Exploring Machine Learning Algorithms for Enhanced Diagnosis of Breast Cancer : A Comparative Study

Abstract

Breast cancer remains a significant global health concern, necessitating accurate and efficient diagnostic methods for timely intervention and treatment. This study investigates the efficacy of various machine learning algorithms in diagnosing breast cancer based on clinical data. Leveraging a comprehensive dataset comprising demographic information, medical history, and diagnostic features, we employ supervised learning techniques to train and evaluate multiple classifiers. Through a comparative analysis, we assess the performance of popular machine learning algorithms including logistic regression, support vector machines, decision trees, random forests, and neural networks. Evaluation metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC) are utilized to quantify the diagnostic capabilities of each model. Our results demonstrate promising performance across the evaluated algorithms, with some exhibiting superior accuracy and predictive power compared to others. Furthermore, we explore feature importance to gain insights into the characteristics influencing the classification process. This research contributes to the growing body of literature on utilizing machine learning for medical diagnosis, offering valuable insights for developing robust and accurate tools for detecting breast cancer.