Enhancing Breast Cancer Detection: Exploring Machine LearningApproaches Through AUC-ROC Evaluation

Abstract

Breast cancer is a prominent cause of female mortality worldwide addressed through machine learning techniques using the Wisconsin Breast Cancer Dataset (WBCD) to compare classifier effectiveness. The Random Forest (RF), Logistic Regression (LR), and Decision Tree (DT) models are assessed in this job scenario with an emphasis on metrics related to recall, accuracy, and precision. This research emphasizes the value of early detection and the prospective applications of machine learning in the medical field. According to this research, the use of cutting-edge technology in medical diagnostics has shown encouraging results, providing hope for more effective and prompt identification and treatment of breast cancer.