Artificial Intelligence-Based Nonlinear Mathematical Modeling and Control of Glucose-Insulin Dynamics in Type 2 Diabetic Patients


Abstract views: 58 / PDF downloads: 10

Authors

  • Vivek Jayan Assistant Professor, Department of Community Medicine,Saveetha Medical College and Hospitals, SIMATS, Thandalam, Chennai, Tamilnadu, India.
  • Boborayimov Okhunjon Khushmurod ugli Department of Information Processing and Management Systems, Tashkent State Technical University, Tashkent, 100095.
  • Gulirano Khodjieva Assistant of the Department of Propedeutics of Internal Diseases, Bukhara state medical university named after Abu Ali ibn Sino, Uzbekistan
  • Sindhu Shankar S Assistant Professor, Department of Community Medicine, Aduchunchungiri University,NAGARUR, Nelamangala, Bangalore, India.
  • Ulugbek Bobamuratov PhD,Department of Information Technology and Exact Sciences, Termez University of Economics and Service, Termez, Uzbekistan.
  • K.Natarajan Assistant Professor, Department of Biomedical Engineering, Vinayaka Mission's Kirupananda Variyar Engineering College, Salem, (Vinayaka Mission's Research Foundation), Tamilnadu, India.
  • A.Malarvizhi Assistant professor, Department of Electronics and Communication Engineering, Vinayaka Mission`s Kirupananda Variyar Engineering College, Salem. (Vinayaka Mission`s Research Foundation)

Keywords:

Glucose–insulin modeling, Type 2 diabetes mellitus, Nonlinear dynamics, Artificial intelligence, Reinforcement learning, Predictive control, Physiological modeling

Abstract

The relationship between glucose and insulin regulation in type 2 diabetes mellitus (T2DM) is non-linear and highly dynamic and cannot be dealt with by exact modelling and smart control. The proposed study is a combination of artificial intelligence (AI)-based nonlinear mathematical modelling and control in addressing glucose insulin dynamics in diabetic patients with type 2 diabetes (T2DM). It begins with the construction of a nonlinear physiological model based on lengthy principles of minimal modelling of Bergman of the absorption of glucose into the body and the secretion of insulin and peripheral uptake in the face of pathological insulin resistance. Machine learning-based adaptive estimators are also used to further optimise the model parameters in capturing the inter-individual physiological variability. Subsequently, a hybrid type of control that involves both model predictive control (MPC) and reinforcement learning (RL) is created to control exogenous insulin delivery in the face of meals and metabolic disturbances. The results of the simulation prove that the system proposed will have a much higher level of glucose regulation, less postprandial hyperglycemia, and a stronger response to parameter uncertainty than the traditional proportional-integral-derivative (PID) and classical MPC plans. The AI-enhanced model predicts the glucose kinetics accurately and it attains a stable control without causing the hypoglycemia. The results demonstrate how AI-based nonlinear models can be effective in aiding patient-specific closed-loop insulin therapy and that this can provide a viable direction toward real-time individualized diabetes treatment.

References

Beolet, T., Adenis, A., Huneker, E., & Louis, M. (2024). End-to-end offline reinforcement learning for glycemia control. Artificial Intelligence in Medicine, 154, 102920. https://doi.org/10.1016/j.artmed.2024.102920

Bianchi, G. G., & Rossi, F. M. (2025). Reconfigurable computing platforms for bioinformatics applications. SCCTS Transactions on Reconfigurable Computing, 2(1), 16–23.

Dénes-Fazakas, L., Szilágyi, L., Kovács, L., Gaetano, A. D., & Eigner, G. (2024). Reinforcement Learning: A Paradigm Shift in Personalized Blood Glucose Management for Diabetes. Biomedicines, 12(9), 2143. https://doi.org/10.3390/biomedicines12092143

Dorofte, M., & Krein, K. (2024). Novel approaches in AI processing systems for their better reliability and function. International Journal of Communication and Computer Technologies, 12(2), 21–30. https://doi.org/10.31838/IJCCTS/12.02.03

Jacobs, P. G., Hilts, W. W., Dodier, R. H., Leitschuh, J., Eom, J., Branigan, D., Ling, F., Howard, M. O., Mosquera-Lopez, C., & Wilson, L. M. (2025). An AI-enabled dual-hormone model predictive control algorithm that delivers insulin and pramlintide. IFAC-PapersOnLine, 59(2), 61. https://doi.org/10.1016/j.ifacol.2025.06.011

López-Palau, N. E., Naranjo-Meneses, P., Szendroedi, J., Eils, R., & Kallenberger, S. M. (2025). Reinforcement learning optimization of automated insulin delivery in type 1 and type 2 diabetes mellitus. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2025.10.12.25337835

Lozhkina, A., Piazza, C., Gabr, Z., Rupp, M. E., Herzig, D., Bally, L., & Jaun, A. (2025). Individualized Therapy Optimization for Type 2 Diabetes. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2025.10.13.25337959

Lv, W., Wu, T., Xiong, L., Wu, L., Zhou, J., Tang, Y., & Qian, F. (2024). Hybrid Control Policy for Artificial Pancreas Via Ensemble Deep Reinforcement Learning. IEEE Transactions on Biomedical Engineering, 1. https://doi.org/10.1109/tbme.2024.3451712

Mameche, O., Abedou, A., Mezaache, T., & Tadjine, M. (2025). Precise Insulin Delivery for Artificial Pancreas: A Reinforcement Learning Optimized Adaptive Fuzzy Control Approach. https://doi.org/10.48550/ARXIV.2503.06701

Michael, P., & Jackson, K. (2025). Advancing scientific discovery: A high performance computing architecture for AI and machine learning. Journal of Integrated VLSI, Embedded and Computing Technologies, 2(2), 18–26. https://doi.org/10.31838/JIVCT/02.02.03

Minar, V., Mohan, V., & Ramarathnam, K. (2024). In silico model and sensitivity analysis of plasma glucose regulation: towards an individualized maximal model for physiology and pathophysiology. Current Science, 126(10), 1254. https://doi.org/10.18520/cs/v126/i10/1254-1264

Mujahid, O., Contreras, I., Beneyto, A., & Vehı, J. (2024). Generative deep learning for the development of a type 1 diabetes simulator. Communications Medicine, 4(1). https://doi.org/10.1038/s43856-024-00476-0

Roquemen-Echeverri, V., Kushner, T., Jacobs, P. G., & Mosquera-Lopez, C. (2025). A Physiologically-Constrained Neural Network Digital Twin Framework for Replicating Glucose Dynamics in Type 1 Diabetes. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2508.05705

Sakkoum, A., Toufga, H., Benahmadi, L., Chahid, W., & Lhous, M. (2025). Enhancing blood glucose control through the fixed point theorem. Mathematical Modelling and Analysis, 30(3), 514. https://doi.org/10.3846/mma.2025.22147

Sonzogni, B., Manzano, J. M., Polver, M., Previdi, F., & Ferramosca, A. (2024). CHoKI-based MPC for blood glucose regulation in Artificial Pancreas. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2401.17157

Sonzogni, B., Manzano, J. M., Polver, M., Previdi, F., & Ferramosca, A. (2025). CHoKI-based MPC for blood glucose regulation in Artificial Pancreas. IFAC Journal of Systems and Control, 100294. https://doi.org/10.1016/j.ifacsc.2024.100294

Surendar, A. (2024). Internet of medical things (IoMT): Challenges and innovations in embedded system design. SCCTS Journal of Embedded Systems Design and Applications, 1(1), 43–48. https://doi.org/10.31838/ESA/01.01.08

Uvarajan, K. P. (2024). Integration of artificial intelligence in electronics: Enhancing smart devices and systems. Progress in Electronics and Communication Engineering, 1(1), 7–12. https://doi.org/10.31838/PECE/01.01.02

Wang, W., Pei, R., Li, D., Liu, S., Geng, Y., & Wang, S. (2025). A physics-informed glucose-insulin neural network model for glucose prediction. Tsinghua Science & Technology. https://doi.org/10.26599/tst.2025.9010140

Wasi, A. T. (2024). Neural Control System for Continuous Glucose Monitoring and Maintenance. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2402.13852

Downloads

Published

2025-12-28

How to Cite

Vivek Jayan, Boborayimov Okhunjon Khushmurod ugli, Gulirano Khodjieva, Sindhu Shankar S, Ulugbek Bobamuratov, K.Natarajan, & A.Malarvizhi. (2025). Artificial Intelligence-Based Nonlinear Mathematical Modeling and Control of Glucose-Insulin Dynamics in Type 2 Diabetic Patients. Results in Nonlinear Analysis, 8(3), 180–189. Retrieved from https://www.nonlinear-analysis.com/index.php/pub/article/view/795

Issue

Vol. 8 No. 3 (2025): Volume 8 issue 3

Section

Articles

License

Copyright (c) 2025 Results in Nonlinear Analysis

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.