Evaluative Comparison of Machine Learning Algorithms for Precision Diagnosis in Breast Cancer

Abstract

Breast cancer remains a prominent issue in worldwide public health, exhibiting a gender disparity that primarily impacts women. This study systematically evaluates the diagnostic capabilities of various machine learning algorithms in predicting breast cancer recurrences. Utilising a dataset of 569 data points, the algorithms scrutinised include Artificial Neural Networks (ANN), Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), XGBoost (XGB), Logistic Regression (LR), and K-Nearest Neighbours (KNN). Principal Component Analysis (PCA) was applied and employed with the algorithmic evaluation for selecting features and reducing dimensionality. The study utilised multiple evaluative metrics, focusing on Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values. The findings suggest that Logistic Regression and Support Vector Machines performed better than the other algorithms. Specifically, Logistic Regression achieved an AUC value of 99.77%, and Support Vector Machines achieved an AUC value of 99.74%. Additionally, these algorithms demonstrated an accuracy rate of 97.37%, precision of 97.62%, recall of 95.35%, F1 score of 96.47%, and Cohen's Kappa coefficient of 94.37%, consistent. The study suggests potential avenues for further investigation into the utility of machine learning algorithms and dimensionality reduction techniques in diagnosing breast cancer recurrence. These preliminary findings have the potential to make a valuable contribution to the current discourse around the use of machine learning technologies within healthcare environments