ECG arrhythmia classification based on logistic model tree


This paper presents a diagnostic system for classification of cardiac arrhythmia from ECG data, using Logistic Model Tree (LMT) classifier. Clinically useful information in the ECG is found in the intervals and amplitudes of the characteristic waves. Any abnormality in the wave shape and duration of the wave features of the ECG is considered as arrhythmia. The ampli-tude and duration of the characteristic waves of the ECG can be more accurately obtained using Discrete Wavelet Transform (DWT) analysis. Further, the non-linear behavior of the cardiac system is well characterized by Heart Rate Variability (HRV). Hence, DWT and HRV techniques have been employed to extract a set of linear (time and frequency domain) and non-linear characteristic features from the ECG signals. These features are used as input to the LMT classifier to classify 11 different arrhyth-mias. The results obtained indicate an impressive prediction accuracy of 98%, validating the choice and combined use of the current popular techniques (DWT and HRV) for cardiac arrhythmia classification. The system can be de-ployed for practical use after validation by experts.

Share and Cite:

Mahesh, V. , Kandaswamy, A. , Vimal, C. and Sathish, B. (2009) ECG arrhythmia classification based on logistic model tree. Journal of Biomedical Science and Engineering, 2, 405-411. doi: 10.4236/jbise.2009.26058.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] S. Palreddy, Y. H. Hu, V. Mani, and W. J. T ompkins (1997) A multipleclassifier architecture for ECG beat classification, IEEE Workshop on Neural Network for Signal Processing, 172–181.
[2] B. Mohammadzadeh-Asl and S. K. Setarehdan, (2006) Neural network based arrhythmia classification using heart rate vari-ability signal, Proceedings of the EUSI- PCO.
[3] J. Lee, K. L. Park, M. H. Song, and K. J. Lee, (2005) Arrhyth-mia classification with reduced features by linear discriminant analysis, IEEE EMBS 2005, 27th Annual International Con-ference, Engineering in Medicine and Biology Society, 1142–1144.
[4] P. Chazal, M. O’Dwyer, and R. B. Reilly, (2004) Automatic classification of heartbeats using ECG morphology and heart-beat interval features, IEEE Trans. Biomedical Engineering, 51(7), 1196–1206.
[5] G. Dingfei, N. Srinivasan, and S. Krishnan, (2002) Cardiac arrhythmia classification using autoregressive modeling, Bio-Medical Engineering OnLine, 1–5.
[6] T. H. Linh, S. Osowki, and M. Stodolski, (2003) On-line heart beat recognition using hermite polynomials and neuro-fuzzy network, IEEE Trans. Instrumentation and Measurement, 52(4), 1224–1231.
[7] N. Kannathal, S. K. Puthusserypady, C. M. Lim, U. R. Acharya, and S. Laxminarayan, (2005) Cardiac state diagnosis using adaptive neuro-fuzzy technique, Proceedings of the IEEE En-gineering in Medicine and Biology 27th Annual Conference Shanghai, China.
[8] M. H. Kadbi, J. Hashemi, H. R. Mohseni and A. Maghsoudi, (2006) Classification of ECG arrhythmias based on statistical and time-frequency features, 3rd International Conference on Advances in Medical, Signal and Information Processing, MEDSIP.
[9] D. Dancey, Z. A. Bandar, and D. McLean, (2007) Logistic model tree extraction from artificial neural networks, IEEE Trans on Systems, Man and Cybernetics, 37(4), 794–802.
[11] S. Z. Mahmoodabadi, A. Ahmadian, M. D. Abolhasani, M. Eslami, and J. H. Bidgoli, (2005) ECG feature extraction based on multiresolution wavelet transform, in Proc. IEEE Engineer-ing in Medicine and Biology, 3902–3905.
[12] E. M. Tamil, N. H. Kamarudin, R. Salleh, M. Yamani Idna Idris, M. N. Noorzaily, and A. M. Tamil, (2008) Heartbeat electrocardiogram (ECG) signal feature extraction using dis-crete wavelet transforms (DWT), in Proceedings of CSPA, 1112–1117.
[13] D. N. Dutt and S. M. Krishnan, (2000) Computer processing of heart rate variability signals for detection of patient status in cardiac care units, Current Science, 78(7), 864–868.
[14] Task force of the European society of cardiology and the North American society of pacing and electrophysiology (1996), Heart rate variability–standards of measurements, physiologi-cal interpretation, and clinical use, European Heart Journal, 17, 354–381.
[15] S. I. Niwas, R. S. S. Kumari, and V. Sadasivam, (2005) Artifi-cial neural network based automatic cardiac abnormalities classification, Proceeding of the Sixth International Conference on Computational Intelligence and Multimedia Application.
[16] U. R. Acharya, A. Kumar, P. S. Bhat, C. M. Lim, S. S. Iyengar, N. Kannathal, and S. Krishnan, (2004) Classification of cardiac abnormalities using heart rate signals, medical, Biological Engineering and Computing, 42, 288–293.
[17] H. Kun, C. I. Plamen, C. Zhi, C. Pedro, and H. E. Stanley, (2001) Effect of trends on detrended fluctuation analysis, Physical Review E, 64, 011114.
[18] R. U. Acharya, C. M. Lim, and P. Joseph, (2002) Heart rate variability analysis using correlation dimension and detrended fluctuation analysis, ITBM–RBM, 23(6), 333– 339.
[19] N. Landwehr, M. Hall, and E. Frank, (2005) Logistic model trees, Machine Learning, 59(1/2), 161–205.
[20] D. W. Hosmer and S. Lemeshow, (2000) Applied logistic re-gression, 2nd Edition, Wiley-Interscience, New York.
[21] J. Friedman, T. Hastie, and R. Tibshirani, (2000) Additive lo-gistic regression: A statistical view of boosting, Annals of Staistics, 32(2), 337–374.
[22] Z. H. Zhou, Y. Jiang, and S. F. Chen, (2003) Extracting sym-bolic rules from trained neural network ensembles, Artificial Intelligence Communication, 16(1), 2–15.

Copyright © 2024 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.