Greylag Goose Optimization for Diabetes Prediction: Feature Selection Meets Advanced Machine Learning

Diabetes mellitus remains a global health concern, necessitating both accurate and effective diagnostic methodologies. This condition presents a significant challenge due to the high dimensionality of clinical datasets and the inherent complexity of diabetes classification. To address this problem, this study integrates feature selection and machine learning architectures to enhance diabetes prediction accuracy. A novel framework based on the Binary Greylag Goose Optimization (bGGO) algorithm is proposed to optimize feature selection, thereby improving classification performance. A comprehensive evaluation uses multiple classifiers, including Decision Trees, k-nearest Neighbors, Support Vector Machines, Random Forests, and Multilayer Perceptron (MLP). The experimental results demonstrate that bGGO significantly enhances feature selection quality, improving classification metrics, particularly for MLP, which achieves the highest classification accuracy of 95.98%. These findings underscore the efficacy of combining metaheuristic optimization with machine learning for diabetes diagnosis, offering a scalable and interpretable approach for real-world healthcare applications. The proposed methodology contributes to more precise risk estimation and the development of individualized intervention strategies, facilitating early diagnosis and effective disease management.