Skip to main content
SpringerLink
Log in

Hierarchical state space partitioning with a network self-organising map for the recognition of ST-T segment changes

  • Published:
Medical and Biological Engineering and Computing Aims and scope Submit manuscript

Abstract

The problem of maximising the performance of ST-T segment automatic recognition for ischaemia detection is a difficult pattern classification problem. The paper proposes the network self-organising map (NetSOM) model as an enhancement to the Kohonen self-organised map (SOM) model. This model is capable of effectively decomposing complex large-scale pattern classification problems into a number of partitions, each of which is more manageable with a local classification device. The NetSOM attempts to generalise the regularisation and ordering potential of the basic SOM from the space of vectors to the space of approximating functions. It becomes a device for the ordering of local experts (i.e. independent neural networks) over its lattice of neurons and for their selection and co-ordination. Each local expert is an independent neural network that is trained and activated under the control of the NetSOM. This method is evaluated with examples from the European ST-T database. The first results obtained after the application of NetSOM to ST-T segment change recognition show a significant improvement in the performance compared with that obtained with monolithic approaches, i.e. with single network types. The basic SOM model has attained an average ischaemic beat sensitivity of 73.6% and an average ischaemic beat predictivity of 68.3%. The work reports and discusses the improvements that have been obtained from the implementation of a NetSOM classification system with both multilayer perceptrons and radial basis function (RBF) networks as local experts for the ST-T segment change problem. Specifically, the NetSOM with multilayer perceptrons (radial basis functions) as local experts has improved the results over the basic SOM to an average ischaemic beat sensitivity of 75.9% (77.7%) and an average ischaemic beat predictivity of 72.5% (74.1%).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Bazett, H. C. (1920): ‘An analysis of the time relation of electrocardiograms’Heart,7, p. 353.

    Google Scholar 

  • Bertsekas, D. P. (1995). ‘Dynamic programming and optimal control, vol. I and II’ (Athenas Scientific, Belmont, MA)

    Google Scholar 

  • Bezerianos, A., Papadimitriou, S. andAlexopoulos, D. (1999): ‘Radial basis function neural networks for the characterization of heart rate variability dynamics’,Artif. Intell. Med.,15, pp. 215–234

    Google Scholar 

  • Birnbaum, Y., Sclarovsky, S., Blum, A., Mager, A. andGabbay, U. (1993): ‘Prognostic significance of the initial electrocardiographic pattern in a first acute anterior wall myocardial infarction’,Chest,103, pp. 1681–1687

    Google Scholar 

  • Bishop, C. M. (1996): ‘Neural networks for pattern recognition’ (Clarendon Press, Oxford)

    Google Scholar 

  • Donoho, D. L. andJohnstone, I. M. (1994): ‘Ideal spatial adaptation by wavelet shrinkage’,Biometrika,81, pp. 425–455

    MathSciNet  Google Scholar 

  • Garcia, J., Lander, P., Sornmo, L., Olmos, S., Wagner, G. andLaguna, P. (1998): ‘Comparative study of local and Karhunen-Loeve based ST-T indexes in recordings from human subjects with induced myocardial ischemia’,Comput. Biomed. Res.,31, pp. 271–297.

    Google Scholar 

  • Garcia, J. andLaguna, P. (1999): ‘Automatic ischemia episodes detection on ECG recordings’. Fifth Conf. Eur. Soc. Eng. & Med., pp. 387–388

  • Haykin, S. (1999): ‘Neural networks’. (Prentice Hall International Inc.), 2nd edn

  • Jager, F. Mark, R. G. andMoody G. B. (1991): ‘Analysis of transient ST segment changes during ambulatory monitoring’, in ‘Computers in cardiology’ (IEEE Computer Society Press), pp. 453–456

  • Jager, F., Moody, G. B. andMark, R. G. (1998): ‘Detection of transient ST segment episodes during ambulatory ECG monitoring’,Comput. Biomed. Res.,31 (5), pp. 305–322

    Article  Google Scholar 

  • Kohonen, T. (1990): ‘The self-organizing map’,Proc. IEEE,78, pp. 1464–1480

    Article  Google Scholar 

  • Kohonen, T. (1997): ‘Self-organized maps’ (Springer-Verlag)

  • Konta, T., Ikeda, K., Yamaki, M., Nakamura, K., Honma, K., Kobota, I. andYasui, S. (1990): ‘Significance of discordant ST afternans in ventricular fibrillation’Circulation,82 (2), p. 2185

    Google Scholar 

  • Laguna, P., Moody, G. B., Garcia, J., Goldberger, A. andMark, R. (1999): ‘Analysis of the ST-T complex of the electrocardiogram using the Karhunen-Loeve transform: adaptive monitoring and alternans detection’,Med. Biol. Eng. Comput.,37, pp. 175–189.

    Google Scholar 

  • Lee, T.-W. (1998): ‘Independent component analysis, theory and applications’ (Kluwer-Academic Publishers)

  • Maglaveras, N., Stamkopoulos, T., Pappas, C. andStrintzis, M. G. (1998): ‘An adaptive backpropagation neural network for realtime ischaemia episodes detection: development and performance analysis using the European ST-T database’,IEEE Trans.,BME-45

  • Mallat, S. (1991): ‘Zero-crossings of a wavelet transform’,IEEE Trans. Inform. Theory,37, pp. 1019–1033

    Article  MathSciNet  Google Scholar 

  • Mallat, S. andZhong, S. (1992): ‘Characterization of signals from multiscale edges’,IEEE Trans. Pattern Anal. Mach. Intell.,14, pp. 710–732

    Article  Google Scholar 

  • Mallat, S. andHwang, W. L. (1992): ‘Singularity detection and processing with wavelets’,IEEE Trans. Inform. Theory,38, pp. 617–643

    Article  MathSciNet  Google Scholar 

  • Meyer, C. R. andKeiser, H. N. (1977): ‘Electrocardiogram baseline noise estimation and removal using cubic splines and state-space computation techniques’,Comput. Biomed. Res.,10, p. 459

    Article  Google Scholar 

  • Myerburg, R. J., Kessler, M. andCastellanos, A. (1993): Sudden cardiac death: epidemiology, transient risk, and intervention assessment’,Ann. Intern Med.,119, pp. 1187–1197

    Google Scholar 

  • Papadimitriou, S., Gatzounas, D., Papadopoulos, V., Tzigounis, V. andBezerianos, A. (1996). Fetal heart rate signal denoising by processing the wavelet transform modulus maxima’, 18th Annual Int. Conf. IEEE Eng. Med. Biol. Soc., 31 October–3 November, Amsterdam, The Netherlands (CD-ROM)

  • Papadimitriou, S. andBezerianos, A. (1996): ‘Denoising computer performance evaluation measurements with the wavelet transform’,J. Sys. Archit.,42, pp. 55–65

    Google Scholar 

  • Papadimitriou, S., Gatzounas, D., Papadopoulos, V., Tzigounis, V. andBezerianos, A. (1997). ‘Denoising of the fetal heart rate signal with non-linear filtering of the wavelet transform maxima’,Int. J. Med. Inform.,44, pp. 177–192

    Google Scholar 

  • Poggio, T. andGirosi, F. (1990): ‘Regularization algorithms for learning that are equivalent to multilayer perceptrons’,Science,247, pp. 978–982

    MathSciNet  Google Scholar 

  • Poggio, T. andGirosi, F. (1990): ‘Networks for approximation and learning’,Proc. IEEE,78, pp. 1481–1497

    Article  Google Scholar 

  • Ritter, H., Martinetz, T. andSchulten, K. (1992): ‘Neural computation and self-organizing maps’ (Addison-Wesley)

  • Rosensaum, D. S., Jackson, L. E., Smith, J. M., Garan, H., Rusnin, J. N. andCohen, R. J. (1994): ‘Electrical alternans and vulnerability to ventricular arrhythmias’,New Engl. J. Med.,19, pp. 203–212

    Google Scholar 

  • Rosenbaum, D. S., Albrecht, P. andCohen, R. J. (1996): ‘Predicting sudden cardiac death from T wave alternans of the surface electrocardiogram: promise and pitfalls’,J. Cardiovascular Electrophysiology,7, pp. 1095–1111

    Google Scholar 

  • Silipo, R., Laguna, P., Marchesi, C. andMark, R. G. (1995): ‘ST-T segment change recognition using artificial neural networks and principal component analysis’,Comput. Cardiol., pp. 213–216

  • Silipo, R. andMarchesi, C. (1998): ‘Artificial neural networks for automatic ECG analysis’,IEEE Trans. Signal Process.,46, pp. 1417–1425

    Article  Google Scholar 

  • Stamkopoulos, T., Diamantaras, K., Maglaveras, N. andStrintzis, M. G. (1998): ‘ECG analysis using nonlinear PCA neural networks for ischemia detection’,IEEE Trans. Signal Process.,46, pp. 3058–3067

    Article  Google Scholar 

  • Taddei, A., Buiagini, A. et al. (1991): ‘The European ST-T database, distribution and use’ in ‘Computers in cardiology’, (IEEE) pp. 177–180

  • Taddei, A., Distante, G., Emdin, M., Pisani, P., Moody, G. B., Zeelenberg, C. andMarchesi, C. (1992): “The European ST-T database: standard for evaluation systems for the analysis of ST-T changes in ambulatory electrocardiography’,Eur. Heart J.,13, pp. 1164–1172

    Google Scholar 

  • Taddei, A., Constantino, G., Silipo, R., Emdin, M. andMarchesi, C. (1995): ‘A system for the detection of ischemic episodes in ambulatory ECG’ in ‘Computers in cardiology’ (IEEE Computer Society Press), pp. 705–708

  • Vapnik, V. N. (1998): ‘Statistical learning theory’ (Wiley, New York)

    Google Scholar 

  • Verrier, R. L. et al. (1995): ‘T wave alternans as a harbinger of ischemia-induced sudden cardiac death’ inJipes, D. andJaliffe, J. (Ed): Cardiac electrophysiology-from cell to bedside (W. B. Saunders Company, Philadelphia), 2nd edn

    Google Scholar 

  • Verrier, R. L., Nearing, B. D., MacCallum, G. andStone, P. H. (1996): “T-wave alternans during ambulatory ischemia in patients with stable coronary disease’,Ann. Noninvasive Electrocardiol.,1, pp. 113–120

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Medical Physics, School of Medicine, University of Patras, Patras, Greece

    A. Bezerianos, L. Vladutu & S. Papadimitriou

  2. Department of Computer Engineering & Informatics, University of Patras, Patras, Greece

    S. Papadimitriou

Authors
  1. A. Bezerianos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. L. Vladutu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Papadimitriou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. Bezerianos.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bezerianos, A., Vladutu, L. & Papadimitriou, S. Hierarchical state space partitioning with a network self-organising map for the recognition of ST-T segment changes. Med. Biol. Eng. Comput. 38, 406–415 (2000). https://doi.org/10.1007/BF02345010

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02345010

Keywords

Search

Navigation