Comparative Analysis of Conventional and Ensemble Machine Learning Techniques for Sleep Disorder Classification

Öz

Computer-aided automatic diagnosis systems have become increasingly important in early detection and management of sleep disorders, as they provide rapid analytical capabilities and assist clinicians in making more accurate and consistent decisions. In this study, two prevalent sleep disorders, apnea and insomnia, were classified using four widely utilized machine learning techniques: Naive Bayes, Support Vector Machine, Logistic Regression, and Random Forest. Each classifier offers a unique analytical perspective, thereby contributing to a more comprehensive assessment of diagnostic performance. To further enhance the robustness and reliability of classification results, three ensemble learning algorithms (AdaBoost, Bagging, and Random Subspace) are employed and integrated with base classifiers. The performance of all models was quantitatively assessed using several key evaluation metrics, including accuracy, kappa coefficient, precision and Area Under the Curve, which together provide a holistic view of classification quality. According to the experimental findings, Logistic Regression stands out as the most effective individual classifier, achieving the highest accuracy rate of 94.667%. Moreover, when Logistic Regression was combined with Bagging or Random Subspace ensemble methods, additional improvements were observed across all evaluation criteria, demonstrating the potential of ensemble-based approaches to further strengthen automated sleep disorder diagnosis.

Anahtar Kelimeler

• Classification
• Disease Prediction
• Ensemble Learning
• Machine Learning
• Sleep Disorders

Etik Beyan

This study does not require ethics committee approval.

Uyku Bozukluğu Sınıflandırması için Geleneksel ve Topluluk Makine Öğrenmesi Tekniklerinin Karşılaştırmalı Analizi

Öz

Bilgisayar destekli otomatik tanı sistemleri, hızlı analitik yetenekler sunarak ve klinisyenlerin daha doğru ve tutarlı kararlar almasına yardımcı olarak uyku bozukluklarının erken teşhisinde ve yönetiminde giderek daha önemli hale gelmiştir. Bu çalışmada, yaygın olarak görülen iki uyku bozukluğu olan apne ve uykusuzluk, yaygın olarak kullanılan dört makine öğrenimi tekniği kullanılarak sınıflandırılmıştır: Naive Bayes, Destek Vektör Makinesi, Lojistik Regresyon ve Rastgele Orman. Her sınıflandırıcı, benzersiz bir analitik bakış açısı sunarak tanı performansının daha kapsamlı bir şekilde değerlendirilmesine katkıda bulunur. Sınıflandırma sonuçlarının sağlamlığını ve güvenilirliğini daha da artırmak için, üç topluluk öğrenme algoritması (Uyarlanabilir Yükseltme (AdaBoost), Torbalama (Bagging) ve Rastgele Alt Uzay (Random Subspace)) kullanılmış ve temel sınıflandırıcılarla entegre edilmiştir. Tüm modellerin performansı, doğruluk, kappa katsayısı, kesinlik ve Eğri Altındaki Alan gibi sınıflandırma kalitesinin bütünsel bir görünümünü sağlayan birkaç temel değerlendirme metriği kullanılarak nicel olarak değerlendirilmiştir. Deney sonuçlarına göre, Lojistik Regresyon %94,667 ile en yüksek doğruluk oranını elde ederek en etkili tekil sınıflandırıcı olarak öne çıkmaktadır. Ayrıca, Lojistik Regresyon Torbalama veya Rastgele Alt Uzay topluluk yöntemleriyle birleştirildiğinde, tüm değerlendirme kriterlerinde ek iyileşmeler gözlemlenmiştir. Bu da otomatik uyku bozukluğu tanısını daha da güçlendirmek için topluluk tabanlı yaklaşımların potansiyelini göstermektedir.

Anahtar Kelimeler

• Sınıflandırma
• Hastalık Tahmini
• Topluluk Öğrenmesi
• Makine Öğrenmesi
• Uyku Bozuklukları

Etik Beyan

Bu çalışma için etik kurul onayına gerek yoktur.

Kaynakça

1. G. M. Migliaccio, The Science of Deep Sleep, Towards Success: Unleashing energies in Sports and Life thanks to quality sleep. Sport Science Lab S.R.L., 2023.
2. A. Huffington, The sleep revolution: Transforming your life, one night at a time. New York: Harmony Books, 2016.
3. C. Stampi, “Sleep and circadian rhythms in space,” Journal of Clinical Pharmacology, vol. 34, no. 5, May, pp. 518-534, 1994.
4. M. Partinen, “Epidemiology of sleep disorders,” Handbook of Clinical Neurology, vol. 98, pp. 275-314, 2011.
5. Y. Dauvilliers, S. Maret, and M. Tafti, “Genetics of normal and pathological sleep in humans,” Sleep Medicine Reviews, vol. 9, no. 2, April, pp. 91-100, 2005.
6. A. A. Moosavi-Movahedi, F. Moosavi-Movahedi, and R. Yousefi, Good sleep as an important pillar for a healthy life. In Rationality and Scientific Lifestyle for Health, Cham, Switzerland: Springer International Publishing, pp. 167-195, 2021.
7. L. Besedovsky, T. Lange, and M. Haack, “The sleep-immune crosstalk in health and disease,” Physiological Reviews, vol. 99, no. 3, March, pp. 1325-1380, 2019.
8. M. Chennaoui, D. Leger, and D. Gomez-Merino, “Sleep and the GH/IGF-1 axis: Consequences and countermeasures of sleep loss/disorders,” Sleep Medicine Reviews, vol. 49, 101223, Feb., pp. 1-11, 2020.

9. T. Roth, “Insomnia: definition, prevalence, etiology, and consequences,” Journal of Clinical Sleep Medicine, vol. 3, no. 5 Suppl, pp. S7-S10, 2007.
10. C. M. Morin, C. L. Drake, A. G. Harvey, A. D. Krystal, R. Manber, D. Riemann, and K. Spiegelhalder, “Insomnia disorder,” Nature Reviews Disease Primers, vol. 1, no. 1, Sept., pp. 1-18, 2015.
11. Y. S. Taspinar and I. Cinar, “Prediction of sleep health status, visualization and analysis of data,” In 11th International Conference on Advanced Technologies (ICAT), 2023, pp. 29-34.
12. K. Kumarasamy, M. W. Sebastian, R. R. Sakkariyas, and V. Dhandapani, Sleep quality assessment using ensembles of machine learning and deep learning models. In Advancing the Investigation and Treatment of Sleep Disorders Using AI, IGI Global, pp. 204-213, 2021.
13. M. Ravan, “A machine learning approach using EEG signals to measure sleep quality,” AIMS Electronics and Electrical Engineering, vol. 3, no. 4, Nov., pp. 347-358, 2019.
14. X. Liu, B. Sun, Z. Zhang, Y. Wang, H. Tang, and T. Zhu, “Gait can reveal sleep quality with machine learning models,” PLoS ONE, vol. 14, no. 9, e0223012, Sept., pp. 1-10, 2019.
15. H. Fritz, C. Wu, K. Kinney, and Z. Nagy, “Comparison of machine learning methods to predict sleep quality from daytime activity and nightly bedroom environmental conditions,” in Proc. 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2021, pp. 222-223.
16. C. Mencar, C. Gallo, M. Mantero, P. Tarsia, G. E. Carpagnano, M. P. Foschino Barbaro, and D. Lacedonia, “Application of machine learning to predict obstructive sleep apnea syndrome severity,” Health Informatics Journal, vol. 26, no. 1, March, pp. 298-317, 2020.
17. A. Ramachandran and A. Karuppiah, “A survey on recent advances in machine learning based sleep apnea detection systems,” Healthcare, vol. 9, no. 7, 914, July, pp. 1-19, 2021.
18. R. Alazaidah, G. Samara, M. Aljaidi, M. H. Qasem, A. Alsarhan, and M. Alshammari, “Potential of machine learning for predicting sleep disorders: A comprehensive analysis of regression and classification models,” Diagnostics, vol. 14, no. 1, 27, Dec., pp. 1-19, 2023.
19. A. Shamim, “Sleep Health and Lifestyle Dataset,” kaggle.com, Aug. 1, 2025. [Online]. Available: https://www.kaggle.com/datasets/adilshamim8/sleep-cycle-and-productivity [Accessed Sept. 20, 2025].
20. R. U. Arslan, Z. Pamuk, and C. Kaya, “Usage of WEKA software based on machine learning algorithms for prediction of liver fibrosis/cirrhosis,” Black Sea Journal of Engineering and Science, vol. 7, no. 3, May, pp. 445-456, 2024.
21. S. A. Arpacı and O. Kalıpsız, “A comparison of different naive Bayes techniques for software defect classification,” Nigde Omer Halisdemir University Journal of Engineering Sciences, vol. 7, no. 1, Jan., pp. 1-13, 2018.
22. E. Sayilgan, Y. K. Yüce, and Y. İşler, “Evaluation of wavelet features selected via statistical evidence from steady-state visually-evoked potentials to predict the stimulating frequency,” Journal of the Faculty of Engineering and Architecture of Gazi University, vol. 36, no. 2, March, pp. 593-605, 2021.
23. A. R. Ghanizadeh, A. Tavana Amlashi, S. Dessouky, and S. A. Ebrahimi, “A comparison of novel hybrid ensemble learners to predict the compressive strength of green engineering materials: a case of concrete composed of rice husk ash,” European Journal of Environmental and Civil Engineering, vol. 28, no. 14, April, pp. 3264-3291, 2024.
24. S. Kazan and H. Karakoca, “Product category classification with machine learning,” Sakarya University Journal of Computer and Information Sciences, vol. 2, no. 1, April, pp. 18-27, 2019.
25. A. Ozcift and A. Gulten, “Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms,” Computer Methods and Programs in Biomedicine, vol. 104, no. 3, Dec., pp. 443-451, 2011.
26. M. J. Kim and D. K. Kang, “Classifiers selection in ensembles using genetic algorithms for bankruptcy prediction,” Expert Systems with Applications, vol. 39, no. 10, Aug., pp. 9308-9314, 2012.
27. A. Onan, S. Korukoğlu, and H. Bulut, “Ensemble of keyword extraction methods and classifiers in text classification,” Expert Systems with Applications, vol. 57, Sept., pp. 232-247, 2016.
28. S. M. Nagarajan, V. Muthukumaran, R. Murugesan, R. B. Joseph, and M. Munirathanam, “Feature selection model for healthcare analysis and classification using classifier ensemble technique,” International Journal of System Assurance Engineering and Management, May, pp. 1-12, 2021.
29. K. Ramasamy, K. Balakrishnan, and D. Velusamy, “Detection of cardiac arrhythmias from ECG signals using FBSE and Jaya optimized ensemble random subspace K-nearest neighbor algorithm,” Biomedical Signal Processing and Control, vol. 76, 103654, July, pp. 1-13, 2022.
30. A. M. Elshewey, E. Selem, and A. H. Abed, “Improved CKD classification based on explainable artificial intelligence with extra trees and BBFS,” Scientific Reports, vol. 15, 17861, May, pp. 1-25, 2025.
31. A. J. Bowers, R. Sprott, and S. A. Taff, “Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity,” The High School Journal, vol. 96, no. 2, Jan., pp. 77-100, 2013.
32. K. Chu, “An introduction to sensitivity, specificity, predictive values and likelihood ratios,” Emergency Medicine, vol. 11, no. 3, Sept., pp. 175-181, 1999.
33. S. M. Vieira, U. Kaymak, and J. M. Sousa, “Cohen's kappa coefficient as a performance measure for feature selection,” in Proc. IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2010, pp. 1-8.
34. D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Computer Science, vol. 7, e623, July, pp. 1-24, 2021.
35. W. Z. T. Tareq, Sleep disorders detection and classification using random forests algorithm. In Decision Making in Healthcare Systems, Cham, Switzerland: Springer International Publishing, pp. 257–266, 2024.
36. M. Warunlawan, P. Homsud, P. Sapphaphab, O. Rinthon, and S. Pechprasarn, ‘‘Identification of crucial factors in sleep quality using machine learning models and MRMR feature selection technique,’’ in Proc. 15th Biomedical Engineering International Conference (BMEiCON), 2023, pp. 1–5.
37. T. S. Alshammari, “Applying machine learning algorithms for the classification of sleep disorders,’’ IEEE Access, vol. 12, March, pp. 36110-36121, 2024.
38. A. Taher, and W. I. Z. Ayon, “Exploring sleep disorders: A comparative analysis of machine learning algorithms on sleep health and lifestyle data,” in IEEE International Conference on Power, Electrical, Electronics and Industrial Applications (PEEIACON), 2024, pp. 71-75.