Adaptive Zone Model Predictive Control of Artificial Pancreas Based on Glucose- and Velocity-Dependent Control Penalties

A Performance-Based Adaptation Index for Automated Insulin Delivery Systems

BACKGROUND

Automated insulin delivery (AID) algorithms can benefit from tuning of their aggressiveness to meet individual needs, as insulin requirements vary among and within users. We introduce the Performance-Based Adaptation Index (PAI), a tool designed to enable automatic adjustment of an AID system aggressiveness based on continuous glucose monitoring (CGM) metrics.

METHODS

PAI integrates two CGM-based metrics-one for hypoglycemia and another for hyperglycemia exposure-over a previous time window into a single index (α θ ). We propose two methods to compute α θ : one based on time in range (TIR, 70-180 mg/dL), and the other on glycemic risk indices. Using α θ , we developed a multiplicative strategy to adjust the AID system's aggressiveness, accounting for situations where α θ cannot be reliably calculated. The feasibility of this method was assessed in-silico using the UVA/Padova Type 1 Diabetes Simulator and our full closed-loop algorithm (UVA-model predictive control (MPC)) across five scenarios: optimal tuning (baseline), conservative and aggressive tunings, and temporary and permanent changes in insulin needs. Glycemic outcomes were evaluated from the simulated glucose traces.

RESULTS

Negligible performance variations were observed in the baseline scenario. For the conservative scenario, adjusting α θ improved TIR (35.1% vs 71.8%) and increased total daily insulin (32.1 U vs 41.2 U). Conversely, for the aggressive scenario, it reduced hypoglycemia exposure (TBR: 2.6% vs 1.4%) and overall insulin usage (45.6 U vs 43.0 U).

CONCLUSION

In-silico results demonstrated the safety and efficacy of using PAI to automatically tune the UVA-MPC controller, achieving TIR values above 70% under fully closed-loop conditions and across various physiological states. Clinical validation of these results is warranted.

Multivariable identification based MPC for closed-loop glucose regulation subject to individual variability

The controller is important for the artificial pancreas to guide insulin infusion in diabetic therapy. However, the inter- and intra-individual variability and time delay of glucose metabolism bring challenges to control glucose within a normal range. In this study, a multivariable identification based model predictive control (mi-MPC) is developed to overcome the above challenges. Firstly, an integrated glucose-insulin model is established to describe insulin absorption, glucose-insulin interaction under meal disturbance, and glucose transport. On this basis, an observable glucose-insulin dynamic model is formed, in which the individual parameters and disturbances can be identified by designing a particle filtering estimator. Next, embedded with the identified glucose-insulin dynamic model, a mi-MPC method is proposed. In this controller, plasma glucose concentration (PGC), an important variable and indicator of glucose regulation, is estimated and controlled directly. Finally, the method was tested on 30 in-silico subjects produced by the UVa/Padova simulator. The results show that the mi-MPC method including the model, individual identification, and the controller can regulate glucose with the mean value of 7.45 mmol/L without meal announcement.

Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning

OBJECTIVE

The artificial pancreas (AP) shows promise for closed-loop glucose control in type 1 diabetes mellitus (T1DM). However, designing effective control policies for the AP remains challenging due to complex physiological processes, delayed insulin response, and inaccurate glucose measurements. While model predictive control (MPC) offers safety and stability through the dynamic model and safety constraints, it lacks individualization and is adversely affected by unannounced meals. Conversely, deep reinforcement learning (DRL) provides personalized and adaptive strategies but struggles with distribution shifts and substantial data requirements.

METHODS

We propose a hybrid control policy for the artificial pancreas (HyCPAP) to address the above challenges. HyCPAP combines an MPC policy with an ensemble DRL policy, leveraging the strengths of both policies while compensating for their respective limitations. To facilitate faster deployment of AP systems in real-world settings, we further incorporate meta-learning techniques into HyCPAP, leveraging previous experience and patient-shared knowledge to enable fast adaptation to new patients with limited available data.

RESULTS

We conduct extensive experiments using the UVA/Padova T1DM simulator across five scenarios. Our approaches achieve the highest percentage of time spent in the desired range and the lowest occurrences of hypoglycemia.

CONCLUSION

The results clearly demonstrate the superiority of our methods for closed-loop glucose management in individuals with T1DM.

SIGNIFICANCE

The study presents novel control policies for AP systems, affirming their great potential for efficient closed-loop glucose control.

Recent advances in the precision control strategy of artificial pancreas

The scientific diagnosis and treatment of patients with diabetes require frequent blood glucose testing and insulin delivery to normoglycemia. Therefore, an artificial pancreas with a continuous blood glucose (BG) monitoring function is an urgent research target in the medical industry. The problem of closed-loop algorithmic control of the BG with a time delay is a key and difficult issue that needs to be overcome in the development of an artificial pancreas. Firstly, the composition, structure, and control characteristics of the artificial pancreas are introduced. Subsequently, the research progress of artificial pancreas control algorithms is reviewed, and the characteristics, advantages, and disadvantages of proportional-integral-differential control, model predictive control, and artificial intelligence control are compared and analyzed to determine whether they are suitable for the practical application of the artificial pancreas. Additionally, key advancements in areas such as blood glucose data monitoring, adaptive models, wearable devices, and fully automated artificial pancreas systems are also reviewed. Finally, this review highlights that meal prediction, control safety, integration, streamlining the optimization of control algorithms, constant temperature preservation of insulin, and dual-hormone artificial pancreas are issues that require further attention in the future.

Neural-Net Artificial Pancreas: A Randomized Crossover Trial of a First-in-Class Automated Insulin Delivery Algorithm

Background: Automated insulin delivery (AID) is now integral to the clinical practice of type 1 diabetes (T1D). The objective of this pilot-feasibility study was to introduce a new regulatory and clinical paradigm-a Neural-Net Artificial Pancreas (NAP)-an encoding of an AID algorithm into a neural network that approximates its action and assess NAP versus the original AID algorithm. Methods: The University of Virginia Model-Predictive Control (UMPC) algorithm was encoded into a neural network, creating its NAP approximation. Seventeen AID users with T1D were recruited and 15 participated in two consecutive 20-h hotel sessions, receiving in random order either NAP or UMPC. Their demographic characteristics were ages 22-68 years old, duration of diabetes 7-58 years, gender 10/5 female/male, White Non-Hispanic/Black 13/2, and baseline glycated hemoglobin 5.4%-8.1%. Results: The time-in-range (TIR) difference between NAP and UMPC, adjusted for entry glucose level, was 1 percentage point, with absolute TIR values of 86% (NAP) and 87% (UMPC). The two algorithms achieved similar times <70 mg/dL of 2.0% versus 1.8% and coefficients of variation of 29.3% (NAP) versus 29.1 (UMPC)%. Under identical inputs, the average absolute insulin-recommendation difference was 0.031 U/h. There were no serious adverse events on either controller. NAP had sixfold lower computational demands than UMPC. Conclusion: In a randomized crossover study, a neural-network encoding of a complex model-predictive control algorithm demonstrated similar performance, at a fraction of the computational demands. Regulatory and clinical doors are therefore open for contemporary machine-learning methods to enter the AID field. Clinical Trial Registration number: NCT05876273.

Estimation and Prediction of Glucose Appearance Rate for Use in a Fully Closed-Loop Dual-Hormone Intraperitoneal Artificial Pancreas

OBJECTIVE

A fully automated artificial pancreas requires a meal estimator and predictions of blood glucose levels (BGL) to handle disturbances during meal times, all without relying on manual meal announcements and user interventions. This study introduces a technique for estimating the glucose appearance rate (GAR) and predicting BGL in people with type 1 diabetes and insulin and glucagon administration. It is demonstrated for intraperitoneal insulin and glucagon delivery but may be adapted to other delivery sites.

METHOD

The estimator is designed based on the moving horizon estimation (MHE) approach, where the underlying cost function incorporates prior statistical information on the GAR in subjects over the course of a day. The proposed prediction scheme is developed to predict GAR using estimated states and an intestinal model, which is then used to predict BGL with the help of an animal glucose metabolic model.

RESULTS

The intraperitoneal dual-hormone estimator was evaluated on three anesthetized animals, achieving a 21.8% mean absolute percentage error (MAPE) for GAR estimation and a 10.0% MAPE for BGL prediction when the future GAR is known. For a 120-minute prediction horizon, the proposed predictor achieved an 18.0% MAPE for GAR and a 28.4% MAPE for BGL.

CONCLUSION

The findings demonstrate the effectiveness and reliability of the proposed estimator and its potential for use in a fully automated artificial pancreas and reducing user interventions.

SIGNIFICANCE

This study represents advancements toward the development of a fully automated artificial pancreas, ultimately enhancing the quality of life for people with type 1 diabetes.

Automated blood glucose regulation for nonlinear model of type-1 diabetic patient under uncertainties: GWOCS type-2 fuzzy approach

Regulating blood glucose level (BGL) for type-1 diabetic patient (T1DP) accurately is very important issue, an uncontrolled BGL outside the standard safe range between 70 and 180 mg/dl results in dire consequences for health and can significantly increase the chance of death. So the purpose of this study is to design an optimized controller that infuses appropriate amounts of exogenous insulin into the blood stream of T1DP proportional to the amount of obtained glucose from food. The nonlinear extended Bergman minimal model is used to present glucose-insulin physiological system, an interval type-2 fuzzy logic controller (IT2FLC) is utilized to infuse the proper amount of exogenous insulin. Superiority of IT2FLC in minimizing the effect of uncertainties in the system depends primarily on the best choice of footprint of uncertainty (FOU) of IT2FLC. So a comparison includes four different optimization methods for tuning FOU including hybrid grey wolf optimizer-cuckoo search (GWOCS) and fuzzy logic controller (FLC) method is constructed to select the best controller approach. The effectiveness of the proposed controller was evaluated under six different scenarios of T1DP using Matlab/Simulink platform. A 24-h scenario close to real for 100 virtual T1DPs subjected to parametric uncertainty, uncertain meal disturbance and random initial condition showed that IT2FLC accurately regulate BGL for all T1DPs within the standard safe range. The results indicated that IT2FLC using GWOCS can prevent side effect of treatment with blood-sugar-lowering medication. Also stability analysis for the system indicated that the system operates within the stability region of nonlinear system.

Developing the UVA/Padova Type 1 Diabetes Simulator: Modeling, Validation, Refinements, and Utility

Arguably, diabetes mellitus is one of the best quantified human conditions. In the past 50 years, the metabolic monitoring technologies progressed from occasional assessment of average glycemia via HbA1c, through episodic blood glucose readings, to continuous glucose monitoring (CGM) producing data points every few minutes. The high-temporal resolution of CGM data enabled increasingly intensive treatments, from decision support assisting insulin injection or oral medication, to automated closed-loop control, known as the "artificial pancreas." Throughout this progress, mathematical models and computer simulation of the human metabolic system became indispensable for the technological progress of diabetes treatment, enabling every step, from assessment of insulin sensitivity via the now classic Minimal Model of Glucose Kinetics, to in silico trials replacing animal experiments, to automated insulin delivery algorithms. In this review, we follow these developments, beginning with the Minimal Model, which evolved through the years to become large and comprehensive and trigger a paradigm change in the design of diabetes optimization strategies: in 2007, we introduced a sophisticated model of glucose-insulin dynamics and a computer simulator equipped with a "population" of N = 300 in silico "subjects" with type 1 diabetes. In January 2008, in an unprecedented decision, the Food and Drug Administration (FDA) accepted this simulator as a substitute to animal trials for the pre-clinical testing of insulin treatment strategies. This opened the field for rapid and cost-effective development and pre-clinical testing of new treatment approaches, which continues today. Meanwhile, animal experiments for the purpose of designing new insulin treatment algorithms have been abandoned.

A practical approach based on learning-based model predictive control with minimal prior knowledge of patients for artificial pancreas

BACKGROUND AND OBJECTIVES

Complete identification of the glucose dynamics for a patient generally requires prior clinical procedures and several measurements for the patient. However, these steps may not be always feasible. To address this limitation, we propose a practical approach integrating learning-based model predictive control (MPC), adaptive basal and bolus injections, and suspension with minimal requirements of prior knowledge of the patient.

METHODS

The glucose dynamic system matrices were periodically updated using only input values, without any pretrained models. The optimal insulin dose was calculated based on a learning-based MPC algorithm. Meal detection and estimation modules were also introduced. The basal and bolus insulin injections were fine-tuned using the performance of glucose control from the previous day. To validate the proposed method, evaluations with 20 virtual patients from a type 1 diabetes metabolic simulator were employed.

RESULTS

Time-in-range (TIR) and time-below-range (TBR) were 90.8% (84.1% - 95.6%) and 0.3% (0% - 0.8%), as represented by the median, first (Q1), and third quartiles (Q3), respectively, when meal intakes were fully announced. When one out of three meal intake announcements was missing, TIR and TBR were 85.2% (75.0% - 88.9%) and 0.9% (0.4% - 1.1%), respectively.

CONCLUSIONS

The proposed approach obviates the need for prior tests from patients and shows effective regulation of blood glucose levels. From the perspective of practical implementation in clinical environments, to deal with minimal prior information of the patient, our study demonstrates how essential clinical knowledge and learning-based modules can be integrated into a control framework for an artificial pancreas.

Glucose Rate-of-Change and Insulin-on-Board Jointly Weighted Zone Model Predictive Control

We present design and evaluation of closed-loop insulin delivery using zone model predictive control (MPC) featuring an adaptive weighting scheme to address prolonged hyperglycemia due to changes in insulin sensitivity, underdelivery from profile mismatch, and meal composition. In the MPC cost function, the penalty on predicted glucose deviation from the upper zone boundary is weighted by a joint function of predicted glucose rate-of-change (ROC) and insulin-on-board (IOB). The asymmetric weighting gradually increases when glucose ROC and IOB were jointly low, independent of glucose magnitude, to limit hyperglycemia while aggressively reduces for negative glucose ROC to avoid hypoglycemia. The proposed controller was evaluated using two simulation scenarios: an induced resistance scenario and a nominal scenario to highlight the performance over a reference zone MPC with glucose ROC weighting only. The continuous adaption scheme resulted in consistent improvement for the entire glucose range without incurring additional risk of hypoglycemia. For the induced resistance and no feedforward bolus scenario, the percent time in 70-180 mg/dL was higher (53.5% versus 48.9%, p<0.001) with larger improvement in the overnight percent time in tighter glucose range 70-140 mg/dL (70.9% versus 52.9%, p<0.001). The results from extensive simulations, as well as clinical validation in three different outpatient studies demonstrate the utility and safety of the proposed zone MPC.

Intermittent closed-loop blood glucose control for people with type 1 diabetes on multiple daily injections

BACKGROUND AND OBJECTIVES

Recent advances in Automated Insulin Delivery systems have been shown to dramatically improve glycaemic control and reduce the risk of hypoglycemia in people with type 1 diabetes. However, they are complex systems that require specific training and are not affordable for most. Attempts to reduce the gap with closed-loop therapies using advanced dosing advisors have so far failed, mainly because they require too much human intervention. With the advent of smart insulin pens, one of the main constraints (having reliable bolus and meal information) disappears and new strategies can be employed. This is our starting hypothesis, which we have validated in a very demanding simulator. In this paper, we propose an intermittent closed-loop control system specifically intended for multiple daily injection therapy to bring the benefits of artificial pancreas to the application of multiple daily injections.

METHODS

The proposed control algorithm is based on model predictive control and integrates two patient-driven control actions. Correction insulin boluses are automatically computed and recommended to the patient to minimize the duration of hyperglycemia. Rescue carbohydrates are also triggered to avoid hypoglycemia episodes. The algorithm can adapt to different patient lifestyles with customizable triggering conditions, closing the gap between practicality and performance. The proposed algorithm is compared with conventional open-loop therapy, and its superiority is demonstrated through extensive in silico evaluations using realistic cohorts and scenarios. The evaluations were conducted in a cohort of 47 virtual patients. We also provide detailed explanations of the implementation, imposed constraints, triggering conditions, cost functions, and penalties for the algorithm.

RESULTS

The in-silico outcomes combining the proposed closed-loop strategy with slow-acting insulin analog injections at 09:00 h resulted in percentages of time in range (TIR) (70-180 mg/dL) of 69.5%, 70.6%, and 70.4% for glargine-100, glargine-300, and degludec-100, respectively, and injections at 20:00 h resulted in percentages of TIR of 70.5%, 70.3%, and 71.6%, respectively. In all the cases, the percentages of TIR were considerably higher than those obtained from the open-loop strategy, being only 50.7%, 53.9%, and 52.2% for daytime injection and 55.5%, 54.1%, and 56.9% for nighttime injection. Overall, the occurrence of hypoglycemia and hyperglycemia was notably reduced using our approach.

CONCLUSIONS

Event-triggering model predictive control in the proposed algorithm is feasible and may meet clinical targets for people with type 1 diabetes.

Minimal and Maximal Models to Quantitate Glucose Metabolism: Tools to Measure, to Simulate and to Run in Silico Clinical Trials

Several models have been proposed to describe the glucose system at whole-body, organ/tissue and cellular level, designed to measure non-accessible parameters (minimal models), to simulate system behavior and run in silico clinical trials (maximal models). Here, we will review the authors' work, by putting it into a concise historical background. We will discuss first the parametric portrait provided by the oral minimal models-building on the classical intravenous glucose tolerance test minimal models-to measure otherwise non-accessible key parameters like insulin sensitivity and beta-cell responsivity from a physiological oral test, the mixed meal or the oral glucose tolerance tests, and what can be gained by adding a tracer to the oral glucose dose. These models were used in various pathophysiological studies, which we will briefly review. A deeper understanding of insulin sensitivity can be gained by measuring insulin action in the skeletal muscle. This requires the use of isotopic tracers: both the classical multiple-tracer dilution and the positron emission tomography techniques are discussed, which quantitate the effect of insulin on the individual steps of glucose metabolism, that is, bidirectional transport plasma-interstitium, and phosphorylation. Finally, we will present a cellular model of insulin secretion that, using a multiscale modeling approach, highlights the relations between minimal model indices and subcellular secretory events. In terms of maximal models, we will move from a parametric to a flux portrait of the system by discussing the triple tracer meal protocol implemented with the tracer-to-tracee clamp technique. This allows to arrive at quasi-model independent measurement of glucose rate of appearance (Ra), endogenous glucose production (EGP), and glucose rate of disappearance (Rd). Both the fast absorbing simple carbs and the slow absorbing complex carbs are discussed. This rich data base has allowed us to build the UVA/Padova Type 1 diabetes and the Padova Type 2 diabetes large scale simulators. In particular, the UVA/Padova Type 1 simulator proved to be a very useful tool to safely and effectively test in silico closed-loop control algorithms for an artificial pancreas (AP). This was the first and unique simulator of the glucose system accepted by the U.S. Food and Drug Administration as a substitute to animal trials for in silico testing AP algorithms. Recent uses of the simulator have looked at glucose sensors for non-adjunctive use and new insulin molecules.

Control of blood glucose induced by meals for type-1 diabetics using an adaptive backstepping algorithm

In this study, an adaptive backstepping method is proposed to regulate the blood glucose induced by meals for type-1 diabetic patients. The backstepping controller is used to control the blood glucose level and an adaptive algorithm is utilized to compensate for the blood glucose induced by meals. Moreover, the effectiveness of the proposed method is evaluated by comparing results in two different case studies: in the presence of actuator faults and the loss of control input for a short while during treatment. Effects of unannounced meals three times a day are investigated for a nominal patient in every case. It is argued that adaptive backstepping is the preferred control method in either case. The Lyapunov theory is used to prove the stability of the proposed method. Obtained results, indicated that the adaptive backstepping controller is stable, and the desired level of glucose concentration is being tracked efficiently.

A Dual-Hormone Multicontroller for Artificial Pancreas Systems

Artificial pancreas (AP) algorithms can be divided into single-hormone (SH) and dual-hormone (DH). SH algorithms regulate glycemia using insulin as their control input. On the other hand, DH algorithms also use glucagon to counteract insulin. While SH-AP systems are already commercially available, DH-AP systems are still in an earlier research phase. DH-AP systems have been questioned since the added complexity of glucagon infusion does not always guarantee hypoglycemia prevention and might significantly raise insulin delivery. In this work, a DH multicontroller is proposed based on a SH linear quadratic gaussian (LQG) algorithm with an additional LQG controller to deliver glucagon. This strategy has a switched structure that allows activating one of the following three controllers when necessary: a conservative insulin LQG controller to modulate basal delivery ( K₁), an aggressive insulin LQG controller to counteract meals ( K₂), or a glucagon LQG controller to avoid imminent hypoglycemia ( K₃). Here, an in silico study of the benefits of incorporating controller K₃ is carried out. Intra-patient variability and mixed meals are considered. Results indicate that the proposed switched, dual-hormone strategy yields to a reduction in hypoglycemia without increasing hyperglycemia, with no significant rise in insulin delivery.

Interval Safety Layer Coupled With an Impulsive MPC for Artificial Pancreas to Handle Intrapatient Variability

The aim of control strategies for artificial pancreas systems is to calculate the insulin doses required by a subject with type 1 diabetes to regulate blood glucose levels by reducing hyperglycemia and avoiding the induction of hypoglycemia. Several control formulations developed for this end involve a safety constraint given by the insulin on board (IOB) estimation. This constraint has the purpose of reducing hypoglycemic episodes caused by insulin stacking. However, intrapatient variability constantly changes the patient's response to insulin, and thus, an adaptive method is required to restrict the control action according to the current situation of the subject. In this work, the control action computed by an impulsive model predictive controller is modulated with a safety layer to satisfy an adaptive IOB constraint. This constraint is established with two main steps. First, upper and lower IOB bounds are generated with an interval model that accounts for parameter uncertainty, and thus, define the possible system responses. Second, the constraint is selected according to the current value of glycemia, an estimation of the plant-model mismatch, and their corresponding first and second time derivatives to anticipate the changes of both glucose levels and physiological variations. With this strategy satisfactory results were obtained in an adult cohort where random circadian variability and sensor noise were considered. A 92% time in normoglycemia was obtained, representing an increase of time in range compared to previous MPC strategies, and a reduction of time in hypoglycemia to 0% was achieved without dangerously increasing the time in hyperglycemia.

Advanced hybrid artificial pancreas system improves on unannounced meal response - In silico comparison to currently available system

BACKGROUND AND OBJECTIVE

Glycemic control, especially meal-related disturbance rejection, has proven to be a major challenge for people with type 1 diabetes. In this manuscript, we introduce a novel, personalized, advanced hybrid insulin infusion system (a.k.a. artificial pancreas) based on the Model Predictive Control (MPC) methodology to adjust insulin infusion while automatically rejecting uninformed meals.

METHODS

The proposed advanced hybrid closed-loop system relies on the integration of three key elements: (i) an adaptive personalized MPC control law that modulates the control strength depending on recent past control actions, glucose measurements, and its derivative, (ii) an automatic Bolus Priming System (BPS) that commands additional insulin injections safely upon the detection of enabling metabolic conditions (e.g., an unacknowledged meal), and (iii) a new hyperglycemia mitigation system to avoid prevailing hyperglycemia. The benefits of the proposed system are demonstrated through simulations and tests using the most up-to-date Type 1 UVA/Padova simulator as preclinical stage prior to in vivo clinical tests. We used a legacy algorithm (USS Virginia), currently used in clinical care, as a benchmark controller.

RESULTS

Overall, the proposed control strategy enhanced by an automatic BPS improves glycemic control when compared with an available system. When a large meal is not announced (80g CHO), the proposed controller outperformed the legacy controller in time-in-target-range TIR (postprandial and overnight) and time-in-tight-range TTR (overall, postprandial, and overnight).

CONCLUSION

The integration of a novel BPS into an advanced control system allowed to automatically reject unannounced meals. Exhaustive simulation studies indicated the safety and feasibility of the proposed controller to be deployed in human clinical trials.

Toward a Fully Automated Artificial Pancreas System Using a Bioinspired Reinforcement Learning Design: In Silico Validation

OBJECTIVE

The automation of insulin treatment is the most challenge aspect of glucose management for type 1 diabetes owing to unexpected exogenous events (e.g., meal intake). In this article, we propose a novel reinforcement learning (RL) based artificial intelligence (AI) algorithm for a fully automated artificial pancreas (AP) system.

METHODS

A bioinspired RL designing method was developed for automated insulin infusion. This method has reward functions that imply the temporal homeostatic objective and discount factors that reflect an individual specific pharmacological characteristic. The proposed method was applied to a training method using an RL algorithm and was evaluated in virtual patients from the FDA approved UVA/Padova simulator with unannounced meal intakes.

RESULTS

For a single-meal experiment with preprandial fasting, the trained policy demonstrated fully automated regulation in both the basal and postprandial phases. In the in silico trial with a variation of insulin sensitivity and dawn phenomenon, the policy achieved a mean glucose of 124.72 mg/dL and percentage time in the normal range of 89.56%. The layer-wise relevance propagation provides interpretable information on AI-driven decision for robustness to sensor noise, automated postprandial regulation, and insulin stacking avoidance.

CONCLUSION

The AP algorithm based on the bioinspired RL approach enables fully automated blood glucose control with unannounced meal intake.

SIGNIFICANCE

The proposed framework can be extended to other drug-based treatments for systems with significant uncertainties.

Intelligent automated drug administration and therapy: future of healthcare

In the twenty-first century, the collaboration of control engineering and the healthcare sector has matured to some extent; however, the future will have promising opportunities, vast applications, and some challenges. Due to advancements in processing speed, the closed-loop administration of drugs has gained popularity for critically ill patients in intensive care units and routine life such as personalized drug delivery or implantable therapeutic devices. For developing a closed-loop drug delivery system, the control system works with a group of technologies like sensors, micromachining, wireless technologies, and pharmaceuticals. Recently, the integration of artificial intelligence techniques such as fuzzy logic, neural network, and reinforcement learning with the closed-loop drug delivery systems has brought their applications closer to fully intelligent automatic healthcare systems. This review's main objectives are to discuss the current developments, possibilities, and future visions in closed-loop drug delivery systems, for providing treatment to patients suffering from chronic diseases. It summarizes the present insight of closed-loop drug delivery/therapy for diabetes, gastrointestinal tract disease, cancer, anesthesia administration, cardiac ailments, and neurological disorders, from a perspective to show the research in the area of control theory.

Performance Analysis of Different Embedded Systems and Open-Source Optimization Packages Towards an Impulsive MPC Artificial Pancreas

Current technological advances have brought closer to reality the project of a safe, portable, and efficient artificial pancreas for people with type 1 diabetes (T1D). Among the developed control strategies for T1D, model predictive control (MPC) has been emphasized in literature as a promising control for glucose regulation. However, these control strategies are commonly designed in a computer environment, regardless of the limitations of a portable device. In this paper, the performances of six embedded platforms and three open-source optimization solver algorithms are assessed for T1D treatment. Their advantages and limitations are clarified using four MPC formulations of increasing complexity and a hardware-in-the-loop methodology to evaluate glucose control in virtual adult subjects. The performance comparison includes the execution time, the difference concerning the evolution obtained in MATLAB, the processor temperature, energy consumption, time percentage in normoglycemia, and the number of hypo- and hyperglycemic events. Results show that Quadprog is the package that faithfully follows the results obtained with control strategies designed and tuned on a computer with the MATLAB software. In addition, the Raspberry Pi 3 and the Tinker Board S embedded systems present the appropriate characteristics to be implemented as portable devices in the artificial pancreas application according to the criteria set out in this work.

The Padova Type 2 Diabetes Simulator from Triple-Tracer Single-Meal Studies: In Silico Trials Also Possible in Rare but Not-So-Rare Individuals

Background:In silico trials in type 2 diabetes (T2D) would be useful for testing diabetes treatments and accelerating the development of new antidiabetic drugs. In this study, we present a T2D simulator able to reproduce the variability observed in a T2D population. The simulator also allows to safely experiment on virtual subjects with severe (and possibly rare) pathological conditions. Methods: A meal simulation model of glucose, insulin, and C-peptide systems, made of 15 differential equations and 39 parameters, has been identified using a system decomposition and forcing function Bayesian strategy on data of 51 T2D subjects undergoing a single triple-tracer mixed meal. One hundred T2D in silico subjects have been generated from the joint distribution of estimated model parameters. A case study is presented to illustrate the simulator use for testing a virtual drug (improving insulin action and secretion) in a subpopulation of rare, extremely impaired, T2D subjects. Results: The model well fitted T2D data and parameters were estimated with precision. Simulated plasma glucose, insulin, and C-peptide well matched the data (e.g., median [25^th-75^th percentile] glucose area under the curves of 6.9 [6.1-8.5] 10⁴ mg/dL·min in silico vs. 7.0 [5.6-8.2] 10⁴ mg/dL·min in vivo). The potential use of the simulator was shown in a case study, in which the (virtual) antidiabetic drug dose was optimized for very insulin-resistant T2D subjects. Conclusions: We have developed a T2D simulator that captures the behavior of T2D population during a meal, both in terms of average and intersubject variability. The simulator represents a cost-effective way to test new antidiabetic drugs, before moving to human trials.

A Hybrid Dynamic Wavelet-Based Modeling Method for Blood Glucose Concentration Prediction in Type 1 Diabetes

Background:

Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction of blood glucose concentration (BGC) is essential to improve the therapy of type 1 DM (T1DM).

Methods:

Having considered the risk of hyper- and hypo-glycemia, we provide a new hybrid modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN) model, including a heuristic input selection. The proposed models include a hybrid dynamic WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet-based networks are designed based on dominant wavelets selected by the genetic algorithm-orthogonal least square method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction, an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on real data from 12 T1DM patients and also simulated data from 33 virtual patients with an UVa/ Padova simulator, an approved simulator by the US Food and Drug Administration.

Results:

A comparison study is performed in terms of new glucose-based assessment metrics, such as gFIT, glucose-weighted form of ESOD_n (gESOD_n), and glucose-weighted R² (gR²). For real patients’ data, the values of the mentioned indices are accomplished as gFIT = 0.97 ± 0.01, gESOD_n = 1.18 ± 0.38, and gR² = 0.88 ± 0.07. HDFWNN, HDWNN and jump NN method showed the prediction error (root mean square error [RMSE]) of 11.23 ± 2.77 mg/dl, 10.79 ± 3.86 mg/dl and 16.45 ± 4.33 mg/dl, respectively.

Conclusion:

Furthermore, the generalized estimating equation and post hoc tests show that proposed models perform better compared with other proposed methods.

Automatic glycemic regulation for the pediatric population based on switched control and time-varying IOB constraints: an in silico study

Artificial pancreas (AP) systems have shown to improve glucose regulation in type 1 diabetes (T1D) patients. However, full closed-loop performance remains a challenge particularly in children and adolescents, since these age groups often present the worst glycemic control. In this work, an algorithm based on switched control and time-varying IOB constraints is presented. The proposed control strategy is evaluated in silico using the FDA-approved UVA/ Padova simulator and its performance contrasted with the previously introduced Automatic Regulation of Glucose (ARG) algorithm in the pediatric population. The effect of unannounced meals is also explored. Results indicate that the proposed strategy achieves lower hypo- and hyperglycemia than the ARG for both announced and unannounced meals. Graphical Abstract Block diagram and illustrative example of insulin and glucose evolution over time for the proposed algorithm (ARGAE).

In-Silico Evaluation of Glucose Regulation Using Policy Gradient Reinforcement Learning for Patients with Type 1 Diabetes Mellitus

In this paper, we test and evaluate policy gradient reinforcement learning for automated blood glucose control in patients with Type 1 Diabetes Mellitus. Recent research has shown that reinforcement learning is a promising approach to accommodate the need for individualized blood glucose level control algorithms. The motivation for using policy gradient algorithms comes from the fact that adaptively administering insulin is an inherently continuous task. Policy gradient algorithms are known to be superior in continuous high-dimensional control tasks. Previously, most of the approaches for automated blood glucose control using reinforcement learning has used a finite set of actions. We use the Trust-Region Policy Optimization algorithm in this work. It represents the state of the art for deep policy gradient algorithms. The experiments are carried out in-silico using the Hovorka model, and stochastic behavior is modeled through simulated carbohydrate counting errors to illustrate the full potential of the framework. Furthermore, we use a model-free approach where no prior information about the patient is given to the algorithm. Our experiments show that the reinforcement learning agent is able to compete with and sometimes outperform state-of-the-art model predictive control in blood glucose regulation.

Artificial Pancreas: Evaluating the ARG Algorithm Without Meal Announcement

BACKGROUND

Either under standard basal-bolus treatment or hybrid closed-loop control, subjects with type 1 diabetes are required to count carbohydrates (CHOs). However, CHO counting is not only burdensome but also prone to errors. Recently, an artificial pancreas algorithm that does not require premeal insulin boluses-the so-called automatic regulation of glucose (ARG)-was introduced. In its first pilot clinical study, although the exact CHO counting was not required, subjects still needed to announce the meal time and classify the meal size.

METHOD

An automatic switching signal generator (SSG) is proposed in this work to remove the manual mealtime announcement from the control strategy. The SSG is based on a Kalman filter and works with continuous glucose monitoring readings only.

RESULTS

The ARG algorithm with unannounced meals (ARG_um) was tested in silico under the effect of different types of mixed meals and intrapatient variability, and contrasted with the ARG algorithm with announced meals (ARG_am). Simulations reveal that, for slow-absorbing meals, the time in the euglycemic range, [70-180] mg/dL, increases using the unannounced strategy (ARG_am: 78.1 [68.6-80.2]% (median [IQR]) and ARG_um: 87.8 [84.5-90.6]%), while similar results were found with fast-absorbing meals (ARG_am: 87.4 [86.0-88.9]% and ARG_um: 87.6 [86.1-88.8]%). On the other hand, when intrapatient variability is considered, time in euglycemia is also comparable (ARG_am: 81.4 [75.4-83.5]% and ARG_um: 80.9 [77.0-85.1]%).

CONCLUSION

In silico results indicate that it is feasible to perform an in vivo evaluation of the ARG algorithm with unannounced meals.

Controlling the AP Controller: Controller Performance Assessment and Modification

BACKGROUND

Despite recent advances in closed-loop control of blood glucose concentration (BGC) in people with type 1 diabetes (T1D), online performance assessment and modification of artificial pancreas (AP) control systems remain a challenge as the metabolic characteristics of users change over time.

METHODS

A controller performance assessment and modification system (CPAMS) analyzes the glucose concentration variations and controller behavior, and modifies the parameters of the control system used in the multivariable AP system. Various indices are defined to quantitatively evaluate the controller performance in real time. Controller performance assessment and modification system also incorporates online learning from historical data to anticipate impending disturbances and proactively counteract their effects.

RESULTS

Using a multivariable simulation platform for T1D, the CPAMS is used to enhance the BGC regulation in people with T1D by means of automated insulin delivery with an adaptive learning predictive controller. Controller performance assessment and modification system increases the percentage of time in the target range (70-180) mg/dL by 52.3% without causing any hypoglycemia and hyperglycemia events.

CONCLUSIONS

The results demonstrate a significant improvement in the multivariable AP controller performance by using CPAMS.