Breast Cancer Prediction using Feature Selection and Classification with XGBoost

As a result of high population growth, medical research and early sickness identification has become a responsibility. As the inhabitants grows, the likelihood of succumbing to breast cancer rises. A illness detection system that's automated reduces the danger of mortality, provides dependable, efficient, and rapid reaction, and assists doctors in disease diagnosis. to reinforce the predictive efficacy of current models and To estimate the risk of breast cancer, proposed model used Extreme Gradient Boosting (XGBoost) and compared it to Logistic Regression (LR), The Random Forest (RF), and Support Vector Machines (SVM). In this work, target picking the most weighted features using the XGBoost method and training the model with those features was performed. This approach yielded the identical accuracy as training the model with all features, however training the model with all features takes longer. The suggested approach has produced findings that are comparable and may help radiologists provide opinions