Abstract
In this paper, transfer learning is used for the adaptation of pre-trained deep convolutional neural networks (DCNNs) to find the best appropriate method for the classification of obstructive sleep apnea (OSA) using electrocardiogram (ECG) signals. The Physio Apnea-ECG data set has been used for the evaluation of the proposed method. In deep learning algorithms, especially in image data classification, more data leads to better performance. For this reason, in this paper, we propose a novel technique as follows. First, the ECG signal is divided into 2-s segments and filtered, then the recurrence plots (RP) algorithm is used to convert these segments into two-dimensional images. The RP is an advanced tool that can indicate how resemblances between particular orders vary over time. These plots are generally used for the qualitative evaluation of the time series in dynamic systems. Finally, in the classification stage, 5 pre-trained DCNN models on ImageNet datasets including EfficienNet-B0, EfficienNet-B1, EfficienNet-B2, Inception-v3, and Xception are considered for final decision. By using these methods, the classification accuracies of 88.67%, 90.59%, 90.52%, 93.33%, and 93.19%, were obtained respectively. In this research, by analyzing the performance of the models used, we can see that by increasing the input image size, the number of network parameters, its depth, and the classification performance is improved. Also, the performance of the Inception-v3 model which has the largest input image size and number of parameters with 93.33% accuracy, is better than other models for OSA detection.
Similar content being viewed by others
References
Abdel-Mageed FZ, Abou Chadi FEZ, Salah HM, Loza SF (2012) K9. Detection of sleep apnea events using analysis of thoraco-abdominal excursion signals and adaptive neuro-fuzzy inference system (ANFIS). In: 2012 29th National Radio Science Conference, IEEE, pp 691–698
Acharya UR, Fujita H, Lih OS, Adam M, Tan JH, Chua CK (2017) Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network. Knowl-Based Syst 132:62–71
Afrakhteh S, Ayatollahi A, Soltani F (2021) Classification of sleep apnea using EMD-based features and PSO-trained neural networks. Biomed Eng Tech 66:459–472
Al-Angari HM, Sahakian AV (2012) Automated recognition of obstructive sleep apnea syndrome using support vector machine classifier. IEEE Trans Inf Technol Biomed 16:463–468
Atila Ü, Uçar M, Akyol K, Uçar E (2021) Plant leaf disease classification using EfficientNet deep learning model. Ecol Inform 61:101182
Bahrami M, Forouzanfar M (2021) Detection of sleep apnea from single-lead ecg: comparison of deep learning algorithms. In: 2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA), IEEE, pp 1–5
Bahrami M, Forouzanfar M (2022) Sleep apnea detection from single-lead ECG: a comprehensive analysis of machine learning and deep learning algorithms. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2022.3151947
Choi SH, Yoon H, Kim HS, Kim HB, Bin Kwon H, Oh SM, Lee YJ, Park KS (2018) Real-time apnea-hypopnea event detection during sleep by convolutional neural networks. Comput Biol Med 100:123–131
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of IEEE Conference on Computing Vision and Pattern Recognition, pp 1251–1258
De Chazal P, Heneghan C, Sheridan E, Reilly R, Nolan P, O’Malley M (2003) Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea. IEEE Trans Biomed Eng 50:686–696
Erdenebayar U, Kim YJ, Park J-U, Joo EY, Lee K-J (2019) Deep learning approaches for automatic detection of sleep apnea events from an electrocardiogram. Comput Methods Progr Biomed 180:105001
Fatimah B, Singh P, Singhal A, Pachori RB (2020) Detection of apnea events from ECG segments using Fourier decomposition method. Biomed Signal Process Control 61:102005
Feng L, Wang X (2020) Automate obstructive sleep apnea diagnosis using convolutional neural networks. arXiv Prepr. arXiv2006.07664
Finamore P, Scarlata S, Cardaci V, Incalzi RA (2019) Exhaled breath analysis in obstructive sleep apnea syndrome: a review of the literature. Medicina (b. Aires) 55:538
Guijarro-Berdiñas B, Hernández-Pereira E, Peteiro-Barral D (2012) A mixture of experts for classifying sleep apneas. Expert Syst Appl 39:7084–7092
Hassan AR (2015) Automatic screening of obstructive sleep apnea from single-lead electrocardiogram. In: 2015 International Conference on Electrical Engineering and Information Communications Technoloogy, IEEE, pp 1–6
Hassan AR (2016) Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting. Biomed Signal Process Control 29:22–30
Hassan AR, Haque MA (2015) Computer-aided sleep apnea diagnosis from single-lead electrocardiogram using dual tree complex wavelet transform and spectral features. In: 2015 International Conference on Electrical Engineering, IEEE, pp 49–52
Hassan AR, Haque MA (2017) An expert system for automated identification of obstructive sleep apnea from single-lead ECG using random under sampling boosting. Neurocomputing 235:122–130
Hussain M, Bird JJ, Faria DR (2018) A study on cnn transfer learning for image classification. 18th UK workshop on computational intelligence. Springer, Berlin, pp 191–202
Hwang SH, Lee YJ, Jeong D-U, Park KS (2016) Apnea–hypopnea index prediction using electrocardiogram acquired during the sleep-onset period. IEEE Trans Biomed Eng 64:295–301
Isa SM et al (2011) Sleep apnea detection from ECG signal: analysis on optimal features, principal components, and nonlinearity. In: 2011 5th International Conference on Bioinformatics and Biomedical Engineering, IEEE, pp 1–4.
Janbakhshi P, Shamsollahi MB (2018) Sleep apnea detection from single-lead ECG using features based on ECG-derived respiration (EDR) signals. Irbm 39:206–218
Jun TJ, Nguyen HM, Kang D, Kim D, Kim D, Kim YH (2018) ECG arrhythmia classification using a 2-d convolutional neural network. Preprint arXiv1804.06812
Kalaivani V (2020) Automated recognition of obstructive sleep apnea using ensemble support vector machine classifier. Int J Biomed Eng Technol 33:274–289
Khandoker AH, Palaniswami M (2011) modeling respiratory movement signals during central and obstructive sleep apnea events using electrocardiogram. Ann Biomed Eng 39:801–811
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv1412.6980
Lun X, Jia S, Hou Y, Shi Y, Li Y (2020) GCNs-net: a graph convolutional neural network approach for decoding time-resolved eeg motor imagery signals. arXiv preprint arXiv:2006.08924. arXiv:2006.08924
Mahbod A, Schaefer G, Wang C, Dorffner G, Ecker R, Ellinger I (2020) Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification. Comput Methods Progr Biomed 193:105475
Marwan N, Romano MC, Thiel M, Kurths J (2007) Recurrence plots for the analysis of complex systems. Phys Rep 438:237–329
Mathunjwa BM, Lin Y-T, Lin C-H, Abbod MF, Shieh J-S (2021) ECG arrhythmia classification by using a recurrence plot and convolutional neural network. Biomed Signal Process Control 64:102262
Mendez MO, Ruini DD, Villantieri OP, Matteucci M, Penzel T, Cerutti S, Bianchi AM (2007) Detection of sleep apnea from surface ECG based on features extracted by an autoregressive model. In: 2007 29th Annual International Conference on IEEE Engineering in Medicine and Biologu Society, IEEE, pp 6105–6108
Nguyen HD, Wilkins BA, Cheng Q, Benjamin BA (2013) An online sleep apnea detection method based on recurrence quantification analysis. IEEE J Biomed Heal Inform 18:1285–1293
Nishad A, Pachori RB, Acharya UR (2018) Application of TQWT based filter-bank for sleep apnea screening using ECG signals. J Ambient Intell Humaniz Comput 5:5. https://doi.org/10.1007/s12652-018-0867-3
Poupard L, Philippe C, Goldman MD, Sartène R, Mathieu M (2012) Novel mathematical processing method of nocturnal oximetry for screening patients with suspected sleep apnoea syndrome. Sleep Breath 16:419–425
Ravelo-García AG, Kraemer JF, Navarro-Mesa JL, Hernández-Pérez E, Navarro-Esteva J, Juliá-Serdá G, Penzel T, Wessel N (2015) Oxygen saturation and RR intervals feature selection for sleep apnea detection. Entropy 17:2932–2957
Schulz J, Mentges A, Zielinski O (2016) Deriving image features for autonomous classification from time-series recurrence plots. J Eur Opt Soc Publ 12:5
Sharma H, Sharma KK (2016) An algorithm for sleep apnea detection from single-lead ECG using Hermite basis functions. Comput Biol Med 77:116–124
Sharma M, Agarwal S, Acharya UR (2018) Application of an optimal class of antisymmetric wavelet filter banks for obstructive sleep apnea diagnosis using ECG signals. Comput Biol Med 100:100–113
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of IEEE Conference on Computing Vision and Pattern Recognition, pp 2818–2826
Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, pp 6105–6114. PMLR. ICML
Tripathy RK (2018) Application of intrinsic band function technique for automated detection of sleep apnea using HRV and EDR signals, Biocybern. Biomed Eng 38:136–144
Urtnasan E, Park J-U, Joo E-Y, Lee K-J (2018) Automated detection of obstructive sleep apnea events from a single-lead electrocardiogram using a convolutional neural network. J Med Syst 42:104
Varon C, Caicedo A, Testelmans D, Buyse B, Van Huffel S (2015) A novel algorithm for the automatic detection of sleep apnea from single-lead ECG. IEEE Trans Biomed Eng 62:2269–2278
Wang T, Lu C, Shen G, Hong F (2019) Sleep apnea detection from a single-lead ECG signal with automatic feature-extraction through a modified LeNet-5 convolutional neural network. Peer J 7:e7731
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Train-Validation accuracy Xception model for fold (1–5).
Train-Validation diagram of InceptionV3 model for fold (1–5).
Train-Validation accuracy EfficientNetB2 model for fold (1–5).
Train-Validation accuracy EfficientNetB1 model for fold (1–5).
Train-Validation accuracy diagram of EfficientNetB0 model for fold (1–5).
Rights and permissions
About this article
Cite this article
Ayatollahi, A., Afrakhteh, S., Soltani, F. et al. Sleep apnea detection from ECG signal using deep CNN-based structures. Evolving Systems 14, 191–206 (2023). https://doi.org/10.1007/s12530-022-09445-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-022-09445-1