Precision Measurement and Feature Selection in Medical Diagnostics using Hybrid Genetic Algorithm and Support Vector Machine

The rapid development of intelligent systems has had a significant impact on healthcare, forensics, and medicine, offering innovative solutions to critical problems. Breast cancer, which affects a large number of women each year, requires effective methods for early detection and accurate diagnosis to improve patient outcomes. This study introduces a hybrid feature selection method based on genetic algorithm (GA) and Bucket of Models (BoM) approach to improve breast cancer detection and classification. In the proposed method, GA is used to identify the most relevant features from the breast cancer diagnosis data, to improve the efficiency of the classification process. BoM is then used to select the optimal classification model from a set of candidates, to further improve the accuracy of diagnosis. The support vector machine (SVM) is used as the primary classifier due to its robustness in classifying medical data. The GA feature selection process includes encoding chromosomes, initializing the population, evaluating fitness, and iterating through reproduction steps, that systematically evaluate and select the most informative features for breast cancer diagnosis. In this study, a breast cancer detection accuracy of 97.16 % was achieved, which is a superior performance compared to existing state-of-the-art methods. This study contributes to the development of more accurate and efficient breast cancer screening tools to help healthcare providers make informed diagnostic decisions.