Abstract
Decision trees have been successfully used for years in many medical decision making applications. Transparent representation of acquired knowledge and fast algorithms made decision trees one of the most often used symbolic machine learning approaches. This paper concentrates on the problem of separating acute appendicitis, which is a special problem of acute abdominal pain, from other diseases that cause acute abdominal pain by use of an decision tree approach. Early and accurate diagnosing of acute appendicitis is still a difficult and challenging problem in everyday clinical routine. An important factor in the error rate is poor discrimination between acute appendicitis and other diseases that cause acute abdominal pain. This error rate is still high, despite considerable improvements in history-taking and clinical examination, computer-aided decision-support, and special investigation such as ultrasound. We investigated three databases of different size with ca ses of acute abdominal pain to complete this task as successful as possible. The results show that the size of the database does not necessary directly influence the success of the decision tree built on it. Surprisingly we got the best results from the decision trees built on the smallest and the biggest database, where the database with medium size (relative to the other two) was not so successful. Despite this we were able to produce decision tree classifiers that were capable of producing correct decisions on test data sets with accuracy up to 84%, sensitivity to acute appendicitis up to 90%, and specificity up to 80% on the same test set.
Similar content being viewed by others
REFERENCES
af Klercker, T., Effect of pruning of a decision-tree for the ear, nose and throat realm in primary health care based on case-notes. J. Med. Syst. 20(4):215-226, 1996.
Zorman, M., Podgorelec, V., Kokol, P., Peterson, M., and Lane, J., Decision tree's induction strategies evaluated on a hard real world problem. 13th IEEE Symposium on Computer-Based Medical Systems 22-24 June 2000, Houston, Texas, USA, pp. 19-24, 2000.
Andersson, R. E., Hungander, A., and Thulin, J. G., Diagnostic accuracy and perforation rate in appendicitis: Association with age and sex of the patient and with appendectomy rate. European J. Surg. 158:37-41, 1992.
Blind, P. J., and Dahlgren, S. T., The continuing challenge of the negative appendix. Acta Chir. Scand. 152:623-627, 1986.
Ohmann, C., Moustakis, V., Yang, Q., and Lang, K., Evaluation of automatic knowledge acquisition techniques in the diagnosis of acute abdominal pain. Artif. Intell. Med. 8:23-36, 1996.
Pesonen, E., Eskelinen, M., and Juhola, M., Comparison of different neural network algorithms in the diagnosis of acute appendicitis. Int. J. Bio-Med. Comput. 40:227-233, 1996.
de Dombal, F. T., Diagnosis of Acute Abdominal Pain, Churchhill Livingstone, Edinburgh, 1991, pp. 105-106.
Quinlan, J. R., C4.5: Programs for Machine Learning, Morgan Kaufmann, San Mateo, CA, 1993.
Russel, S. J., Norvig, P., et al.: Artificial Intelligence: A Modern Approach, Prentice-Hall, Englewood Cliffs, 1995, pp. 525-562.
Zorman, M., Hleb, S., and Sprogar, M., Advanced tool for building decision trees MtDeciT 2.0. In Kokol, P., Welzer-Dru¡zovec, T., and Arabnia, H. R. (eds.), International Conference on Artificial Intelligence, June 28-July 1, 1999, Las Vegas, Nevada, USA. Book 1, pp. 315-318.
Zorman, M., and Kokol, P., Dynamic discretization of continuous attributes for building decision trees. In Fyfe, C. (ed.), Proceedings of the Second ICSC Symposium on Engineering of Intelligent Systems, EIS 2000, June 27-30, 2000, University of Paisley, Scotland,U.K. Academic Press, Wetaskiwin; Zürich, pp. 252-257, 2000.
de Dombal, F. T., de Baere, H., van Elk, P. J., Fingerhut, A., Henriques, J., Lavelle, S. M., Malizia, G., Ohmann, C., Pera, C., Sitter, H., and Tsiftsis, D., Objective medical decision making in acute abdoinal pain. In Benken, J. E.W., and Thevin, V. (eds.), Advances in Biomedical Engineering, IOS Press, 1993, pp. 65-87.
Ohmann, C., Platen, C., Belenky, G., Franke, C., Otterbeck, R., Lang, K., et al.: Expertensystem zur Unterstützung von Diagnosestellung und Therapiewahl bei akuten Bauchschmerzen. Informatik, Biometrie und Epidemiologie in Medizin und Biologie 26(3):262-274, 1995.
Ohmann, C., Eich, H. P., and Sippel, H., A data dictionary approach to multilingual documentation and decision support for the diagnosis of acute abdominal pain (COPERNICUS 555, An European Concerted Action). Medinfo 9(Pt 1):462-466, 1998.
Pesonen, E., Ohmann, C., Eskelinen, M., and Juhola, M., Increasing the accuracy of the acute appendicitis of a LVQ neural network by the use of larger neighborhoods. Methods Inf. Med. 37(1):59-63, 1996.
Puppe, B., Ohmann, C., Goos, K., Puppe, F., and Mootz, O., Evaluating four diagnostic methods with acute abdominal pain cases. Methods Inf. Med. 34:361-368, 1995.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zorman, M., Eich, HP., Stiglic, B. et al. Does Size Really Matter—Using a Decision Tree Approach for Comparison of Three Different Databases from the Medical Field of Acute Appendicitis. Journal of Medical Systems 26, 465–477 (2002). https://doi.org/10.1023/A:1016461301710
Issue Date:
DOI: https://doi.org/10.1023/A:1016461301710