Comparative analysis of machine learning models in breast cancer diagnosis
Peirui Liu · Applied and Computational Engineering · 2024
This comprehensive article explores four prominent machine learning models: Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and Neural Network (NN). It provides historical foundations, mathematical principles, and practical applications. The article includes a noteworthy experiment using the Breast Cancer Wisconsin (Diagnostic) Data Set to diagnose breast cancer. Notably, LR stands out with an impressive accuracy of 97%, the highest among the models. It demonstrates precision rates of 98% for benign cases and 97% for malignant cases, making it the top-performing model in both accuracy and precision. The integrated conclusion offers a comparative analysis of the models, highlighting their strengths and limitations for practical use in medical diagnostics. This article serves as a valuable resource for understanding and applying machine learning techniques, especially in the context of breast cancer diagnosis and prediction.