A new method of cardiac sympathetic index estimation using a 1D-convolutional neural network

• Autorzy: Kołodziej Marcin , Majkowski Andrzej , Tarnowski Paweł , Rak Remigiusz Jan , Rysz Andrzej

Identyfikatory

DOI

10.24425/bpasts.2021.136921

• Języki publikacji: EN

Abstrakty

EN

Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

Słowa kluczowe

EN

epilepsy; seizure detection; seizure prediction; convolutional neural network; deep learning; ECG; HRV; cardiac sympathetic index

PL

padaczka; wykrywanie napadu; przewidywanie napadu; splotowa sieć neuronowa; głęboka nauka; technika deep learning; EKG; HRV; wskaźnik współczulny serca

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2021
• Tom: Vol. 69, nr 3
• Strony: art. no. e136921
• Opis fizyczny: Bibliogr. 41 poz., rys., tab.

Twórcy

autor

Kołodziej Marcin

• Warsaw University of Technology, Institute of Theory of Electrical Engineering, Measurements and Information Systems, ul. Koszykowa 75, 00-662 Warsaw, Poland

• https://orcid.org/0000-0003-2856-7298

autor

Majkowski Andrzej

• Warsaw University of Technology, Institute of Theory of Electrical Engineering, Measurements and Information Systems, ul. Koszykowa 75, 00-662 Warsaw, Poland

• https://orcid.org/0000-0002-6557-836X

autor

Tarnowski Paweł

• Warsaw University of Technology, Institute of Theory of Electrical Engineering, Measurements and Information Systems, ul. Koszykowa 75, 00-662 Warsaw, Poland

• https://orcid.org/0000-0003-0392-4084

autor

Rak Remigiusz Jan

• Warsaw University of Technology, Institute of Theory of Electrical Engineering, Measurements and Information Systems, ul. Koszykowa 75, 00-662 Warsaw, Poland

• https://orcid.org/0000-0003-0674-453X

autor

Rysz Andrzej

• Medical University of Warsaw, Department of Neurosurgery, ul. Banacha 1, 02-097 Warsaw, Poland

• https://orcid.org/0000-0002-8272-7275

Bibliografia

• [1] World Health Organization (WHO), “Epilepsy”, 2019. Accessed: Jul. 10, 2020. [Online]. Available: https://www.who.int/newsroom/fact-sheets/detail/epilepsy
• [2] B. Sommer et al., “Resection of cerebral gangliogliomas causing drug-resistant epilepsy: short- and long-term outcomes using intraoperative MRI and neuronavigation”, Neurosurg. Focus 38(1), E5 (2015), doi: 10.3171/2014.10.FOCUS14616.
• [3] T. Harnod, C.C.H. Yang, Y.-L. Hsin, P.-J. Wang, K.-R. Shieh, and T.B.J. Kuo, “Heart rate variability in patients with frontal lobe epilepsy”, Seizure 18(1), 21–25 (2009), doi: 10.1016/j.seizure.2008.05.013.
• [4] K. Jansen and L. Lagae, “Cardiac changes in epilepsy”, Seizure 19(8),455–460 (2010), doi: 10.1016/j.seizure.2010.07.008.
• [5] R. Brotherstone and A. McLellan, “Parasympathetic alteration during sub-clinical seizures”, Seizure 21(5), 391–398 (2012), doi: 10.1016/j.seizure.2012.03.011.
• [6] A. Van de Vel et al., “Non-EEG seizure detection systems and potential SUDEP prevention: State of the art: Review and update”, Seizure 41,141–153 (2016), doi: 10.1016/j.seizure.2016.07.012.
• [7] U.R. Acharya, Y. Hagiwara, and H. Adeli, “Automated seizure prediction”, Epilepsy Behav. 88, 251–261 (2018), doi: 10.1016/j.yebeh.2018.09.030.
• [8] G. Giannakakis, V. Sakkalis, M. Pediaditis, and M. Tsiknakis, “Methods for Seizure Detection and Prediction: An Overview”, in Modern Electroencephalographic Assessment Techniques: Theory and Applications, pp. 131–157, V. Sakkalis, Ed. New York, NY: Springer, 2015.
• [9] E. Bou Assi, D.K. Nguyen, S. Rihana, and M. Sawan, “Towards accurate prediction of epileptic seizures: A review”, Biomed. Signal Process. Control 34, 144–157 (2017), doi: 10.1016/j.bspc.2017.02.001.
• [10] G. Giannakakis, M. Tsiknakis, and P. Vorgia, “Focal epileptic seizures anticipation based on patterns of heart rate variability parameters”, Computer Methods and Programs in Biomedicine 178, 123–133 (2019), doi: 10.1016/j.cmpb.2019.05.032.
• [11] M. Kotas, “Projective filtering of time-aligned beats for foetal ECG extraction”, Bull. Pol. Acad. Sci. Tech. Sci. 55(4), 331‒339 2007.
• [12] K. Lewenstein, M. Jamroży, and T. Leyko, “The use of recurrence plots and beat recordings in chronic heart failure detection”, Bull. Pol. Acad. Sci. Tech. Sci. 64(2), 339–345 (2016).
• [13] J. Jarczewski, A. Furgała, A. Winiarska, M. Kaczmarczyk, and A. Poniatowski, “Cardiovascular response to different types of acute stress stimulations”, Folia Medica Cracoviensia 59(4), 95–110 (2019).
• [14] J. Jeppesen, S. Beniczky, P. Johansen, P. Sidenius, and A. Fuglsang-Frederiksen, “Comparing maximum autonomic activity of psychogenic non-epileptic seizures and epileptic seizures using heart rate variability”, Seizure 37, 13–19 (2016), doi: 10.1016/j.seizure.2016.02.005.
• [15] J. Jeppesen, S. Beniczky, P. Johansen, P. Sidenius, and A. Fuglsang-Frederiksen, “Detection of epileptic seizures with a modified heart rate variability algorithm based on Lorenz plot”, Seizure 24, 1–7 (2015), doi: 10.1016/j.seizure.2014.11.004.
• [16] J. Jeppesen, S. Beniczky, P. Johansen, P. Sidenius, and A. Fuglsang- Frederiksen, “Using Lorenz plot and Cardiac Sympathetic Index of heart rate variability for detecting seizures for patients with epilepsy”, in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014, pp. 4563–4566, doi: 10.1109/EMBC.2014.6944639.
• [17] F. Fürbass, S. Kampusch, E. Kaniusas, J. Koren, S. Pirker, R. Hopfengärtner, H. Stefan, T. Kluge, C. Baumgartner, “Automatic multimodal detection for long-term seizure documentation in epilepsy”, Clinical Neurophysiology 128(8), 1466–1472 (2017), doi: 10.1016/j.clinph.2017.05.013.
• [18] M. Toichi, T. Sugiura, T. Murai, and A. Sengoku, “A new method of assessing cardiac autonomic function and its comparison with spectral analysis and coefficient of variation of R-R interval”, J. Auton. Nerv. Syst. 62(1–2), 79–84 (1997), doi: 10.1016/s0165-1838(96)00112-9.
• [19] J. Pan and W.J. Tompkins, “A Real-Time QRS Detection Algorithm”, IEEE Transactions on Biomedical Engineering BME-32(3), 230–236 (1985), doi: 10.1109/TBME.1985.325532.
• [20] S. Rezaei, S. Moharreri, S. Ghiasi, and S. Parvaneh, “Diagnosis of sleep apnea by evaluating points distribution in poincare plot of RR intervals”, in 2017 Computing in Cardiology (CinC), 2017, pp. 1–4, doi: 10.22489/CinC.2017.158-398.
• [21] S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, and D. J. Inman, “1D Convolutional Neural Networks and Applications: A Survey”, arXiv:1905.03554 [cs, eess], May 2019, Accessed: Jul. 10, 2020. [Online]. Available: http://arxiv.org/abs/1905.03554.
• [22] T. Poggio and Q. Liao, “Theory I: Deep networks and the curse of dimensionality”, Bull. Pol. Acad. Sci. Tech. Sci. 66(6), 761–773 (2018).
• [23] J. Kurek, B. Świderski, S. Osowski, M. Kruk, and W. Barhoumi, “Deep learning versus classical neural approach to mammogram recognition”, Bull. Pol. Acad. Sci. Tech. Sci. Vol. 66(6), 831‒840 2018, doi: 10.24425/bpas.2018.125930.
• [24] Y. Zhang and Z. Wang, “Research on intelligent algorithm for detecting ECG R waves”, in 2015 IEEE 5th International Conference on Electronics Information and Emergency Communication, 2015, pp. 47–50, doi: 10.1109/ICEIEC.2015.7284484.
• [25] M. Kołodziej, A. Majkowski, P. Tarnowski, R.J. Rak, and A. Rysz, “Implementation of 1DConvolutional Neural Network for Cardiac Sympathetic Index Estimation”, presented at the 2020 IEEE 21st International Conference on Computational Problems of Electrical Engineering (CPEE), 2020.
• [26] K.M. Gaikwad and M.S. Chavan, “Removal of high frequency noise from ECG signal using digital IIR butterworth filter”, in 2014 IEEE Global Conference on Wireless Computing Networking (GCWCN), 2014, pp. 121–124, doi: 10.1109/GCWCN.2014.7030861.
• [27] M. Kołodziej, A. Majkowski, and R.J. Rak, “A new method of feature extraction from EEG signal for brain-computer interface design”, Prz. Elektrotechniczny 9, 35–38 (2010).
• [28] K. Hayase, K. Hayashi, and T. Sawa, “Hierarchical Poincaré analysis for anaesthesia monitoring”, J. Clin. Monit. Comput. 34, 1321–1330 (2020), doi: 10.1007/s10877-019-00447-0.
• [29] J. Niehoff, M. Matzkies, F. Nguemo, J. Hescheler, and M. Reppel, “The Effect of Antiarrhythmic Drugs on the Beat Rate Variability of Human Embryonic and Human Induced Pluripotent Stem Cell Derived Cardiomyocytes”, Sci. Rep. 9(1), 14106 (2019), doi: 10.1038/s41598-019-50557-7.
• [30] M.M. Platiša, T. Bojić, S. Mazić, and A. Kalauzi, “Generalized Poincaré plots analysis of heart period dynamics in different physiological conditions: Trained vs. untrained men”, PLoS ONE 14(7), e0219281 (2019), doi: 10.1371/journal.pone.0219281.
• [31] P. Fontana, N.R.A. Martins, M. Camenzind, M. Boesch, F. Baty, O.D. Schoch, M.H. Brutsche, R.M. Rossi, and S. Annaheim, “Applicability of a Textile ECG-Belt for Unattended Sleep Apnoea Monitoring in a Home Setting”, Sensors (Basel) 19(15), 3367 (2019), doi: 10.3390/s19153367.
• [32] T. Schmidt, S. Wulff, K.-M. Braumann, and R. Reer, “Determination of the Maximal Lactate Steady State by HRV in Overweight and Obese Subjects”, Sports Med. Int. Open 3(2), E58–E64 (2019), doi: 10.1055/a-0883-5473.
• [33] J. Piskorski and P. Guzik, “Geometry of the Poincaré plot of RR intervals and its asymmetry in healthy adults”, Physiol. Meas. 28(3), 287–300 (2007), doi: 10.1088/0967-3334/28/3/005.
• [34] Ö. Yıldırım, P. Pławiak, R.-S. Tan, and U. R. Acharya, “Arrhythmia detection using deep convolutional neural network with long duration ECG signals”, Computers in Biology and Medicine 102, 411–420, (2018), doi: 10.1016/j.compbiomed.2018.09.009.
• [35] B. Zhao, H. Lu, S. Chen, J. Liu, and D. Wu, “Convolutional neural networks for time series classification”, Journal of Systems Engineering and Electronics 28(1), 162–169 (2017), doi: 10.21629/JSEE.2017.01.18.
• [36] V. Lebedev and V. Lempitsky, “Speeding-up convolutional neural networks: A survey”, Bull. Pol. Acad. Sci. Tech. Sci. 66(6), 799‒810 (2018), doi: 10.24425/BPAS.2018.125927.
• [37] M. Grochowski, A. Kwasigroch, and A. Mikołajczyk, “Selected technical issues of deep neural networks for image classification purposes”, Bull. Pol. Acad. Sci. Tech. Sci. 67(2), 363–376 (2019).
• [38] X. Glorot, A. Bordes, and Y. Bengio, “Deep Sparse Rectifier Neural Networks”, in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011, 315–323, [Online]. Available: http://proceedings.mlr.press/v15/glorot11a.html.
• [39] A. Krizhevsky, I. Sutskever, and G.E. Hinton, “ImageNet classification with deep convolutional neural networks”, Commun. ACM 60(6), 84–90 (2017), doi: 10.1145/3065386.
• [40] Y. Gal and Z. Ghahramani, “A Theoretically Grounded Application of Dropout in Recurrent Neural Networks”, in Advances in Neural Information Processing Systems 29, pp.1019–1027, Eds. D.D. Lee, M. Sugiyama, U.V. Luxburg, I. Guyon, and R. Garnett, Curran Associates, Inc., 2016.
• [41] S. Albawi, T.A. Mohammed, and S. Al-Zawi, “Understanding of a convolutional neural network”, in 2017 International Conference on Engineering and Technology (ICET), 2017, pp. 1–6, doi: 10.1109/ICEngTechnol.2017.8308186.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).