Enhancing Diabetes Prediction with Hybrid Ensemble Learning: A Comparative Evaluation of Traditional and Innovative Models

DOI

10.2991/978-94-6239-768-2_23How to use a DOI?

Keywords

Diabetes prediction; Machine learning models; Hybrid Forest Boosting; Gradient Boosting; Logistic Regression; Random Forest; SVM; Feature importance; Cross-validation

Abstract

There are sixty million people who have diabetes in the world today, and they all have a condition that if left untreated can eventually cause blind ness, kidney failure and other cardiac diseases. In predicting diabetes, this study undertakes a comparative analysis of the different machine learning methods. It develops a new model, the Hybrid Forest-Boosting which is a union of Random Forest and Gradient Boosting despite the fact that the later has the highest accuracy level. The hybrid model is regarded more as a powerful tool when used in clinical practice since it demonstrated much higher reliability and accuracy, comparable to gradient boosting. The avoiding diabetes classification model was concluded to be interpretable and usable for early diabetes prevention because the feature importance analysis reaffirmed crucial indices, including age, BMI, blood glucose, and HbA1c, as clinically important. These findings suggest the Hybrid Forest-Boosting model as a reliable, interpretable solution for diabetes prediction, outperforming traditional algorithms and addressing the need for clinically-relevant tools to tackle this global health challenge.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits any noncommercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if you modified the licensed material. You do not have permission under this license to share adapted material derived from this chapter or parts of it.

Download article (PDF)

TY  - CONF
AU  - Dhruv Bhatnagar
AU  - Preety Shoran
AU  - Vidushi Vidushi
PY  - 2026
DA  - 2026/09/07
TI  - Enhancing Diabetes Prediction with Hybrid Ensemble Learning: A Comparative Evaluation of Traditional and Innovative Models
BT  - Proceedings of the Third International Conference on Recent Advances in Computing Sciences (RACS 2025)
PB  - Atlantis Press
SP  - 212
EP  - 226
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-768-2_23
DO  - 10.2991/978-94-6239-768-2_23
ID  - Bhatnagar2026
ER  -