Advertisement

The Use of Fuzzy ARTMAP to Identify Low Risk Coronary Care Patients

  • J. Downs
  • R. F. Harrison
  • R. L. Kennedy
  • K. Woods

Abstract

The performance of fuzzy ARTMAP and modified fuzzy ARTMAP is compared using real-world data from a medical domain, the task being to predict the death or survival of patients admitted to a coronary care ward. Modified fuzzy ARTMAP is shown to perform consistently more accurately than fuzzy ARTMAP and is also much less prone to variations in performance with different orderings of training data. However, modified fuzzy ARTMAP does not show as large an improvement in performance as fuzzy ARTMAP when employed in the voting strategy. When unanimous voting decisions alone are considered, fuzzy ARTMAP is able to increase significantly accuracy in identifying survivors at the cost of decreased coverage of cases. This allows the identification of a subset of patients who have a low-risk of death from their condition and are thus potentially suitable for early discharge from hospital.

Keywords

Coronary Care Unit Vote Strategy Medical Domain Category Cluster Individual Network 
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.
    Rumelhart, D., Hinton, G., Williams, R.: Nature, 323. 533 (1986).CrossRefGoogle Scholar
  2. 2.
    Harrison, R.F., Lim, C.P., Kennedy, R.L.: Proc. of the Int. Conf. on Neural Networks and Expert Systems in Medicine and Healthcare, 15 (1994).Google Scholar
  3. 3.
    Downs, J., Harrison, R.F., Cross, S.S.: Proc. of the 10th Conf. of the Society for the Study of A.I. and Simulation of Behaviour (In Press).Google Scholar
  4. 4.
    Carpenter, G.A., Grossberg, S., Markuzon, N., Reynolds, J.H., Rosen, D.B.: IEEE Transactions on Neural Networks, 3, 698 (1992).CrossRefGoogle Scholar
  5. 5.
    Lim, C.P., Harrison, R.F.: Neural Networks (In Press).Google Scholar
  6. 6.
    Carpenter, G.A., Grossberg, S. (eds): Pattern Recognition by Self-Organizing Neural Networks. Cambridge, MA: MIT Press 1991.Google Scholar
  7. 7.
    Carpenter, G.A., Grossberg, S.: IEEE Computer, 21, 77 (1988).CrossRefGoogle Scholar
  8. 8.
    Marriott, S., Harrison, R.F.: Neural Networks (In Press).Google Scholar
  9. 9.
    Kasuba, T.: AI Expert, 8, 18 (1993).Google Scholar
  10. 10.
    Parsons, R.W., Jamrozik, K.D., Hobbs, M.S.T., Thompson, D.L.: British Medical Journal, 308, 1006 (1994).CrossRefGoogle Scholar
  11. 11.
    Carpenter, G.A., Tan, A.H.: Proc. of the World Congress on Neural Networks, Volume I, 501 (1993).Google Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • J. Downs
    • 1
  • R. F. Harrison
    • 1
  • R. L. Kennedy
    • 2
  • K. Woods
    • 3
  1. 1.Dept. of Automatic Control and Systems EngineeringUniversity of SheffieldUK
  2. 2.Dept. of MedicineUniversity of EdinburghUK
  3. 3.Dept. of PharmacologyUniversity of LeicesterUK

Personalised recommendations