Diabetes Prediction using Machine Learning with Ensemble and Feature Selection Approaches

• Author(s): Divyanshu
• Paper ID: 1712845
• Page: 1168-1174
• Published Date: 15-12-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 6 December-2025

Abstract

Diabetes Mellitus is a long-term metabolic condition that can quietly damage the body if not identified in time. Early and reliable prediction helps patients receive timely lifestyle guidance and medical support, reducing the chances of serious complications such as kidney failure, heart disease, and nerve damage. In this work, we explore how machine learning can support early diabetes detection by analyzing patterns in patient health data. Using the PIMA Indian Diabetes dataset, we trained several well-known classification models including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and k-Nearest Neighbors. Instead of relying on a single model, we combined multiple models using an ensemble-based Voting Classifier, allowing the strengths of different algorithms to complement each other. The performance of each model was compared using standard evaluation measures such as accuracy, precision, recall, and F1-score. Our results show that the Voting Classifier provides more stable and accurate predictions than individual models. To make the system accessible, we also developed an easy-to-use Streamlit web application that allows users to input medical parameters and receive instant prediction results. This work demonstrates how ensemble learning can improve diabetes risk assessment and supports the development of user-friendly digital health tools. In the future, the system can be expanded to include larger datasets and additional clinical factors to further enhance prediction reliability.

Keywords

Diabetes Prediction, Ensemble Learning, Machine Learning, Voting Classifier, Healthcare Application, Streamlit, PIMA Dataset.

Citations

IRE Journals:
Divyanshu "Diabetes Prediction using Machine Learning with Ensemble and Feature Selection Approaches" Iconic Research And Engineering Journals Volume 9 Issue 6 2025 Page 1168-1174 https://doi.org/10.64388/IREV9I6-1712845

IEEE:
Divyanshu "Diabetes Prediction using Machine Learning with Ensemble and Feature Selection Approaches" Iconic Research And Engineering Journals, 9(6) https://doi.org/10.64388/IREV9I6-1712845