An Ensemble Learning Approach to Predict Breast Cancer Disease

• Published in: 2025 8th International Conference on Computing Methodologies and Communication (ICCMC) pp. 1397 - 1402
• Main Authors: Ahmed, Sara, Pundir, Meena, Goel, Paurav
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23.07.2025
• Subjects: Bayes methods; Breast cancer; decision tree; Decision trees; Ensemble learning; ensemble technique; Logistic regression; machine learning; multi layer perceptron; naive bayes; Predictive models; Prognostics and health management; random forest; Random forests; Stacking; Surgery
• DOI: 10.1109/ICCMC65190.2025.11140665

The concept of Machine Learning is used now a days to describe the diagnosis and prognosis of many kinds of cancer. This forecast reduces subsequent surgical procedures. The prediction of breast cancer is the main subject of this paper. The incidence of deaths from breast cancer has recently declined due to early diagnosis, breast screening and improved treatment. In this research, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset is used to offer a robust Stacking Ensemble Learning framework for breast cancer prediction. Four different supervised Machine Learning algorithms as base learners: Random Forest, Naïve Bayes, Decision Tree and Multi-Layer Perceptron and Logistic Regression as the meta model have been employed to integrate each of their separate predictions. To improve model performance, extensive preprocessing procedures were carried out. In comparison to individual classifiers, the stacked model outperformed them with an accuracy of 97.37%, highlights how well the suggested Ensemble approach improves diagnostic precision and show that it has the potential to be a significant instrument for clinical judgment in the identification of breast cancer.