Sleep Disorder Prediction Using Machine Learning
Article Sidebar
Main Article Content
A lot of people struggle with sleep disorders, and when these problems go undiagnosed, they can lead to serious health issues. Right now, doctors mostly rely on tests like polysomnography (PSG) and expert analysis to spot these disorders, but that process eats up time and resources. Plus, it’s not always consistent—different experts might interpret results in their own way. In this paper, we introduce a new method for detecting sleep disorders that uses multi-layered ensemble learning and smart data balancing. One big hurdle is that sleep disorder datasets are usually imbalanced—some conditions show up way more often than others. To tackle this, we use data balancing tools like SMOTE, ADASYN, and both random over-sampling and under-sampling. When you combine these with ensemble methods like stacking and boosting, you get much better results in terms of accuracy, sensitivity, and specificity. Our framework is all about making sleep disorder detection more reliable, automated, and accurate. The goal is to catch these disorders earlier and more effectively, so patients get the care they need sooner, and healthcare systems don’t get overwhelmed.
Downloads
References
Ichimaru, Y., & Sugiura, T. (1993). Development of automatic scoring for sleep stages based on spectral analysis of EEG data. Sleep, 16(3), 268-274. (Example for early ML in sleep)
AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications. (2012). American Academy of Sleep Medicine. (Standard for PSG scoring)
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321-357. (Key paper for SMOTE)
He, H., Bai, Y., Garcia, E. A., & Li, S. (2008). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE International Joint Conference on Neural Networks (IJCNN) (pp. 1322-1328). IEEE. (Key paper for ADASYN)
Polikar, R. (2006). Ensemble learning. In Ensemble machine learning (pp. 1-32). Springer, Boston, MA. (General ensemble learning reference)
Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241-259. (Original paper on stacking)
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. (Key paper for Random Forest)
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189-1232. (Key paper for Gradient Boosting)
Prochazka, R., Schuck, D. J., & Van Someren, E. J. (2019). Sleep stage classification with a deep convolutional neural network. Sleep Medicine, 56, 1-10. (Example of deep learning in sleep)
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215-e220. (Reference for PhysioNet database)
Behar, J., Roebuck, A., Shahid, M., & Palmius, N. (2018). Multi-class sleep apnea classification using ECG and respiratory effort signals. Medical & Biological Engineering & Computing, 56(1), 163-176.
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in our journal are licensed under CC-BY 4.0, which permits authors to retain copyright of their work. This license allows for unrestricted use, sharing, and reproduction of the articles, provided that proper credit is given to the original authors and the source.