Expert System of Ischemia Classification Based on Wavelet MLP

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 214)

Abstract

This paper proposes an expert system capable of identifying pathological ECG with signs of ischemia. The system design is based on the knowledge of a team of cardiologists who have been commissioned to identify ECG segments that contain information about the target disease, and subsequently validated the results of the system. The expert system comprises four modules, namely, a pre-processing module which is responsible for improving the SNR, a segmentation module, a DSP module which is responsible for applying the wavelet transform to improve the response of the last module, in charge of the classification. We used a database of about 800 ECG obtained in different clinical and extensively annotated by the team of cardiologists. The system achieves a sensitivity of 87.7 % and a specificity of 82.6 % with the set of ECG testing.

Keywords

Classification Expert system ECG ischemia MLP DWT 

Notes

Acknowledgments

This investigation is allocated in the project TSI-020302-2010-136.

References

  1. 1.
    Klabunde RE (2011) Cardiovascular physiology concepts. Lippincott Williams & Wilkins, Philadelphia. ISBN 9781451113846Google Scholar
  2. 2.
    Bayès de Luna, Antoni. Bases de la electrocardiografía. De las variantes de la normalidad a los patrones diagnósticos (III): Isquemia, lesión y necrosis. Barcelona: Prous Science, 2007. B-1749-07Google Scholar
  3. 3.
    Taouli SA, Bereksi-Reguig F (2010) Noise and baseline wandering suppression of ECG signals by morphological filter. J Med Eng Technol 34:87–96Google Scholar
  4. 4.
    Christov I et al (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 32:465–479Google Scholar
  6. 6.
    Wiggins M et al (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 Signal Process Control 5:214–222Google Scholar
  8. 8.
    Morise AP et al (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 28:372–378Google Scholar
  10. 10.
    Sekkal M, Chick MA, Settouti N (2011) Evolving neural networks using a genetic algorithm for heartbeat classification. J Med Eng Technol 35:215–223Google 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 et al (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 34:551–560Google Scholar
  14. 14.
    Khorrami H, Moavenian M (2010) A comparative study of DWT, CWT, and DCT transformations in ECG arrhythmias classification. Expert Syst Appl 37:5151–5157Google Scholar
  15. 15.
    Ranjith P, Baby PC, Joseph P (2003) ECG analysis using wavelet transform: application to myocardial ischemia detection. ITBM RBM, 24:44–47Google 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 2007:286–295Google Scholar
  17. 17.
    Gaetano A et al (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 for ECG arrhythmias using neural network with adaptative activation function. Digit Signal Process 20:1040–1049Google Scholar
  19. 19.
    Korurek M, Dogan B (2010) ECG beat classification using swarm optimization and radial basis function neural network. Expert Syst Appl 37:7563–7569Google Scholar
  20. 20.
    Daubechies I (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics, Philadelphia. ISBN 0-89871-274-2Google Scholar
  21. 21.
    Vetterli M, Cormac H (1992) Wavelets and filter banks: theory and design. IEEE Trans Signal Process 40:2207–2232Google Scholar
  22. 22.
    Li C, Zheng C, Tai C (1995) Detection of ECG characteristic points using wavelet transform. IEEE Trans Biomed Eng 42:21–28Google Scholar
  23. 23.
    Baldi P et al (2000) Assessing the accuracy of prediction algorithms for classification: an overview. Bioinform Rev 16:412–424Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Rafaela Regional FacultyArgentinian Technological UniversityRafaelaArgentina
  2. 2.Department of Languages and Computer SciencesMalaga UniversityMalagaSpain

Personalised recommendations