Evaluation Methods for Breast Cancer Prediction in Machine Learning Field

Abstract

Breast cancer is the most common malignant tumor found in women, and there is no cure for advanced breast cancer. Early detection and treatment can effectively improve patient survival. This paper uses five machine learning classification models, namely Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbors Algorithm (KNN). The training data for the five models are provided by the Wisconsin Breast Cancer Dataset (WBCD). By evaluating and comparing the performance of the five models in accuracy, F1Score, ROC curve, and PR curve, the study finds that LR has the best performance.