Skip to content
Microsystems, Electronics and Acoustics
ISSN 2523-4447 · e‑ISSN 2523-4455 Open Access · CC BY-SA 4.0
Vol. 27 · Issue 1 · 2022 Apr 29, 2022 Electronic Systems and Signals

Detection of Episodes of Sleep Apnea and Hypopnea in ECG and EEG Signals by Machine Learning

АР
Анна Костянтинівна Рихальська Corresponding Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського",Igor Sikorsky Kyiv Polytechnic Institute Ukraine
КІ
Катерина Олегівна Іванько Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського",Igor Sikorsky Kyiv Polytechnic Institute Ukraine
НІ
Наталія Георгіївна Іванушкіна Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського",Igor Sikorsky Kyiv Polytechnic Institute Ukraine
ДІ
Дмитро Олегович Іванько Норвезький університет природничих та технічних наук Norway
Pages251487-1-251487-11 PublishedApr 29, 2022
PDF (Ukrainian)
VOL 27 · ISS 1 · 2022 View issue

Abstract

The article is devoted to the application of machine learning methods for computerized detection of sleep apnea episodes based on the analysis of single-channel signals of the electrocardiogram (ECG) and electroencephalogram (EEG). To study the possibilities of machine learning to detect apnea based on ECG and EEG analysis, we used Apnea-ECG database and MIT-BIH polysomnographic database from PhysioNet, which contain annotations to each minute of records indicating the presence or absence of apnea/hypopnea at the current time. In order to apply machine learning methods to the problem of automated detection of sleep apnea/hypopnea episodes in ECG and EEG signals, long-term polysomnograms available in MIT-BIH polysomnographic database were segmented according to annotations into shorter sections lasting 30 seconds each. The study used 267 segments lasting 30 seconds for the class "norm", 258 segments for the class "apnea" and 273 segments for the class "hypopnea", a total of 798 simultaneous ECG and EEG recordings. The aim of this work is to identify and compare informative signs of sleep apnea episodes in terms of heart rate variability (HRV) and brain electrical activity, as well as the choice of classification methods that provide the highest accuracy for this task. Features of cardiorhythmograms in time and frequency domains, spectral-temporal and wavelet characteristics, as well as parameters of EEG signals based on energy ratio of EEG rhythms, Hearst index, Higuchi fractal dimension and sample entropy for EEG signals are considered. Using different sets of features, the accuracy of classifiers based on decision trees, discriminant analysis, support vector machines, k-nearest neighbor method, and ensemble training was determined. Based on this, combination of features and classifiers is proposed, which provides the highest accuracy of recognition of sleep apnea episodes according to single-channel ECG and EEG signals, taken separately and in the case of a combination of their features. The best results of classification of signals "norm", "apnea" and "hypopnea" were obtained for the model trained using weighted method k nearest neighbors with 25 features of HRV: the total percentage of correctly identified cases for three classes was 99.9% (797 correctly identified cases of 798). By reducing the number of HRV parameters to 9, the best machine learning result was achieved using the bagging ensemble algorithm with 30 decision trees: the total percentage of correctly identified cases for all three classes was 99.4% (793 correctly identified cases from 798: for "norm" - 265 cases from 267, for "apnea" - 257 cases from 258, for "hypopnea" - 271 cases from 273). The use of EEG parameters as features for apnea/hypopnea recognition showed worse results compared to HRV parameters. In this case, the best result of machine learning was achieved using support vector machines with quadratic kernel function: the total percentage of correctly identified cases for three classes was 91.9% and the signals corresponding to norm were most badly recognized (27 cases were classified as hypopnea, and in 9 cases - as sleep apnea). The combination of HRV and EEG parameters gave the best accuracy of 99.1%, but the results are comparable to using only HRV parameters. The obtained results indicate that HRV parameters allow recognizing sleep apnea and hypopnea with higher accuracy than EEG parameters, but EEG signal undoubtedly reflects signs of sleep apnea/hypopnea and also can be used for apnea recognition.

Keywords

#sleep apnea and hypopnea #heart and brain electrical activity #heart rate variability #spectral analysis #spectral-temporal analysis #wavelet analysis #fractal analysis #entropy #classification #machine learning

References

  1. S. F. Quan and B. J. Gersh, “Cardiovascular Consequences of Sleep-Disordered Breathing: Past, Present and Future: Report of a Workshop From the National Center on Sleep Disorders Research and the National Heart, Lung, and Blood Institute”, Circulation, vol. 109, no. 8, pp. 951–957, Mar. 2004. DOI: https://doi.org/10.1161/01.CIR.0000118216.84358.22
  2. W. R. Ruehland, P. D. Rochford, F. J. O’Donoghue, R. J. Pierce, P. Singh, and A. T. Thornton, “The New AASM Criteria for Scoring Hypopneas: Impact on the Apnea Hypopnea Index”, Sleep, vol. 32, no. 2, pp. 150–157, Feb. 2009. DOI: https://doi.org/10.1093/sleep/32.2.150
  3. X. Li, A. Al-Ani, and S. H. Ling, “Feature Selection for the Detection of Sleep Apnea using Multi-Bio Signals from Overnight Polysomnography”, in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, 2018, pp. 1444–1447. DOI: https://doi.org/10.1109/EMBC.2018.8512585
  4. T. Penzel, M. Glos, C. Schobel, M. Sebert, B. Diecker, and I. Fietze, “Revised recommendations for computer-based sleep recording and analysis”, in 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Minneapolis, MN, 2009, pp. 7099–7101. DOI: https://doi.org/10.1109/IEMBS.2009.5332903
  5. D. Álvarez-Estévez and V. Moret-Bonillo, “Identification of Electroencephalographic Arousals in Multichannel Sleep Recordings”, IEEE Transactions on Biomedical Engineering, vol. 58, no. 1, pp. 54–63, Jan. 2011. DOI: https://doi.org/10.1109/TBME.2010.2075930
  6. F. Liu, X. Zhou, Z. Wang, T. Wang, H. Ni, and J. Yang, “Identifying Obstructive Sleep Apnea by Exploiting Fine-Grained BCG Features Based on Event Phase Segmentation”, in 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering (BIBE), Taichung, Taiwan, 2016, pp. 293–300. DOI: https://doi.org/10.1109/BIBE.2016.45
  7. A. R. Hassan, “A comparative study of various classifiers for automated sleep apnea screening based on single-lead electrocardiogram”, in 2015 International Conference on Electrical & Electronic Engineering (ICEEE), Rajshahi, Bangladesh, 2015, pp. 45–48. DOI: https://doi.org/10.1109/CEEE.2015.7428288
  8. K. Zhu, “Overnight heart rate variability in patients with obstructive sleep apnoea: A time and frequency domain study”, Clinical and Experimental Pharmacology and Physiology, vol. 39, no. 11, pp. 901–908, Oct. 2012. DOI: https://doi.org/10.1111/1440-1681.12012
  9. J. Foussier, P. Fonseca, X. Long, B. Misgeld, and S. Leonhardt, “Combining HRV features for automatic arousal detection”, in Computing in Cardiology, pp. 1003–1006, 2013. URL: https://ieeexplore.ieee.org/abstract/document/6713549
  10. M. J. Lado, X. A. Vila, L. Rodríguez-Liñares, A. J. Méndez, D. N. Olivieri, and P. Félix, “Detecting Sleep Apnea by Heart Rate Variability Analysis: Assessing the Validity of Databases and Algorithms”, Journal of Medical Systems, vol. 35, no. 4, pp. 473–481, Oct. 2009. DOI: https://doi.org/10.1007/s10916-009-9383-5
  11. J. Gubbi, A. Khandoker, and M. Palaniswami, “Classification of sleep apnea types using wavelet packet analysis of short-term ECG signals”, Journal of Clinical Monitoring and Computing, vol. 26, no. 1, pp. 1–11, Dec. 2011. DOI: https://doi.org/10.1007/s10877-011-9323-z
  12. N. Sadr and P. de Chazal, “A fast approximation method for principal component analysis applied to ECG derived respiration for OSA detection”, in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA, 2016, pp. 6198–6201. DOI: https://doi.org/10.1109/EMBC.2016.7592144
  13. C. Varon, D. Testelmans, B. Buyse, J. A. K. Suykens, and S. Van Huffel, “Sleep apnea classification using least-squares support vector machines on single lead ECG”, in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, 2013, pp. 5029–5032. DOI: https://doi.org/10.1109/EMBC.2013.6610678
  14. K. Ivanko, N. Ivanushkina, and A. Rykhalska, “Identifying episodes of sleep apnea in ECG by machine learning methods”, in 2020 IEEE 40th International Conference on Electronics and Nanotechnology (ELNANO), Kyiv, Ukraine, 2020, pp. 588–593. DOI: https://doi.org/10.1109/ELNANO50318.2020.9088749 .
  15. G. Zhou, Y. Pan, J. Yang, X. Zhang, X. Guo, and Y. Luo, “Sleep Electroencephalographic Response to Respiratory Events in Patients With Moderate Sleep Apnea–Hypopnea Syndrome”, Frontiers in Neuroscience, vol. 14, Apr. 2020. DOI: https://doi.org/10.3389/fnins.2020.00310
  16. S. Saha, A. Bhattacharjee, and S. A. Fattah, “Automatic detection of sleep apnea events based on inter‐band energy ratio obtained from multi‐band EEG signal”, Healthcare Technology Letters, vol. 6, no. 3, pp. 82–86, Jun. 2019. DOI: https://doi.org/10.1049/htl.2018.5101 .
  17. X. Zhao, “Classification of sleep apnea based on EEG sub-band signal characteristics”, Scientific Reports, vol. 11, no. 1, Mar. 2021. DOI: https://doi.org/10.1038/s41598-021-85138-0
  18. G. Zhou, Y. Pan, J. Yang, X. Zhang, X. Guo, and Y. Luo, “Sleep Electroencephalographic Response to Respiratory Events in Patients With Moderate Sleep Apnea–Hypopnea Syndrome”, Frontiers in Neuroscience, vol. 14, Apr. 2020. DOI: https://doi.org/10.3389/fnins.2020.00310
  19. R. Jayaraj and J. Mohan, “Classification of Sleep Apnea Based on Sub-Band Decomposition of EEG Signals”, Diagnostics, vol. 11, no. 9, p. 1571, Aug. 2021. DOI: https://doi.org/10.3390/diagnostics11091571
  20. A. L. Goldberger, “PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals”, Circulation, vol. 101, no. 23, Jun. 2000. DOI: https://doi.org/10.1161/01.CIR.101.23.e215
  21. T. Penzel, G. Moody, R. Mark, A. Goldberger, and J. Peter, “The apnea-ECG database”, in Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163), Cambridge, MA, USA, 2000, pp. 255–258. DOI: https://doi.org/10.1109/CIC.2000.898505
  22. MIT-BIH Polysomnographic Database. – URL: https://physionet.org/content/slpdb/1.0.0/ .
  23. Y. Ichimaru and G. Moody, “Development of the polysomnographic database on CD‐ROM”, Psychiatry and Clinical Neurosciences, vol. 53, no. 2, pp. 175–177, Apr. 1999. DOI: https://doi.org/10.1046/j.1440-1819.1999.00527.x
  24. Task Force of the European Society of Cardiology the North American Society of Pacing Electrophysiology, “Heart Rate Variability: Standards of Measurement, Physiological Interpretation, and Clinical Use”, Circulation, vol. 93, no. 5, pp. 1043–1065, Mar. 1996. DOI: https://doi.org/10.1161/01.CIR.93.5.1043
  25. N. L. Chamberlin, “Brain circuitry mediating arousal from obstructive sleep apnea”, Current Opinion in Neurobiology, vol. 23, no. 5, pp. 774–779, Oct. 2013. DOI: https://doi.org/10.1016/j.conb.2013.06.001
  26. S. Lahmiri, “Generalized Hurst exponent estimates differentiate EEG signals of healthy and epileptic patients”, Physica A: Statistical Mechanics and its Applications, vol. 490, pp. 378–385, Jan. 2018. DOI: https://doi.org/10.1016/j.physa.2017.08.084 .
  27. S. Kesić and S. Z. Spasić, “Application of Higuchi’s fractal dimension from basic to clinical neurophysiology: A review”, Computer Methods and Programs in Biomedicine, vol. 133, pp. 55–70, Sep. 2016. DOI: https://doi.org/10.1016/j.cmpb.2016.05.014
  28. R. Bhavsar, N. Helian, Y. Sun, N. Davey, T. Steffert, and D. Mayor, “Efficient Methods for Calculating Sample Entropy in Time Series Data Analysis”, Procedia Computer Science, vol. 145, pp. 97–104, Jan. 2018. DOI: https://doi.org/10.1016/j.procs.2018.11.016
§ 06 — Related

Similar articles in this journal

Related peer-reviewed studies published in this journal.
View all issues

Quasistatic Identification of The Shading Structure of Solar Panels by The Method of Cardinal Number Vectors

PhD, Assoc. Prof. Olena Olehivna Abakumova, Dr.Sc.(Eng.), Prof. Valerii Yakovych Zhuikov, Mykola O. Lukianov

In the article the problem of identification the shading structure of solar panels is considered. The relevance of the study is conditioned by the necessity of rapid and…

#solar panels #photovoltaic surface #shadow structure modeling #quasistatic identification
p. 362283.1-362283.7
10.20535/2523-4455.mea.362283

Simulation Modeling of a Filter-Compensating Converter for a Three-Phase Three-Wire Network

Ivan Andriiovych Vakulenko, PhD, Assoc. Prof. Dmytro Anatoliiovych Mykolaiets, PhD, Assoc. Prof. Kateryna Serhiivna Klen

This paper addresses the critical issue of power quality degradation in modern power systems caused by the proliferation of non-linear loads. The study focuses on the…

#filter-compensating converter #three-phase three-wire network #power quality #total harmonic distortion
p. 361138.1-361138.6
10.20535/2523-4455.mea.361138

A A Complex Method for Non-invasive Fetal Electrocardiogram Signal Extraction and Cardiac Arrhythmia Classification

Dmytro A. Shevchuk, PhD, Assoc. Prof. Nataliia Heorhiivna Ivanushkina

This study is devoted to the development of a complex method for extracting the fetal electrocardiogram (fECG) from non-invasive abdominal recordings and for the…

#abdominal electrocardiogram #fetal electrocardiogram #arrhythmia #blind source separation
p. 356487.1-356487.11
10.20535/2523-4455.mea.356487

Most read articles by the same author(s)

Similar Articles

1-10 of 141

You may also start an advanced similarity search for this article.