Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)

<Previous Article In Volume
Next Article In Volume>

Feature Selection Based Machine Learning for Non-invasive Type 2 Diabetes Detection

Authors
Mohammed El Amine Mihoubi1, *, Abderrahmane Sider1, Kamal Amroun1
1University of Bejaia, Faculty of Exact Sciences, Laboratory of Medical Informatics and Intelligent and Dynamic Environments (LIMED), 06000, Bejaia, Algeria
*Corresponding author. Email: mohammed.mihoubi@univ-bejaia.dz
Corresponding Author
Mohammed El Amine Mihoubi
Available Online 5 August 2025.
DOI
10.2991/978-94-6463-805-9_17How to use a DOI?
Keywords
Type 2 Diabetes; Machine Learning; Classification; Random Forest; Feature Selection; Cross-Validation; Hyperparameter Optimization
Abstract

Early detection of Type 2 Diabetes Mellitus (T2D) is crucial for mitigating complications. Current diagnostic methods remain invasive, costly, and inaccessible in resource-limited settings. This paper explores machine learning (ML) for a non-invasive T2D screening, focusing on the impact of feature selection. Three feature selection techniques, Mutual Information, XGB importance, and ANOVA FTest, were applied to optimize a Random Forest (RF) classifier using a 1000-iteration randomized grid search optimized hyperparameters. Results indicate that ANOVA-based selection provided the most stable and accurate results while mitigating overfitting, achieving the highest AUC-ROC (0.785). These findings underscore the critical role of feature selection in non-invasive T2D screening, offering scalable and cost-effective solutions.

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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)
Series
Advances in Intelligent Systems Research
Publication Date
5 August 2025
ISBN
978-94-6463-805-9
ISSN
1951-6851
DOI
10.2991/978-94-6463-805-9_17How to use a DOI?
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.

Cite this article

risenwbib
TY  - CONF
AU  - Mohammed El Amine Mihoubi
AU  - Abderrahmane Sider
AU  - Kamal Amroun
PY  - 2025
DA  - 2025/08/05
TI  - Feature Selection Based Machine Learning for Non-invasive Type 2 Diabetes Detection
BT  - Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)
PB  - Atlantis Press
SP  - 149
EP  - 155
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-805-9_17
DO  - 10.2991/978-94-6463-805-9_17
ID  - Mihoubi2025
ER  -