Journal of Medical Systems

, Volume 21, Issue 6, pp 429–444 | Cite as

Induction of Decision Trees and Bayesian Classification Applied to Diagnosis of Sport Injuries

  • Igor Zelič
  • Igor Kononenko
  • Nada Lavrač
  • Vanja Vuga


Machine learning techniques can be used to extract knowledge from data stored in medical databases. In our application, various machine learning algorithms were used to extract diagnostic knowledge which may be used to support the diagnosis of sport injuries. The applied methods include variants of the Assistant algorithm for top-down induction of decision trees, and variants of the Bayesian classifier. The available dataset was insufficient for reliable diagnosis of all sport injuries considered by the system. Consequently, expert-defined diagnostic rules were added and used as pre-classifiers or as generators of additional training instances for diagnoses for which only few training examples were available. Experimental results show that the classification accuracy and the explanation capability of the naive Bayesian classifier with the fuzzy discretization of numerical attributes were superior to other methods and estimated as the most appropriate for practical use.

machine learning Bayesian classification 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aha, D., Kibler, D., and Albert, M. Instance-based learning algorithms. Mach. Learn.6:37–66, 1991.Google Scholar
  2. 2.
    Anderson, J. A., and Rosenfeld, E., Neurocomputing: Foundations of Research, The MIT Press, 1988.Google Scholar
  3. 3.
    Cestnik, B., Estimating probabilities: A crucial task in machine learning, Proc. European Conf. on Artificial Intelligence, Stockholm, August, 1990, pp. 147–149.Google Scholar
  4. 4.
    Cestnik, B., Kononenko, I., and Bratko, I., ASSISTANT 86: A knowledge elicitation tool for sophisticated users. Progress in Machine Learning(I. Bratko and N. Lavrac, eds.). Sigma Press, Wilmslow, pp. 31–45, 1987.Google Scholar
  5. 5.
    Clark, P., and Boswell, R. Rule induction with CN2: Some recent improvements. In Proc. Fifth European Working Session on Learning, Springer, Berlin, pp. 151–163, 1991.Google Scholar
  6. 6.
    Clark, P., and Niblett, T., The CN2 induction algorithm. Mach. Learn.3(4):261–283.Google Scholar
  7. 7.
    Dasarthy, B. V. (ed.). Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques, IEEE Computer Society Press, Los Alamitos, CA, 1990.Google Scholar
  8. 8.
    Hunt, E., Martin, J., and Stone, P., Experiments in Induction, Academic Press, New York.Google Scholar
  9. 9.
    Kira, K., and Rendell, L., A practical approach to features selection. Proc. Int. Conf. on Machine Learning ICML-92(Aberdeen, July 1992). (D. Sleeman and P. Edwards, eds.), Morgan Kaufmann, pp. 249–256.Google Scholar
  10. 10.
    Kononenko, I., Inductive and Bayesian learning in medical diagnosis. Appl. Artificial Intell.7:317–337.Google Scholar
  11. 11.
    Kononenko, I., Estimating attributes: Analysis and extensions of RELIEF. Proc. European Conf. on Machine Learning ECML-94(Catania, Sicily, April 1994) (F. Bergadano and L. de Readt, eds.), Springer Verlag, Berlin, pp. 171–182.Google Scholar
  12. 12.
    Kononenko, I., and Bratko, I., Information-based evaluation criterion for classifier's performance. Mach. Learn.6(1):67–80, 1991.Google Scholar
  13. 13.
    Kononenko, I., and Kukar, M., Machine learning for medical diagnosis. Proc. Workshop on Computer-Aided Data Analysis in Medicine, CADAM-95(Bled, November 1995) (N. Lavrac, ed.), IJS Scientific Publishing, Ljubljana.Google Scholar
  14. 14.
    Kononenko, I., and %imec, E., Induction of decision trees using RELIEFF. Proc. of ISSEK Workshop on Mathematical and Statistical Methods in ARtificial Intelligence, (Udine, September 1994 (G. Della Riccia, R. Kruse, and R. Viertl, eds.), Springer Verlag, pp. 199–220.Google Scholar
  15. 15.
    Lavrac, N., and Dzeroski, S., Inductive Logic Programming: Techniques and Applications, Ellis Horwood, Chichester, 1994.Google Scholar
  16. 16.
    Lavrac, N., Keravnou, E., and Zupan, B. (eds.), Intelligent Data Analysis in Medicine and Pharmacology, Kluwer Academic Publishers, 1997.Google Scholar
  17. 17.
    Michalski, R. S., Carbonell, J. G., and Mitchell, T. M. (eds.), Machine Learning: An Artificial Intelligence Approach, Volume I, Tioga, Palo Alto, CA, 1983.Google Scholar
  18. 18.
    Michalski, R. S., Mozetic, I., Hong, J., and Lavrac, N., The multi-purpose incremental learning system AQ15 and its testing application on three medical domains. In Proc. Fifth National Conference on Artificial Intelligence, Morgan Kaufmann, San Mateo, CA, pp. 1041–1045, 1986.Google Scholar
  19. 19.
    Michie, D., Spiegelhalter, D. J., and Taylor, C. C. (eds.), Machine Learning, Neural and Statistical Classification, Ellis Horwood, Chichester, 1994.Google Scholar
  20. 20.
    Niblett, T., and Bratko, I., Learning decision rules in noisy domains. Research and Development in Expert Systems III, (M. Bramer (ed.), Cambridge University Press, pp. 24–25, 1986.Google Scholar
  21. 21.
    Quinlan, J. R., Induction of decision trees. Mach. Learn.1(1):81–106, 1986.Google Scholar
  22. 22.
    Richeldi, M., and Rossotto, M., Class-driven statistical discretization of continuous attributes. Machine Learning: Proc. ECML-95, (N. Lavrac, and S. Wrobel(eds.), Springer Verlag, Berlin, pp. 335–342.Google Scholar
  23. 23.
    Zelic, I., Kononenko, I., Lavrac, N., and Vuga, V., Machine learning applied to diagnosis of sport injuries. In Proc. Artificial Intelligence in Medicine, AIME'97(Grenoble, France, April 1997), Springer Verlag, Berlin, pp. 138–141, 1997.Google Scholar
  24. 24.
    Zelic, I., Kononenko, I., Lavrac, N., and Vuga, V., Diagnosis of sport injuries with machine learning: Explanation of induced decisions. In Proc. Tenth IEEE Symposium on Computer-Based Medical Systems(Maribor, Slovenia, June 1997), IEEE Computer Society, Los Alamitos, CA, pp. 195–199, 1997.Google Scholar

Copyright information

© Plenum Publishing Corporation 1997

Authors and Affiliations

  • Igor Zelič
    • 1
  • Igor Kononenko
    • 2
  • Nada Lavrač
    • 3
  • Vanja Vuga
    • 4
  1. 1.INFONETKranjSlovenia
  2. 2.Faculty of Computer and Information ScienceLjubljanaSlovenia
  3. 3.J. Stefan InstituteLjubljanaSlovenia
  4. 4.University Medical Centre for Sport MedicineLjubljanaSlovenia

Personalised recommendations