Diabetes Prediction for H1bac Based Machine Learning Classifiers

Diabetes is a chronic metabolic disorder characterized by elevated glucose levels in the human body. If left untreated, it can lead to serious health complications such as cardiovascular diseases, kidney damage, hypertension, vision problems, and may negatively affect multiple vital organs. Early detection plays a crucial role in preventing or controlling these complications. In this project, the aim is to perform early prediction of diabetes with higher accuracy by applying various Machine Learning techniques. Machine learning enables efficient prediction by constructing models from datasets collected from patients. In this work, several classification and ensemble methods are utilized to predict diabetes, including K-Nearest Neighbour (KNN), Decision Tree (DT), Random Forest (RF), AdaBoost, Naïve Bayes, and XGBoost. Each model exhibits different levels of accuracy when compared to one another. The findings of this study indicate that the XGBoost model achieves the highest accuracy among all techniques, demonstrating its effectiveness in predicting diabetes.