A Comparative Study of Machine Learning Algorithms for Benign-Malignant Breast Tumor Classification

Breast cancer is still a major worldwide health concern, and mortality rates are greatly impacted by late-stage diagnoses. Globally, late-stage breast cancer claims the lives of about 685,000 women each year.This study explores new developments in breast cancer detection, highlighting the importance of an early diagnosis. This article examines cutting-edge medical imaging methods and applications of artificial intelligence that could lessen this burden by increasing precision and enabling earlier diagnoses, ultimately improving patient outcomes and lowering breast cancer-related mortality. Additionally, we used three different classifiers—Logistic Regression, Decision Tree, and Random Forest—to thoroughly assess our expanded dataset. Because of their adaptability and appropriateness for handling complicated information, these classifiers were chosen. Our findings indicate promising results, with specific classifiers demonstrating increased sensitivity and specificity in early breast cancer detection.