An Efficient Method for Detection of Breast Cancer Based on Closed Frequent Itemsets Mining

This paper investigates the core factors which contribute to breast cancer. An algorithm MCFI-DS (Mining Closed Frequent ltemsets over Data Streams) is applied to identify these factors and the dataset "Wisconsin Breast Cancer Database" is considered to evaluate the proposed system performances. The core attributes belonging to "malignant" and "benign" conditions are identified. It is seen that bare nuclei contributes more to the presence of breast cancer. Mitoses are an ineffective feature for detecting breast cancer. The algorithm MCFI-DS is compared with two other state of the art algorithms TMoment and MFI-TransSW to claim the performance improvements over other algorithms.