deep learning based framework for diagnosis of mild cognitive impairment,” Knowledge-Based Systems, vol. 248, p. 108815, 2022.
10. [10] F. Jamaloo, M. Mikaeili, and M. Noroozian, “Multi metric functional connectivity analysis based on continuous hidden Markov model with application in early diagnosis of Alzheimer’s disease,” Biomedical Signal Processing and Control, vol. 61, p. 102056, 2020.
11. [11] E. Andries, and R. Nikzad‐Langerodi, “Dual‐Constrained and Primal‐Constrained principal component analysis,” Journal of Chemometrics, e3403, 2022.
12. [12] J. Kevric, and A. Subasi, “The effect of multiscale PCA de-noising in epileptic seizure detection,” Journal of Medical Systems, vol. 38, no. 10, pp. 1-13, 2014.
13. [13] H. Zhang, M. Zhao, C. Wei, D. Mantini, Z. Li, and Q. Liu, “EEGdenoiseNet: A benchmark dataset for deep learning solutions of EEG denoising,” Journal of Neural Engineering, vol. 18, no. 5, p. 056057, 2021.
14. [14] D. K. Barrow, and S. F. Crone, “Crogging (cross-validation aggregation) for forecasting—A novel algorithm of neural network ensembles on time series subsamples,” IEEE proceedings of 2013 International Joint Conference on Neural Networks (IJCNN), 2013, pp. 1-8.
15. [15] H. L. Vu, K. T. W. Ng, A. Richter, and C. An, “Analysis of input set characteristics and variances on k-fold cross validation for a Recurrent Neural Network model on waste disposal rate estimation,” Journal of Environmental Management, vol. 311, p. 114869, 2022.
16. [16] A. Al-Qerem, F. Kharbat, S. Nashwan, S. Ashraf, and K. Blaou, “General model for best feature extraction of EEG using discrete wavelet transform wavelet family and differential evolution,” International Journal of Distributed Sensor Networks, vol. 16, no. 3, p. 1550147720911009, 2020.
17. [17] S. H, Syed, and V. Muralidharan, “Feature extraction using Discrete Wavelet Transform for fault classification of planetary gearbox–A comparative study,” Applied Acoustics, vol. 188, p. 108572, 2022.
18. [18] M. Ustundag, “A novel analog modulation classification: discrete wavelet transform-extreme learning machine (DWT-ELM),” Bitlis Eren University Journal of Science, vol. 10, no. 2, pp. 492-506, 2021.
19. [19] D. Benouioua, D. Candusso, F. Harel, and L. Oukhellou, “Multifractal analysis of stack voltage based on wavelet leaders: A new tool for PEMFC diagnosis,” Fuel Cells, vol. 17, no. 2, pp. 217-224, 2017.
20. [20] E. Serrano, and A. Figliola, “Wavelet leaders: a new method to estimate the multifractal singularity spectra,” Physica A: Statistical Mechanics and its Applications, vol.388, no.14, pp. 2793-2805, 2009.
21. [21] R. F. Leonarduzzi, G. Schlotthauer, and M. E. Torres, “Wavelet leader based multifractal analysis of heart rate variability during myocardial ischaemia,” In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, 2010, pp. 110-113.
22. [22] K. Gadhoumi, D. Do, F. Badilini, M. M. Pelter, and X. Hu, “Wavelet leader multifractal analysis of heart rate variability in atrial fibrillation,” Journal of Electrocardiology, vol. 51, no. 6, pp. S83-S87, 2018.
23. [23] Z. Tan, and J. Chen, “Detecting stock market turning points using wavelet leaders method,” Physica A: Statistical Mechanics and its Applications, vol. 565, p. 125560, 2021.
24. [24] Z. H. Zhou, “Ensemble learning,” In Machine learning, Singapore: Springer, 2021, pp. 181-210. [Online]. Available: https://link.springer.com/chapter/10.1007/978-981-15-1967-3_8#citeas
25. [25] A. A. ABRO, “Vote-based: Ensemble approach,” Sakarya University Journal of Science, vol. 25, no. 3, pp. 858-866, 2021.
26. [26] R. Salam, and A. R. M. T. Islam, “Potential of RT, Bagging and RS ensemble learning algorithms for reference evapotranspiration prediction using climatic data-limited humid region in Bangladesh,” Journal of Hydrology, vol. 590, p. 125241, 2020.
27. [27] A. Saday, and I. A. Ozkan, “Classification of epileptic EEG signals using DWT-based feature extraction and machine learning methods,” International Journal of Applied Mathematics Electronics and Computers, vol. 9, no. 4, pp. 122-129, 2021.
28. [28] P. Chen, and C. Pan, “Diabetes classification model based on boosting algorithms,” BMC Bioinformatics, vol. 19, pp.1-9, 2018.
29. [29] S. Krishnaveni, and M. Hemalatha, “A perspective analysis of traffic accident using data mining techniques,” International Journal of Computer Applications, vol. 23, no. 7, pp. 40-48, 2011.
30. [30] S. J. Ruiz-Gómez, C. Gómez, J. Poza, G. C. Gutiérrez-Tobal, M. A. Tola-Arribas, M. Cano, and R. Hornero, “Automated multiclass classification of spontaneous EEG activity in Alzheimer’s disease and mild cognitive impairment,” Entropy, vol. 20, no. 1, p. 35, 2018.
31. [31] J. Poza, C. Gomez, M. Garcia, M. A Tola-Arribas, A. Carreres, M. Cano, and R. Hornero, “Spatio-temporal fluctuations of neural dynamics in mild cognitive impairment and Alzheimer's disease,” Current Alzheimer Research, vol. 14, no. 9, pp. 924-936, 2017.
32. [32] S. Hadiyoso, and L. E. Tati, “Mild Cognitive Impairment Classification using Hjorth Descriptor Based on EEG Signal,” In 2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC), 2018, pp. 231-234.
33. [33] S. Hadiyoso, C. L. F. A. R. Cynthia, M. T. L. ER, and H. Zakaria, “Early detection of mild cognitive impairment using quantitative analysis of EEG signals,” IEEE proceedings of 2019 2nd International Conference on Bioinformatics, Biotechnology and Biomedical Engineering (BioMIC)-Bioinformatics and Biomedical Engineering, 2019, pp. 1-5.
34. [34] M. Kashefpoor, H. Rabbani, and M. Barekatain, “Automatic diagnosis of mild cognitive impairment using electroencephalogram spectral features,” Journal of Medical Signals and Sensors, vol. 6, no. 1, p. 25, 2016.