Evaluation of Feature Transformation and Machine Learning Models on Early Detection of Diabetes Mellitus

DOI

10.2991/978-94-6463-718-2_52How to use a DOI?

Keywords

diabetes mellitus; early detection; feature transformation; machine learning; predictive modeling; ensemble learning; deep learning; hybrid models; data augmentation; non-invasive detection; feature engineering; scalability; interpretability; synthetic data; transformer models; healthcare solutions; clinical applications; diabetes prevention; predictive performance; generalizability

Abstract

Early detection of diabetes mellitus is imperative to decreasing complications and improving patient prognosis. In this study, we analysed the machine learning models and feature transformation techniques to predict diabetes at initial stages. This research tackles the significant issues of accuracy, scalability, and interpretability, using sophisticated techniques like feature engineering, hybrid models, and non-invasive signal processing. Although several of the comparative analyses reinforce the advantages of customized methods for certain diabetes classes, other novel techniques such as transformer-based models and ensemble learning have proven extensive improvements in prediction accuracy. With synthetic data and heterogeneous datasets, the proposed model maintains good generalizability in various clinical scenarios. It helps to reduce the disconnect between academia and industry, offering diabetes prevention and management solutions that can be scaled and implemented across healthcare settings.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, 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 changes were made.

Download article (PDF)

TY  - CONF
AU  - K. Meiyalazhan
AU  - K. S. Nishanth
AU  - M. Pradeep Sudharshan
AU  - P. Priyadharshini
AU  - M. Jayanthi
AU  - U. Kasthuri
PY  - 2025
DA  - 2025/05/23
TI  - Evaluation of Feature Transformation and Machine Learning Models on Early Detection of Diabetes Mellitus
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 596
EP  - 611
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_52
DO  - 10.2991/978-94-6463-718-2_52
ID  - Meiyalazhan2025
ER  -