ANN Based Classification of Arrhythmias

  • M. Jabri
  • S. Pickard
  • P. Leong
  • Z. Chi
  • E. Tinker
  • R. Coggins
  • B. Flower
Chapter

Abstract

Implantable cardioverter-defibrillators (ICDs) represent an important therapy for people susceptible to sudden cardiac death. These devices monitor the heart for abnormal rhythms, and can deliver either pacing or shock therapy to terminate the episode. ICDs sense the electrical activity of the heart through leads attached to the internal surface. Present devices use a single ventricular lead inserted in the right ventricular apex (RVA). Future devices will use an additional atrial lead placed in the high right atrium (HRA). These leads measure electrical potential and recordings made from such leads are called intracardiac electrograms (ICEGs).

Keywords

Ventricular Tachycardia Ventricular Fibrillation Sinus Tachycardia Normal Sinus Rhythm Probability Density Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Z. Chi and M. Jabri (1991), ”Identification of Supraventricular and Ventricular Arrhythmias Using a Combination of Three Neural Networks”. Proceedings of the Computers in Cardiology Conference, Venice, Italy, September 1991Google Scholar
  2. [2]
    Z. Chi and M. Jabri (1991), ”A Comparison of MLP and ID3-derived Approaches for ECG Classification”, Proceedings of the Second Australian Conference on Neural Networks, Sydney, Australia.Google Scholar
  3. [3]
    M. Jabri and B. Flower (1991), ”Weight Perturbations: An optimal architecture and learning technique for analogue VLSI feed-forward and recurrent multi-layer networks”, Neural Computation, Vol. 3, No. 4, MIT Press.Google Scholar
  4. [4]
    M. Jabri, S. Pickard, P. Leong, Z. Chi, B. Flower and Y. Xie, ”ANN based classification for heart defibrillators”, NIPS 4, pp 637-644, Morgan Kaufmann publishers, 1992.Google Scholar
  5. [5]
    S. Lee (1990), ”Using a translation-invariant neural network to diagnose heart arrhythmia”, NIPS 2, pp. 240-247, Morgan Kaufmann Publishers, 1990.Google Scholar
  6. [6]
    P.H.W. Leong and M. Jabri (1993), ”A VLSI Arrhythmia Classifier”, Proceedings of the Fourth Australian Conference on Neural Networks, pp. 41-44, Melbourne, Australia.Google Scholar
  7. [7]
    P.H.W. Leong and M. Jabri (1992a), ”MATIC — An Intracardiac Tachycardia Classification System”, Pacing and Clinical Electrophysiology (PACE), Sept. 1992, USA.Google Scholar
  8. [8]
    S. Pickard, M. Jabri, P.H.W. Leong, B.G. Flower and P. Henderson (1992), ”Low Power Analogue VLSI Implementation of A Feed-Forward Neural Network”, Proceedings of the Third Australian Conference on Neural Net-works, pp. 88-91, Canberra, Australia.Google Scholar
  9. [9]
    J.R. Quinlan (1986), ”Induction of decision trees”, Machine Learning, 1(1):81–106.Google Scholar

Copyright information

© Springer Science+Business Media New York 1995

Authors and Affiliations

  • M. Jabri
    • 1
  • S. Pickard
    • 1
  • P. Leong
    • 1
  • Z. Chi
    • 1
  • E. Tinker
    • 1
  • R. Coggins
    • 1
  • B. Flower
    • 1
  1. 1.Systems Engineering and Design Automation LaboratorySydney University Electrical EngineeringAustralia

Personalised recommendations