Improving human brucellosis susceptibility mapping using effective and simultaneously metaheuristic-based feature selection and hyperparameter tuning

Abstract

Human Brucellosis, a neglected zoonotic disease, affects 1.6 to 2.1 million people globally each year. In Iran, it has become a significant health concern, with an average annual incidence rate of 19.91 cases per 100,000 people. This study aims to create a reliable Human Brucellosis Susceptibility Map (HBSM) for Mazandaran Province using a hybrid machine learning approach that enhances performance through metaheuristic algorithms for feature and hyperparameter optimization. A transformation function is integrated into these algorithms to reduce computational and time complexities while simultaneously executing feature selection and hyperparameter tuning. Additionally, a two-phase mutation operator is employed to improve the performance of feature selection. The results indicate that the hybrid model of Support Vector Regression-Transformation Mutation Grey Wolf Optimizer (SVR-TMGWO) outperformed other models, achieving RMSE=0.7723, MAE=0.614, MdAE=0.473, and R = 0.536. The predicted HBSM for 2018 identified 68 rural districts in Mazandaran Province as being in the High and Very High susceptibility classes. The susceptibility map can help decision-makers more effectively prevent, control, and manage Human Brucellosis in Mazandaran Province.