Self-Supervised Representation Learning-Based OSA Detection Method Using Single-Channel ECG Signals

Sleep apnea (SA) is a pervasive and highly prevalent sleep disorder identified by recurrent breathing-related problems such as respiratory pauses for almost 10 s (called apnea events) during sleep. It is a strongly underdiagnosed problem because the person suffering from this disease is not aware of this situation. It may cause serious health issues and badly affect the quality of life. Therefore, the diagnosis of sleep is crucial to cure disease. Polysomnography (PSG) is a golden technique for diagnosing sleep disorders. In this technique, multiple sensors are used to collect specific physiological signals such as electroencephalogram (EEG), electromyogram (EMG), electrooculogram (EOG), and many more. In regular clinical practice, medical experts need to manually analyze the signals of sleep hours which is a tedious process. Therefore, the automatic diagnosis tool is needed to simplify this process. Recently, many research groups have proposed deep learning models for the automatic diagnosis of SA using physiological signals with good accuracy. However, all these models require a large amount of annotated data in the supervised training process, which limits the use of those models in real-time scenarios. However, annotating a huge amount of biomedical signals is challenging and requires lots of time and domain expertise. This study proposes a self-supervised representation learning (SSRL) method for detecting hypopnea events from single-channel electrocardiography (ECG) signals. The proposed model is trained in two phases. In the first training phase, an encoder is trained to learn signal representation from the unlabeled data. In the second training phase, the classifier and the encoder are fine-tuned for the classification. Our proposed model performed well on the test dataset with a per-segment classification accuracy of 85%, 89%, and 92% using only 1%, 10%, and 100% of the training data with labels, respectively, for fine-tuning encoder along with the classifier. Also, our proposed model can identify a person suffering from the obstructive SA (OSA) with the accuracy of 100%, even when the encoder and classifier are fine-tuned using only 1% of the training data with the label. The proposed model outperformed the state-of-the-art techniques and can be implemented offline or online for rapid and accurate diagnosis of the problem.

[1]  M. Mahdi Roozbahani,et al.  ScaleNet: An Unsupervised Representation Learning Method for Limited Information , 2023, GCPR.

[2]  Arnab Mondal.  COVID-19 prognosis using limited chest X-ray images , 2022, Applied Soft Computing.

[3]  M. V. van Putten,et al.  Automated Scoring of Respiratory Events in Sleep With a Single Effort Belt and Deep Neural Networks , 2021, IEEE Transactions on Biomedical Engineering.

[4]  Guanzheng Liu,et al.  Obstructive sleep apnea detection from single-lead electrocardiogram signals using one-dimensional squeeze-and-excitation residual group network , 2021, Comput. Biol. Medicine.

[5]  Jianhui Zhao,et al.  Self-supervised Contrastive Learning for EEG-based Sleep Staging , 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

[6]  Yiqiong Zhang,et al.  Self-Supervised Learning for Sleep Stage Classification with Predictive and Discriminative Contrastive Coding , 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  K. Kashino,et al.  BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation , 2021, IEEE International Joint Conference on Neural Network.

[8]  Roberto Hornero,et al.  A Convolutional Neural Network Architecture to Enhance Oximetry Ability to Diagnose Pediatric Obstructive Sleep Apnea , 2021, IEEE Journal of Biomedical and Health Informatics.

[9]  D. Tilbury,et al.  Gaussian Mixture Models for Detecting Sleep Apnea Events Using Single Oronasal Airflow Record , 2020, Applied Sciences.

[10]  Thomas Penzel,et al.  Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals , 2020, Sensors.

[11]  Geoffrey E. Hinton,et al.  Big Self-Supervised Models are Strong Semi-Supervised Learners , 2020, NeurIPS.

[12]  Pierre H. Richemond,et al.  Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning , 2020, NeurIPS.

[13]  Chen Sun,et al.  What makes for good views for contrastive learning , 2020, NeurIPS.

[14]  Junnan Li,et al.  Prototypical Contrastive Learning of Unsupervised Representations , 2020, ICLR.

[15]  Velayudhan M. Kumar,et al.  Importance of Sleep for Health and Wellbeing Amidst COVID-19 Pandemic , 2020, Sleep and vigilance.

[16]  Kaiming He,et al.  Improved Baselines with Momentum Contrastive Learning , 2020, ArXiv.

[17]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[18]  Changhua Lu,et al.  Detection of Sleep Apnea from Single-Lead ECG Signal Using a Time Window Artificial Neural Network , 2019, BioMed research international.

[19]  Ross B. Girshick,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Tom Dhaene,et al.  Automated Sleep Apnea Detection in Raw Respiratory Signals Using Long Short-Term Memory Neural Networks , 2019, IEEE Journal of Biomedical and Health Informatics.

[21]  Tao Wang,et al.  Sleep apnea detection from a single-lead ECG signal with automatic feature-extraction through a modified LeNet-5 convolutional neural network , 2019, PeerJ.

[22]  Swanirbhar Majumder,et al.  A NOVEL APPROACH OSA DETECTION USING SINGLE-LEAD ECG SCALOGRAM BASED ON DEEP NEURAL NETWORK , 2019, Journal of Mechanics in Medicine and Biology.

[23]  Phillip Isola,et al.  Contrastive Multiview Coding , 2019, ECCV.

[24]  R Devon Hjelm,et al.  Learning Representations by Maximizing Mutual Information Across Views , 2019, NeurIPS.

[25]  Ali Razavi,et al.  Data-Efficient Image Recognition with Contrastive Predictive Coding , 2019, ICML.

[26]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[27]  Haoqi Sun,et al.  Expert-level sleep scoring with deep neural networks , 2018, J. Am. Medical Informatics Assoc..

[28]  Kwang Suk Park,et al.  Real-time apnea-hypopnea event detection during sleep by convolutional neural networks , 2018, Comput. Biol. Medicine.

[29]  Theerawit Wilaiprasitporn,et al.  Deep Neural Networks with Weighted Averaged Overnight Airflow Features for Sleep Apnea-Hypopnea Severity Classification , 2018, TENCON 2018 - 2018 IEEE Region 10 Conference.

[30]  Theerawit Wilaiprasitporn,et al.  Single Channel ECG for Obstructive Sleep Apnea Severity Detection Using a Deep Learning Approach , 2018, TENCON 2018 - 2018 IEEE Region 10 Conference.

[31]  R. Devon Hjelm,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[32]  Oriol Vinyals,et al.  Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[33]  Irena Koprinska,et al.  Convolutional Neural Networks on Multiple Respiratory Channels to Detect Hypopnea and Obstructive Apnea Events , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[34]  Irena Koprinska,et al.  Detecting Hypopnea and Obstructive Apnea Events Using Convolutional Neural Networks on Wavelet Spectrograms of Nasal Airflow , 2018, PAKDD.

[35]  Yifan Li,et al.  A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal , 2018, Neurocomputing.

[36]  David Atienza Alonso,et al.  Online Obstructive Sleep Apnea Detection on Medical Wearable Sensors , 2018, IEEE Transactions on Biomedical Circuits and Systems.

[37]  Stella X. Yu,et al.  Unsupervised Feature Learning via Non-parametric Instance Discrimination , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  Kyogu Lee,et al.  Detection of sleep disordered breathing severity using acoustic biomarker and machine learning techniques , 2018, BioMedical Engineering OnLine.

[39]  Andrew Zisserman,et al.  Multi-task Self-Supervised Visual Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[40]  Wenpeng Yin,et al.  Comparative Study of CNN and RNN for Natural Language Processing , 2017, ArXiv.

[41]  K. K. Sharma,et al.  An algorithm for sleep apnea detection from single-lead ECG using Hermite basis functions , 2016, Comput. Biol. Medicine.

[42]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[43]  Xi Zhang,et al.  An Obstructive Sleep Apnea Detection Approach Using a Discriminative Hidden Markov Model From ECG Signals , 2016, IEEE Transactions on Biomedical Engineering.

[44]  Luis A. Hernández Gómez,et al.  Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment , 2015, Comput. Math. Methods Medicine.

[45]  Yaniv Zigel,et al.  Breath-by-breath detection of apneic events for OSA severity estimation using non-contact audio recordings , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[46]  Matthew J. Hausknecht,et al.  Beyond short snippets: Deep networks for video classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Javier Gomez-Pilar,et al.  Assessment of Time and Frequency Domain Entropies to Detect Sleep Apnoea in Heart Rate Variability Recordings from Men and Women , 2015, Entropy.

[48]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[49]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[50]  Philip de Chazal,et al.  Automated detection of obstructive sleep apnoea by single-lead ECG through ELM classification , 2014, Computing in Cardiology 2014.

[51]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[52]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[53]  L. Parrino,et al.  Commentary from the Italian Association of Sleep Medicine on the AASM manual for the scoring of sleep and associated events: for debate and discussion. , 2009, Sleep medicine.

[54]  D. Abásolo,et al.  Nonlinear characteristics of blood oxygen saturation from nocturnal oximetry for obstructive sleep apnoea detection , 2006, Physiological measurement.

[55]  P. Hamilton,et al.  Open source ECG analysis , 2002, Computers in Cardiology.

[56]  G. Moody,et al.  The apnea-ECG database , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[57]  P. de Chazal,et al.  Automatic classification of sleep apnea epochs using the electrocardiogram , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[58]  Geoffrey E. Hinton,et al.  Self-organizing neural network that discovers surfaces in random-dot stereograms , 1992, Nature.

[59]  Guanzheng Liu,et al.  Multiscale Deep Neural Network for Obstructive Sleep Apnea Detection Using RR Interval From Single-Lead ECG Signal , 2021, IEEE Transactions on Instrumentation and Measurement.

[60]  Weifeng Pan,et al.  A Sleep Apnea Detection Method Based on Unsupervised Feature Learning and Single-Lead Electrocardiogram , 2021, IEEE Transactions on Instrumentation and Measurement.

[61]  Xi Zhang,et al.  An Automatic Screening Approach for Obstructive Sleep Apnea Diagnosis Based on Single-Lead Electrocardiogram , 2015, IEEE Transactions on Automation Science and Engineering.

[62]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[63]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .