Diabetes Prediction System Using Machine Learning Techniques

Abstract

Introduction: Diabetes mellitus is a chronic metabolic disorder caused by high blood glucose levels and insufficient insulin production. If left untreated, it may lead to severe complications such as cardiovascular disease, kidney failure, nerve damage, and vision loss. Early detection of diabetes plays a crucial role in preventing these complications and improving patient outcomes.

Objectives: The objective of this study is to develop a predictive system using machine learning techniques to identify diabetic patients at an early stage with higher accuracy.

Methods: The study uses the Pima Indians Diabetes Dataset obtained from the UCI Machine Learning Repository. Several supervised learning algorithms including Logistic Regression, Support Vector Machine, Decision Tree, K-Nearest Neighbor, Random Forest, and Gradient Boosting were applied. Data preprocessing techniques such as missing value removal, normalization, and dataset splitting were performed prior to model training.

Results: Experimental analysis shows that ensemble models outperform individual classifiers. Among all algorithms, the Random Forest classifier achieved the highest prediction accuracy, demonstrating its effectiveness for diabetes prediction.

Conclusions: Machine learning-based predictive models can significantly support healthcare professionals in early diabetes detection and clinical decision-making. The proposed system can be extended for real-time healthcare applications.