An Automated Diagnosis Of Breast Cancer Using Farthest First Clustering And Decision Tree J48 Classifier

Breast cancer is one of the most widespread and deadly cancer for women. Early diagnosis and treatment of breast cancer can enhance the outcome of the patients. Due to the difficulties of outlier and skewed data, the prediction of breast cancer survey has presented many challenges in the field of data mining and pattern recognition .To solve these troubles, we have proposed an automated breast cancer diagnosis using data mining algorithms. This approach comprises two main steps: (1) utilization of an outlier filtering approach based on Farthest Clustering to identify and eliminate outlier instances; and (2) Classify the benign or malignant cancer using decision tree J48 classifier. To test the efficacy of the proposed classification model we used the Wisconsin Breast Cancer Dataset (WBCD). In order to assess the capability and effectiveness of the proposed approach, several measurement methods including basic performance (e.g., sensitivity, accuracy, and specificity), AUC and F-measure were utilized. The obtained classification accuracy of 98.4% is a very optimistic result compared to the existing works for the same data set. The result also shows that our approach works well with the breast cancer database and can be a good choice to the well-known machine learning