Το έργο με τίτλο Automated revision of expert rules for treating acute abdominal pain in children από τον/τους δημιουργό/ούς Moustakis Vasilis, Sašo Džeroski, Giorgos Potamias, Giorgos Charissis διατίθεται με την άδεια Creative Commons Αναφορά Δημιουργού 4.0 Διεθνές
Βιβλιογραφική Αναφορά
S. Dzeroski, G. Potamias, V. Moustakis, G. Charissis, "Automated Revision of
Expert Rules for Treating Acute Abdominal Pain in Children," in 6th Conference on Artificial Intelligence in Medicine Europe, 1997, pp. 98-109. doi: 10.1007/BFb0029440
https://doi.org/10.1007/BFb0029440
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.