Rough set theory and rule induction techniques for discovery of attribute dependencies in medical information systems

Problems connected with applications of the rough set theory to identify the most important attributes and with induction of decision rules from the medical data set are discussed in this paper. The medical data set concerns patients with multiple injuries. The direct use of the original rough set model leads to finding too many possibilities of reducing the input data. To solve this difficulty, a new approach integrating rough set theory, rule induction and statistical techniques is introduced. First, the Chi-square test is additionally performed in order to reject non-significant attributes. Then, starting from remaining attributes we try to construct such definitions of new attributes that improve finally discovered decision rules. The results have shown that the proposed approach integrating all methods has given better results than those obtained by applying the original rough set method.