AI-Enabled Algorithm for Automatic Classification of Sleep Disorders Based on Single-Lead Electrocardiogram

Erdenebayar Urtnasan, Eun Yeon Joo, Kyu Hee Lee, Erdenebayar Urtnasan, Eun Yeon Joo, Kyu Hee Lee

Abstract

Healthy sleep is an essential physiological process for every individual to live a healthy life. Many sleep disorders both destroy the quality and decrease the duration of sleep. Thus, a convenient and accurate detection or classification method is important for screening and identifying sleep disorders. In this study, we proposed an AI-enabled algorithm for the automatic classification of sleep disorders based on a single-lead electrocardiogram (ECG). An AI-enabled algorithm-named a sleep disorder network (SDN)-was designed for automatic classification of four major sleep disorders, namely insomnia (INS), periodic leg movement (PLM), REM sleep behavior disorder (RBD), and nocturnal frontal-lobe epilepsy (NFE). The SDN was constructed using deep convolutional neural networks that can extract and analyze the complex and cyclic rhythm of sleep disorders that affect ECG patterns. The SDN consists of five layers, a 1D convolutional layer, and is optimized via dropout and batch normalization. The single-lead ECG signal was extracted from the 35 subjects with the control (CNT) and the four sleep disorder groups (seven subjects of each group) in the CAP Sleep Database. The ECG signal was pre-processed, segmented at 30 s intervals, and divided into the training, validation, and test sets consisting of 74,135, 18,534, and 23,168 segments, respectively. The constructed SDN was trained and evaluated using the CAP Sleep Database, which contains not only data on sleep disorders, but also data of the control group. The proposed SDN algorithm for the automatic classification of sleep disorders based on a single-lead ECG showed very high performances. We achieved F1 scores of 99.0%, 97.0%, 97.0%, 95.0%, and 98.0% for the CNT, INS, PLM, RBD, and NFE groups, respectively. We proposed an AI-enabled method for the automatic classification of sleep disorders based on a single-lead ECG signal. In addition, it represents the possibility of the sleep disorder classification using ECG only. The SDN can be a useful tool or an alternative screening method based on single-lead ECGs for sleep monitoring and screening.

Keywords: automatic classification; convolutional neural network; deep learning; electrocardiogram; sleep disorders.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Schematic diagram of this study. (A) CAP sleep database, (B) ECG dataset, (C) deep learning model, and (D) Outputs.
Figure 2
Figure 2
Confusion matrix of the proposed SDN model for the automatic classification of sleep disorders based on a single-lead ECG signal. The performances of the training set (A), validation set (B), and test set (C), respectively.
Figure 3
Figure 3
Example of the intermediate feature map of the designed deep learning SDN model for automatic classification of sleep disorders using a single-lead ECG signal. Intermediate feature maps of (A) INS, (B) PLM, (C) CNT, (D) RBD, and (E) NFE groups.

References

    1. Thorpy M. Sleep Disorders Medicine. Springer; New York, NY, USA: 2017. International classification of sleep disorders; pp. 475–484.
    1. Šušmáková K. Human Sleep and Sleep EEG. Meas. Sci. Rev. 2004;4:59–74.
    1. Banno K., Kryger M.H. Sleep apnea: Clinical investigations in humans. Sleep Med. 2007;8:400–426.
    1. Morin C.M., Benca R. Chronic insomnia. Lancet. 2012;379:1129–1141.
    1. Moore H., IV, Leary E., Lee S.Y., Carrillo O., Stubbs R., Peppard P., Young T., Widrow B., Mignot E. Design and validation of a periodic leg movement detector. PLoS ONE. 2014;9:e114565. doi: 10.1371/journal.pone.0114565.
    1. McCarter S.J., Boswell C.L., Louis E.K.S., Dueffert L.G., Slocumb N., Boeve B.F., Silber M.H., Olson E.J., Tippmann-Peikert M. Treatment outcomes in REM sleep behavior disorder. Sleep Med. 2013;14:237–242.
    1. Chervin R.D. Sleepiness, fatigue, tiredness, and lack of energy in obstructive sleep apnea. Chest. 2000;118:372–379. doi: 10.1378/chest.118.2.372.
    1. Graff-Radford S.B., Newman A. Obstructive sleep apnea and cluster headache. Headae. 2004;44:607–610. doi: 10.1111/j.1526-4610.2004.446010.x.
    1. Lattimore J.D.L., Celermajer D.S., Wilcox I. Obstructive sleep apnea and cardiovascular disease. J. Am. Coll. Cardiol. 2003;41:1429–1437. doi: 10.1016/S0735-1097(03)00184-0.
    1. Lal C., Strange C., Bachman D. Neurocognitive impairment in obstructive sleep apnea. Chest. 2012;141:1601–1610. doi: 10.1378/chest.11-2214.
    1. Gamaldo C.E., Shaikh A.K., McArthur J.C. The sleep-immunity relationship. Neurol. Clin. 2012;30:1313–1343. doi: 10.1016/j.ncl.2012.08.007.
    1. Kapur V., Strohl K.P., Redline S., Iber C., O’connor G., Nieto J. Underdiagnosis of sleep apnea syndrome in US communities. Sleep Breath. 2002;6:49–54. doi: 10.1055/s-2002-32318.
    1. Douglas N.J., Thomas S., Jan M.A. Clinical value of polysomnography. Lancet. 1992;339:347–350. doi: 10.1016/0140-6736(92)91660-Z.
    1. Penzel T., Moody G.B., Mark R.G., Goldberger A.L., Peter J.H. Computers in Cardiology. Vol. 27. IEEE; Cambridge, MA, USA: 2000. The apnea-ECG database; pp. 255–258.
    1. Faust O., Hagiwara Y., Hong T.J., Lih O.S., Acharya U.R. Deep learning for healthcare applications based on physiological signals: A review. Comput. Methods Programs Biomed. 2018;161:1–13.
    1. Stein P.K., Pu Y. Heart rate variability, sleep and sleep disorders. Sleep Med. Rev. 2012;16:47–66.
    1. Spiegelhalder K.A.I., Fuchs L., Ladwig J., Kyle S.D., Nissen C., Voderholzer U., Feige B., Riemann D. Heart rate and heart rate variability in subjectively reported insomnia. J. Sleep Res. 2011;20:137–145. doi: 10.1111/j.1365-2869.2010.00863.x.
    1. De Chazal P., Heneghan C., Sheridan E., Reilly R., Nolan P., O’Malley M. Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea. IEEE Trans. Biomed. Eng. 2003;50:686–696.
    1. Mendez M.O., Bianchi A.M., Matteucci M., Cerutti S., Penzel T. Sleep apnea screening by autoregressive models from a single ECG lead. IEEE Trans. Biomed. Eng. 2009;56:2838–2850. doi: 10.1109/TBME.2009.2029563.
    1. Chen L., Zhang X., Song C. An automatic screening approach for obstructive sleep apnea diagnosis based on single-lead electrocardiogram. IEEE Trans. Autom. Sci. Eng. 2015;12:106–115. doi: 10.1109/TASE.2014.2345667.
    1. Adnane M., Jiang Z., Yan Z. Sleep–wake stages classification and sleep efficiency estimation using single-lead electrocardiogram. Expert Syst. Appl. 2012;39:1401–1413.
    1. Xiao M., Yan H., Song J., Yang Y., Yang X. Sleep stages classification based on heart rate variability and random forest. Biomed. Signal Process. Control. 2013;8:624–633.
    1. Singh J., Sharma R.K., Gupta A.K. A method of REM-NREM sleep distinction using ECG signal for unobtrusive personal monitoring. Comput. Biol. Med. 2016;78:138–143. doi: 10.1016/j.compbiomed.2016.09.018.
    1. Yücelbaş Ş., Yücelbaş C., Tezel G., Özşen S., Yosunkaya Ş., Yosunkaya S. Automatic sleep staging based on SVD, VMD, HHT and morphological features of single-lead ECG signal. Expert Syst. Appl. 2018;102:193–206.
    1. Wei R., Zhang X., Wang J., Dang X. The research of sleep staging based on single-lead electrocardiogram and deep neural network. Biomed. Eng. Lett. 2018;8:87–93. doi: 10.1007/s13534-017-0044-1.
    1. Li Q., Li Q., Liu C., Shashikumar S.P., Nemati S., Clifford G.D. Deep learning in the cross-time frequency domain for sleep staging from a single-lead electrocardiogram. Physiol. Meas. 2018;39:124005.
    1. Radha M., Fonseca P., Ross M., Cerny A., Anderer P., Aarts R.M. LSTM knowledge transfer for HRV-based sleep staging. arXiv. 20181809.06221v1
    1. Erdenebayar U., Park J.U., Lee S., Joo E.Y., Lee K.J. Prediction Method of Periodic Limb Movements Based on Deep Learning Using ECG Signal. Int. J. Fuzzy Log. Intell. Syst. 2020;20:138–144. doi: 10.5391/IJFIS.2020.20.2.138.
    1. Dodds K.L., Miller C.B., Kyle S.D., Marshall N.S., Gordon C.J. Heart rate variability in insomnia patients: A critical review of the literature. Sleep Med. Rev. 2017;33:88–100. doi: 10.1016/j.smrv.2016.06.004.
    1. Benjamens S., Dhunnoo P., Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: An online database. NPJ Digit. Med. 2020;3:118.
    1. Mincholé A., Rodriguez B. Artificial intelligence for the electrocardiogram. Nat. Med. 2019;25:22–23. doi: 10.1038/s41591-018-0306-1.
    1. Castelletti S., Dagradi F., Goulene K., Danza A.I., Baldi E., Stramba-Badiale M., Schwartz P.J. A wearable remote monitoring system for the identification of subjects with a prolonged QT interval or at risk for drug-induced long QT syndrome. Int. J. Cardiol. 2018;266:89–94. doi: 10.1016/j.ijcard.2018.03.097.
    1. Torres-Soto J., Ashley E.A. Multi-task deep learning for cardiac rhythm detection in wearable devices. NPJ Digit. Med. 2020;3:116. doi: 10.1038/s41746-020-00320-4.
    1. Lyell D., Coiera E., Chen J., Shah P., Magrabi F. How machine learning is embedded to support clinician decision making: An analysis of FDA-approved medical devices. BMJ Health Care Inform. 2021;28:e100301. doi: 10.1136/bmjhci-2020-100301.
    1. Terzano M.G., Parrino L., Sherieri A., Chervin R., Chokroverty S., Guilleminault C., Hirshkowitz M., Mahowald M., Moldofsky H., Rosa A., et al. Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleep. Sleep Med. 2001;2:537–553. doi: 10.1016/S1389-9457(01)00149-6.
    1. Berry R.B., Brooks R., Gamaldo C.E., Harding S.M., Marcus C., Vaughn B.V. The AASM manual for the scoring of sleep and associated events. Rules, terminology and technical specifications, Darien, Illinois. Am. Acad. Sleep Med. 2012;176:2012.
    1. Chung J., Gulcehre C., Cho K., Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. [(accessed on 25 November 2015)];arXiv. 2014 Available online: .1412.3555
    1. Ioffe S., Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Int. Conf. Mach. Learn. PMLR. 2015;37:448–456.
    1. Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014;15:1929–1958.
    1. Nair V., Hinton G.E. Rectified linear units improve restricted boltzmann machines; Proceedings of the 27th International Conference on Machine Learning; Haifa, Israel. 21–24 June 2010; pp. 807–814.
    1. Chollet F. Keras. 2015. [(accessed on 7 June 2016)]. Available online:
    1. TensorFlow. [(accessed on 7 April 2021)]. Available online:

Source: PubMed

スポンサーと協力者

医学的状態

薬物療法

3
購読する