DCRNet: Hybrid Deep Learning Architecture for Forecasting of Blood Glucose

Ketan Lad; Maulin Joshi

doi:10.35882/jeeemi.v8i1.1245

Ketan Lad Department of Electronics and Communication Engineering, Gujarat Technological University, Ahmedabad, Gujarat, India https://orcid.org/0000-0002-8794-974X
Maulin Joshi Department of Electronics and Communication, Sarvajanik College of Engineering and Technology, Gujarat, India https://orcid.org/0000-0002-6209-1708

DOI: https://doi.org/10.35882/jeeemi.v8i1.1245

Keywords: Dilated convolution, forecasting, Long Short-Term Memory, Blood Glucose, deep neural network, continuous glucose monitoring

Abstract

Maintaining blood glucose (BG) levels within the euglycemic range is essential for patients with type 1 diabetes (T1D) to prevent both hypoglycemia and hyperglycemia. Often, BG concentration changes due to unannounced carbohydrate intake during meals or an inappropriate amount of insulin dosage. Timely forecasting of BG can help take appropriate actions in advance to keep BG within the euglycemic range. Recent studies indicate that deep learning techniques have demonstrated improved performance in this field. Deep learning approaches often struggle to precisely predict future BG levels. To address these challenges, this paper introduces a novel hybrid deep learning architecture called DCRNet. This architecture incorporates a Dilated Convolution layer that effectively detects multi-scale patterns while minimizing parameter count. Additionally, it utilizes Long Short-Term Memory (LSTM) to handle contextual dependencies and maintain the temporal order of the extracted features. DCRNet predicts future BG levels for short-term durations (15, 30, and 60 minutes) using information on glucose, meals, and insulin dosages. The proposed architecture’s performance is evaluated on 11 simulated subjects from the UVA/Padova T1D Mellitus simulator and 12 actual subjects from the OhioT1DM dataset. In contrast to previous works, the proposed architecture achieves root mean square errors (RMSEs) of 3.42, 6.45, and 17.73 mg/dL for simulated subjects and 12.57, 20.72, and 34.41mg/dL for actual subjects, for prediction horizons (PH) of 15-, 30-, and 60-minute, respectively. The proposed architecture is also evaluated using the mean absolute error (MAE), which is 2.11, 4.47, and 11.78 mg/dL for simulated subjects and 7.9, 14.13, and 25.5 mg/dL for actual subjects, for 15-, 30-, and 60-minute PH. The experimental findings validate that the proposed architecture, which uses a dilated convolutional LSTM, outperforms other recent state-of-the-art models.

Downloads

Download data is not yet available.

Author Biography

Maulin Joshi, Department of Electronics and Communication, Sarvajanik College of Engineering and Technology, Gujarat, India

Dr. Maulin Joshi is a distinguished academic and faculty member at Sarvajanik College of Engineering and Technology (SCET), known for his expertise in the field of Electronics and Communication Engineering. With over 26 years of experience in academia, he holds the position of professor in the department and serves as the Dean of Academics. Dr. Joshi’s academic qualifications include a Ph.D., and he specializes in teaching subjects such as Signal Processing, Mobile Communication, Wireless Communication and Soft Computing Techniques. In addition to his teaching responsibilities, Dr. Joshi has contributed significantly to research, has numerous publications, and has delivered expert lectures in his field. His involvement in administrative duties and active participation in professional bodies demonstrate his commitment to academic and institutional excellence.

References

“IDF Diabetes atlas 11th Edition,” 2025.

E. A. James, A. V. Joglekar, A. K. Linnemann, H. A. Russ, and S. C. Kent, “The beta cell-immune cell interface in type 1 diabetes (T1D),” Dec. 01, 2023, Elsevier GmbH. doi: 10.1016/j.molmet.2023.101809.

S. A. Antar et al., “Diabetes mellitus: Classification, mediators, and complications; A gate to identify potential targets for the development of new effective treatments,” Dec. 01, 2023, Elsevier Masson s.r.l. doi: 10.1016/j.biopha.2023.115734.

M. J. Schoelwer et al., “Predictors of Time-in-Range (70-180 mg/dL) Achieved Using a Closed-Loop Control System,” Diabetes Technol Ther, vol. 23, no. 7, pp. 475–481, Jul. 2021, doi: 10.1089/dia.2020.0646.

C. Toffanin, L. Magni, and C. Cobelli, “Artificial Pancreas: In Silico Study Shows No Need of Meal Announcement and Improved Time in Range of Glucose with Intraperitoneal vs. Subcutaneous Insulin Delivery,” IEEE Trans Med Robot Bionics, vol. 3, no. 2, pp. 306–314, May 2021, doi: 10.1109/TMRB.2021.3075775.

M. N. Pelkey, M. E. Boyle, A. Long, J. C. Castro, C. B. Cook, and B. Thompson, “Hybrid Closed-Loop Insulin Pump Technology Can Be Safely Used in the Inpatient Setting,” Endocrine Practice, vol. 29, no. 1, pp. 24–28, Jan. 2023, doi: 10.1016/j.eprac.2022.11.006.

M. Nwokolo and R. Hovorka, “The Artificial Pancreas and Type 1 Diabetes,” J Clin Endocrinol Metab, vol. 108, no. 7, pp. 1614–1623, Jun. 2023, doi: 10.1210/clinem/dgad068.

D. Pollakova, A. Lauria Pantano, U. Di Folco, M. R. Nardone, and C. Tubili, “Advanced hybrid closed loop (artificial pancreas) and carbohydrate count in type 1 diabetes,” Med J Nutrition Metab, vol. 17, no. 3, pp. 219–227, Sep. 2024, doi: 10.3233/MNM-230125.

B. M. Ahmed, M. E. Ali, M. M. Masud, M. R. Azad, and M. Naznin, “After-meal blood glucose level prediction for type-2 diabetic patients,” Heliyon, vol. 10, no. 7, Apr. 2024, doi: 10.1016/j.heliyon. 2024.e28855.

M. Zhang, K. B. Flores, and H. T. Tran, “Deep learning and regression approaches to forecasting blood glucose levels for type 1 diabetes,” Biomed Signal Process Control, vol. 69, Aug. 2021, doi: 10.1016/j.bspc.2021.102923.

C. Ji, T. Jiang, L. Liu, J. Zhang, and L. You, “Continuous glucose monitoring combined with artificial intelligence: redefining the pathway for prediabetes management,” Front Endocrinol (Lausanne), vol. 16, 2025, doi: 10.3389/fendo.2025.1571362.

S.-M. Lee, D.-Y. Kim, and J. Woo, “Glucose Transformer: Forecasting Glucose Level and Events of Hyperglycemia and Hypoglycemia,” IEEE J Biomed Health Inform, vol. 27, no. 3, pp. 1600–1611, Mar. 2023, doi: 10.1109/JBHI.2023.3236822.

J. Alvarado, J. M. Velasco, F. Chavez, F. Fernández-de-Vega, and J. I. Hidalgo, “Combining wavelet transform with convolutional neural networks for hypoglycemia events prediction from CGM data,” Chemometrics and Intelligent Laboratory Systems, vol. 243, Dec. 2023, doi: 10.1016/j.chemolab.2023.105017.

G. Alfian et al., “Blood glucose prediction model for type 1 diabetes based on artificial neural network with time-domain features,” Biocybern Biomed Eng, vol. 40, no. 4, pp. 1586–1599, Oct. 2020, doi: 10.1016/j.bbe.2020.10.004.

W. Seo, S.-W. Park, N. Kim, S.-M. Jin, and S.-M. Park, “A personalized blood glucose level prediction model with a fine-tuning strategy: A proof-of-concept study,” Comput Methods Programs Biomed, vol. 211, p. 106424, Nov. 2021, doi: 10.1016/j.cmpb.2021.106424.

H. V. Dudukcu, M. Taskiran, and T. Yildirim, “Blood glucose prediction with deep neural networks using weighted decision level fusion,” Biocybern Biomed Eng, vol. 41, no. 3, pp. 1208–1223, Jul. 2021, doi: 10.1016/j.bbe.2021.08.007.

D. Kalita, H. Sharma, J. K. Panda, and K. B. Mirza, “Platform for precise, personalised glucose forecasting through continuous glucose and physical activity monitoring and deep learning,” Med Eng Phys, vol. 132, p. 104241, Oct. 2024, doi: 10.1016/j.medengphy.2024.104241.

J. Shao et al., “Generalization of a Deep Learning Model for Continuous Glucose Monitoring–Based Hypoglycemia Prediction: Algorithm Development and Validation Study,” JMIR Med Inform, vol. 12, pp. e56909–e56909, May 2024, doi: 10.2196/56909.

U. Krishnamoorthy, V. Karthika, M. K. Mathumitha, H. Panchal, V. K. S. Jatti, and A. Kumar, “Learned prediction of cholesterol and glucose using ARIMA and LSTM models – A comparison,” Results in Control and Optimization, vol. 14, Mar. 2024, doi: 10.1016/j.rico.2023.100362.

Li Kezhi and Liu C., T. Zhu, P. Herrero, and P. Georgiou, “GluNet: A Deep Learning Framework for Accurate Glucose Forecasting,” IEEE J Biomed Health Inform, vol. 24, no. 2, pp. 414–423, Feb. 2020, doi: 10.1109/JBHI.2019.2931842.

P. Domanski, A. Ray, K. Lafata, F. Firouzi, K. Chakrabarty, and D. Pflüger, “Advancing blood glucose prediction with neural architecture search and deep reinforcement learning for type 1 diabetics,” Biocybern Biomed Eng, vol. 44, no. 3, pp. 481–500, Jul. 2024, doi: 10.1016/j.bbe.2024.07.006.

M. De Bois, M. A. El Yacoubi, and M. Ammi, “GLYFE: review and benchmark of personalized glucose predictive models in type 1 diabetes,” Med Biol Eng Comput, vol. 60, no. 1, pp. 1–17, Jan. 2022, doi: 10.1007/s11517-021-02437-4.

X. Huang et al., “Comparison of feature learning methods for non-invasive interstitial glucose prediction using wearable sensors in healthy cohorts: a pilot study,” Intelligent Medicine, vol. 4, no. 4, pp. 226–238, Nov. 2024, doi: 10.1016/j.imed.2024.05.002.

W. Wang, M. Tong, and M. Yu, “Blood Glucose Prediction with VMD and LSTM Optimized by Improved Particle Swarm Optimization,” IEEE Access, vol. 8, pp. 217908–217916, 2020, doi: 10.1109/ACCESS.2020.3041355.

V. B. Liu, L. Y. Sue, O. M. Padilla, and Y. Wu, “Optimizing blood glucose predictions in type 1 diabetes patients using a stacking ensemble approach,” Endocrine and Metabolic Science, vol. 18, Jun. 2025, doi: 10.1016/j.endmts.2025.100253.

Y. Shen and S. Kleinberg, “Personalized Blood Glucose Forecasting from Limited CGM Data Using Incrementally Retrained LSTM,” IEEE Trans Biomed Eng, vol. 72, no. 4, pp. 1266–1277, Apr. 2025, doi: 10.1109/TBME.2024.3494732.

H. Nemat, H. Khadem, J. Elliott, and M. Benaissa, “Data-driven blood glucose level prediction in type 1 diabetes: a comprehensive comparative analysis,” Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-70277-x.

A. Neumann, Y. Zghal, M. A. Cremona, A. Hajji, M. Morin, and M. Rekik, “A data-driven personalized approach to predict blood glucose levels in type-1 diabetes patients exercising in free-living conditions,” Comput Biol Med, vol. 190, May 2025, doi: 10.1016/j.compbiomed.2025.110015.

M. He, W. Gu, Y. Kong, L. Zhang, C. J. Spanos, and K. M. Mosalam, “CausalBG: Causal Recurrent Neural Network for the Blood Glucose Inference with IoT Platform,” IEEE Internet Things J, vol. 7, no. 1, pp. 598–610, 2020, doi: 10.1109/JIOT.2019.2946693.

R. Giancotti et al., “Forecasting glucose values for patients with type 1 diabetes using heart rate data,” Comput Methods Programs Biomed, vol. 257, Dec. 2024, doi: 10.1016/j.cmpb.2024.108438.

G. Cappon, F. Prendin, A. Facchinetti, G. Sparacino, and S. Del Favero, “Individualized Models for Glucose Prediction in Type 1 Diabetes: Comparing Black-Box Approaches to a Physiological White-Box One,” IEEE Trans Biomed Eng, vol. 70, no. 11, pp. 3105–3115, Nov. 2023, doi: 10.1109/TBME.2023.3276193.

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, p. 340, Jan. 2023, doi: 10.3390/diagnostics13030340.

F. J. Lara-Abelenda, D. Chushig-Muzo, P. Peiro-Corbacho, A. M. Wägner, C. Granja, and C. Soguero-Ruiz, “Personalized glucose forecasting for people with type 1 diabetes using large language models,” Comput Methods Programs Biomed, vol. 265, Jun. 2025, doi: 10.1016/j.cmpb.2025.108737.

M. A. Karagoz, M. D. Breton, and A. El Fathi, “A Comparative study of transformer-based models for multi-horizon blood glucose prediction,” in IFAC-PapersOnLine, Elsevier B.V., May 2025, pp. 83–88. doi: 10.1016/j.ifacol.2025.06.027.

S. J. Kim, J. S. Moon, and S. Y. Jung, “Long-term blood glucose prediction using deep learning-based noise reduction,” ICT Express, Aug. 2025, doi: 10.1016/j.icte.2025.05.009.

T. Koutny and M. Mayo, “Predicting glucose level with an adapted branch predictor,” Comput Biol Med, vol. 145, Jun. 2022, doi: 10.1016/j.compbiomed.2022.105388.

M. F. Rabby, Y. Tu, M. I. Hossen, I. Lee, A. S. Maida, and X. Hei, “Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction,” BMC Med Inform Decis Mak, vol. 21, no. 1, Dec. 2021, doi: 10.1186/s12911-021-01462-5.

A. Della Cioppa, I. De Falco, T. Koutny, U. Scafuri, M. Ubl, and E. Tarantino, “Reducing high-risk glucose forecasting errors by evolving interpretable models for Type 1 diabetes,” Appl Soft Comput, vol. 134, Feb. 2023, doi: 10.1016/j.asoc.2023.110012.

K. Li, J. Daniels, C. Liu, P. Herrero, and P. Georgiou, “Convolutional Recurrent Neural Networks for Glucose Prediction,” IEEE J Biomed Health Inform, vol. 24, no. 2, pp. 603–613, 2020, doi: 10.1109/JBHI.2019.2908488.

M. Jaloli and M. Cescon, “Long-Term Prediction of Blood Glucose Levels in Type 1 Diabetes Using a CNN-LSTM-Based Deep Neural Network,” J Diabetes Sci Technol, vol. 17, no. 6, pp. 1590–1601, Nov. 2023, doi: 10.1177/19322968221092785.

R. I. Alkanhel et al., “Hybrid CNN-GRU Model for Real-Time Blood Glucose Forecasting: Enhancing IoT-Based Diabetes Management with AI,” Sensors, vol. 24, no. 23, Dec. 2024, doi: 10.3390/s24237670.

X. Xiong, X. L. Yang, Y. Cai, Y. Xue, J. F. He, and H. Su, “Exploring the potential of deep learning models integrating transformer and LSTM in predicting blood glucose levels for T1D patients,” Digit Health, vol. 11, Jan. 2025, doi: 10.1177/20552076251328980.

D. M. Chiara, F. Micheletto, D. Lv, M. Breton, B. Kovatchev, and C. Cobelli, “The UVA/PADOVA type 1 diabetes simulator: New features,” J Diabetes Sci Technol, vol. 8, no. 1, pp. 26–34, 2014, doi: 10.1177/1932296813514502.

R. Visentin et al., “The UVA/Padova Type 1 Diabetes Simulator Goes from Single Meal to Single Day,” J Diabetes Sci Technol, vol. 12, no. 2, pp. 273–281, Mar. 2018, doi: 10.1177/1932296818757747.

M. Cindy and B. Razvan, “The ohioT1DM dataset for blood glucose level prediction: Update 2020,” CEUR Workshop Proc, vol. 2675, pp. 71–74, 2020, [Online]. Available: http://smarthealth.cs.ohio.edu/bglp/OhioT1DM-dataset-paper.pdf

A. K. Singh and D. Koundal, “A Temporal Convolutional Network for modeling raw 3D sequences and air-writing recognition,” Decision Analytics Journal, vol. 10, Mar. 2024, doi: 10.1016/j.dajour.2023.100373.

A. Zaitcev, M. R. Eissa, Z. Hui, T. Good, J. Elliott, and M. Benaissa, “A Deep Neural Network Application for Improved Prediction of HbA 1c in Type 1 Diabetes,” IEEE J Biomed Health Inform, vol. 24, no. 10, pp. 2932–2941, 2020, doi: 10.1109/JBHI.2020.2967546.

C. Xu, X. Wang, and S. Zhang, “Dilated convolution capsule network for apple leaf disease identification,” Front Plant Sci, vol. 13, Nov. 2022, doi: 10.3389/fpls.2022.1002312.

A. Ghosh, A. Sufian, F. Sultana, A. Chakrabarti, and D. De, “Fundamental concepts of convolutional neural network,” in Recent Trends and Advances in Artificial Intelligence and Internet of Things. Intelligent Systems Reference Library, vol. 172, Springer, Cham, 2020, pp. 519–567. doi: 10.1007/978-3-030-32644-9_36.

H. V. Dudukcu, M. Taskiran, and T. Yildirim, “Consolidated or individual training: Which one is better for blood glucose prediction?” in 2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), IEEE, Aug. 2021, pp. 1–6. doi: 10.1109/INISTA52262.2021.9548612.