Advertisement

Art-Based Autonomous Learning Systems: Part II — Applications

  • C. P. Lim
  • R. F. Harrison
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 43)

Abstract

This chapter presents an evaluation of the practical applicability of the multiple classifier systems developed in Part I. First, a benchmark study is conducted to compare the system performance with other machine learning algorithms. Then, two medical decision-making problems comprising real patient records collected from a number of hospitals are investigated, viz. (i) the prognosis of patients exhibiting complications admitted to coronary care units, and (ii) the prediction of survival rates among trauma patients. Various operating strategies including off-line and on-line learning are examined, and implications of the results are discussed. In particular, the outcomes reveal the potential of employing such an autonomously learning system as a useful decision support tool in the medical arena.

Keywords

Multiple Classifier Coronary Care Unit Confusion Matrice Learn Classifier System Revise Trauma Score 
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]
    Apolloni, B., Avanzini, G., Cesa-Bianci, N., and Ronchini, G. (1990), “Diagnosis of epilepsy via backpropagation,” Proceedings of the International Joint Conference on Neural Networks, Vol. 2, pp. 571–574.Google Scholar
  2. [2]
    Bounds, D., Lloyd, P., and Mathew, B. (1990), “A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders,” Neural Networks, vol. 3, pp. 583–591.CrossRefGoogle Scholar
  3. [3]
    Harrison, R.F., Marshall, S.J., and Kennedy, R.L. (1991), “A connectionist approach to the early diagnosis of myocardial infarction,” Proceedings of the Third European Conference on Artificial Intelligence in Medicine (AIME-91), pp. 119–128.Google Scholar
  4. [4]
    Harrison, R.F., Lim, C.P., and Kennedy, R.L. (1994), “Autonomously learning neural networks for clinical decision support,” in Ifeachor, E.C. and Rosen, K.G. (Eds.), Proceedings of the International Conference on Neural Networks and Expert Systems in Medicine and Healthcare (NNESMED-94), pp. 15–22, Plymouth: University of Plymouth.Google Scholar
  5. [5]
    Baxt, W.G., (1990), “Use of an artificial neural network for data analysis in clinical decision support: the diagnosis of acute coronary occlusion,” Neural Computation, Vol. 2, pp. 480–489.CrossRefGoogle Scholar
  6. [6]
    Ravdin, P.M. and Clark, G.M. (1992), “A practical application of neural network analysis for predicting outcome of individual breast cancer patients,” Breast Cancer Research Treat, Vol. 22, pp. 285–293.CrossRefGoogle Scholar
  7. [7]
    Downs, J., Harrison, R.F., Kennedy, R.L., and Cross, S.S. (1996), “Application of the Fuzzy ARTMAP neural network model to medical pattern classification tasks,” Artificial Intelligence in Medicine, Vol. 8, pp. 403–428.CrossRefGoogle Scholar
  8. [8]
    Snow, P.B., Smith, D.S., and Catalona, W.J., (1994), “Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study,” Journal of Urology, Vol. 152 (5 Pt 2), pp. 1923–26.Google Scholar
  9. [9]
    Lin J.S., et al., (1993), “Application of neural networks for reduction of false-positive detections in digital chest radiographs,” Proceedings of Annual Symposium on Computers Applied to Medical Care, pp. 434–438.Google Scholar
  10. [10]
    Edenbrandt, L., Helen, B., and Fahlm, O. (1993), “Neural networks for analysis of ECG complexes,” Journal of Electrocardiology, Vol. 26, pp. 74.CrossRefGoogle Scholar
  11. [11]
    Bortolan, G. and Willems, J.L. (1993), “Diagnostic ECG classification based on neural networks,” Journal of Electrocardiology, Vol. 26, pp. 75–79.Google Scholar
  12. [12]
    Michie, D., Spiegelhalter, D.J., and Taylor, C.C. (1994), Machine Learning, Neural and Statistical Classification, Oxford: Oxford Press.MATHGoogle Scholar
  13. [13]
    Blake, C, Keogh, E., and Merz, CJ. (1998), UCI Repository of machine learning databases [http://www.ics.uci.edu/~mlearn/ MLRepository.html ]. Irvine, CA: University of California, Depart¬ment of Information and Computer Science.Google Scholar
  14. [14]
    Asfour, R.Y. (1995), Fusion ARTMAP: neural networks for multi-sensor fusion and classification, Ph.D. Thesis, Boston University.Google Scholar
  15. [15]
    Parsons, R.W., Jamrozik, K.D., Hobbs, M.S.T. and Thompson, D.L. (1994), “Early identification of patients at low risk of death after myocardial infarction and potentially suitable for early hospital discharge,” British Medical Journal, Vol. 308, pp. 1006–1010.CrossRefGoogle Scholar
  16. [16]
    Kennedy, R.L., Harrison, R.F., Fraser, H.S., Fletcher, S., Burton, A.M., McStay, L.N., and Woods, K.L. (1996), Prediction of severe complications and mortality in patients admitted to a coronary care unit, Research Report No. 655, Department of Automatic Control and Systems Engineering, University of Sheffield.Google Scholar
  17. [17]
    Swets, J.A. and Pickett, R.M. (1982), Evaluation of Diagnostic Systems, London: Academic Press.Google Scholar
  18. [18]
    Hanley, J.A. and McNeil, B.J. (1982), “The meaning and use of the area under a Receiver Operating Characteristic (ROC) Curve,” Radiology, Vol. 143, pp. 29–36.Google Scholar
  19. [19]
    Hanley, J.A. and McNeil, B.J. (1983), “A method for comparing the areas under Receiver Operating Characteristic curves derived from the same cases,” Radiology, Vol. 148, pp. 839–843.Google Scholar
  20. [20]
    Meistrell, M. (1990), “Evaluation of neural network performance by Receiver Operating Characteristic analysis: examples from the biotechnology domain,” Computer Methods and Programs in Biomedicine, Vol. 32, pp. 73–80.CrossRefGoogle Scholar
  21. [21]
    Bland, M. (1987), An Introduction to Medical Statistics, Oxford: Oxford University Press.Google Scholar
  22. [22]
    Yates, D.W., Woodford, M., and Hollis, S. (1992), “Preliminary analysis of the care of injured patients in 33 British hospitals: first report of the United Kingdom major trauma outcome study,” British Medical Journal, Vol. 305, pp. 737–740.CrossRefGoogle Scholar
  23. [23]
    Little, K. et al (1995), “Preliminary analysis of the care of injured patients in five Scottish teaching hospitals: first report from the Scottish Trauma Audit Group (STAG),” Health Bulletin, Vol. 53, pp. 55–65.Google Scholar
  24. [24]
    Boyd, C.R., Tolson, M.A., and Copes, W.S. (1987), “Evaluating trauma care: the TRISS method,” Journal of Trauma, Vol. 27, pp. 370–378.CrossRefGoogle Scholar
  25. [25]
    Xu, L., Krzyzak, A., and Suen, C.Y. (1992), “Methods of combining multiple classifiers and their applications to handwriting recognition,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 22, pp. 418–435.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • C. P. Lim
    • 1
  • R. F. Harrison
    • 2
  1. 1.School of Industrial TechnologyUniversiti Sains MalaysiaPenangMalaysia
  2. 2.Department of Automatic Control and Systems EngineeringThe University of SheffieldSheffieldUK

Personalised recommendations