Application of Heterogenous Bagging Ensemble Model for predicting Breast Cancer

  • C.I. Ejiofor
  • L.C. Ochei
Keywords: Decision Tree (DT), Logistic Regression, Breast Cancer, prediction


Breast cancer is associated with abnormal breast cells emanating from the breast tissues, having the propensity for malignancy or non-malignancy. The causativeness of breast cancer can be linked with genetic or environmental factors. Reliable prediction is integral to proper management and treatment of breast cancer. Sequent to this, researchers have placed a high priority toward enhancing the accuracy for breast cancer prediction. This study employs the rich capability of ensemble bagging machine learning technique for predicting breast cancer. The Heterogenous Bagging Ensemble Model for Predicting Breast Cancer (HBEM-BC) was initiated employing Decision Tree (DT) and Logistic Regression (LR) as base learners. The HBEM-BC was implemented utilizing python programming language with subsequently interfaces presented. The validation of the HBEM-BC presented an accuracy value of 0.74(74%) while independently presenting a Root Square Means Error (RMSE) of 0.41(41%) for Logistic Regression (LR) and 0.51(51%) for Decision Tree (DT) respectively.


Journal Identifiers

eISSN: 2006-5523
print ISSN: 2006-5523