Machine Learning in Oncology: A Comparative Study of Algorithms for Breast Cancer Prediction and Diagnosis
Keywords:
Breast Cancer Diagnosis, Machine Learning Algorithms, Oncology, Predictive Modeling, Comparative Analysis, Data-Driven Healthcare.Abstract
Breast cancer remains one of the leading causes of mortality among women globally, necessitating accurate and timely diagnosis to improve treatment outcomes. Machine learning (ML) has emerged as a transformative tool in oncology, offering potential for enhanced precision in breast cancer detection and prediction. This study conducts a comprehensive comparative assessment of various machine learning algorithms, including Support Vector Machines (SVM), Random Forest (RF), Gradient Boosting Machines (GBM), k-Nearest Neighbors (k-NN), and deep learning models. Using publicly available breast cancer datasets, we evaluate these algorithms based on accuracy, sensitivity, specificity, and computational efficiency. Our findings reveal significant variations in algorithm performance across different diagnostic scenarios, highlighting the strengths and limitations of each method. The study underscores the importance of selecting the appropriate ML model tailored to specific clinical and operational requirements. This work contributes to advancing data-driven methodologies in breast cancer diagnosis, paving the way for more reliable and scalable diagnostic solutions.