Breast Cancer Diagnosis Using Machine Learning and PSO

Healthcare systems around the world are facing huge challenges in responding to trends of the rise of chronic diseases. Early detection of breast cancer is essential for successful treatment since it is a common and potentially fatal condition. Based on clinical data, machine learning algorithms have shown potential in the categorization of breast cancer. This work aimed to build classification models Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Random Forest (RF), Logistic Regression (LR), and Artificial Neural Network (ANN) for Diagnostic Wisconsin Breast Cancer Dataset (WDBC) also improves classifier performance by using feature selection optimization and cross validation. The Particle Swarm Optimization (PSO) technique is used to select relevant, irredundant and most informative features that dependent on the performance of a classifier utilizing certain characteristics. The effectiveness of five distinct classifiers is assessed in this work. According to the findings, PSO-based SVM classifier has the greatest mean subset accuracy over a wide variety of training testing ratios.