Abstract
Artificial Intelligence-enabled applications on edge devices have the potential to revolutionize disease detection and monitoring in future smart health (sHealth) systems. In this study, we investigated a minimalist approach for the severity classification, severity estimation, and progression monitoring of obstructive sleep apnea (OSA) in a home environment using wearables. We used the recursive feature elimination technique to select the best feature set of 70 features from a total of 200 features extracted from polysomnogram. We used a multi-layer perceptron model to investigate the performance of OSA severity classification with all the ranked features to a subset of features available from either Electroencephalography or Heart Rate Variability (HRV) and time duration of SpO2 level. The results indicate that using only computationally inexpensive features from HRV and SpO2, an area under the curve of 0.91 and an accuracy of 83.97% can be achieved for the severity classification of OSA. For estimation of the apnea-hypopnea index, the accuracy of RMSE = 4.6 and R-squared value = 0.71 have been achieved in the test set using only ranked HRV and SpO2 features. The Wilcoxon-signed-rank test indicates a significant change (p < 0.05) in the selected feature values for a progression in the disease over 2.5 years. The method has the potential for integration with edge computing for deployment on everyday wearables. This may facilitate the preliminary severity estimation, monitoring, and management of OSA patients and reduce associated healthcare costs as well as the prevalence of untreated OSA.
- [1] . 2014. Healthcare-related data in the cloud: Challenges and opportunities. IEEE Cloud Computing 6, (2014), 10–14.Google Scholar
- [2] 2019. A generative model for speech segmentation and obfuscation for remote health monitoring. The 2019 IEEE International Conference on Wearable and Implantable Body Sensor Networks, Chicago, IL, May 2019.Google Scholar
- [3] . 2011. Home is safer than the cloud! Privacy concerns for consumer cloud storage. In Proceedings of the Seventh Symposium on Usable Privacy and Security (2011), 1–20. Google Scholar
Digital Library
- [4] Mobile-Edge Computing Introductory Technical White Paper. ETSI. [Online]. Available: https://portal.etsi.org/Portals/0/TBpages/MEC/Docs/Mobile-edge Computing - Introductory Technical White Paper V1%2018-09-14.pdfGoogle Scholar
- [5] . 2019. Edge intelligence: Paving the last mile of artificial intelligence with edge computing. In Proceedings of the IEEE 107, 8 (2019), 1738–1762.Google Scholar
Cross Ref
- [6] . 2019. Deep learning with edge computing: A review. In Proceedings of the IEEE 107, 8 (2019), 1655–1674.Google Scholar
- [7] . 2018. Edge-cloud collaborative processing for intelligent Internet of Things. In Proceedings of the 55th Annual Design Automation Conference (DAC 2018) (2018), 1–6. Google Scholar
Digital Library
- [8] 2016. Edge computing: Vision and challenges. IEEE Internet of Things Journal 3, 5 (2016), 637–646Google Scholar
Cross Ref
- [9] . 2015. Obstructive sleep apnea is a common disorder in the population—a review on the epidemiology of sleep apnea. Journal of Thoracic Disease 7, 8 (2015), 1311.Google Scholar
- [10] . 2008. The epidemiology of adult obstructive sleep apnea. Proceedings of the American Thoracic Society 5, 2 (2008), 136–143.Google Scholar
Cross Ref
- [11] 2002. Underdiagnoses of sleep apnea syndrome in U.S. communities. Sleep Breath 6, (2002), 49–54.Google Scholar
Cross Ref
- [12] . 2009. Epidemiology, risk factors, and consequences of obstructive sleep apnea and short sleep duration. Progress in Cardiovascular Diseases 51, 4 (2009), 285–293.Google Scholar
Cross Ref
- [13] . 1993. The occurrence of sleep-disordered breathing among middle-aged adults. New England Journal of Medicine 328, 17 (1993), 1230–1235.Google Scholar
Cross Ref
- [14] . 2009. Automated recognition of patients with obstructive sleep apnoea using wavelet-based features of electrocardiogram recordings. Computers in Biology and Medicine 39, 1 (2009), 88–96. Google Scholar
Digital Library
- [15] . 2015. A novel algorithm for the automatic detection of sleep apnea from single-lead ECG. IEEE Tran. on Biomedical Engineering 62, 9 (2015), 2269–2278.Google Scholar
Cross Ref
- [16] . 2012. Hht based cardiopulmonary coupling analysis for sleep apnea detection. Sleep Medicine 13, 5 (2012), 503–509.Google Scholar
Cross Ref
- [17] . 2007. Detection of sleep apnea episodes from multi-lead ECGs considering different physiological influences. Methods of Information in Medicine 46, 2 (2007), 216–221.Google Scholar
- [18] . 2011. Apnea MedAssist: Real-time sleep apnea monitor using single-lead ECG. IEEE Transactions on Information Technology in Biomedicine 15, 3 (2011), 416–427. Google Scholar
Digital Library
- [19] . 2019. Automatic detection of obstructive sleep apnea using wavelet transform and entropy-based features from single-lead ECG signal. In IEEE Journal of Biomedical and Health Informatics 23, 3 (2019), 1011–1021.Google Scholar
- [20] . 2016. Evaluation of a decision support system for obstructive sleep apnea with nonlinear analysis of respiratory signals. PLoS ONE 11, 3 (2016), e0150163Google Scholar
- [21] . 2019. Exacerbation in obstructive sleep apnea: Early detection and monitoring using a single channel EEG with quadratic discriminant analysis. 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), San Francisco, CA, USA, 2019, 85–88.Google Scholar
- [22] . 2017. Clinical practice guideline for diagnostic testing for adult obstructive sleep apnea: An American Academy of sleep medicine clinical practice guideline. Journal of Clinical Sleep Medicine 13, 03 (2017), 479–504.Google Scholar
- [23] 2009. Clinical guideline for the evaluation, management and long-term care of obstructive sleep apnea in adults. J. of Clinical Sleep Medicine 5, 03 (2009), 263–276.Google Scholar
- [24] 2017. A new method for self-estimation of the severity of obstructive sleep apnea using easily available measurements and neural fuzzy evaluation system. In IEEE Journal of Biomedical and Health Informatics 21, 6 (2017), 1524–1532.Google Scholar
Cross Ref
- [25] . 2017. Apnea–hypopnea index prediction using electrocardiogram acquired during the sleep-onset period. In IEEE Transactions on Biomedical Engineering 64, 2 (2017), 295–301.Google Scholar
- [26] 2019. Apnea-hypopnea index (AHI) estimation using breathing sounds, accelerometer and pulse oximeter. European Respiratory J. Open Research 5, 63 (2019).Google Scholar
- [27] . 2015. A home sleep apnea screening device with time-domain signal processing and autonomous scoring capability. In IEEE Transactions on Biomedical Circuits and Systems 9, 1 (2015), 96–104.Google Scholar
Cross Ref
- [28] 2019. Estimation of the apnea-hypopnea index in a heterogeneous sleep-disordered population using optimised cardiovascular features. Scientific Reports 9, (2019), 17448.Google Scholar
- [29] . 2008. Severity of obstructive sleep apnoea/hypopnoea syndrome and subsequent waking EEG spectral power. European Respiratory Journal 32, 3 (2008), 705–709.Google Scholar
- [30] Taking an ECG with the ECG app on Apple Watch Series 4 or later. Available online at https://support.apple.com/en-us/HT208955, accessed on 23 Jan, 2020.Google Scholar
- [31] . 2014. Novel cloud and SOA-based framework for e-health monitoring using wireless biosensors. In IEEE Journal of Biomedical and Health Informatics 18, 1 (2014), 46–55.Google Scholar
Cross Ref
- [32] 2017. Real-time signal quality-aware ECG telemetry system for IoT-based health care monitoring. In IEEE Internet of Things Journal 4, 3 (2017), 815–823.Google Scholar
- [33] 2017. Smart health solution integrating IoT and cloud: A case study of voice pathology monitoring. In IEEE Communications Magazine 55, 1 (2017), 69–73. Google Scholar
Digital Library
- [34] 2020. The future of sleep health: A data-driven revolution in sleep science and medicine. NPJ Digital Medicine 3, 1 (2020), 1–15.Google Scholar
- [35] 2016. Scaling up scientific discovery in sleep medicine: The national sleep research resource. Sleep 39, 5 (2016), 1151–1164.Google Scholar
Cross Ref
- [36] 1998. Methods for obtaining and analyzing unattended polysomnography data for a multicenter study. Sleep Heart Health Research Group. Sleep 21, 7 (1998), 759–767.Google Scholar
- [37] . 2019. Obstructive sleep apnea syndrome and autonomic dysfunction. Autonomic Neuroscience 221, 2019, 102563, ISSN 1566–0702.Google Scholar
Cross Ref
- [38] . 1998. Obstructive sleep apnoea and the autonomic nervous system. Sleep Medicine Reviews 2, 2 (1998), 69–92.Google Scholar
- [39] 1985. Bradycardia during sleep apnea. Characteristics and mechanisms. J Clin Invest 69, (1982), 1286–1292.Google Scholar
- [40] . 1985. A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 32, 3 (1985), 230–236.Google Scholar
Cross Ref
- [41] . 1989. Heart rate variability in relation to prognosis after myocardial infarction: Selection of optimal processing techniques. European Heart Journal 10, 12 (1989), 1060–1074.Google Scholar
- [42] 2000. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 101, 23 (2000), e215–e220.Google Scholar
Cross Ref
- [43] . 2019. Sleep study and oximetry parameters for predicting postoperative complications in patients with OSA. Chest 155, 4 (2019), 855–867.Google Scholar
- [44] 2020. The correlation between oxygen saturation indices and the standard obstructive sleep apnea severity. Annals of Thoracic Medicine 15, 2 (2020), 70–75.
DOI: DOI: 10.4103/atm.ATM_215_19Google Scholar - [45] , SpectralTrainFig, MATLAB Central File Exchange. Retrieved February 14, 2020.Google Scholar
- [46] . 2002. Gene selection for cancer classification using support vector machines. Machine Learning 46, 1–3 (2002), 389–422. Google Scholar
Digital Library
- [47] . 2002. Selection bias in gene extraction on the basis of microarray gene-expression data. Proceedings of the National Academy of Sciences 99, 10 (2002), 6562–6566.Google Scholar
- [48] . 2008. Building predictive models in R using the caret package. Journal of Statistical Software 28, 5 (2008), 1–26.Google Scholar
Cross Ref
- [49] 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, (2011) 2825–2830. Google Scholar
Digital Library
- [50] . 2015. Keras: Deep learning library for Theano and TensorFlow. URL: https://keras.io/k.Google Scholar
- [51] . 2013. SMOTE for high-dimensional class-imbalanced data. BMC Bioinformatics 14, 106 (2013).
DOI:
https://doi.org/10.1186/1471-2105-14-106Google Scholar
- [52] . 2007. Learning on the border: Active learning in imbalanced data classification. In Proceedings of the Sixteenth ACM Conference on Information and Knowledge Management (2007), 127–136. Google Scholar
Digital Library
- [53] . 2002. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research (2002), 321–357. Google Scholar
Digital Library
- [54] . 1996. Large-scale machine learning with stochastic gradient descent. Proceedings of COMPSTAT'2010. Physica-Verlag HD 2010. 177–186.Google Scholar
- [55] . 1996. Applied Linear Statistical Models. 4th ed. Chicago: Irwin, 1996.Google Scholar
- [56] 1993. A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6, 4 (1993), 525–533. Google Scholar
Digital Library
- [57] . 2017. Potential underestimation of sleep apnea severity by at-home kits: Rescoring in-laboratory polysomnography without sleep staging. Journal of Clinical Sleep Medicine 13, 4 (2017), 551.Google Scholar
- [58] . 2019. SCC Health: A framework for online estimation of disease severity for the smart and connected community. 2019 IEEE International Conference on Electro Information Technology (EIT) 2019, 373–378.
DOI: DOI: 10.1109/EIT.2019.8834189Google Scholar - [59] . 2020. A field study to capture events of interest (EoI) from living labs using wearables for spatiotemporal monitoring towards a framework of smart health (sHealth). 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC’20). 5943–5947.
DOI: DOI: 10.1109/EMBC44109.2020.9175771Google Scholar
Index Terms
A Minimalist Method Toward Severity Assessment and Progression Monitoring of Obstructive Sleep Apnea on the Edge
Recommendations
Development of Lead System for ECG-Derived Respiration Aimed at Detection of Obstructive Sleep Apnea Syndrome
SITIS '13: Proceedings of the 2013 International Conference on Signal-Image Technology & Internet-Based SystemsObstructive sleep apnea syndrome is the most common type of sleep apnea, characterized by repetitive pauses in breathing during sleep. Recent studies have investigated screening methods based only on an electrocardiogram (ECG). Generally, in ECG-based ...
Monitoring obstructive sleep apnea with electrocardiography and 3-axis acceleration sensor
PETRA '15: Proceedings of the 8th ACM International Conference on PErvasive Technologies Related to Assistive EnvironmentsObstructive sleep apnea syndrome is a sleep-related breathing disorder that is caused by obstruction of the upper airway. This condition may be related with many clinical sequelae such as cardiovascular disease, high blood pressure, stroke, diabetes, ...
Automatic sleep staging in obstructive sleep apnea patients using photoplethysmography, heart rate variability signal and machine learning techniques
It is extremely significant to identify sleep stages accurately in the diagnosis of obstructive sleep apnea. In the study, it was aimed at determining sleep and wakefulness using a practical and applicable method. For this purpose , the signal of heart ...






Comments