Breast Cancer Detection Using Optimal Machine Learning Techniques: Uncovering the Most Effective Approach

Abstract

This research paper aimed to identify the most effective machine-learning approach for breast cancer detection. The study utilized the Breast Cancer Wisconsin (Diagnostic) Data Set and evaluated five different algorithms: Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, and K-Nearest Neighbours (KNN). After thorough analysis, all five algorithms demonstrated high accuracy rates, ranging from 93% to 97.37%. The SVM and Random Forest models achieved the highest accuracy, F1-score, recall, and precision values, making them the most effective approaches for breast cancer detection. These models successfully classified benign and malignant tumours, reducing unnecessary treatments and improving patient safety. Additionally, the research reviewed other studies in the field of breast cancer detection using machine learning. These studies highlighted the potential of uncertain expert systems, deep learning models, microarray analysis, and multi-classifier approaches to enhance breast cancer diagnosis and prognosis prediction. The findings of this research have significant implications for healthcare. SVM and Random Forest, as machine learning techniques, can be leveraged to develop accurate and efficient breast cancer detection systems. Implementing these models in clinical practice can improve early detection rates, minimize unnecessary surgeries, and enhance patient outcomes. This research contributes to the existing knowledge on breast cancer detection using machine learning techniques and offers valuable insights into the most effective approach for improving early diagnosis and treatment outcomes for breast cancer patients.