Assessing the Effectiveness of Machine Learning Algorithms in Breast Cancer Classification

Abstract

By using massive datasets and sophisticated computational methods to discover patterns and correlations that may not be visible to human eyes, machine learning algorithms have tremendous promise for enhancing breast cancer risk assessment and detection. This research compares the performance of four machine learning algorithms on the original datasets for Wisconsin breast cancer: Support Vector Machine (SVM), Decision Tree (C4.5), Naive Bayes (NB), and k-Nearest Neighbors (k-NN). The primary goal is to evaluate the efficacy of each algorithm in terms of data classification accuracy, precision, sensitivity, and specificity. In terms of accuracy (97.13%) and error rate (lowest), experimental findings demonstrate that SVM delivers the best performance. The trials are carried out using the WEKA data mining tool in a simulated setting.