Comparative Analysis of Machine Learning Algorithms for Breast Cancer Diagnosis

Breast cancer remains a significant health challenge globally, driving the need for accurate and efficient diagnostic tools. Machine learning (ML) algorithms have gained prominence in enhancing breast cancer diagnosis by analyzing complex medical data. This review offers a comparative analysis of several ML algorithms, including Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), k-Nearest Neighbors (k-NN), and Artificial Neural Networks (ANN), with a focus on their application in breast cancer diagnosis. The study also examines the role of feature selection techniques, such as Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA), in improving the performance of these algorithms. Performance metrics like accuracy, sensitivity, specificity, and computational efficiency are used to evaluate the algorithms. The findings indicate that while ANN and RF excel in accuracy, feature selection techniques significantly enhance the performance of simpler models like SVM and DT by reducing dimensionality and improving interpretability. This review underscores the importance of integrating feature selection in ML models to optimize diagnostic accuracy and efficiency.