Ensemble Learning for Diabetes Prediction: An Integration of TabNet and Neural Oblivious Decision Ensembles (NODE)
Engineering, Technology & Applied Science Research · 08.12.2025 · 15 (6) · 30426-30431
DOI: 10.48084/etasr.15192 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 08.12.2025. Verfasst von Majid Rahardi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Diabetes mellitus
Abstract (Originalsprache)
The accurate prediction of diabetes risk is paramount for advancing healthcare and personalized medicine. This study presents a comparative analysis of advanced deep learning models for structured data, focusing on two novel architectures, Neural Oblivious Decision Ensembles (NODE) and TabNet. The method encompasses comprehensive data preprocessing, including a critical technique to address the imbalanced nature of the dataset (oversampling). Finally, a combined modeling approach (a soft-voting ensemble) was implemented to combine the predictive probabilities from the trained individual models. The soft-voting ensemble demonstrated strong performance, achieving a validation accuracy of 93.55, a precision of 92.60, a recall of 94.58, and an F1-score of 93.58. These findings underscore the potential of advanced deep learning techniques, especially when combined in an ensemble, to provide highly reliable and accurate diabetes risk prediction from complex tabular data.
Zitieren
APA
Rahardi, M., Abdulloh, F. F., Masruro, A., Asaddulloh, B. P., Aminuddin, A., & Sholihah, N. (2025). Ensemble Learning for Diabetes Prediction: An Integration of TabNet and Neural Oblivious Decision Ensembles (NODE). Engineering, Technology & Applied Science Research, 15(6), 30426-30431. https://doi.org/10.48084/etasr.15192
Vancouver
Rahardi M, Abdulloh FF, Masruro A, Asaddulloh BP, Aminuddin A, Sholihah N. Ensemble Learning for Diabetes Prediction: An Integration of TabNet and Neural Oblivious Decision Ensembles (NODE). Engineering, Technology & Applied Science Research. 2025;15(6):30426-30431. doi:10.48084/etasr.15192
BibTeX
@article{Rahardi2025,
author = {Rahardi, Majid and Abdulloh, Ferian Fauzi and Masruro, Ahlihi and Asaddulloh, Bima Pramudya and Aminuddin, Afrig and Sholihah, Nafiatun},
title = {Ensemble Learning for Diabetes Prediction: An Integration of TabNet and Neural Oblivious Decision Ensembles (NODE)},
journal = {Engineering, Technology & Applied Science Research},
year = {2025},
volume = {15},
number = {6},
pages = {30426--30431},
doi = {10.48084/etasr.15192}
}
EUVIMED