Abstract

Obstructive sleep apnea (OSA) is a prevalent sleep disorder associated with severe health complications, including cardiovascular diseases and cognitive decline. Traditional diagnostic methods, such as polysomnography (PSG), are expensive, time-consuming, and require clinical supervision. This study proposes a deep learningbased framework for automated sleep apnea detection using singlelead electrocardiogram (ECG) signals. The proposed model leverages wavelet transform for feature extraction, heart rate variability (HRV) analysis, and a deep neural network (DNN) optimized with Bayesian optimization for classification. The ECG5000 dataset is utilized to train and validate the model, achieving a classification accuracy of 93.51%, outperforming conventional methods. The results demonstrate the potential of an ECG-based deep learning approach for scalable, cost-effective, and real-time OSA detection in wearable healthcare applications.

References

• M. Bahrami and M. Forouzanfar. Sleep apnea detection from single-lead ecg: A comprehensive analysis of machine learning and deep learning algorithms. IEEE Transactions on Instrumentation and Measurement, 71:1–11, 2022.
• E. Carter and R.Wilson. Advancements in ai-driven sleep apnea detection. IEEE Journal of Biomedical Health Informatics, 25(8):2845–2857, 2021.
• G. Chen and J. Wu. Wavelet transform and lstm-based model for sleep apnea detection. IEEE Sensors Journal, 21:2345– 2356, 2021.
• T. Chen and X. Liu. Feature extraction and cnn-based classification of ecg signals for sleep apnea diagnosis. Journal of Healthcare Engineering, 2021:1–10, 2021.
• J. Choi, H. Lee, and S. Kim. A comparative study of deep learning models for sleep apnea detection from ecg signals. IEEE Transactions on Neural Networks and Learning Systems, 33(3):974–986, 2022.
• R. K. Das and M. Ghosh. A review of machine learning approaches for sleep apnea detection. Sensors, 23(4):1859, 2023.
• D. Dey, S. Chaudhuri, and S. Munshi. Obstructive sleep apnea detection using convolutional neural network-based deep learning framework. Biomedical Engineering Letters, 8:95– 100, 2018.
• Author Names from Base Paper. An adaptive sleep apnea detection model using multi cascaded atrous-based deep learning schemes with hybrid artificial humming bird pity beetle algorithm. IEEE Access, 11:113114–113133, 2023.
• S. Ghosh and A. Banerjee. Time-frequency feature extraction for ecg-based sleep apnea detection. IEEE Transactions on Biomedical Engineering, 69(5):2032–2042, 2022.
• A. Gupta and P. Sharma. Ecg-based sleep apnea detection using hybrid cnn-lstm architecture. Biomedical Signal Processing and Control, 71:103087, 2022.
• K. Gupta, V. Bajaj, and I. A. Ansari. Osacn-net: Automated classification of sleep apnea using deep learning model and smoothed gabor spectrograms of ecg signal. IEEE Transactions on Instrumentation and Measurement, 71:1–9, 2021.
• H. Kim, J. Park, and S. Lee. Sleep apnea detection using single-lead ecg and deep learning models. IEEE Sensors Journal, 21(12):14477–14485, 2021.
• H. Korkalainen, J. Aakko, S. Nikkonen, and T. Lepp¨anen. Accurate deep learning-based sleep staging in a clinical population with suspected obstructive sleep apnea. IEEE Journal of Biomedical and Health Informatics, 24(7):2073–2081, 2019.
• J. Lee and H. Park. Heart rate variability analysis for sleep apnea detection using recurrent neural networks. Frontiers in Physiology, 13:924153, 2022.
• X. Li and M. Chan. Feature engineering for ecg classification using deep learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31:1021–1033, 2023.
• G. Martin and J. Thomas. Real-time sleep apnea detection using edge computing and ai models. IEEE Internet of Things Journal, 10(7):10532–10544, 2023.
• C. Martinez and R. Gupta. Ecg signal processing using attention-based deep learning for sleep apnea detection. IEEE Transactions on Biomedical Engineering, 70:319–330, 2023.
• S. S. Mostafa, F. Mendonc¸a, A. G. Ravelo-Garc´ıa, and F. Morgado-Dias. A systematic review of detecting sleep apnea using deep learning. Sensors, 19(22):4934, 2019.
• D. Mukherjee, K. Dhar, F. Schwenker, and R. Sarkar. Ensemble of deep learning models for sleep apnea detection: an experimental study. Sensors, 21(16):5425, 2021.
• H. Nakamura and T. Kimura. Feature selection for ecg-based sleep apnea detection using genetic algorithms. Expert Systems with Applications, 198:116865, 2022.
• A. Patel and R. Shah. Automated ecg classification for sleep apnea detection using attention-based deep learning. IEEE Access, 11:10245–10256, 2023.
• M. Patel and S. Kumar. Deep learning-based obstructive sleep apnea classification from ecg signals. Neural Computing and Applications, 35:1173–1185, 2023.
• R. K. Pathinarupothi, E. S. Rangan, E. A. Gopalakrishnan, R. Vinaykumar, and K. P. Soman. Single sensor techniques for sleep apnea diagnosis using deep learning. In 2017 IEEE International Conference on Healthcare Informatics (ICHI), pages 524–529, 2017.
• A. Roy and B. Verma. Automatic sleep stage classification using deep belief networks. Artificial Intelligence in Medicine, 128:102162, 2022.
• A. Sheta, H. Turabieh, T. Thaher, and M. Mafarja. Diagnosis of obstructive sleep apnea from ecg signals using machine learning and deep learning classifiers. Applied Sciences, 11(14):6622, 2021.
• R. Singh and P. Verma. Efficient ecg-based sleep apnea detection using deep residual networks. IEEE Transactions on Biomedical Engineering, 69(2):667–677, 2022.
• E. Urtnasan, J. U. Park, E. Y. Joo, and K. J. Lee. Identification of sleep apnea severity based on deep learning from a short-term normal ecg. Journal of Korean Medical Science, 35(47):1–11, 2020.
• S. Vattamthanam, G. B. Mrudula, and C. S. Kumar. Sleep apnea classification using deep neural network. In 2020 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER), pages 133– 136, 2020.
• E.Wang, I. Koprinska, and B. Jeffries. Sleep apnea prediction using deep learning. IEEE Journal of Biomedical and Health Informatics, 27(11):5644–5654, 2023.
• K. Wang and L. Zhang. Automated detection of sleep apnea using deep transfer learning on ecg signals. IEEE Access, 9:112530–112540, 2021.
• M. Yildirim and S. Aslan. Hybrid cnn-rnn model for automatic sleep apnea detection. Computers in Biology and Medicine, 148:105837, 2022.
• B. Zhang and X. Li. Sleep apnea severity prediction using wavelet transform and deep cnn. Biomedical Engineering Online, 20:58, 2021.
• L. Zhang and Q. Xu. Graph neural networks for sleep apnea classification using ecg signals. IEEE Transactions on Neural Networks and Learning Systems, 34:890–900, 2023.
• T. Zhang and M. Singh. End-to-end deep learning approach for ecg-based sleep apnea detection. IEEE Transactions on Biomedical Circuits and Systems, 17:432–442, 2023.
• L. Zhao, Y. Wang, and X. Zhou. A hybrid cnn-lstm model for ecg-based sleep apnea classification. IEEE Transactions on Biomedical Circuits and Systems, 14(4):753–762, 2020.