Breast cancer is the most prevalent cancer diagnosed and the basis of mortality among women worldwide. However, the early prognosis and treatment can avoid the death rate of the patients. Since the traditional method of detecting cancer is error-prone, machine learning has shown significant promise in aiding the accurate diagnosis. Moreover, using a minimal number of features is highly pertinent in decision-making. Therefore, this chapter proposes a novel evolutionary algorithm-based feature selection method to identify the most appropriate attributes. The suggested model fuses the Genetic Algorithm with Ant Colony Optimization to increase the search operation in the global search space. Finally, the Random Forest classifier is employed on the reduced attribute subset to examine and determine the nature of breast tumors. The developed system is evaluated on the Wisconsin Diagnostic Breast Cancer dataset. The experimental outcomes demonstrate the efficiency of the proposed method over other popular single algorithms and ensemble learners.