GlucoNet ‐ MM : A multimodal attention‐based multi‐task learning framework with decision transformer for personalised and explainable blood glucose forecasting
Diabetes, Obesity and Metabolism · 2025-12 · 27 (12) · 7416-7430
DOI: 10.1111/dom.70147 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diabetes, Obesity and Metabolism, online erschienen am 22.09.2025. Verfasst von Sarmad Maqsood und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania. Hauptthemen laut MEDLINE: Blood Glucose, Precision Medicine, Deep Learning, Diabetes Mellitus. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: Lietuvos Mokslo Taryba.
Abstract (Originalsprache)
Aims
Accurate and personalized blood glucose prediction is critical for proactive diabetes management. Conventional machine learning (ML) models often struggle to generalize across patients due to individual variability, nonlinear glycemic dynamics, and sparse multimodal input data. This study aims to develop an advanced, interpretable deep learning (DL) framework for patient‐specific, policy‐aware blood glucose forecasting. Materials and Methods We propose GlucoNet‐MM, a novel multimodal DL framework that combines attention‐based multi‐task learning (MTL) with a Decision Transformer (DT), a reinforcement learning paradigm that frames policy learning as sequence modeling. The model integrates heterogeneous physiological and behavioral data, continuous glucose monitoring (CGM), insulin dosage, carbohydrate intake, and physical activity, to capture complex temporal dependencies. The MTL backbone learns shared representations across multiple prediction horizons, while the DT module conditions future glucose predictions on desired glycemic outcomes. Temporal attention visualizations and integrated gradient‐based attribution methods are used to provide interpretability, and Monte Carlo dropout is employed for uncertainty quantification.
Results
GlucoNet‐MM was evaluated on two publicly available datasets, BrisT1D and OhioT1DM. The model achieved R 2 scores of 0.94 and 0.96 and mean absolute error (MAE) values of 0.031 and 0.027, respectively. These results outperform single‐modality and conventional non‐adaptive baseline models, demonstrating superior predictive accuracy and generalizability.
Conclusion
GlucoNet‐MM represents a promising step toward intelligent, personalized clinical decision support for diabetes care. Its multimodal design, policy‐aware forecasting, and interpretability features enhance both prediction accuracy and clinical trust, enabling proactive glycemic management tailored to individual patient needs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania.
- Centre of Real Time Computer Systems, Faculty of Informatics, Kaunas University of Technology, Kaunas University of Technology, Kaunas, Lithuania.
- Department of Intensive Care, University of Health Sciences, Kaunas, Lithuania.
ORCID-Profile: Sarmad Maqsood
Förderung
- Lietuvos Mokslo Taryba
Zitieren
APA
Maqsood, S., Sarwar, M. A., Belousovienė, E., & Maskeliūnas, R. (2025). GlucoNet ‐ MM : A multimodal attention‐based multi‐task learning framework with decision transformer for personalised and explainable blood glucose forecasting. Diabetes, Obesity and Metabolism, 27(12), 7416-7430. https://doi.org/10.1111/dom.70147
Vancouver
Maqsood S, Sarwar MA, Belousovienė E, Maskeliūnas R. GlucoNet ‐ MM : A multimodal attention‐based multi‐task learning framework with decision transformer for personalised and explainable blood glucose forecasting. Diabetes, Obesity and Metabolism. 2025;27(12):7416-7430. doi:10.1111/dom.70147
BibTeX
@article{Maqsood2025,
author = {Maqsood, Sarmad and Sarwar, Muhammad Abdullah and Belousovienė, Egle and Maskeliūnas, Rytis},
title = {GlucoNet ‐ MM : A multimodal attention‐based multi‐task learning framework with decision transformer for personalised and explainable blood glucose forecasting},
journal = {Diabetes, Obesity and Metabolism},
year = {2025},
volume = {27},
number = {12},
pages = {7416--7430},
doi = {10.1111/dom.70147}
}
EUVIMED