Diabetes Prediction Using Machine Learning

Abstract

Diabetes is one of the most common chronic diseases affecting people globally. It occurs when the body is unable to 
properly regulate blood sugar levels, leading to severe health complications such as heart disease, kidney failure, and 
nerve damage. Early detection of diabetes plays a crucial role in controlling the disease and preventing long-term 
complications. 
In this project, a Machine Learning-based approach is used to predict whether a person is diabetic or not. The model 
is built using the Support Vector Machine (SVM) algorithm with a linear kernel, which is highly effective for 
classification problems. The dataset used consists of various medical parameters such as glucose level, blood pressure, 
insulin level, Body Mass Index (BMI), age, and other relevant health attributes. 
The system includes data preprocessing, feature scaling using Standard Scaler, and model training and testing using 
split datasets. The trained model is deployed through a Django web application, allowing users to enter their health 
details and instantly receive diabetes prediction results. The system also stores patient records for future reference and 
monitoring. 
This project demonstrates how Machine Learning can be effectively applied in healthcare to support early diagnosis, 
improve clinical decision-making, and enhance patient care through accurate and efficient diabetes prediction.