An Ensemble‐Based Machine Learning Framework for Breast Cancer Prediction
Ramya Palaniappan, Maha Lakshmi, Namitha, Nirmala Devi, Naga Phani · 2025
Breast cancer is a category of disease defined by aberrant cell proliferation in the breast, which depending on the features of the cells may be benign or malignant. It rarely affects men and primarily affects women. Clinical scientists are increasingly concentrating on applying Artificial Diagnosis methods to identify, classify, and diagnose cancer cells. The broadly utilized Wisconsin Bosom Malignant growth Dataset from the College of California, Irvine AI storehouse is utilized in this work. This data, encompassing 32 parameters like mean, radius, compactness, and texture, allows for the evaluation of the proposed structure's effectiveness in characterizing breast cancer, a superior troupe classifier is assembled, and the best model among a few standard models — including Choice Tree, Irregular Woodland, and Backing Vector Machine — is picked. The performance of selected model is then enhanced via the Ada Boosting technique. To gauge the proposed model's performance, various metrics like the confusion matrix, F1-Score, accuracy, recall, and precision are employed. The experimental findings demonstrate that the suggested ensemble model outperforms prior literature research, achieving an accuracy of 98.06%. The review features how AI calculations and computerized reasoning procedures can further develop bosom disease analysis and expectation. It offers likely bearings for progressing clinical judgment and, in the long run, bettering patient results.