A new data mining approach based on rough set

In this work, a new and an efficient RS is used to perform the task of predicting breast cancer recurrence. The rough sets based approach was applied to obtain risk factors for the breast cancer recurrence. The set of selected attributes, which ensured high quality of the classification, was obtained. This so-called "recurrence" is the return of cancer after initial treatment. It causes considerable distress for breast cancer survivors. To design interventions to breast cancer recurrence, we must know what survivors are potential to recurrence, what factors that influence the likelihood that breast cancer may return. Various published algorithms have been applied to breast cancer datasets, but rough set is a fairly new intelligent technique that applies to predict breast cancer recurrence. We analyze Ljubljana Breast Cancer Dataset, firstly, obtain lower and upper approximations and calculate the accuracy and quality of the classification. The high values of the quality of classification and accuracy prove that the attributes selected can well approximate the classification. Rough sets approach for generation of all reducts that contains minimal number of attributes and rules are introduced. Finally, rules based-on rough set are generated and the proposed rules are promising for improving prediction accuracy.