Abstract

Diabetes Mellitus is a chronic disease that affects millions of people worldwide and is known to cause an increase in blood sugar levels. The main objective of this study is to build a model that can accurately predict the early stages of diabetes and reduce the risk associated with it. To achieve this goal, several supervised machine learning algorithms such as Support Vector Machines, Decision Trees, K-Nearest Neighbors, and Logistic Regression have been employed. Additionally, ensemble techniques like Random Forest have been used to improve the accuracy of the machine learning models for the PIMA diabetes dataset, which is widely used for diabetes prediction. To further enhance the accuracy of the model, LGBM Feature Selector have been utilized. Moreover, Grasshopper Optimization, a metaheuristic optimization algorithm, has been employed to optimize the machine learning models. This study provides a comprehensive and effective method for diabetes prediction using machine learning and optimization techniques, which can be beneficial for healthcare professionals and researchers in the field of diabetes management