Abstract
Diagnostic processes for many diseases are becoming increasingly complex. Many results, obtained from tests with substantial imperfections, must be integrated into a diagnostic conclusion about the probability of disease in a given patient. A practical approach to this problem is to estimate the pretest probability of disease, and the sensitivity and specificity of different diagnostic tests. With this information, test results can be analyzed by sequential use of Bayes' theorem of conditional probability. The calculated posttest probability is then used as a pretest probability for the next test. This results in a series of tests, where each test is performed independently. Its results may be interpreted with or without any knowledge of other test results. By using Machine Learning techniques for test result evaluation, this process can be almost completely automated. The computer can learn from previously diagnosed patients and apply the acquired knowledge to new patients. Different Machine Learning methods can be used for evaluation of each test result. They may assist the physician as a powerful tool for assistance in pretest probability estimation, interpretation of individual test results and in the final decision making. The presented approach has been successfully evaluated in practice in the problem of clinical diagnosis of coronary artery disease.
Parts of this work are taken from both Matjaž Kukar’s and Ciril Grošelj’s Ph.D. theses. This work was supported by the Slovenian Ministry of Science and Technology.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. A. Diamond and J. S. Forester. Analysis of probability as an aid in the clinical diagnosis of coronary artery disease. New Eng J Med, 300:1350, 1979.
C. Grošelj, M. Kukar, J. Fettich, and I. Kononenko. Machine learning improves the accuracy of coronary artery disease diagnostic methods. In Proc. Computers in Cardiology, volume 24, pages 57–60, Lund, Sweden, 1997.
I. Kononenko. Inductive and Bayesian learning in medical diagnosis. Applied Intelligence, 7:317–337, 1993.
I. Kononenko. Estimating attributes: Analysis and extensions of RELIEF. In L. De Raedt and F. Bergadano, editors, Proc. European Conf. on Machine Learning, pages 171–182, Catania, Italy, 1994. Springer-Verlag.
M. Kukar, C. Grošelj, I. Kononenko, and J. Fettich. An application of machine learning in the diagnosis of ischaemic heart disease. In Proc. Sixth European Conference of AI in Medicine Europe, pages 461–464, Grenoble, France, 1997.
M. Kukar and I. Kononenko. Cost-sensitive learning with neural networks. In Proc. European Conference on Artificial Intelligence ECAI'98, pages 445–449, Brighton, UK, 1998.
M. Kukar, I. Kononenko, C. Grošelj, K. Kralj, and J. Fettich. Analysing and improving the diagnosis of ischaemic heart disease with machine learning. Artificial Intelligence in Medicine: Special Issue on Data Mining Techniques and Applications in Medicine, 1999. In press.
M. Olona-Cabases. The probability of a correct diagnosis. In J. Candell-Riera and D. Ortega-Alcalde, editors, Nuclear Cardiology in Everyday Practice, pages 348–357. Kluwer, 1994.
B. H. Pollock. Computer-assisted interpretation of noninvasive tests for diagnosis of coronary artery disease. Cardiovasc. Rev. Rep. 4, pages 367–375, 1983.
D.E. Rumelhart and J. L. McClelland. Parallel Distributed Processing, volume 1: Foundations. MIT Press, Cambridge, 1986.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kukar, M., Grošelj, C. (1999). Machine Learning in Stepwise Diagnostic Process. In: Horn, W., Shahar, Y., Lindberg, G., Andreassen, S., Wyatt, J. (eds) Artificial Intelligence in Medicine. AIMDM 1999. Lecture Notes in Computer Science(), vol 1620. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48720-4_34
Download citation
DOI: https://doi.org/10.1007/3-540-48720-4_34
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66162-7
Online ISBN: 978-3-540-48720-3
eBook Packages: Springer Book Archive