Title :
Generating classifier for the acute abdominal pain diagnosis problem
Author :
Wozniak, Michal ; Kurzynski, Marek
Author_Institution :
Div. of Syst. & Comput. Networks, Wroclaw Univ. of Technol., Poland
Abstract :
The inductive learning algorithms are very attractive methods for generating hierarchical classifiers. They generate the hypothesis of the target concept on the basis of the set of labeled examples. This paper presents some of the rule generation methods, their usefulness for the rule-base classifier and their quality of classification for the medical decision problem.
Keywords :
decision support systems; decision trees; fuzzy logic; learning by example; medical expert systems; pattern classification; acute abdominal pain diagnosis problem; hierarchical classifiers; inductive decision tree algorithms; inductive learning algorithms; labeled examples; medical decision problem; quality of classification; rule generation methods; rule-base classifier; target concept; Abdomen; Algorithm design and analysis; Bellows; Biomedical imaging; Classification tree analysis; Decision support systems; Decision trees; Image databases; Machine learning; Pain;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1019671
