Sleep Disorder Prediction Using Machine Learning Techniques

Abstract

Sleep problems, especially sleep apnoea, have an impact on people\'s health, which indicates the necessity for a correct diagnosis. Sleep experts, however, have highly complex and time-consuming methods to manually identify the various sleep stages. We present here a ML classification model, publicly available for use that has 13 features and 400 records and relates to the Sleep Disorder Data. We investigate and evaluate the effectiveness of numerous DL models based on techniques for reliable diagnosis of sleep disorders. The data includes important lifestyle indicators and sleep health measures that are useful in identifying patterns. Patterns may be indicative of other sleep disorders. The bagged models, and especially the Voting Classifier with RF and DT, have the best performance among the models considered. The method achieved accuracy, precision, recall and F1-score values of 0.973, which means the method is useful for the sleep disorder classification and reliable. The results indicate that the proposed ML methods offer the potential for more intelligent, faster and precise sleep disorders diagnosis, benefiting the physicians\' decision making process and the patient\'s health.

Introduction

This paper investigates the application of machine learning (ML) techniques for the automatic detection and classification of sleep disorders, particularly sleep apnoea and insomnia. Sleep is a vital physiological process that supports physical health, brain function, memory consolidation, and cognitive performance. Poor sleep quality is associated with numerous health problems, including heart disease, diabetes, obesity, and increased accident risk. Despite the importance of sleep assessment, traditional diagnosis relies on the manual analysis of polysomnography (PSG) recordings by medical experts, which is time-consuming, labour-intensive, and prone to human error.

The paper highlights the growing prevalence of sleep disorders worldwide. A global survey by Philips found that 55% of adults were dissatisfied with their sleep, with significant proportions reporting insomnia, sleep disturbances related to COVID-19, snoring, shift-work sleep disorder, and sleep apnoea. These findings emphasize the need for faster, more reliable, and automated diagnostic methods.

Sleep is divided into five stages: wakefulness, N1, N2, N3, and rapid eye movement (REM) sleep. Each stage contributes to physical recovery and cognitive functioning and is typically monitored using EEG and ECG signals collected through PSG. Machine learning and deep learning techniques have increasingly been employed to automate the classification of these sleep stages and reduce dependence on manual interpretation.

The literature review demonstrates that both traditional machine learning methods, such as Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), K-Nearest Neighbours (KNN), and Artificial Neural Networks (ANNs), and deep learning models, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, have been successfully applied to sleep disorder diagnosis. While traditional ML methods require manual feature extraction, deep learning models automatically learn complex features from physiological signals such as EEG and ECG, often achieving higher accuracy and faster classification. Previous studies have shown that CNNs and LSTMs outperform conventional machine learning techniques in detecting sleep apnoea and classifying sleep stages, while wearable AI devices have further expanded opportunities for continuous sleep monitoring.

The proposed methodology develops a machine learning framework that compares several classification algorithms, including SVM, KNN, Decision Tree, Random Forest, ANN with Multi-Layer Perceptron (MLP), and a Voting Classifier. The ensemble Voting Classifier combines Decision Trees and Random Forest through bagging to improve overall classification accuracy. The system follows a standard workflow consisting of data preprocessing, feature selection, model training, testing, and performance evaluation using metrics such as accuracy, precision, recall, F1-score, specificity, sensitivity, and Area Under the Curve (AUC).

The study uses the Sleep Health and Lifestyle Dataset from Kaggle, containing 400 records with 13 features, including demographic information, sleep duration and quality, physical activity, stress level, body mass index (BMI), blood pressure, heart rate, daily steps, and sleep disorder classification. The target variable categorizes individuals into three classes: no sleep disorder, sleep apnoea, and insomnia.

Conclusion

The ML algorithms used in this article have shown that classification of sleep disorder can be realized by using public Sleep Disorder Data set. The VC, constructed using bagging with RF and DT obtained the maximum accuracy as compared to a selection of DL and classical ML techniques. The performance was good in all the evaluation matrices with accuracy 97.3%, precision 97.3%, recall 97.3% and F1-score 97.3%. These results also show that the VC developed here is a very reliable and robust approach for classifying sleep disorders. The results presented below provide consistent improvements in practically all evaluated measures which shows that the model can be effective in delivering accurate and quick diagnosis of sleep problems, therefore helping the patient and improving the clinical decisions. With the high classification accuracy, the Voting Classifier may be recommended as the useful equipment to automate the process of Sleep disorders’ diagnostic, thus more accurate diagnoses and better prognosis in individuals with Sleep disorders are promoted. The scope of this research for the future will be exploring other advanced ML methods to achieve high accuracy in sleep disorder categorisation, specifically DL architectures like the CNN and recurrent networks. The system’s prediction powers could be improved by including real-time data from wearable devices. In addition, the generalisation of the model can be further enhanced by further expanding the variety of population and sleep disorders in the data set.

References

[1] F. Mendonça, S. S. Mostafa, F. Morgado-Dias, and A. G. Ravelo-García, ‘‘A portable wireless device for cyclic alternating pattern estimation from an EEG monopolar derivation,’’ Entropy, vol. 21, no. 12, p. 1203, Dec. 2019. [2] Y. Li, C. Peng, Y. Zhang, Y. Zhang, and B. Lo, ‘‘Adversarial learning for semi-supervised pediatric sleep staging with single-EEG channel,’’ Methods, vol. 204, pp. 84–91, Aug. 2022. [3] E. Alickovic and A. Subasi, ‘‘Ensemble SVM method for automatic sleep stage classification,’’ IEEE Trans. Instrum. Meas., vol. 67, no. 6, pp. 1258–1265, Jun. 2018. [4] D. Shrivastava, S. Jung, M. Saadat, R. Sirohi, and K. Crewson, ‘‘How to interpret the results of a sleep study,’’ J. Community Hospital Internal Med. Perspect., vol. 4, no. 5, p. 24983, Jan. 2014. [5] V. Singh, V. K. Asari, and R. Rajasekaran, ‘‘A deep neural network for early detection and prediction of chronic kidney disease,’’ Diagnostics, vol. 12, no. 1, p. 116, Jan. 2022. [6] J. Van Der Donckt, J. Van Der Donckt, E. Deprost, N. Vandenbussche, M. Rademaker, G. Vandewiele, and S. Van Hoecke, ‘‘Do not sleep on traditional machine learning: Simple and interpretable techniques are competitive to deep learning for sleep scoring,’’ Biomed. Signal Process. Control, vol. 81, Mar. 2023, Art. no. 104429. [7] H. O. Ilhan, ‘‘Sleep stage classification via ensemble and conventional machine learning methods using single channel EEG signals,’’ Int. J. Intell. Syst. Appl. Eng., vol. 4, no. 5, pp. 174–184, Dec. 2017. [8] Y. Yang, Z. Gao, Y. Li, and H. Wang, ‘‘A CNN identified by reinforcement learning-based optimization framework for EEG-based state evaluation,’’ J. Neural Eng., vol. 18, no. 4, Aug. 2021, Art. no. 046059. [9] Y. J. Kim, J. S. Jeon, S.-E. Cho, K. G. Kim, and S.-G. Kang, ‘‘Prediction models for obstructive sleep apnea in Korean adults using machine learning techniques,’’ Diagnostics, vol. 11, no. 4, p. 612, Mar. 2021. [10] Z. Mousavi, T. Y. Rezaii, S. Sheykhivand, A. Farzamnia, and S. N. Razavi, ‘‘Deep convolutional neural network for classification of sleep stages from single-channel EEG signals,’’ J. Neurosci. Methods, vol. 324, Aug. 2019, Art. no. 108312. [11] S. Djanian, A. Bruun, and T. D. Nielsen, ‘‘Sleep classification using consumer sleep technologies and AI: A review of the current landscape,’’ Sleep Med., vol. 100, pp. 390–403, Dec. 2022. [12] N. Salari, A. Hosseinian-Far, M. Mohammadi, H. Ghasemi, H. Khazaie, A. Daneshkhah, and A. Ahmadi, ‘‘Detection of sleep apnea using machine learning algorithms based on ECG signals: A comprehensive systematic review,’’ Expert Syst. Appl., vol. 187, Jan. 2022, Art. no. 115950. [13] C. Li, Y. Qi, X. Ding, J. Zhao, T. Sang, and M. Lee, ‘‘A deep learning method approach for sleep stage classification with EEG spectrogram,’’ Int. J. Environ. Res. Public Health, vol. 19, no. 10, p. 6322, May 2022. [14] H. Han and J. Oh, ‘‘Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity,’’ Sci. Rep., vol. 13, no. 1, p. 6379, Apr. 2023. [15] M. Bahrami and M. Forouzanfar, ‘‘Detection of sleep apnea from single-lead ECG: Comparison of deep learning algorithms,’’ in Proc. IEEE Int. Symp. Med. Meas. Appl. (MeMeA), Jun. 2021, pp. 1–5. [16] S. Satapathy, D. Loganathan, H. K. Kondaveeti, and R. Rath, ‘‘Performance analysis of machine learning algorithms on automated sleep staging feature sets,’’ CAAI Trans. Intell. Technol., vol. 6, no. 2, pp. 155–174, Jun. 2021. [17] M. Bahrami and M. Forouzanfar, ‘‘Sleep apnea detection from single-lead ECG: A comprehensive analysis of machine learning and deep learning algorithms,’’ IEEE Trans. Instrum. Meas., vol. 71, pp. 1–11, 2022. [18] J. Ramesh, N. Keeran, A. Sagahyroon, and F. Aloul, ‘‘Towards validating the effectiveness of obstructive sleep apnea classification from electronic health records using machine learning,’’ Healthcare, vol. 9, no. 11, p. 1450, Oct. 2021. [19] S. K. Satapathy, H. K. Kondaveeti, S. R. Sreeja, H. Madhani, N. Rajput, and D. Swain, ‘‘A deep learning approach to automated sleep stages classification using multi-modal signals,’’ Proc. Comput. Sci., vol. 218, pp. 867–876, Jan. 2023. [20] O. Yildirim, U. Baloglu, and U. Acharya, ‘‘A deep learning model for automated sleep stages classification using PSG signals,’’ Int. J. Environ. Res. Public Health, vol. 16, no. 4, p. 599, Feb. 2019. [21] S. Akbar, A. Ahmad, M. Hayat, A. U. Rehman, S. Khan, and F. Ali, ‘‘IAtbP-Hyb-EnC: Prediction of antitubercular peptides via heterogeneous feature representation and genetic algorithm based ensemble learning model,’’ Comput. Biol. Med., vol. 137, Oct. 2021, Art. no. 104778. [22] (2023). Sleep Health and Lifestyle Dataset. [Online]. Available: http://www.kaggle.com/datasets/uom190346a/sleep-health-and-lifestyle-dataset [23] P. Tripathi, M. A. Ansari, T. K. Gandhi, R. Mehrotra, M. B. B. Heyat, F. Akhtar, C. C. Ukwuoma, A. Y. Muaad, Y. M. Kadah, M. A. Al-Antari, and J. P. Li, ‘‘Ensemble computational intelligent for insomnia sleep stage detection via the sleep ECG signal,’’ IEEE Access, vol. 10, pp. 108710–108721, 2022. [24] [Y. You, X. Zhong, G. Liu, and Z. Yang, ‘‘Automatic sleep stage classification: A light and efficient deep neural network model based on time, frequency and fractional Fourier transform domain features,’’ Artif. Intell. Med., vol. 127, May 2022, Art. no. 102279. [25] I. A. Hidayat, ‘‘Classification of sleep disorders using random forest on sleep health and lifestyle dataset,’’ J. Dinda : Data Sci., Inf. Technol., Data Anal., vol. 3, no. 2, pp. 71–76, Aug. 2023.

Copyright

Copyright © 2026 Syed Shabbeer Ahmad, Asra Fatima. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.