Abstract
Decision making knowledge acquired directly from a medical expert is often incorrect and incomplete. Another source of knowledge about a decision making problem are examples of expert decisions in situations that have occurred in practice, stored in patient records of clinical information systems. Such examples can be used to revise the expert-provided knowledge, i.e., to discover and repair its deficiences. The revised knowledge performs better than the original one and often better than rules learned from examples alone. In addition, it inherits parts of the original expert knowledge and is thus easier to understand and accept for the expert. We present an application of the machine learning approach of theory revision to the problem of revising an expert-provided theory for treating children with acute abdominal pain.
Preview
Unable to display preview. Download preview PDF.
References
Baffes, P.T., and Mooney, R.J. (1993). Symbolic revision of theories with M-of-N rules. In Proc. Thirteenth International Joint Conference on Artificial Intelligence, pp. 1135–1140. Chambery, France, 1993.
de Dombal, F.T. (1991). Diagnosis of abdominal pain. Churchil Livingstone, Singapore.
De Jong, J.F., and Mooney, R.J. (1986). Explanation based learning: an alternative view. Machine Learning, 1(2): 145–176.
Morik, K., Wrobel, S., Kietz, J.-U., and Emde, W. (1993). Knowledge Acquisition and Machine Learning — Theory, Methods, and Applications. Academic Press, London.
Potamias, G., Moustakis, V., and Charissis, G. (1996). Iterative knowledge construction and maintenance. In Proc. ICML'96 Workshop Machine Learning Meets Human Computer Interaction. Bari, Italy, 1996.
Richards, B.L., and Mooney, R.J. (1991). Refinement of first-order Horn-clause domain theories. Machine Learning, 19(2): 95–131.
Ourston, D., and Mooney, R.J. (1994). Theory refinement combining analytical and empirical methods. Artificial Intelligence, 66: 273–309.
Waldschmit, J., and Charissis, G. (1990). Das akute Abdomen im Kindesalter. Diagnose und Differentialdiagnose. Edition Medezin, New York.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Džeroski, S., Potamias, G., Moustakis, V., Charissis, G. (1997). Automated revision of expert rules for treating acute abdominal pain in children. In: Keravnou, E., Garbay, C., Baud, R., Wyatt, J. (eds) Artificial Intelligence in Medicine. AIME 1997. Lecture Notes in Computer Science, vol 1211. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0029440
Download citation
DOI: https://doi.org/10.1007/BFb0029440
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62709-8
Online ISBN: 978-3-540-68448-0
eBook Packages: Springer Book Archive