Development of Disease Prediction Model Based on Ensemble Learning Approach for Diabetes and Hypertension

Diabetes and hypertension are two of the most prevalent chronic diseases affecting a significant portion of the global population. Early detection and diagnosis are crucial for effective treatment and prevention. This project presents a disease prediction model developed using an ensemble learning approach to predict diabetes and hypertension. The model is trained on two separate datasets, one for diabetes and the other for hypertension, with health parameters like age, BMI, blood pressure, stress levels, and medication history. The ensemble learning techniques, including Random Forest, XGBoost, AdaBoost, and Voting Classifier, are employed to combine the predictions of multiple models, enhancing overall accuracy and reliability. The system is designed as a web application, where users can input their health data and receive predictions regarding their likelihood of having either of the conditions. The project aims to provide a useful tool for healthcare professionals and individuals for early detection and preventive measures.

Keywords: Diabetes, Hypertension, Ensemble Learning, Prediction Model, Random Forest, XGBoost, AdaBoost, Voting Classifier, Health Parameters, Early Detection.