A Novel Resampling Model for Classifying an Imbalanced Breast Cancer Dataset

Breast cancer is a significant health concern within medical care systems, necessitating accurate classification. The patient data are recorded and statistically analyzed, revealing an increasing number of files. And then transferred to the statistics department with increasing numbers. This study investigates breast cancer data imbalance utilizing Khartoum State Hospital. An imbalanced data problem occurs when one class has a significantly larger number of samples than another. To address this, resampling, attribute selection, handling missing values, classifier algorithms (ANN, REP TREE, SVM, J48), and ensemble learning models were employed. The base classifier yielded the first result, the meta-learning algorithms (Bagging, Boosting, and Random Subspace) the second, and an ensemble model the third. The boosting with the J48 ensemble model achieved the highest accuracy, 95.2797 %, outperforming bagging with j48 (90.559%) and random subspace with j48 (84.2657%).