Comparative Analysis of Machine Learning Algorithms for Breast Cancer Detec-tion: A Study of Support Vector Classification, Logistic Regression, and

Abstract

Worldwide, breast cancer is a frequent medical problem, and successful treatment to a large extent counts on early diagnosis. Machine learning algorithms have demonstrated a high potential of integration into breast cancer detection system, which in turn will increase the diagnostic facility's precision. Three popular machine learning techniques are compared in this study: K-Nearest Neighbors (KNN), Support Vector Classification (SVC), and Logistic Regression. In this context, the study is based on the several study that use the algorithms to detect breast cancer. By SVC, Logistic Regression, and KNN for breast cancer diagnosis, the study of medical literature was executed thoroughly.  We conducted a thorough analysis of each paper's methodology, dataset, feature selection strategies, and performance measures. With an average accuracy of more than 98%, our data show that Support Vector Classification surpassed K-Nearest Neighbors and Logistic Regression in every study that was analyzed. SVC outperformed other methods for detecting breast cancer in terms of sensitivity, specificity, and total predictive power. While KNN produced somewhat lower accuracy rates, Logistic Regression demonstrated moderate accuracy. The results of this investigation highlight Support Vector Classification's efficacy as a strong algorithm for tasks involving the identification of breast cancer. Patient outcomes for early identification and treatment of breast cancer could be greatly enhanced by enhanced detection systems driven by machine learning algorithms.