Rough set techniques for medical diagnosis systems

The process of discovering natural phenomena or complex system was until recently limited to finding formulas that fit empirical data. This process used with success in science and engineering has its limits when the complexity of the natural processes increases. Therefore, to analyze data in the medical domain an alternative approach was needed. Several mathematical methods including neural nets, inductive learning fuzzy sets and rough sets were proposed to model data in the form of decision tables or rules. Pawlak's rough sets theory for handling imprecision and uncertainty in data has a main advantage over the other techniques which is the possibility to analyze data without any preliminary information what favor its usage in medical decision systems. In this paper we present the results of rule generation from our implementation of the LEM2 algorithm on reduced sets of attributes calculated using the Wrapper method with different learning algorithms