Certificate of Registration Media number Эл #ФС77-53688 of 17 April 2013. ISSN 2308-6033. DOI 10.18698/2308-6033
  • Русский
  • Английский

Algorithm for detecting QRS-complex on the electrocardiogram in real-time mode

Published: 23.05.2019

Authors: Obukhov S.A., Stepanov V.P.

Published in issue: #5(89)/2019

DOI: 10.18698/2308-6033-2019-5-1877

Category: Mechanics | Chapter: Biomechanics and Bioengineering

Most methods of morphological analysis of the electrocardiogram (ECG) are based on the search for R-wave. Knowing the position of the R-wave, it is rather simple to determine the remaining components of the QRS complex. The main problems of machine detection of the R-wave are ECG trace artifacts and high variability of cardiac complexes. The algorithm for detecting the QRS-complex consisting of two stages is proposed and implemented. At the preliminary stage, time-frequency transformations as in the Pan-Tompkins detector are used to remove noise and non-informative ECG components. The algorithm has adaptive parameters to account for the variability of R-wave. The arithmetic mean and the standard deviation of the height of the preceding R-wave and the lengths of the RR intervals are used as these parameters. At the main stage of the algorithm, adaptive parameters are used to predict the characteristics of the next R-wave. A function evaluating the difference between the current metrics of the conditional R-wave with a vertex at the given point and the expected ones is proposed. The minimum of the given function on a given interval is a criterion for the detection of the R-wave. The software implementation of the algorithm showed high sensitivity and specificity on MIT-BIH test databases. The algorithm can be used in cardiomonitors, automatic defibrillators, artificial pacemakers with feedback and other devices with real-time ECG processing

[1] Bakhilin V.M. Informatsionno-upravlyayuhchie sistemy — Information and Control Systems, 2010, vol. 5, pp. 78–84.
[2] Tong Z.Z., Filist S.A., Shatalova O.V. Nauchnye vedomosti Belgorodskogo gosudarstvennogo universiteta. Ser. Ekonomika. Informatika — Belgorod State University Scientific Bulletin. Series: Economics. Computer science, 2011, vol. 7, pp. 132–139.
[3] Ladyaev D.A. Sistemy upravleniya i informatsionnye tekhnologii (Control systems and information technologies), 2007, vol. 2, pp. 162–166.
[4] Istomin B.A. Izvestiya Yuzhnogo federalnogo universiteta. Tekhnicheskie nauki — Izvestiya of Southern Federal University. Engineering Sciences, 2010, vol. 8, pp. 86–91.
[5] Krivonogov L.Yu. Izvestiya Yuzhnogo federalnogo universiteta. Tekhnicheskie nauki — Izvestiya of Southern Federal University. Engineering Sciences, 2014, vol. 10, pp. 104–114.
[6] Roslyakova A.V., Chuprakov P.G. Vyatskiy meditsinskiy vestnik (Vyatka Medical Bulletin), 2012, vol. 2, pp. 29–35.
[7] Singh O. A Robust R-peak Detection Algorithm using Wavelet Packets. International Journal of Computer Applications, 2011, vol. 36 (5), pp. 37–43.
[8] Ling H., Lin Q.H., Chen J.D. Application of the Empirical Mode decomposition to the analysis of Esophageal Reflux Disease. IEEE transactions on Biomedical Engineering, 2005, vol. 52 (10), pp. 32–39.
[9] Yu S.N., Chou K.T. Integration of independent component analysis and neural networks for ECG beat classification. Expert systems with applications, 2008, vol. 34 (4), pp. 2841–2846.
[10] Kuzilek J., Lhotska L., Hanuliak M. An automatic method for holter ECG denoising using ICA. Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies. Barcelona, Spain, October 26–29, 2011. New York, USA, ACM, 2011, vol. 3, pp. 1–5.
[11] Pan J., Tompkins W.J. A real time QRS detection algorithm. IEEE transactions on Biomedical Engineering, 1985, vol. 32, pp. 230–236.
[12] Leonova A.V., Ageychenko A.A. Inzhenernyy vestnik Dona — Engineering journal of Don, 2015, vol. 36 (2), pp. 106–120.
[13] Khokhlov I.O., Kalinichenko A.N. Izvestiya SPbGETU “LETI”, 2017, vol. 1, pp. 72–77.
[14] Goldberger A.L., Amaral L.A.N. Glass L. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation Electronic Pages, 2017, vol. 101 (23), pp. 215–220.