Diabetes Management Through Glucose Dynamics Analysis Network: A Novel Approach for Accurate Blood Glucose Level Forecasting
Diabetes, Obesity and Metabolism · 2026
DOI: 10.1111/dom.70930 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diabetes, Obesity and Metabolism, 2026. Verfasst von Pallavi M Sawant und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, Maharashtra, India. Hauptthemen laut MEDLINE: Blood Glucose, Diabetes Mellitus, Diabetes Mellitus, Type 1. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben.
Themen: Diabetes mellitus
Abstract (Originalsprache)
Background
Accurate real‐time prediction of blood glucose (BG) levels is essential for improving insulin‐dosing decision support systems, including closed‐loop insulin delivery and bolus calculators. However, existing deep learning models often suffer from high computational complexity, limited utilization of physiological factors, and inadequate handling of temporal glucose dependencies.
Methods
This study proposes Glucose Dynamics Analysis Network (GlucoDiaNet), a hybrid framework for BG prediction integrating spline interpolation for missing value handling, a Dilated Convolutional Residual Network (DilaConv‐ResNet) for spatial‐temporal feature extraction, Adamax optimization for feature selection and hyperparameter tuning, and a Bidirectional Long Short‐Term Memory network for bidirectional sequence learning. The model was evaluated using the OhioT1DM dataset across multiple prediction horizons ranging from 30 to 60 min.
Results
At the 30‐min prediction horizon, GlucoDiaNet achieved a Root Mean Squared Error (RMSE) of 5.2435 mg/dL, Mean Absolute Error (MAE) of 4.3622 mg/dL, R 2 value of 0.9948, and Mean Squared Error (MSE) of 29.3056. The proposed model consistently outperformed baseline models including LSTM, GRU, and TCN across both short‐ and long‐term forecasting tasks while maintaining robust predictive performance at extended prediction intervals.
Conclusion
GlucoDiaNet effectively enhances blood glucose prediction by integrating efficient preprocessing, deep temporal modeling, and optimization strategies. The proposed framework demonstrates strong potential for future deployment in real‐time and wearable diabetes monitoring systems, subject to further hardware‐level validation and computational efficiency analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Electronics, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, Maharashtra, India.
- Department of Electronics and Telecommunication, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, Maharashtra, India.
ORCID-Profile: Pallavi M Sawant
Zitieren
APA
Sawant, P. M., & Ghongade, R. B. (2026). Diabetes Management Through Glucose Dynamics Analysis Network: A Novel Approach for Accurate Blood Glucose Level Forecasting. Diabetes, Obesity and Metabolism. https://doi.org/10.1111/dom.70930
Vancouver
Sawant PM, Ghongade RB. Diabetes Management Through Glucose Dynamics Analysis Network: A Novel Approach for Accurate Blood Glucose Level Forecasting. Diabetes, Obesity and Metabolism. 2026. doi:10.1111/dom.70930
BibTeX
@article{Sawant2026,
author = {Sawant, Pallavi M and Ghongade, Rajesh B},
title = {Diabetes Management Through Glucose Dynamics Analysis Network: A Novel Approach for Accurate Blood Glucose Level Forecasting},
journal = {Diabetes, Obesity and Metabolism},
year = {2026},
doi = {10.1111/dom.70930}
}
EUVIMED