Healthcare Effective Type-2 Diabetes Risk Prediction using Machine Learning Technique

Abstract

Type-2 Diabetes Mellitus is a chronic metabolic disorder that poses a significant global health burden due to its rising prevalence and associated complications. Early detection of individuals at high risk can significantly improve patient outcomes and reduce healthcare costs. This study proposes an effective machine learning-based approach for predicting the risk of Type-2 Diabetes using clinical and lifestyle data. Various supervised machine learning algorithms—including Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosting—are trained and evaluated on benchmark datasets such as the Pima Indian Diabetes Dataset. The system utilizes key features such as age, BMI, glucose level, blood pressure, and insulin levels for prediction. Feature selection and data preprocessing techniques like normalization, handling missing values, and balancing imbalanced data are employed to enhance model performance. Evaluation metrics including accuracy, precision, recall, F1-score, and ROC-AUC are used to assess the models