A Hybrid Firefly-Stacking Ensemble Model for Early Prediction of Type II Diabetes
InfoTech Spectrum: Iraqi Journal of Data Science · 30.06.2026 · 3 (2) · 13-24
DOI: 10.51173/ijds.v3i2.71 ↗Kurz gefasst
Fachartikel in der Zeitschrift InfoTech Spectrum: Iraqi Journal of Data Science, online erschienen am 30.06.2026. Verfasst von Michael Favour EDAFEAJIROKE und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben.
Themen: Diabetes mellitus
Abstract (Originalsprache)
The increasing global prevalence of Type II Diabetes (T2D) demands an advanced predictive model, as conventional machine learning algorithms perform poorly on such complex biomedical datasets. The proposed study aims to develop a trustworthy early prediction model by integrating the Firefly Algorithm (FA) for feature selection with a comparative stacking ensemble technique. The proposed methodology uses the large-scale Behavioral Risk Factor Surveillance System (BRFSS) dataset. The FA algorithm identified the optimal combination of 16 important features to train a stack ensemble of base models using a Meta Random Forest classifier. The most important results reveal that the FA-improved Meta Random Forest classifier achieved the best possible balance between accuracy and efficiency, with 88.68% accuracy, 83.26% sensitivity, and an AUC of 94.37%. It is concluded that the hybrid strategy is an efficient and effective approach to early risk stratification in T2D and addresses an important gap in predictive medicine by combining feature selection optimization and ensemble methods. The hybrid strategy provides a platform for future validation studies across different clinical datasets, enabling proactive, data-driven interventions.
Zitieren
APA
EDAFEAJIROKE, M. F., & Osubor, V. I. (2026). A Hybrid Firefly-Stacking Ensemble Model for Early Prediction of Type II Diabetes. InfoTech Spectrum: Iraqi Journal of Data Science, 3(2), 13-24. https://doi.org/10.51173/ijds.v3i2.71
Vancouver
EDAFEAJIROKE MF, Osubor VI. A Hybrid Firefly-Stacking Ensemble Model for Early Prediction of Type II Diabetes. InfoTech Spectrum: Iraqi Journal of Data Science. 2026;3(2):13-24. doi:10.51173/ijds.v3i2.71
BibTeX
@article{EDAFEAJIROKE2026,
author = {EDAFEAJIROKE, Michael Favour and Osubor, Veronica Ijebusomma},
title = {A Hybrid Firefly-Stacking Ensemble Model for Early Prediction of Type II Diabetes},
journal = {InfoTech Spectrum: Iraqi Journal of Data Science},
year = {2026},
volume = {3},
number = {2},
pages = {13--24},
doi = {10.51173/ijds.v3i2.71}
}
EUVIMED