Advancing breast cancer prediction: machine learning, data balancing, and ant colony optimization

Abstract

Breast cancer constitutes a significant threat to women's health worldwide. The World Health Organization (WHO) reports around 2.3 million new cases each year, making this disease the primary reason for cancer-related fatalities among women. In light of this alarming situation, developing innovative tools for early detection and optimal treatment is imperative, as it directly addresses the pressing need to enhance our capabilities in the quest to overcome breast cancer. This study fits in with this approach, introducing a comparative assessment of multiple machine learning algorithms and integrating data preprocessing, data balancing and feature selection techniques. The studied Coimbra dataset, composed of 116 records and including 10 medical characteristics, exhibited promising performance in all classification metrics, reaching an accuracy of 89.74%, and an area under the receiver operating characteristic curve (AUC-ROC) of 89.68%. These findings highlight the significant potential of our approaches to improve breast cancer treatment and detection systems, providing health practitioners with more efficient resources.