Advertisement

Bundle Branch Blocks Classification Via ECG Using MLP Neural Networks

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 213)

Abstract

This paper proposes a two-stage system based on neural network models to classify bundle branch blocks via electrocardiogram (ECG) analysis. Two artificial neural network (ANN) models have been developed in order to  discriminate bundle branch blocks and hemiblocks from normal ECG and other heart diseases. This method includes pre-processing and classification modules. ECG segmentation and wavelet transform were used as pre-processing stage to improve classical multilayer perceptron (MLP) network. A new set of about 800 ECG were collected from different clinics in order to create a new ECG database to train ANN models. For bundle branch blocks classifier in the test phases, the best specificity of all models was found to be 94.56 % and the best sensitivity was found to be 92.45 %. In the case of hemiblocks classifier, the best results were a sensitivity of 93.26 % and a specificity of 92.55 %.

Keywords

Classification ECG Bundle branch blocks Hemiblocks MLP DWT 

Notes

Acknowledgments

This work is supported by the Ministry of Industry, Tourism, and Trade of Spain (Project TSI-020302-2010-136).

References

  1. 1.
    Bayès de Luna, Antoni. Bases de la (2006) electrocardiografía. Semiología electrocardiográfica II: Patrones diagnósticos de crecimiento, bloqueos y preexcitación. Barcelona : Prous Science, B-15239-06Google Scholar
  2. 2.
    Klabunde RE (2011) Cardiovascular physiology concepts. Lippincott Williams & Wilkins, Philadelphia. ISBN 9781451113846Google Scholar
  3. 3.
    Taouli SA, Bereksi-Reguig F (2010) Noise and baseline wandering suppression of ECG signals by morphological filter. J Med Eng Technol 34:87–96CrossRefGoogle Scholar
  4. 4.
    Christov I, y otros (2006) Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification. Med Eng Phys 28:876–887Google Scholar
  5. 5.
    Sun Y, Chan KL, Krishnan SM (2002) ECG signal conditioning by morphological filtering. Comput Biol Med 32:465–479CrossRefGoogle Scholar
  6. 6.
    Wiggins M, y otros (2008) Evolving a Bayesian classifier for ECG-based age classification in medical applications. Appl Soft Comput 8:599–608Google Scholar
  7. 7.
    Sharma LN, Dandapat S, Mahanta A (2010) ECG signal denoising using higher order statistics in wavelet subbands. Biomed Sig Process Control 5:214–222CrossRefGoogle Scholar
  8. 8.
    Morise AP, y otros (1992) Comparison of logistic regression and Bayesian-based algorithms to estimate posttest probability in patients with suspected coronary artery disease undergoing exercise ECG. J Electrocardiol 25:89–99Google Scholar
  9. 9.
    Gholam H, Luo D, Reynolds KJ (2006) The comparison of different feed forward neural network architectures for ECG signals diagnosis. Med Eng Phys 28:372–378CrossRefGoogle Scholar
  10. 10.
    Sekkal M, Chick MA, Settouti N (2011) Evolving neural networks using a genetic algorithm for heartbeat classification. J Med Eng Technol 35:215–223CrossRefGoogle Scholar
  11. 11.
    Moavenian M, Khorrami H (2010) A qualitative comparison of ANN and SVM in ECG arrhythmias classification. Expert Syst Appl 37:3088–3093Google Scholar
  12. 12.
    Ahmed SM, y otros (2009) ECG signal compression using combined modified discrete cosine and discrete wavelet transforms. J Med Eng Technol 33:1–8Google Scholar
  13. 13.
    Mitra S, Mitra M, Chaudhuri BB (2004) Generation of digital time database from paper ECG records and Fourier transform-based analysis for disease identification. Comput Biol Med 34:551–560CrossRefGoogle Scholar
  14. 14.
    Khorrami H, Moavenian M (2010) A comparative study of DWT, CWT, and DCT transformations in ECG arrhythmias classification. Expert Syst Appl 37:5151–5157CrossRefGoogle Scholar
  15. 15.
    Ranjith P, Baby PC, Joseph P (2003) ECG analysis using wavelet transform: application to myocardial ischemia detection. ITBM RBM 24:44–47CrossRefGoogle Scholar
  16. 16.
    Ceylan R, Ozbay Y (2007) Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network. Expert Syst Appl 2007:286–295CrossRefGoogle Scholar
  17. 17.
    Gaetano A, y otros (2009) A patient adaptable ECG beat classifier based on neural networks. Appl Math Comput 213:243–249Google Scholar
  18. 18.
    Ozbay Y, Tezel G (2010) A new method for classification of ECG arrhythmias using neural network with adaptative activation function. Digit Sig Process 20:1040–1049CrossRefGoogle Scholar
  19. 19.
    Korurek M, Dogan B (2010) ECG beat classification using swarm optimization and radial basis function neural network. Expert Syst Appl 37:7563–7569CrossRefGoogle Scholar
  20. 20.
    Lin CC (2008) Enhancement of accuracy and reproducibility of parametric modeling for estimating abnormal intra-QRS potentials in signal-averaged electrocardiograms. Med Eng Phys 30:834–842CrossRefGoogle Scholar
  21. 21.
    Daubechies I (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics, Philadelphia. ISBN 0-89871-274-2CrossRefMATHGoogle Scholar
  22. 22.
    Vetterli M, Cormac H (1992) Wavelets and filter banks: theory and design. IEEE Trans Sig Process 4:2207–2232CrossRefGoogle Scholar
  23. 23.
    Mak JNF, Hu Y, Luk KDK (2010) An automated ECG-artifact removal method for trunk muscle surface EMG recordings. Med Eng Phys 32:840–848CrossRefGoogle Scholar
  24. 24.
    Li C, Zheng C, Tai C (1995) Detection of ECG characteristic points using wavelet transform. IEEE Trans Biomed Eng 42:21–28CrossRefGoogle Scholar
  25. 25.
    Møller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533CrossRefGoogle Scholar
  26. 26.
    Baldi P, y otros (2000) Assessing the accuracy of prediction algorithms for classification: an overview. Bioinf Rev 16:412–424Google Scholar
  27. 27.
    Ennett CM, Frize M, Charette E (2004) Improvement and automation of artificial neural networks to estimate medical outcomes. Med Eng Phy 26:321–328CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Javier F. Fornari
    • 1
  • José I. Peláez Sánchez
    • 2
  1. 1.Argentinian Technological UniversitySanta FeArgentina
  2. 2.Department of Languages and Computer SciencesMalaga UniversityMalagaSpain

Personalised recommendations