The impact of rough set approach on medical diagnosis for cost effective feature selection

The medical diagnosis process can be interpreted as a decision making process, during which the physician includes the diagnosis of a new and unknown case from an available set of clinical data and from clinical experience which can be computerized. A method that enhances the performance of a model that is based on Rough set theory for feature selection and classification is proposed. For this purpose, the PIMA dataset is used. The proposed system provides the solution to a feature subset selection problem which is nothing but a task of identifying and analysing an optimal subset from a larger set of features. It is concluded that the method certainly helps in cost reduction associated with the diagnosis.