COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS; RANDOM FOREST, DECISION TREE, SUPPORT VECTOR CLASSIFIER AND XGBOOST TO PREDICTBREAST CANCER WITH A WEBAPP

ABSTRACT

Breast cancer is a form of cancer that originates in the breast cells. Breast cancer is commonly treated with Xrays, chemotherapy, or a combination of the two. Early detection of cancer can be lifesaving. Artificial intelligence (AI) is particularly significant in this field. As a result, doctors and researchers continue to face significant challenges in predicting breast cancer. This study aims to predict the likelihood of breast cancer occurrence in patients using machine learning (ML) models, specifically XGBoost, Decision Tree, SVC, and Random Forest (RF). The Breast Cancer Diagnostic Medical Database, sourced from the Wisconsin repository, was utilized. The dataset comprises 569 observations and 32 features. The data analysis process included data cleaning, exploratory analysis, training, testing, and validation. The models' performance was evaluated based on classification accuracy, specificity, sensitivity, F1 score, and precision. The training and results indicate that the six trained models are capable of achieving optimal classification and prediction outcomes.