Breast Cancer Prediction Using Traditional and Ensemble Machine Learning Techniques

Abstract

Physical diseases like breast cancer have been on the rise recently.The majority of women are affected by breast cancer. The ratio of normal to diseased areas and the pace of unchecked tissue growth are used to quantify the illness. Breast cancer detection and prediction have been the subject of several research in the past. We have identified a few excellent chances to develop the methodology. We suggest employing efficient algorithm models to forecast dangers and raise early awareness. Our suggested approach is suited for straightforward breast cancer forecasts and is simple to apply in the actual world. We have used two dataset and Kaggle website hosted the dataset. Decision tree (DT), Random Forest (RF), Logistic Regression (LR), K-Nearest Classifier (KNN), and other classifiers have all been integrated in our model. Test accuracy for the Random Forest Classifier was 97.36% and 97.81% which was good performance for datasets A and B. We are getting better accuracy for the Logistic Regression was 98.54% using Dataset B. Other algorithms, Decision Tree tested accurate to 96.49%. In order to defend the performances, we also employed a variety of ensemble models. We used Bagging, Boosting, and Voting algorithms. To assign the optimal parameters to each classifier, we employed hyper-parameter tweaking. The experimental investigation reviewed the results of previous recent studies and found that RFBO and LRGD performed best, with 98.24% and 99.27% accuracy being the highest level of accuracy for breast cancer predictions.