Detection of Sleep Apnea using 1D-CNN-BiLSTM: Fine-Tuning Convolutional Neural Network and Long Short-Term Memory Architecture for Improved Performance
DOI:
https://doi.org/10.21467/proceedings.7.6.13Keywords:
Sleep Apnea, Deep Learning, CNN-LSTMAbstract
Sleep Apnea is a commonly undiagnosed disease characterized by repeated interruptions in breathing during sleep, which leads to fragmented sleep and reduced blood oxygen levels. Handcrafted single- lead Electrocardiogram (ECG) signals are very complex in nature due to their large dimensions and not so robust nature. In this research, a 23 layered deep-learning based hybrid model was made by combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) with an attention mechanism module to process such complex ECG signals efficiently. The dataset was also preprocessed and segmented into time series data to improve the model training efficiency. Then, the Apnea-Hypopnea Index (AHI) was applied to identify normal and apnea subjects and categorize them into normal, mild-apnea, moderate-apnea and severe-apnea categories. These experiments were conducted on the publicly available Apnea-ECG dataset to assess the method’s usefulness. Our proposed model succeeds in achieving a higher accuracy of 95.79% in comparison to other sleep apnea detection methods.
References
1. A. Zarei, H. Beheshti, and B. M. Asl, “Detection of sleep apnea using deep neural networks and single-lead ECG signals,” Biomedical Signal Processing and Control, vol. 71, p. 103125, Jan. 2022.
2. 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, vol. 71, pp. 1–11, 2022.
3. F. Mendonca, S. S. Mostafa, A. G. Ravelo-Garcia, F. Morgado-Dias, and T. Penzel, “A review of obstructive sleep apnea detection approaches,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 2, pp. 825–837, Mar. 2019.
4. A. Zarei and B. M. Asl, “Automatic classification of apnea and normal subjects using new features extracted from HRV and ECG-derived respiration signals,” Biomedical Signal Processing and Control, vol. 59, p. 101927, May 2020.
5. H. D. Nguyen, B. A. Wilkins, Q. Cheng, and B. A. Benjamin, “An online sleep apnea detection method based on recur-rence quantification analysis,” IEEE Journal of Biomedical and Health Informatics, vol. 18, no. 4, pp. 1285–1293, Jul. 2014.
6. A. H. Khandoker, M. Palaniswami, and C. K. Karmakar, “Support vector machines for automated recognition of obstruc-tive sleep apnea syndrome from ECG recordings,” IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 1, pp. 37–48, Jan. 2009.
7. M. O. Mendez, A. M. Bianchi, M. Matteucci, S. Cerutti, and T. Penzel, “Sleep apnea screening by autoregressive models from a single ECG lead,” IEEE Transactions on Biomedical Engineering, vol. 56, no. 12, pp. 2838–2850, Dec. 2009.
8. U. Erdenebayar, Y. J. Kim, J. U. Park, E. Y. Joo, and K. J. Lee, “Deep learning approaches for automatic detection of sleep apnea events from an electrocardiogram,” Computer Methods and Programs in Biomedicine, vol. 180, p. 105001, Oct. 2019.
9. D. Dey, S. Chaudhuri, and S. Munshi, “Obstructive sleep apnoea detection using convolutional neural network based deep learning framework,” Biomedical Engineering Letters, vol. 8, no. 1, pp. 95–100, Feb. 2018.
10. D. Novak, K. Mucha, and T. Al-Ani, “Long short-term memory for apnea detection based on heart rate variability,” in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Van-couver, BC, Canada, Aug. 2008, pp. 5234–5237.
11. R. K. Pathinarupothi, R. Vinaykumar, E. Rangan, E. Gopalakrishnan, and K. P. Soman, “Instantaneous heart rate as a ro-bust feature for sleep apnea severity detection using deep learning,” in Proceedings of the IEEE EMBS International Con-ference on Biomedical and Health Informatics (BHI), Orlando, FL, USA, Feb. 2017, pp. 293–296.
12. S. Goswami, U. Srivastava, P. M. Chinni, and S. Dhanalakshmi, “Enhancing brain MRI tumor detection: Exploring vision transformers and fine-tuned convolutional neural network architecture for improved performance,” in Proceedings of the International Conference on Advanced Computing and Intelligent Technologies, Singapore, Dec. 2023, pp. 303–316.
13. T. Penzel, G. B. Moody, R. G. Mark, A. L. Goldberger, and J. H. Peter, “The apnea-ECG database,” in Computers in Cardiology 2000, vol. 27, Cambridge, MA, USA, Sep. 2000, pp. 255–258.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
