Medical & Biological Engineering & Computing

, Volume 37, Issue 5, pp 560–565 | Cite as

Classification of premature ventricular complexes using filter bank features, induction of decision trees and a fuzzy rule-based system

Article

Abstract

The classification of heart beats is important for automated arrhythmia monitoring devices. The study describes two different classifiers for the identification of premature ventricular complexes (PVCs) in surface ECGs. A decision-tree algorithm based on inductive learning from a training set and a fuzzy rule-based classifier are explained in detail. Traditional features for the classification task are extracted by analysing the heart rate and morphology of the heart beats from a single lead. In addition, a novel set of features based on the use of a filter bank is presented. Filter banks allow for time-frequency-dependent signal processing with low computational effort. The performance of the classifiers is evaluated on the MIT-BIH database following the AAMI recommendations. The decision-tree algorithm has a gross sensitivity of 85.3% and a positive predictivity of 85.2%, whereas the gross sensitivity of the fuzzy rule-bassed system is 81.3%, and the positive predictivity is 80.6%.

Keywords

Beat classification ECG analysis Fuzzy logic Filter bank Time-frequency analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Association for the Advancement of Medical Instrumentation (1998): ‘Testing and reporting performance results of ventricular arrhythmia detection algorithms’. AAMI, 3330 Washington Blvd., Suite 400, Arlington, VA 22201, USAGoogle Scholar
  2. Afonso, V. X., Tompkins, W. J., Nguyen, T. Q., Michler, K., andLuo, S. (1966): ‘Comparing stress ECG enhancement algorithms: with an introduction to a filter bank based approach’,IEEE Eng. Med. Biol. Mag.,15, pp. 37–44CrossRefGoogle Scholar
  3. Afonso, V. X., Wieben, O., Tompkins, W. J., Nguyen, T. Q., andLuo, S. (1997): ‘Filter bank-based ECG beat classification’, Proc. Ann. Int. Conf. IEEE Eng. Med. Biol. Soc.,19, pp. 97–100.Google Scholar
  4. Afonso, V. X., Tompkins, W. J., Nguyen, T. Q., andLuo, S. (1999): ‘ECG beast detection using filter banks’,IEEE Trans.,BME-46, pp. 192–202.Google Scholar
  5. Bezdek, J. C. (1981): ‘Pattern recognition with fuzzy objective function algorithms’ (Plenum Press, New York)MATHGoogle Scholar
  6. Chow, H. S., Moody, G. B., andMark, R. G. (1992): ‘Detection of ventricular ectopic beats using neural networks’, Comput. in Cardiol. Conf. 1992, IEEE Computer Society Press, pp. 659–662Google Scholar
  7. Clayton, R. H., Murray, A., andCampbell, R. W. F. (1995): ‘Objective features, of the surface electrocardiogram during ventricular tachyarrhythmias’,Eur. Heart J.,16, pp. 115–1119Google Scholar
  8. Dassen, W. R., Karthaus, V. L., Talmon, J. L., Mulleneers, R. G., Smeets, J. L., andWellens, H. J. (1995): ‘Evaluation of new self learning techniques for the generation of criteria for differentiation of wide-QRS tachycardia in supraventricular tachycardia and ventricular tachycardia’,Clin. Cardiol.,18, pp. 103–108CrossRefGoogle Scholar
  9. Gulley, N., andJang, J. S. (1995): ‘Fuzzy logic toolbox for use with MATLAB’ (MathWorks Inc, Natick, MA)Google Scholar
  10. Ham, F. M., andHan, S. (1996): ‘Classification of cardiac arrhythmias using fuzzy ARTMAP’,IEEE Trans.,BME-43, pp. 425–430Google Scholar
  11. Hamdan, M., andScheinman, M. (1995): ‘Current approaches in patients with ventricular tachyarrhythmias’,Med. Clin. North Am.,79, pp. 1097–1120Google Scholar
  12. Hu, Y. H., Tompkins, W. J., Urrusti, J. L., andAfonso, V. X. (1994): ‘Applications of artificial neural networks for ECG signal detection and classification’,J. Electrocardiol.,26, (suppl.), pp. 66–73Google Scholar
  13. Jenkins, J. M., andCaswell, S. A. (1996): ‘Detection algorithms in implantable cardioverter defibrillators’,Proc. IEEE,84, pp. 428–445CrossRefGoogle Scholar
  14. Kohavi, R., Sommerfield, D., andDougherty, J. (1996): ‘Data mining using MLC++: a machine learning library in C++’. Proc. Tools in Artificial Intelligence, IEEE Computer Society Press pp. 234–245Google Scholar
  15. Malvar, H. S. (1992): ‘Signal processing with lapped transfroms’ (Artech House, Norwood, MA)Google Scholar
  16. Mendel, J. M. (1995): ‘Fuzzy logic systems for engineering: a tutorial’,Proc. IEEE,83, pp. 345–377CrossRefGoogle Scholar
  17. Moody, G. B., andMark, R. G. (1982): ‘Development and evaluation of a 2-lead ECG analysis program’, Comput. in Cardiol. Conf., IEEE Computer Society Press, pp. 39–44Google Scholar
  18. Quinlan, J. R. (1986): ‘Induction of decision trees’,Mach. Learn.,1, pp. 81–106Google Scholar
  19. Rappaport, S. H., Gillick, L., Moody, G. B., andMark, R. G. (1982): ‘QRS morphology classification: quantitative evaluation of different strategies’. Comput. in Cardiol. Conf., IEEE Computer Society Press, pp. 33–38Google Scholar
  20. Ripley, K. L., Bump, T. E., andArzbaeche, R. C. (1989): ‘Evaluation of techniques for recognition of ventricular arrhythmias by implanted devices’,IEEE Trans.,BME-36, pp. 618–624Google Scholar
  21. Silipo, R., Taddei, A., Varanini, M., andMarchesi, C. (1995): ‘Classification of arrhythmic events in ambulatory electrocardiogram, using artificial neural networks,’Comput. Biomed. Res.,28, pp. 305–318CrossRefGoogle Scholar
  22. Soman, A. K., Vaidyanathan, P. P., andNguyen, T. Q. (1993): ‘Linear phase paraunitary filter banks: theory, factorizations and designs’,IEEE Trans. Signal Process.,41, pp. 3480–3495MATHCrossRefGoogle Scholar
  23. Thakor, N. V., Webster, J. G., andTompkins, W. J. (1984): ‘Estimation of QRS complex power spectra for design of a QRS filter’,IEEE Trans.,BME-31, pp. 702–706Google Scholar
  24. Wang, J. Y. J. (1983): ‘Application of pattern recognition techniques to QRS complex classification—a review’, Comput. in Cardiol. IEEE Computer Society Press pp. 77–82Google Scholar
  25. Wieben, O., Afonso, V. X., andTompkins, W. J. (1997): ‘Classification of PVCs with a fuzzy logic system’, Proc. Ann. Int. Conf. IEEE Eng. Med. Biol. Soc., Nov. 1997,19, pp. 65–67.Google Scholar
  26. Zadeh, L. (1965): ‘Fuzzy sets’,Inf. Control,8, pp. 338–352MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© IFMBE 1999

Authors and Affiliations

  1. 1.Department of Electrical & Computer EngineeringUniversity of WisconsinMadisonUSA
  2. 2.Endocardial Solutions, Inc.Saint PaulUSA

Personalised recommendations