Jul 2026· Genetics and Molecular Research· 0 citations· 57 references
TL;DR
RL-based AID systems represent an important step towards fully autonomous and personalized artificial pancreas solutions and will be dependent on multidisciplinary collaboration between AI researchers, clinicians, and regulators to ensure safety, transparency, and reliability in next generation diabetes management.
Abstract
Type 1 Diabetes Mellitus (T1DM) is a chronic autoimmune disease characterized by the destruction of pancreatic β cells, resulting in complete insulin deficiency and an exogenous insulin requirement. However, despite the technological progress, classical insulin therapies and control algorithms such as Proportional-Integral-Derivative (PID) and Model Predictive Control (MPC) are not able to follow unpredictable glucose variations due to meals, exercise, and stress. Automated Insulin Delivery (AID) systems combine continuous glucose monitoring, insulin pumps, and algorithmic decision-making but remain limited by model dependency, computational load, and lack of personalization. Reinforcement Learning (RL) has emerged as a transformative paradigm for AI systems by modeling insulin regulation as a sequential decision-making process that learns optimal dosing policies from experience. Model-free RL algorithms like Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) have demonstrated improved glycemic control, whereas model-based and hybrid RL algorithms have demonstrated increased safety and sample efficiency by integrating physiological constraints. Deep Reinforcement Learning (DRL) further increases adaptability through neural network-based personalization over different patient profiles. RL can be integrated with wearable technologies, Internet of Things (IoT) ecosystems, and digital twin simulations for continuous learning, remote monitoring, and patient specific optimization. Early clinical studies show improved time-in-range (TIR), reduced hypoglycemia, and improved long-term glucose control compared to traditional methods. However, there are still several challenges, including lack of real-world data, safety in online learning, interpretability, and regulatory compliance. Future advances will need to include the development of explainable and federated RL frameworks, lightweight models for wearable deployment, and multi-hormone control systems. In summary, RL-based AID systems represent an important step towards fully autonomous and personalized artificial pancreas solutions. Their clinical success will be dependent on multidisciplinary collaboration between AI researchers, clinicians, and regulators to ensure safety, transparency, and reliability in next generation diabetes management.
Personalized insulin dosing for Type 1 diabetes mellitus (T1DM) remains challenging because of complex glucose-insulin dynamics and substantial patient variability. Reinforcement learning (RL) has emerged as a promising approach for adaptive insulin management, yet the reliability of learned policies depends heavily on reward design and evaluation strategy. This study compares three actor–critic RL algorithms: Soft Actor-Critic (SAC), Advantage Actor-Critic (A2C), and Proximal Policy Optimization (PPO) for personalized insulin dosing using real-world continuous glucose monitoring, insulin delivery, basal insulin, and meal intake data from the OhioT1DM dataset. A custom Gymnasium-based environment was developed, and all algorithms were trained under identical conditions for 100,000 timesteps. Performance was evaluated using cumulative reward together with clinically relevant measures, including Time in Range (TIR) and insulin dosing behaviour. Although A2C and PPO achieved higher cumulative rewards than SAC, both converged to near-zero insulin dosing policies that exploited the reward formulation rather than learning clinically meaningful glucose regulation. In contrast, SAC maintained adaptive dosing behaviour, achieving a TIR of 72.71% with an average insulin dose of 1.769 U/step. These findings show that higher cumulative reward does not necessarily correspond to better clinical decision-making in open-loop reinforcement learning environments. The study highlights the importance of behaviour-focused evaluation alongside conventional reward metrics and provides practical insights for developing safer and more reliable reinforcement learning systems for personalized diabetes management.
C. M. Anyanwu, Nkiru C. Ogbonna, Mary Ofuru Kam et al.· International Journal of Lat...· 0 citations
Because of the nonlinear relationship between blood glucose and insulin and the temporal dependencies in human metabolism, the artificial pancreas (AP), a device for controlling blood glucose levels in type 1 diabetes (T1D), is limited in its ability to do so. The majority of traditional control algorithms produce less-than-ideal control because they are unable to account for the complexity of blood glucose and insulin levels. In order to capture the intricacies of blood glucose and insulin levels, we present a novel architecture for recurrent deep reinforcement learning (DRL) in this study. This is accomplished by adding a long short-term memory (LSTM) network to the soft actor critic (SAC) algorithm. This enables the controller to preserve a memory state that contains all pertinent historical states, including trends in continuous glucose monitoring, insulin on board, and meal history. The FDA-approved UVA/Padova T1DM simulator and thirty virtual adults are then used to train and test the controller in silico.Exercises, unexpected meals, and fluctuating insulin sensitivity are just a few of the realistic scenarios in which the controller is tested. In comparison to other controllers like feedforward DRL (74.2 percent ± 4.5 percent), model predictive control (73.5 percent ± 4.0 percent), and proportional integral derivative control (68.1 percent ± 5.2 percent), the suggested recurrent DRL controller can achieve 82.4 percent andplusmn; 3.1 percent time in range (TIR), which is defined as blood glucose levels between 70 and 180 mg/dL. In comparison to the feedforward DRL controller, the suggested controller can also lower hypoglycemia—defined as blood glucose levels less than 70 mg/dL—by more than 40%. Scenarios involving unexpected meals and quick adaptation to high insulin sensitivity can be handled by the suggested recurrent DRL controller.
Madhav Prasad, Dr. Neha Tyagi, Debosree Sarma· Genetics and Molecular Resea...· 0 citations
The management of type 1 diabetes mellitus (T1DM) represents a major challenge, as it requires continuous regulation of blood glucose (BG) levels. Automated systems, such as the artificial pancreas (AP), address this need by relying on accurate patient-specific models. Linear models are widely adopted in this context due to their simplicity and suitability for control design. However, their linear structure struggles to capture the complex dynamics of the glucose–insulin system, leading to degraded performance. This issue is further accentuated by the significant interpatient variability in glucose–insulin dynamics. A valid alternative to linear models is represented by recurrent neural networks (RNNs), which present higher expressivity while maintaining a level of complexity suitable for control purposes. However, such networks might lead to overfitting whenever the training dataset is scarce. In this work, we tackle this problem by embedding prior physiological knowledge about the glucose–insulin relation in the training procedure of RNNs, following the framework of knowledge-guided learning (KGL). Furthermore, we employ model-agnostic meta-learning (MAML) to deal with interpatient variability. A systematic results analysis is conducted using the UVA/Padova simulator to show that the proposed methodologies increase identification performance while maintaining an affordable level of complexity.
S. De Carli, Nicola Licini, F. Corrini et al.· IEEE Transactions on Control...· 0 citations
Type I diabetes mellitus (T1DM) is a chronic metabolic disease resulting from insufficient insulin secretion into the bloodstream‚ causing elevated blood glucose concentrations to dangerous levels․ Automated regulation of blood glucose levels in T1DM can be modeled as a nonlinear‚ uncertain‚ and disturbance-affected closed-loop control process with a time delay‚ time-varying insulin sensitivity, and imperfect glucose measurements. This paper presents the design, multi-objective tuning, and robustness evaluation of a fuzzy logic controller (FLC) for automated insulin-infusion regulation. The proposed FLC uses the glucose tracking error and its time derivative as feedback signals to determine the required insulin control action and maintain glucose within the desired range of (70–160 mg/dL). The controller parameters are optimized using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to address three competing control objectives: minimizing hypoglycemia risk, minimizing hyperglycemia risk, and reducing total insulin usage. The resulting Pareto-optimal solutions provide a set of trade-off controller designs for decision-makers based on safety, performance, and insulin-efficiency requirements. The robustness of the proposed automated control framework is evaluated under challenging operating conditions, including elevated initial glucose levels, model-parameter uncertainties, external disturbances, variations in insulin sensitivity, distorted glucose measurements, and delayed insulin infusion. A comparative study with a linear quadratic regulator-based controller (LQRC) is conducted as a benchmark. Simulation results demonstrate that the optimized FLC provides superior closed-loop performance and stronger robustness than the LQRC across all tested scenarios. The proposed fuzzy-control framework, therefore, offers a promising automation-based strategy for resilient glucose regulation under uncertainty, measurement imperfections, and actuation delays.
Raya Abu Shaker, Yousef Sardahi, Ahmad M. Alshorman· Automation· 0 citations
Background/Objectives: Diabetes mellitus is a chronic metabolic disorder characterized by impaired regulation of blood glucose due to defects in insulin secretion, insulin action, or both. Physiological and lifestyle factors vary among individuals. General medicine is not applicable to all patients. In this scenario, personalized medicine for each individual becomes costly. Effective management of continuous glucose levels with accurate insulin dosage is challenging. To overcome this, a digital twin (DT)-based insulin dosage simulator with an individual’s metabolic system is proposed in this work. Methods: Various machine learning techniques, mathematical models of physiology, and risk assessment using probability are used to predict the dynamics of patient-specific glucose–insulin. Parameters such as carbohydrate intake, sleep patterns, medications, and physical activity were incorporated into this model to capture real-world variations in daily life. For glucose–insulin interactions, the Bergman Minimal Model (BMM) is used; for time-of-day variability, a circadian insulin sensitivity model is used; and for predicting metabolic risks, Bayesian risk estimation (BRE) is used, which includes hyperglycemia risk. To enhance transparency and interpret model predictions, explainable artificial intelligence (XAI) methods are employed. Results: The simulation results showed improved glucose prediction accuracy, enhanced detection of hypoglycemia risk, and optimized insulin dosing strategies compared with traditional approaches. Conclusions: Overall, the proposed digital twin model offers a scalable solution using the latest techniques A “Prescriptive Analytical Framework” is provided using the BMM and BRE for personalized diabetes management and decision support for clinicians.
Type-I Diabetes Mellitus (TIDM) is characterized by
autoimmune destruction of pancreatic β-cells, resulting in absolute insulin deficiency and
impaired glucose regulation. Maintaining normoglycemia is challenging due to the nonlinear and
time-varying nature of Glucose–Insulin (GI) dynamics, meal disturbances, and physiological
uncertainties. This study proposes a Grasshopper Optimization-based Tilt–Acceleration–
Derivative with Filter (GO-TADF) controller for adaptive insulin delivery in an Artificial
Pancreas (AP) framework. The objective is to improve Blood Glucose (BG) regulation,
robustness, and disturbance rejection. The investigation is conducted entirely through simulation
using a validated physiological model; therefore, clinical and real-patient data validation remains
an important direction for future research.
A nonlinear multi-organ GI model incorporating hepatic balance, gut absorption, renal
excretion, and insulin kinetics is employed. The TADF controller regulates insulin infusion,
while the Grasshopper Optimization Algorithm (GOA) tunes controller parameters using the
Integral Time Absolute Error (ITAE) criterion. Simulations are conducted under meal
disturbances, parameter variations, and sensor noise to evaluate performance.
The GO-TADF controller maintains blood glucose near the normoglycemic range with
faster convergence, reduced overshoot/ undershoot, and stable insulin infusion. Renal glucose
excretion becomes negligible at steady state. Comparative analysis shows superior robustness,
accuracy, and noise rejection over PID, Linear Quadratic Gaussian (LQG), Sliding Mode (SM),
Model Predictive Control (MPC), and related controllers.
The proposed GO-TADF controller demonstrated superior BG regulation in TIDM
patients by effectively handling nonlinear dynamics, meal disturbances, and physiological
uncertainties. Compared with existing controllers, it achieved faster settling time, lower
overshoot, reduced insulin consumption, and improved robustness, making it a promising
solution for AP applications
The proposed GO-TADF controller effectively regulates BG in TIDM patients by
providing robust, adaptive, and stable insulin delivery. Simulation results demonstrate improved
glucose control, reduced insulin consumption, and superior disturbance rejection, highlighting its
potential for artificial pancreas applications.
A. Patra, Smitta Ranjan Dutta, Anuja Nanda· Current Science, Engineering...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
