Advantages of feature selection in identifying and differentiating sleep apnea based on a single-channel EEG signal
DOI:
https://doi.org/10.24425/mms.2025.154672Abstract
Sleep apnea is a sleep disorder that can have serious health consequences. Its detection and differentiation between the types obstructive (OSA), central (CSA), and mixed (MSA) is crucial for selecting appropriate therapy. The aim of this study was to compare three feature selection methods: Particle Swarm Optimization (PSO), Neighbourhood Components Analysis (NCA), and Principal Component Analysis (PCA) in the context of detecting sleep apnea and its types using single-channel EEG signals. In the study, the EEG signals were pre-processed, divided into 30-second segments, and analyzed using a two-stage feature extraction approach. Feature selection methods (PSO, NCA, and PCA) were then applied to reduce data dimensionality and identify the most informative parameters. Parameter optimization was also conducted for each method. Classification was performed using the k-NN algorithm. The results showed that the PSO method achieved the highest average classification accuracy of 98.03%, reducing the number of features from 379 to 134, while NCA achieved an accuracy of 97.96%, reducing the number of features from 424 to 127. Although PCA was effective in dimensionality reduction, it achieved a lower accuracy of 85.56%. The applied methods enabled clear differentiation between normal breathing and sleep apnea episodes, with classification errors occurring only in distinguishing between apnea types.References
[1] Liu, S., Shen, J., Li, Y., Wang, J., Wang, J., Xu, J., Wang, Q., & Chen, R. (2021b). EEG Power spectral analysis of abnormal cortical activations during REM/NREM sleep in obstructive sleep apnea. Frontiers in Neurology, 12. https://doi.org/10.3389/fneur.2021.643855
[2] Hsu, C., & Shih, P. (2010b). A novel sleep apnea detection system in electroencephalogram using frequency variation. Expert Systems with Applications, 38(5), 6014-6024. https://doi.org/10.1016/j.eswa.2010.11.019
[3] Szmajda, M., Chyliński, M., Sacha, J., & Mroczka, J. (2024b). Three methods for determining the respiratory waves from ECG (Part II). Metrology and Measurement Systems, 51-71. https://doi.org/10.24425/mms.2024.148544
[4] Świrniak, G. (2024b). Identification of step-index fibers by static light scattering. Metrology and Measurement Systems, 609-617. https://doi.org/10.24425/mms.2024.150292
[5] Świrniak, G., & Mroczka, J. (2021b). Forward and inverse analysis for particle size distribution measurements of disperse samples: A review. Measurement, 187, 110256. https://doi.org/10.1016/j.measurement.2021.110256
[6] Mroczka, J. (2013b). The cognitive process in metrology. Measurement, 46(8), 2896-2907. https://doi.org/10.1016/j.measurement.2013.04.040
[7] Ratnavadivel, R., Chau, N., Stadler, D., Yeo, A., McEvoy, R. D., & Catcheside, P. G. (2009b). Marked reduction in obstructive sleep apnea severity in slow wave sleep. Journal of Clinical Sleep Medicine, 05(06), 519-524. https://doi.org/10.5664/jcsm.27651
[8] Sabil, A., Vanbuis, J., Baffet, G., Feuilloy, M., Vaillant, M. L., Meslier, N., & Gagnadoux, F. (2018b). Automatic identification of sleep and wakefulness using single-channel EEG and respiratory polygraphy signals for the diagnosis of obstructive sleep apnea. Journal of Sleep Research, 28(2). https://doi.org/10.1111/jsr.12795
[9] Zhao, X., Wang, X., Yang, T., Ji, S., Wang, H., Wang, J., Wang, Y., & Wu, Q. (2021). Classification of sleep apnea based on EEG sub-band signal characteristics. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-85138-0
[10] Prucnal, M. A., & Polak, A. G. (2019). Comparison of information on sleep apnoea contained in two symmetric EEG recordings. Metrology and Measurement Systems, 229-239. https://doi.org/10.24425/mms.2019.128351
[11] Alimardani, M., & De Moor, G. (2021). Automatic Classification of Sleep Apnea Type and Severity using EEG Signals. Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies, 121-128. https://doi.org/10.5220/0010288301210128
[12] Barnes, L. D., Lee, K., Kempa-Liehr, A. W., & Hallum, L. E. (2022). Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN). PLOS ONE, 17(9), e0272167. https://doi.org/10.1371/journal.pone.0272167
[13] Prucnal, M. A., & Polak, A. G. (2023). Single-channel EEG processing for sleep apnea detection and differentiation. Metrology and Measurement Systems. https://doi.org/10.24425/mms.2023.144866
[14] Setiawan, F., & Lin, C. (2022). A Deep Learning Framework for Automatic Sleep Apnea Classification Based on Empirical Mode Decomposition Derived from Single-Lead Electrocardiogram. Life, 12(10), 1509. https://doi.org/10.3390/life12101509
[15] Boukhennoufa, N., Laamari, Y., & Benzid, R. (2024). Signal denoising using a low computational translation-invariant-like strategy involving multiple wavelet bases: application to synthetic and ECG signals. Metrology and Measurement Systems, 259-278. https://doi.org/10.24425/mms.2024.148548
[16] Özşen, S., Koca, Y., Tezel, G., Solak, F. Z., Vatansev, H., & Küçüktürk, S. (2023). Automatic Sleep Stage Classification for the Obstructive Sleep Apnea Patients with Feature Mining. Journal of Biomimetics, Biomaterials and Biomedical Engineering, 60, 119-133. https://doi.org/10.4028/p-svwo5k
[17] Yook, S., Park, H. R., Joo, E. Y., & Kim, H. (2024). Predicting the impact of CPAP on brain health: A study using the sleep EEG-derived brain age index. Annals of Clinical and Translational Neurology, 11(5), 1172-1183. https://doi.org/10.1002/acn3.52032
[18] Moussa, M. M., Alzaabi, Y., & Khandoker, A. H. (2022). Explainable Computer-Aided Detection of Obstructive Sleep Apnea and Depression. IEEE Access, 10, 110916-110933. https://doi.org/10.1109/access.2022.3215632
[19] Afrakhteh, S., Ayatollahi, A., & Soltani, F. (2021). Classification of sleep apnea using EMD-based features and PSO-trained neural networks. Biomedical Engineering / Biomedizinische Technik, 66(5), 459-472. https://doi.org/10.1515/bmt-2021-0025
[20] Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C., & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet.Circulation, 101(23). https://doi.org/10.1161/01.cir.101.23.e215
[21] NJ, S., MSP, S., & S, T. G. (2022). EEG-based classification of normal and seizure types using relaxed local neighbour difference pattern and artificial neural network. Knowledge-Based Systems, 249, 108508. https://doi.org/10.1016/j.knosys.2022.108508
[22] Chen, L., Su, C., Chen, K., & Wang, P. (2011). Particle swarm optimization for feature selection with application in obstructive sleep apnea diagnosis. Neural Computing and Applications, 21(8), 2087-2096. https://doi.org/10.1007/s00521-011-0632-4
[23] Vanhatalo, E., Kulahci, M., & Bergquist, B. (2017). On the structure of dynamic principal component analysis used in statistical process monitoring. Chemometrics and Intelligent Laboratory Systems, 167, 1-11. https://doi.org/10.1016/j.chemolab.2017.05.016
[24] Rahman, M. A., Hossain, M. F., Hossain, M., & Ahmmed, R. (2019). Employing PCA and t-statistical approach for feature extraction and classification of emotion from multichannel EEG signal. Egyptian Informatics Journal, 21(1), 23-35. https://doi.org/10.1016/j.eij.2019.10.002
[25] Choubey, H., & Pandey, A. (2020). A combination of statistical parameters for the detection of epilepsy and EEG classification using ANN and KNN classifier. Signal Image and Video Processing, 15(3), 475-483. https://doi.org/10.1007/s11760-020-01767-4
[26] Alimardani, M., & De Moor, G. (2021b). Automatic Classification of Sleep Apnea Type and Severity using EEG Signals. Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies, 121-128. https://doi.org/10.5220/001028830121012
