Breast Cancer Classification Using ANN and ML Techniques
Nishi Bhuta, Roshani Raut · 2023
Millions of individuals throughout the world are impacted by the significant health issue known as breast cancer. To improve patient outcomes, breast cancer must be identified early and correctly diagnosed. In this study, we used TensorFlow to create an artificial neural network (ANN) model to categorise breast cancer. To compare with our ANN model, we also employed seven alternative ML classifiers as basis models, including Line SNM, LR, KNN, NB, DT, RF, and Gradient Booster. For each model, we determined the precision, accuracy, recall, and F1 score. To improve performance, we ensembled all the classifiers. Each classifier's accuracy was analysed and contrasted, and the classification performance was demonstrated via a confusion matrix. Our results show that the ANN have given an accuracy of 97% and the ML model achieved the highest accuracy of 98.8% using LR, followed by SVM with 97.7%, KNN with 96.7%, RF with 95.6%, DT with 95.4%, NB with 95.3%and Gradient Booster with 94.2% The ensemble model gave the overall accuracy to 97.7%. These findings indicate that our proposed ANN model and ensemble approach are effective but LR gave the highest accuracy in classifying breast cancer and can serve as a useful tool for clinicians and researchers in this field.