Bivariate Markov Model Based Analysis of ECG for Accurate Identification and Classification of Premature Heartbeats and Irregular Beat-Patterns

  • Purva R. GawdeEmail author
  • Arvind K. Bansal
  • Jeffrey A. Nielson
  • Javed I. Khan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 869)


This paper describes a novel intelligent analysis technique based upon bivariate Markov model that integrates morphological and temporal features with a rule-based interval analysis of ECG signals to localize and accurately classify the premature beats to four major classes: (1) Premature Atrial Complex (PAC), (2) Blocked PAC (B-PAC), (3) Premature Ventricular Complex (PVC), and (4) Premature Junctional Complex (PJC). The paper also describes a beat-pattern classification algorithm to sub classify premature beat-patterns into bigeminy, trigeminy and quadrigeminy. The approach utilizes two phases: (1) a training phase that builds bivariate Markov model from standardized databases of ECG signals, and (2) a dynamic phase that detects embedded P and R waves in T-waves of premature beats using a combination of area subtraction and clinically significant rule-based analysis of R-R intervals. It detects and classifies premature beats using graph matching based upon the forward-backward algorithm and performs a look ahead pattern analysis for the sub-classification of beat-patterns. The algorithms have been presented. The software has been implemented that uses a combination of MATLAB and C++ libraries. Performance results show that processing time is realistic for real-time detection with 98%–99% sensitivity for the premature beat classification and 95%-98% sensitivity for the beat pattern identification.


ECG analysis Intelligent system Irregular beat pattern Machine learning Markov model Medical diagnosis Premature beat classification Real-time system Signal analysis 


  1. 1.
    Zipes, D.P., Camm, A.J., Borggrefe, M., Buxton, A.E., Chaitan, B., Fromer, M., et al.: ACC/AHA/ESC 2006 guidelines for management of patients with ventricular arrhythmias and the prevention of sudden cardiac death. J. Am. Coll. Cardiol. 48(5), e247–e346 (2006)CrossRefGoogle Scholar
  2. 2.
    Rautaharju, P.M., Surawicz, B., Gettes, L.S.: AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram: part IV. J. Am. Coll. Cardiol. 53(11), 982–991 (2009)CrossRefGoogle Scholar
  3. 3.
    Thong, T., McNames, J., Aboy, M., Goldstein, B.: Prediction of paroxysmal atrial fibrillation by analysis of atrial premature complexes. IEEE Trans. Biomed. Eng. 51(4), 561–569 (2004)CrossRefGoogle Scholar
  4. 4.
    Lerma, C., Glass, L.: Predicting the risk of sudden cardiac death. J. Physiol. 594(9), 2445–2458 (2016)CrossRefGoogle Scholar
  5. 5.
    Chong, B.H., Pong, V., Lam, K.F., Liu, S., Zuo, M.L., Lau, Y.F., et al.: Frequent premature atrial complexes predict new occurrence of atrial fibrillation and adverse cardiovascular events. Europace 13(7), 942–947 (2011)CrossRefGoogle Scholar
  6. 6.
    Tsipouras, M.G., Fotiadis, D.I., Sideris, D.: An arrhythmia classification system based on the RR-interval signal. Artif. Intell. Med. 33(3), 237–250 (2005)CrossRefGoogle Scholar
  7. 7.
    Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdroff, J.M., Ivanov, P.C.H., Mark, R.G., et al.: Physiobank, physiotoolkit and physionet components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220Google Scholar
  8. 8.
    Palaniappan, R., Krishnan, S.: Detection of ectopic heartbeats using ECG and blood pressure. In: International Conference on Signal Processing & Communications (SPCOM 2004), pp. 573–576. Bangalore, India (2004)Google Scholar
  9. 9.
    Sayadi, O., Mohammad, B., Shamsollahi, M.B., Clifford, G.D.: Robust detection of premature ventricular contractions using a wave-based Bayesian framework. IEEE Trans. Biomed. Eng. 57(2), 353–362 (2010)CrossRefGoogle Scholar
  10. 10.
    Lim, J.S.: Finding features for real-time premature ventricular contraction detection using a fuzzy neural network system. IEEE Trans. Neural Networks 20(3), 522–527 (2009)CrossRefGoogle Scholar
  11. 11.
    Jankowski, S., Dusza, J.J., Wierzbowski, M. Oręziak, A.: SVM detection of premature ectopic excitations based on modified PCA. In: International Symposium of Biological and Medical Data Analysis, Lecture Notes in Computer Science, vol. 3745, pp. 173–183. Aveiro, Portugal, Nov 2005CrossRefGoogle Scholar
  12. 12.
    Smilde, T.D.J., van Veldhuisen, D.J., van den Berg, M.P.: Prognostic value of heart rate variability and ventricular arrhythmias during 13-year follow-up in patients with mild to moderate heart failure. Clin. Res. Cardiol. 98(4), 233–239 (2009)CrossRefGoogle Scholar
  13. 13.
    Garcia, T.B., Miller, G.T.: Arrhythmia Recognition: The Art of Interpretation. Jones and Bartlett (2013)Google Scholar
  14. 14.
    Kerin, N., Mori, I., Levy, M.N.: Ventricular quadrigeminy as a manifestation of concealed bigeminy. Circulation 52(6), 1023–1029 (1975)CrossRefGoogle Scholar
  15. 15.
    Chiang, L.H., Kotanchek, M.E., Kordon, A.K.: Fault diagnosis based on Fisher discriminant analysis and support vector machines. Comput. Chem. Eng. 28(8), 1389–1401 (2004)CrossRefGoogle Scholar
  16. 16.
    Gawde, P.R., Bansal, A.K., Nielson, J.A.: ECG analysis for automated diagnosis of subclasses of supraventricular arrhythmia. In: Arabnia, H.R., Deligiannidid, L. (eds.) International Conference on Health Informatics and Medical Systems, pp. 10–16. Las Vegas, Nevada, USA, July 2015Google Scholar
  17. 17.
    Elgendi M., Jonkman, M., De Boer, F.: Premature atrial complexes detection using the Fisher linear discriminant. In: 7th IEEE International Conference on Cognitive Informatics (ICCI 2008), pp. 83–88. Stanford University, CA, USA, Aug 2008Google Scholar
  18. 18.
    Ching, W., Ng, M.K., Fung, E.S.: Higher-order multivariate Markov chains and their applications. Linear Algebra Appl. 428(2–3), 492–507 (2008)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Tallarida, R.J., Murray, R.B.: Area under a curve: trapezoidal and Simpson’s rules. In: Manual of Pharmacologic Calculations, pp. 77–81. Springer, New York, NY (1987)CrossRefGoogle Scholar
  20. 20.
    Mahmoodabadi, S.Z., Ahmadian, A., Abolhasani, M.D.: ECG feature extraction using Daubechies wavelets. In: Proceedings of the Fifth IASTED International Conference on Visualization, Imaging and Image Processing, pp. 343–348. Benidorm, Spain (2005)Google Scholar
  21. 21.
    Gawde, P.R., Bansal, A.K., Nielson, J.A.: Integrating Markov model and morphology analysis for finer classification of ventricular arrhythmia in real-time. In: IEEE International Conference on Biomedical & Health Informatics, pp. 409–412. Orlando, FL, USA (2017)Google Scholar
  22. 22.
    Russell, S., Norwig, P.: Artificial Intelligence—A Modern Approach, 3rd edn. Prentice Hall (2010)Google Scholar
  23. 23.
    Silva, I., Moody, G.: An open-source toolbox for analysing and processing PhysioNet databases in MATLAB and Octave. J. Open Res. Softw. 2(1), e27 (2014)Google Scholar
  24. 24.
    Everitt, B., Skrondal, A.: The Cambridge Dictionary of Statistics, vol. 106. Cambridge University Press, Cambridge, UK (2002)zbMATHGoogle Scholar
  25. 25.
    Lin, C., Du, Y., Chen, Y., Chen, T.: Multiple ECG beats recognition in the frequency domain using grey relational analysis. In: Proceedings of the 28th IEEE EMBS Annual International Conference, pp. 2154–2158. New York City, USA. Sept 2006Google Scholar
  26. 26.
    Ideka, N., Takayanagi, K., Takeuchi, A., Takayanagi, A., Miyahara, H.: Two types of distribution patterns of bigeminy and trigeminy in long-term ECG: a model-based interpretation. In: Computers in Cardiology, vol. 35, pp. 1049–1052. Bologna, Italy, Sept 2008Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Purva R. Gawde
    • 1
    Email author
  • Arvind K. Bansal
    • 1
  • Jeffrey A. Nielson
    • 2
  • Javed I. Khan
    • 1
  1. 1.Department of Computer ScienceKent State UniversityKentUSA
  2. 2.Department of EmergencyNortheast Ohio Medical UniversityRootstownUSA

Personalised recommendations