Prediction of breast cancer disease using machine learning approach / Wan Nashua Amira and Nor Hayati Shafii

The most prevalent invasive cancer in women, and the second leading cause of cancer mortality in women is breast cancer. Researchers' interest in breast cancer research and prevention has increased recently. However, the advent of data mining techniques has made it possible to efficiently extract more valuable information from large databases, and the information so retrieved may be used for prediction, classification, and clustering. Three different classification models, including Decision Tree (DT), Random Forest (RF), and Logistics Regression (LR), are used for the classification of datasets related to breast cancer in this study to develop an accurate model to predict breast cancer disease and reduce the risk of breast cancer death. Wisconsin Breast Cancer Database (WBCD). Three metrics are utilised to assess how well these three classification models performed: Precision, Recall, and F1 Score. Prediction accuracy numbers are also included. An examination of comparative experiments demonstrates that the random forest model can outperform the other two techniques in terms of performance and accuracy. As a result, it has been determined that the study's model has clinical and referential value in real-world applications