PREDICTING TYPE-2 DIABETES THROUGH MACHINE LEARNING METHODS

Abstract

Diabetes is one of the most common chronic diseases worldwide and early detection is essential to prevent severe health complications such as heart disease, kidney failure, and vision loss. The increasing availability of healthcare data has enabled the use of machine learning techniques to assist in accurate disease prediction. This project focuses on developing a diabetes prediction system using multiple machine learning algorithms applied to medical datasets. The proposed system utilizes the PIMA Indian Diabetes Dataset, which contains several medical attributes such as pregnancies, glucose level, blood pressure, skin thickness, insulin level, body mass index (BMI), diabetes pedigree function, and age. The dataset is preprocessed and used to train different machine learning models including K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The trained models analyze patient data and predict whether a person is diabetic or non-diabetic. A webbased interface is developed where users can input medical parameters and receive instant prediction results. Experimental results show that ensemble models such as Random Forest provide higher prediction accuracy and precision compared to other algorithms. The proposed system demonstrates that machine learning can effectively support early diabetes detection and assist healthcare professionals in clinical decision-making.