Advertisement

Classifying coronary dysfunction using neural networks through cardiovascular auscultation

  • R. Folland
  • E. L. Hines
  • P. Boilot
  • D. Morgan
Article

Abstract

The paper applies artificial neural networks (ANNs) to the analysis of heart sound abnormalities through auscultation. Audio auscultation samples of 16 different coronary abnormalities were collected. Data pre-processing included down-sampling of the auscultated data and use of the fast Fourier transform (FFT) and the Levinson-Durbin autoregression algorithms for feature extraction and efficient data encoding. These data were used in the training of a multi-layer perceptron (MLP) and radial basis function (RBF) neural network to develop a classification mechanism capable of distinguishing between different heart sound abnormalities. The MLP and RBF networks attained classification accuracies of 84% and 88%, respectively. The application of ANNs to the analysis of respiratory auscultation and consequently the development of a combined cardio-respiratory analysis system using auscultated data could lead to faster and more efficient treatment.

Keywords

Cardiac auscultation Multi-layer perceptron Radial basis function network Cardiac dysfunction Levinson-Durbin autoregression 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Cathers, I. (1995): ‘Neural network assisted cardiac auscultation’,Artif. Intell. Med.,7, pp. 53–66Google Scholar
  2. Chen, S., Cowen, C., andGrant, P. (1991): ‘Orthogonal least squares learning algorithm for radial basis function networks’,IEEE Trans. Neural Netw.,2, pp. 302–309CrossRefGoogle Scholar
  3. Christini, D., Kulkarni, A., Rao, S., Stutman, E., Bennett, F., Hausdorff, J., Oriol, N., andLutchen, K. (1995): ‘Influence of autoregressive model parameter uncertainty on spectral estimates of heart rate dynamics’,Ann. Biomed. Eng.,23, pp. 127–134Google Scholar
  4. Demuth, H., andBeale, M. (1998): ‘Neural network toolbox for use with MATLAB’, (The Math Works Inc., Natick, 1998)Google Scholar
  5. Jervase, J., andAl-Alawi, S. (1998): ‘Statistical signal characterization-artificial neural network based hybrid systems for electrocardiogram interpretation’. International Symposium on Communication Systems and Digital Signal Processing,2, p. 515Google Scholar
  6. Khoór, S., Nieberl, J., Szabóki, F., Kail, E., Fügedi, K., andKékes, E. (1994): ‘Two expert systems in cardiology: automated ECG signal and echocardiographic image processing by artificial intelligence technics’. Proceedings of International Conference on Neural Networks and Expert Systems in Medicine and Healthcare, pp. 319–326Google Scholar
  7. Lin, C., andLee, C. (1996): ‘Neural fuzzy systems: a neuro-fuzzy synergism to intelligent systems’ (Prentice-Hall, New Jersey, 1996)Google Scholar
  8. Lippmann, R. (1987): ‘An introduction to computing with neural nets’,IEEE ASSP Mag.,4, pp. 4–22Google Scholar
  9. Luo, F., andUnbeahauen, P. (1997): ‘Applied neural networks for signal processing’ (Cambridge University Press, Cambridge, 1997)Google Scholar
  10. Rakotomamonjy, A., Migeon, B., and Marche, P. (1998): ‘Automated neural network detection of wavelet pre-processed electrocardiogram late potentials’,Med. Biol. Eng. Comput.,36, pp. 346–350Google Scholar
  11. Strum, R., andKirk, D. (1996): ‘Contemporary linear systems using MATLAB 4.0’, (PWS, Boston, 1996)Google Scholar
  12. Tarrasenko, L. (1998): ‘A guide to neural computing applications’ (Arnold, London, 1998)Google Scholar
  13. Widrow, B., andLehr, M. (1990): ‘30 years of adaptive neural networks: perceptron, madaline and backpropagation’,Proc. IEEE,78, pp. 1415–1442CrossRefGoogle Scholar

Copyright information

© IFMBE 2002

Authors and Affiliations

  • R. Folland
    • 1
  • E. L. Hines
    • 1
  • P. Boilot
    • 1
  • D. Morgan
    • 2
  1. 1.Electrical and Electronic Engineering Division, School of EngineeringUniversity of WarwickCoventryUK
  2. 2.Birmingham Heartlands HospitalBirminghamUK

Personalised recommendations