Ensemble Learning Techniques for Breast Cancer Prediction

Abstract

Breast cancer is predominantly diagnosed in women and remains a leading cause of rising health concerns among females. Manual identification of the disease is often time-consuming and limited in accessibility. To address this, automated diagnostic systems using machine learning (ML) have become increasingly valuable for early detection and classification of cancer. This paper explores the use of machine learning and ensemble learning techniques for classifying tumors. Specifically, it evaluates the performance of Logistic Regression, Support Vector Machines (SVM), Decision Trees, and Random Forests on a breast cancer dataset. The study compares models based on key performance metrics, including False Positive Rate, Accuracy, Precision, and Recall. The effectiveness of ensemble learning methods is also analyzed and benchmarked against individual models. Statistical analysis reveals that the ensemble model combining Decision Tree and Random Forest algorithms achieves an accuracy of 89.3%, while the ensemble of Logistic Regression and SVM reaches an accuracy of 90.4%. These ensemble models outperform their counterparts, demonstrating the advantages of combining multiple algorithms for improved diagnostic accuracy.