Prediction of Breast Cancer Using Simple Machine Learning Algorithms

Breast cancer is a significant cause of morbidity and mortality among women, especially in developing countries. Early prediction, and accurate treatment are critical to reduce death rates. Using artificial intelligence and machine learning techniques, this project will evaluate the performance of several models in predicting breast cancer. The prediction models such as Decision Tree, Gradient Boosting, Naive Bayes, Neural Network, SGD, kNN, and CN2 rule inducer are employed utilizing Orange tools. This study used publicly accessible secondary data from Keggle, enabling transparency and accessibility in the evaluation approach. The findings disply that the DT, GB, Neural Network, and CN2 rule inducer had higher accuracy ratings of 0.992, 0.998, 0.997, and 0.997, respectively, with exceptional AUC values of 0.989, 1.000, 1.000, and 0.990. Additionally, their recall and accuracy scores are 0.992, 0.987, 0.998, and 0.997, demonstrating their strong performance in breast cancer prediction. Among the most popular classifier models, GB and Neural Network, are the outperformed models than others.