Enhancing breast cancer risk prediction through comprehensive ensemble machine learning analysis: a study on clinical, genetic, and demographic factors

Breast cancer is a major worldwide health problem, and early risk assessment plays a crucial role in improving patient outcomes. In this study, we employ supervised machine learning techniques to comprehensively analyse and predict breast cancer risk. Leveraging a diverse dataset comprising clinical, genetic, and demographic factors, explore the predictive power of machine learning algorithms. Our comprehensive analysis delves into feature selection, model evaluation, and performance optimisation. The proposed ensemble model has been validated on Wisconsin Breast Cancer Diagnostic medical dataset. The importance of this research in the context of improved patient care, screening programs, and risk assessment tools. It contributes to the ongoing effort to enhance breast cancer risk prediction through advanced data-driven methods, paving the way for more effective preventive strategies and early interventions. It show that effective data pre-processing performed to the raw data and feature selection the model resulted in an enhanced accuracy of 98.24%.