A Personalized, Non-Invasive Blood Glucose Prediction System Using a CNN-LSTM Model with a Sim-to-Real Transfer Learning Strategy
Corresponding author: Komal Dandge
Abstract
The translation of Non-Invasive Glucose Monitoring (NIBGM) into routine clinical care is currently hindered by two significant engineering hurdles: the inherently weak signal fidelity, characterized by a low Signal-to-Noise Ratio (SNR), in optical sensors, and the "Cold Start" constraint common in deep learning applications. Traditional recursive architectures, such as Long Short-Term Memory networks (LSTMs), often struggle to generalize in data-sparse contexts typical of personalized medicine. To address these limitations, this study presents the Hybrid Temporal-Attention Network (HTAN), a novel framework that disentangles sensor artifacts from metabolic trends by integrating Residual Convolutional Neural Networks (CNNs) with Bi-directional LSTMs and Multi-Head Attention mechanisms. The validity of this architecture was assessed using a "Dual-Stream" protocol, with pre-training on a high-precision "Chaos-Augmented" Digital Twin ( samples) followed by benchmarking against three distinct real-world clinical cohorts ( ). Our analysis reveals a significant performance divergence by phenotype: while conventional Random Forest models achieve adequate accuracy for stable Type 2 Diabetes (MARD = 6.18%), the HTAN model exhibits superior robustness in high-volatility Type 1 Diabetes scenarios. Notably, on the complex Shanghai T1DM dataset (N=7), standard Bi-LSTMs struggled to track the dynamics effectively (Mean Absolute Relative Difference, MARD = 8.65%), whereas HTAN achieved a markedly lower MARD of 5.11%. These results indicate that attention-based methodologies, when initialized with synthetic physiological priors, offer a viable approach to modelling intricate metabolic instability in regimes with limited data.
Keywords:
Biomedical signal processing, deep learning, digital twin, glucose monitoring, hybrid neural networks, time-series forecastingDownloads
References
International Diabetes Federation. "IDF Diabetes Atlas, 10th edition." IDF Diabetes Atlas. https://diabetesatlas.org
S. K. Vashist, "Non-invasive glucose monitoring technology in diabetes management: a review," Analytica Chimica Acta, vol. 750, pp. 16–27, Oct. 2012.
N. Uluç et al., "Non-invasive measurements of blood glucose levels by time-gating mid-infrared optoacoustic signals," Nature Metabolism, vol. 6, no. 4, pp. 678–686, Apr. 2024.
S. Ghimire, T. Celik, M. Gerdes, and C. W. Omlin, "Deep learning for blood glucose level prediction: How well do models generalize across different data sets?," PLOS ONE, vol. 19, no. 9, 2024, Art. no. e0310801.
M. R. Vahedi et al., "Predicting Glucose Levels in Patients with Type1 Diabetes Based on Physiological and Activity Data," in Proceedings of the 8th ACM MobiHoc 2018 Workshop on Pervasive Wireless Healthcare Workshop, Mar. 2018, pp. 1–5.
Q. Sun, M. V. Jankovic, L. Bally, and S. G. Mougiakakou, "Predicting Blood Glucose with an LSTM and Bi-LSTM Based Deep Neural Network," in 2018 14th Symposium on Neural Networks and Applications (NEUREL), Aug. 2018, pp. 1–5.
H. Butt, I. Khosa, and M. A. Iftikhar, "Feature Transformation for Efficient Blood Glucose Prediction in Type 1 Diabetes Mellitus Patients," Diagnostics, vol. 13, no. 3, Jan. 2023, Art. no. 340.
Q. Bian, A. As’arry, X. Cong, K. A. bin M. Rezali, and R. M. K. bin R. Ahmad, "A hybrid Transformer-LSTM model apply to glucose prediction," PLOS ONE, vol. 19, no. 9, 2024, Art. no. e0310084.
M. P. Barbato, G. Rigamonti, D. Marelli, and P. Napoletano, "Lightweight Sequential Transformers for Blood Glucose Level Prediction in Type-1 Diabetes," IEEE journal of biomedical and health informatics, vol. PP, Nov. 2025.
T. Zhu, T. Chen, L. Kuang, J. Zeng, K. Li, and P. Georgiou, "Edge-Based Temporal Fusion Transformer for Multi-Horizon Blood Glucose Prediction," in 2023 IEEE International Symposium on Circuits and Systems (ISCAS), Feb. 2023, pp. 1–5.
A. Hina and W. Saadeh, "Noninvasive Blood Glucose Monitoring Systems Using Near-Infrared Technology—A Review," Sensors, vol. 22, no. 13, June 2022, Art. no. 4855.
H. M. C. Leung, G. P. Forlenza, T. O. Prioleau, and X. Zhou, "Noninvasive Glucose Sensing In Vivo," Sensors, vol. 23, no. 16, Aug. 2023, Art. no. 7057.
M. Zeynali, K. Alipour, B. Tarvirdizadeh, and M. Ghamari, "Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML," Scientific Reports, vol. 15, no. 1, Jan. 2025, Art. no. 581.
R. N. Bergman, L. S. Phillips, and C. Cobelli, "Physiologic evaluation of factors controlling glucose tolerance in man: measurement of insulin sensitivity and beta-cell glucose sensitivity from the response to intravenous glucose.," Journal of Clinical Investigation, vol. 68, no. 6, pp. 1456–1467, Dec. 1981.
Y. Zhang et al., "Motion Artifact Reduction for Wrist-Worn Photoplethysmograph Sensors Based on Different Wavelengths," Sensors, vol. 19, no. 3, Feb. 2019, Art. no. 673.
L. Alzubaidi et al., "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions," Journal of Big Data, vol. 8, no. 1, Mar. 2021, Art. no. 53.
T. Zhu, K. Li, P. Herrero, and P. Georgiou, "Personalized Blood Glucose Prediction for Type 1 Diabetes Using Evidential Deep Learning and Meta-Learning," IEEE transactions on bio-medical engineering, vol. 70, no. 1, pp. 193–204, Jan. 2023.
B. P. Kovatchev, M. Breton, C. D. Man, and C. Cobelli, "In silico preclinical trials: a proof of concept in closed-loop control of type 1 diabetes," Journal of Diabetes Science and Technology, vol. 3, no. 1, pp. 44–55, Jan. 2009.
C. Dalla Man, R. A. Rizza, and C. Cobelli, "Meal simulation model of the glucose-insulin system," IEEE transactions on bio-medical engineering, vol. 54, no. 10, pp. 1740–1749, Oct. 2007.
S. Ahmad, C. M. Ramkissoon, A. Beneyto, I. Conget, M. Giménez, and J. Vehi, "Generation of Virtual Patient Populations That Represent Real Type 1 Diabetes Cohorts," Mathematics, vol. 9, no. 11, May 2021, Art. no. 1200.
W. Liu, T. Chen, B. Liang, Y. Wang, and H. Jin, "In-silico evaluation of an artificial pancreas achieving automatic glycemic control in patients with type 1 diabetes," Frontiers in Endocrinology, vol. 14, 2023, Art. no. 1115436.
J. M. Lee, R. Pop-Busui, J. M. Lee, J. Fleischer, and J. Wiens, "Shortcomings in the Evaluation of Blood Glucose Forecasting," IEEE Transactions on Biomedical Engineering, vol. 71, no. 12, pp. 3424–3431, Sept. 2024.
J. P. Cohen, M. Luck, and S. Honari, "Distribution Matching Losses Can Hallucinate Features in Medical Image Translation," in Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, 2018, pp. 529–536.
C. Marling and R. Bunescu, "The OhioT1DM Dataset for Blood Glucose Level Prediction: Update 2020," CEUR workshop proceedings., vol. 2675, pp. 71–74, Sept. 2020.
Q. Zhao et al., "Chinese diabetes datasets for data-driven machine learning," Scientific Data, vol. 10, no. 1, Jan. 2023, Art. no. 35.
C. Piao et al., "GARNN: An interpretable graph attentive recurrent neural network for predicting blood glucose levels via multivariate time series," Neural Networks, vol. 185, May 2025, Art. no. 107229.
M. Sirlanci, M. E. Levine, C. C. Low Wang, D. J. Albers, and A. M. Stuart, "A simple modeling framework for prediction in the human glucose-insulin system," Chaos, vol. 33, no. 7, July 2023, Art. no. 073150.
R. Rastogi, M. Bansal, N. Kumar, S. Singla, P. Singla, and R. A. Jaswal, "Effective Diabetes Prediction using an IoT-based Integrated Ensemble Machine Learning Framework," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20064–20070, Feb. 2025.
Downloads
How to Cite
License
Copyright (c) 2026 Komal Dandge, Manisha Kumawat, Parul Jadhav
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
