Abstract
The aim of this work was to develop a method by which intra-cardiac electrograms could be classified. A new algorithm for training this particular network has been established and applied to the task of finding the onset times of intra-cardiac electrograms. The algorithm is based on adding a choice function to the combination function of each neuron. The choice function enables the network to consider delays in each of its synapses. The gradient of error is then calculated with respect to the weights and delays. A synaptic delay-based artificial neural network was implemented using MATLAB and used to detect the onset times of the atrial, His and ventricular electrograms from the His catheter recordings. Results from a subset of a clinical, 12-channel electrophysiology study demonstrated the ability of the network to successfully identify peak potentials and onset times. Errors in detection of onset times were in the range of 1–2 ms. This method, which does not utilise traditional windowing and/or thresholding operations, can be effectively used to detect temporal patterns in a range of electrophysiological and biological signals.
Similar content being viewed by others
References
Attikiouzel, Y. and deSilva, C.,Applications of neural networks in medicine, Aust Physical & Engineering Sciences in Medicine. 18: 158–164, 1995.
Barro, S., Fernandez-Delgando, M., Vils-Sobrino, J., Regueiro, C. and Sanchez, E.,Classifying multichannel ECG patterns with and adaptive neural network, IEEE Engineering in Medicine and Biology. 17(1): 45–55, 1998.
Carpenter, G.A. and Grossberg, S.,Pattern recognition by self-organizing neural networks, MIT Press, Cambridge, MA, 1991.
Day, S. and Davenport, M.,Continuous-time temporal backpropagation with adaptable time delays, IEEE Transactions on Neural Networks. 4(2): 348–354, 1993.
Dayhoff, J.E.,Neural network architectures: An introduction, Van Nostrand Reinhold, New York, 1990.
Dayhoff, J.E. and Omidvar, O.,Neural networks and pattern recognition, Academic Press Limited, San Diego, 1998.
de Chazal, P. and Celler, B.,Improving ECG diagnostic classification by combining multiple neural networks, Computers in Cardiology. 24: 473–476, 1997.
Demuth, H. and Beale, M.,Neural network toolbox user’s guide, Math Works Inc., Natick, 1998.
Dorffner, G. and Porenta, G.On using feedforward neural networks for clinical diagnostic tasks, Artificial Intelligence in Medicine, 6(5): 417–435, 1994.
Durbin, R. and Rumelhart, D.,Product units: A computationally powerful and biologically plausible extension to backpropagation networks, Neural Computing. 1: 133–142, 1989.
Duro, R. and Santos, J.,Design of ANN architectures for handling the temporal dimensions in signal processing, Eurocast-Computer Aided Systems Theory Proceedings, 485–497. 1997a.
Duro, R. and Santos, J.,Synaptic delay based artificial neural networks and discrete time backpropagation applied to QRS complex detection, IEEE International Conference on Neural Networks. 4: 2566–2570, 1997b.
Duro, R. and Santos, J.,Fast discrete time backpropagation for adaptive synaptic delay based neural networks, IEEE Transactions on Neural Networks. 10(4): 779–789, 1999.
Elman, J.,Finding structure in time, Cognitive Science. 14: 179–211, 1990.
Fu, K. S.,Syntactic pattern recognition, Handbook of Pattern Recognition and Image Processing. 85-117, 1986.
Gelenbe, E.,Neural networks: Advances and applications, Elsevier Science Publishers, Amsterdam, 1991.
Gray, M., Thomas, C., Jandallah, M., Yates, S., Quint, S. and Nagle, H.,A comparison of the noise sensitivity of nine QRS detection algorithms. IEEE Transactions on Biomedical Engineering. 37: 85–98, 1990.
Guyton, C.,Human physiology and mechanisms of disease. W.B. Saunders Company, Philadelphia. 1992.
Kung, S.Y.,Digital neural networks. Prentice-Hall Inc, Englewood Cliffs, 1993.
Khoor, S., Nieberl, J. and Fugedi, K.,CardioScope ECG system for arrhythmia analysis using fuzzy neural network. http://www.bion.hu/bion/article/a5/Plym96.html.
Krusche, J. and Movellan, J.,Benefits of gain: Speeded learning and minimal hidden layers in back-propagation networks. IEEE Transactions on Systems, Man and Cybernetics. 21(1): 273–280, 1991.
Lau, C.Neural networks: Theoretical foundations and analysis. IEEE Press, Piscataway, NJ, 1992.
Lisboa, P.G.J.Neural networks: Current applications. Chapman & Hall, London, 1992.
Lippman, R.An Introduction to Computing with Neural Networks. IEEE Acoustics, Speech, and Signal Processing. April: 1–23, 1987.
Masulli, F., Morasso, P.G. and Schenone, A.,Neural networks in biomedicine. World Scientific Publishing Co Pty Ltd, Singapore, 1994.
Mendel, J.M.,A prelude to neural networks: Adaptive and learning systems. Prentice Hall, Englewood Cliffs, 1994.
Minami, K., Nakajima, H. and Toyoshima, T.,Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network. IEEE Transactions on Biomedical Engineering. 46: 179–185, 1999.
Mahalingam, N. and Kumar, D.Neural networks for signal processing applications: ECG classification. Aust Physical & Eng Sciences in Medicine. 20: 147–151, 1997.
Macfarlane, P., Devine, B., Latif, S., McLaughlin, S., Shoat, D. and Watts, M.,Methodology of ECG interpretation in the Glasgow Program. Methods Inf. Med. 29: 354–361, 1990.
Miller III, W., Glanz, F. and Kraft III, L.,CMAC: An associative neural network alternative to backpropagation. Proceedings of the IEEE, 78(10): 1561–1567, 1990.
Reddy, B., Christenson, G., Rowlandson, G. and Hammill, S.,High resolution ECG. Med. Electron. 23: 60–73, 1992.
Rozanski, J., Mortara, D., Myerburg, M. and Castellanos, A.,Body surface detection of delayed depolarisations in patients with recurrent ventricular tachycardia and left ventricular aneurysm. Circ. 63: 1172–1178, 1981.
Silipo, R., Gori, M. and Marchesi, C.,Autoassociator structured neural network for rhythm classification of long term electrocardiogram. IEEE Computer Society, Computers in Cardiology. 349–352, 1993.
Spersuti, A. and Starita, A.,Speed up learning and network optimisation with extended back propagation. IEEE Transactions on Systems, Man and Cybernetics, 21: 1–28, 1992.
Strand, E., and Jones, W.,A neural network for tracking the prevailing heart rate of the electrocardiogram. Third Annual IEEE Symposium on Computer-Based Medical Systems. Session 16, 358–365, 1990.
Simmons, R.,Basic electrophysiology. 13th Symposium for the EP Allied Health Professional. 1999.
Taur, J., and Kung, S.,Prediction-based networks with ECG application. IEEE International Conference on Neural Networks. 3: 1920–1925, 1993.
Thomson, D., Soraghan, J. and Durrani, T.,An automatic neural-network based SVT/VT classification system. IEEE. 333–336,1993. Computers in Cardiology; London, September 1993.
Van De Graaff, K.,Human anatomy, 4th ed., Wm. C. Brown Publishers, Melbourne, 1995.
Vaz, F. and Principe, J.,Neural networks for EEG signal decomposition and classification. IEEE EMBC and CMBEC. 793–794, 1995.
Vijaya, G., Kumar, V. and Verma, H.,ANN-based QRS-complex analysis of ECG. J. of Medical Engineering and Technology. 22: 160–167, 1998.
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K. and Lang, K.,Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing. 34(3): 328–339, 1989.
Werbos, P.Backpropagation through time: What it does and how it works. Proceedings IEEE, 78(10): 1550–1560, 1990.
Widrow, B. and Lehr, M.,30 years of adaptive neural networks: Perceptron, Madaline, and Backpropagation. Proceedings IEEE, 78(9): 1415–1442, 1990.
William, G., Skora, B. and Skora, J.,Prospective validation of artificial neural network trained to identify acute myocardial infarction. The Lancet. 347: 12–16, 1996.
Xue, Q., Shankara Reddy, B.,Late potential recognition by artificial neural networks. IEEE Transactions on Biomedical Engineering. 44: 132–143, 1997.
Xue, Q., Hu, Y. and Tompkins, W.,Neural network based adaptive matched filtering for QRS detection. IEEE Transactions on Biomedical Engineering. 39: 317–329, 1992.
Yang, T., Devine, B., Macfarlane, P.,Artificial neural networks for the diagnosis of atrial fibrillation. Medical and Biological Computing. 32: 615–619, 1994.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chetham, S.M., Barker, T.M. & Stafford, W. Neural networks in cardiac electrophysiological signal classification. Australas. Phys. Eng. Sci. Med. 25, 124–131 (2002). https://doi.org/10.1007/BF03178773
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF03178773