Diabetes, characterized by elevated glucose levels, poses significant health risks, including heart problems, kidney issues, hypertension, and potential damage to various organs. Early detection and management are crucial to prevent severe complications. This paper aims to enhance the accuracy of diabetes prediction through the application of diverse machine learning techniques. By leveraging datasets collected from patients, machine learning classification and ensemble methods, such as K-Nearest Neighbour (KNN), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), Gradient Boosting (GB), and Random Forest (RF), will be employed. These models play a vital role in predicting diabetes, with varying accuracies. The project emphasizes the importance of identifying diabetes at an early stage for effective control. Notably, the results reveal that Random Forest outperforms other machine learning techniques, displaying its capability for highly accurate diabetes prediction. The findings underscore the significance of leveraging advanced machine learning methods to enhance predictive accuracy and, consequently, the effectiveness of diabetes management.
Diabetes, Machine, Learning, Prediction, Dataset, Ensemble
Ashna Merin Philip. Diabetes Prediction using Machine Learning Techniques. Indian Journal of Modern Research and Reviews. 2024; 2(3):01-06
Download PDF
