Simulation environment to evaluate closed-loop insulin delivery systems in type 1 diabetes

Advanced decision support system for individuals with diabetes on multiple daily injections therapy using reinforcement learning and nearest-neighbors: In-silico and clinical results

Many individuals with diabetes on multiple daily insulin injections therapy use carbohydrate ratios (CRs) and correction factors (CFs) to determine mealtime and correction insulin boluses. The CRs and CFs vary over time due to physiological changes in individuals' response to insulin. Errors in insulin dosing can lead to life-threatening abnormal glucose levels, increasing the risk of retinopathy, neuropathy, and nephropathy. Here, we present a novel learning algorithm that uses Q-learning to track optimal CRs and uses nearest-neighbors based Q-learning to track optimal CFs. The learning algorithm was compared with the run-to-run algorithm A and the run-to-run algorithm B, both proposed in the literature, over an 8-week period using a validated simulator with a realistic scenario created with suboptimal CRs and CFs values, carbohydrate counting errors, and random meals sizes at random ingestion times. From Week 1 to Week 8, the learning algorithm increased the percentage of time spent in target glucose range (4.0 to 10.0 mmol/L) from 51 % to 64 % compared to 61 % and 58 % with the run-to-run algorithm A and the run-to-run algorithm B, respectively. The learning algorithm decreased the percentage of time spent below 4.0 mmol/L from 9 % to 1.9 % compared to 3.4 % and 2.3 % with the run-to-run algorithm A and the run-to-run algorithm B, respectively. The algorithm was also assessed by comparing its recommendations with (i) the endocrinologist's recommendations on two type 1 diabetes individuals over a 16-week period and (ii) real-world individuals' therapy settings changes of 23 individuals (19 type 2 and 4 type 1) over an 8-week period using the commercial Bigfoot Unity Diabetes Management System. The full agreements (i) were 89 % and 76 % for CRs and CFs for the type 1 diabetes individuals and (ii) was 62 % for mealtime doses for the individuals on the commercial Bigfoot system. Therefore, the proposed algorithm has the potential to improve glucose control in individuals with type 1 and type 2 diabetes.

Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportunities

OBJECTIVE

Artificial intelligence and machine learning are transforming many fields including medicine. In diabetes, robust biosensing technologies and automated insulin delivery therapies have created a substantial opportunity to improve health. While the number of manuscripts addressing the topic of applying machine learning to diabetes has grown in recent years, there has been a lack of consistency in the methods, metrics, and data used to train and evaluate these algorithms. This manuscript provides consensus guidelines for machine learning practitioners in the field of diabetes, including best practice recommended approaches and warnings about pitfalls to avoid.

METHODS

Algorithmic approaches are reviewed and benefits of different algorithms are discussed including importance of clinical accuracy, explainability, interpretability, and personalization. We review the most common features used in machine learning applications in diabetes glucose control and provide an open-source library of functions for calculating features, as well as a framework for specifying data sets using data sheets. A review of current data sets available for training algorithms is provided as well as an online repository of data sources.

SIGNIFICANCE

These consensus guidelines are designed to improve performance and translatability of new machine learning algorithms developed in the field of diabetes for engineers and data scientists.

Individualized Models for Glucose Prediction in Type 1 Diabetes: Comparing Black-Box Approaches to a Physiological White-Box One

OBJECTIVE

Accurate blood glucose (BG) prediction are key in next-generation tools for type 1 diabetes (T1D) management, such as improved decision support systems and advanced closed-loop control. Glucose prediction algorithms commonly rely on black-box models. Large physiological models, successfully adopted for simulation, were little explored for glucose prediction, mostly because their parameters are hard to individualize. In this work, we develop a BG prediction algorithm based on a personalized physiological model inspired by the UVA/Padova T1D Simulator. Then we compare white-box and advanced black-box personalized prediction techniques.

METHODS

A personalized nonlinear physiological model is identified from patient data through a Bayesian approach based on Markov Chain Monte Carlo technique. The individualized model was integrated within a particle filter (PF) to predict future BG concentrations. The black-box methodologies considered are non-parametric models estimated via gaussian regression (NP), three deep learning methods: long-short-term-memory (LSTM), gated recurrent unit (GRU), temporal convolutional networks (TCN), and a recursive autoregressive with exogenous input model (rARX). BG forecasting performances are assessed for several prediction horizons (PH) on 12 individuals with T1D, monitored in free-living conditions under open-loop therapy for 10 weeks.

RESULTS

NP models provide the most effective BG predictions by achieving a root mean square error (RMSE), RMSE = 18.99 mg/dL, RMSE = 25.72 mg/dL and RMSE = 31.60 mg/dL, significantly outperforming: LSTM, GRU (for PH = 30 minutes), TCN, rARX, and the proposed physiological model for PH=30, 45 and 60 minutes.

CONCLUSIONS

Black-box strategies remain preferable for glucose prediction even when compared to a white-box model with sound physiological structure and individualized parameters.

ReplayBG: A Digital Twin-Based Methodology to Identify a Personalized Model From Type 1 Diabetes Data and Simulate Glucose Concentrations to Assess Alternative Therapies

OBJECTIVE

Design and assessment of new therapies for type 1 diabetes (T1D) management can be greatly facilitated by in silico simulations. The ReplayBG simulation methodology here proposed allows "replaying" the scenario behind data already collected by simulating the glucose concentration obtained in response to alternative insulin/carbohydrate therapies and evaluate their efficacy leveraging the concept of digital twin.

METHODS

ReplayBG is based on two steps. First, a personalized model of glucose-insulin dynamics is identified using insulin, carbohydrate, and continuous glucose monitoring (CGM) data. Then, this model is used to simulate the glucose concentration that would have been obtained by "replaying" the same portion of data using a different therapy. The validity of the methodology was evaluated on 100 virtual subjects using the UVa/Padova T1D Simulator (T1DS). In particular, the glucose concentration traces simulated by ReplayBG are compared with those provided by T1DS in five different scenarios of insulin and carbohydrate treatment modifications. Furthermore, we compared ReplayBG with a state-of-the-art methodology for the scope. Finally, two case studies using real data are also presented.

RESULTS

ReplayBG simulates with high accuracy the effect of the considered insulin and carbohydrate treatment alterations, performing significantly better than state-of-art method in almost all considered situations.

CONCLUSION

ReplayBG proved to be a reliable and robust tool to retrospectively explore the effect of new treatments for T1D on the glucose dynamics. It is freely available as open source software at https://github.com/gcappon/replay-bg.

SIGNIFICANCE

ReplayBG offers a new approach to preliminary evaluate new therapies for T1D management before clinical trials.

An Adaptive Model Predictive Controller to Address the Biovariability in Blood Clotting Response During Therapy With Warfarin

OBJECTIVE

Effective dosing of anticoagulants aims to prevent blood clot formation while avoiding hemorrhages. This complex task is challenged by several disturbing factors and drug-effect uncertainties, requesting frequent monitoring and adjustment. Biovariability in drug absorption and action further complicates titration and calls for individualized strategies. In this paper, we propose an adaptive closed-loop control algorithm to assist in warfarin therapy management.

METHODS

The controller was designed and tested in silico using an established pharmacometrics model of warfarin, which accounts for inter-subject variability. The control algorithm is an adaptive Model Predictive Control (a-MPC) that leverages a simplified patient model, whose parameters are updated with a Bayesian strategy. Performance was quantitatively evaluated in simulations performed on a population of virtual subjects against an algorithm reproducing medical guidelines (MG) and an MPC controller available in the literature (l-MPC).

RESULTS

The proposed a-MPC significantly (p 0.05) lowers rising time (2.8 vs. 4.4 and 11.2 days) and time out of range (3.3 vs. 7.2 and 12.9 days) with respect to both MG and l-MPC, respectively. Adaptivity grants a significantly (p 0.05) lower number of subjects reaching unsafe INR values compared to when this feature is not present (8.9% vs.15% of subjects presenting an overshoot outside the target range and 0.08% vs. 0.28% of subjects reaching dangerous INR values).

CONCLUSION

The a-MPC algorithm improve warfarin therapy compared to the benchmark therapies.

SIGNIFICANCE

This in-silico validation proves effectiveness of the a-MPC algorithm for anticoagulant administration, paving the way for clinical testing.

The Application of Digital Technologies and Artificial Intelligence in Healthcare: An Overview on Nutrition Assessment

In the last decade, artificial intelligence (AI) and AI-mediated technologies have undergone rapid evolution in healthcare and medicine, from apps to computer software able to analyze medical images, robotic surgery and advanced data storage system. The main aim of the present commentary is to briefly describe the evolution of AI and its applications in healthcare, particularly in nutrition and clinical biochemistry. Indeed, AI is revealing itself to be an important tool in clinical nutrition by using telematic means to self-monitor various health metrics, including blood glucose levels, body weight, heart rate, fat percentage, blood pressure, activity tracking and calorie intake trackers. In particular, the application of the most common digital technologies used in the field of nutrition as well as the employment of AI in the management of diabetes and obesity, two of the most common nutrition-related pathologies worldwide, will be presented.

A simple modeling framework for prediction in the human glucose-insulin system

Forecasting blood glucose (BG) levels with routinely collected data is useful for glycemic management. BG dynamics are nonlinear, complex, and nonstationary, which can be represented by nonlinear models. However, the sparsity of routinely collected data creates parameter identifiability issues when high-fidelity complex models are used, thereby resulting in inaccurate forecasts. One can use models with reduced physiological fidelity for robust and accurate parameter estimation and forecasting with sparse data. For this purpose, we approximate the nonlinear dynamics of BG regulation by a linear stochastic differential equation: we develop a linear stochastic model, which can be specialized to different settings: type 2 diabetes mellitus (T2DM) and intensive care unit (ICU), with different choices of appropriate model functions. The model includes deterministic terms quantifying glucose removal from the bloodstream through the glycemic regulation system and representing the effect of nutrition and externally delivered insulin. The stochastic term encapsulates the BG oscillations. The model output is in the form of an expected value accompanied by a band around this value. The model parameters are estimated patient-specifically, leading to personalized models. The forecasts consist of values for BG mean and variation, quantifying possible high and low BG levels. Such predictions have potential use for glycemic management as part of control systems. We present experimental results on parameter estimation and forecasting in T2DM and ICU settings. We compare the model's predictive capability with two different nonlinear models built for T2DM and ICU contexts to have a sense of the level of prediction achieved by this model.

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.

Modeling the effect of glucagon on endogenous glucose production in type 1 diabetes: On the role of glucagon receptor dynamics

This paper validates a glucoregulatory model including glucagon receptors dynamics in the description of endogenous glucose production (EGP). A set of models from literature are selected for a head-to-head comparison in order to evaluate the role of glucagon receptors. Each EGP model is incorporated into an existing glucoregulatory model and validated using a set of clinical data, where both insulin and glucagon are administered. The parameters of each EGP model are identified in the same optimization problem, minimizing the root mean square error (RMSE) between the simulation and the clinical data. The results show that the RMSE for the proposed receptors-based EGP model was lower when compared to each of the considered models (Receptors approach: 7.13±1.71 mg/dl vs. 7.76±1.45 mg/dl (p=0.066), 8.45±1.38 mg/dl (p=0.011) and 8.99±1.62 mg/dl (p=0.007)). This raises the possibility of considering glucagon receptors dynamics in type 1 diabetes simulators.

Near-optimal feedback control for postprandial glucose regulation in type 1 diabetes

This paper is focused on feedback control of postprandial glucose levels for patients with type 1 Diabetes Mellitus. There are two important limitations that make this a challenging problem. First, the slow subcutaneous insulin pharmacokinetics that introduces a significant lag into the control loop. Second, the positivity constraint on the control action, meaning that it is not possible to remove insulin from the body. In this paper, both issues are explicitly considered in the design process using the internal model control framework, to derive a near-optimal feedback controller. Optimality is understood here as minimizing the blood glucose peak after a meal intake and, at the same time, preventing glucose values below a prescribed threshold. It is shown how the proposed controller approaches the optimal closed-loop performance as a limit case. The theoretical results are supported by a numerical example and the feasibility of the overall strategy under uncertainties is illustrated using an extended version UVa/Padova metabolic simulator.

In Silico Evaluation of the Medtronic 780G System While Using the GS3 and Its Calibration-Free Successor, the G4S Sensor

In silico simulation studies using 5807 virtual patients with insulin dependent diabetes have been conducted to estimate the risk and efficacy with the closed-loop 780G pump when switching between Medtronic Guardian Sensor 3 (GS3) and Medtronic Guardian 4 Sensor (G4S), next generation calibration free glucose sensor. To demonstrate by utilizing a case study that captures the merits of in silico studies with single hormone insulin dependent virtual patients that include variability in pharmacokinetics/pharmacodynamics, age, gender, insulin sensitivity and BMIs. Also, to show that in silico studies can uniquely isolate the effect of a single variable on clinical outcomes. Simulation studies results were compared to clinical and commercial data and were separated by age groups and pump settings. The commercial data, the clinical study data and the simulation studies predicted that switching between GS3 to G4S will introduce a change in glucose average, percentage time between 70 and 180 mg/dL, and percentage time below 70 mg/dL of: 5.2, 3.4, and 3.1 mg/dL, - 1.1, 0.2, and - 1.1%, and - 0.6, - 1.0, and - 0.3%, respectively. We demonstrated that our simulation studies were able to predict the difference in glycemic outcomes when switching between different sensors in real world setting, better than a small clinical controlled study. As predicted, switching between GS3 and G4S sensors with the 780G system does not introduce clinical risk and maintain the clinical outcomes of the sensor. We demonstrated the ability of insulin dependent diabetes virtual patients to predict clinical outcomes and to augment or even replace some small clinical studies.

A physical activity-intensity driven glycemic model for type 1 diabetes

BACKGROUND AND OBJECTIVE

The glucose response to physical activity for a person with type 1 diabetes (T1D) depends upon the intensity and duration of the physical activity, plasma insulin concentrations, and the individual physical fitness level. To accurately model the glycemic response to physical activity, these factors must be considered.

METHODS

Several physiological models describing the glycemic response to physical activity are proposed by incorporating model terms proportional to the physical activity intensity and duration describing endogenous glucose production (EGP), glucose utilization, and glucose transfer from the plasma to tissues. Leveraging clinical data of T1D during physical activity, each model fit is assessed.

RESULTS

The proposed model with terms accommodating EGP, glucose transfer, and insulin-independent glucose utilization allow for an improved simulation of physical activity glycemic responses with the greatest reduction in model error (mean absolute percentage error: 16.11 ± 4.82 vs. 19.49 ± 5.87, p = 0.002).

CONCLUSIONS

The development of a physiologically plausible model with model terms representing each major contributor to glucose metabolism during physical activity can outperform traditional models with physical activity described through glucose utilization alone. This model accurately describes the relation of plasma insulin and physical activity intensity on glucose production and glucose utilization to generate the appropriately increasing, decreasing or stable glucose response for each physical activity condition. The proposed model will enable the in silico evaluation of automated insulin dosing algorithms designed to mitigate the effects of physical activity with the appropriate relationship between the reduction in basal insulin and the corresponding glycemic excursion.

Leeno: Type 1 diabetes management training environment using smart algorithms

A growing number of Type-1 Diabetes (T1D) patients globally use insulin pump technologies to monitor and manage their glucose levels. Although recent advances in closed-loop systems promise automated pump control in the near future, most patients worldwide still use open-loop continuous subcutaneous insulin infusion (CSII) devices which require close monitoring and continuous regulation. Apart from specialized diabetes units, hospital physicians and nurses generally lack necessary training to support the growing number of patients on insulin pumps. Most hospital staff and providers worldwide have never seen or operated an insulin pump device. T1D patients at nurseries, schools, in hospital emergency rooms, surgery theatres, and in-patient units all require close monitoring and active management. The lack of knowledge and necessary training to support T1D patients on pumps puts them at life-threatening risks. In this work, we develop a training simulation software for hospitals to educate and train their physicians and nurses on how to effectively operate a T1D pump and reduce hypoglycemia events. The software includes clinically validated T1D virtual patients that users can monitor and adjust their pump settings to improve glycemic outcomes. We develop a Fuzzy-Logic learning algorithm that helps guide users learn how to improve pump parameters for these patients. We recruited and trained 13 nurses on the software and report their improvement in pump administration, basal rates adjustments, and ICR modulation.

A software interface for in silico testing of type 2 diabetes treatments

BACKGROUND AND OBJECTIVE

The increasing incidence of diabetes continuously stimulates the research on new antidiabetic drugs. Computer simulation can save time and costs, alleviating the need of animal trials and providing useful information for optimal experiment design and drug dosing. We recently presented a type 2 diabetes (T2D) simulator as tool for in silico testing of new molecules and guiding treatment optimization. Here we present a user-friendly interface aimed to increase the usability of the simulator.

METHOD

The simulator, based on a large-scale glucose, insulin, and C-peptide model and equipped with 100 virtual subjects well describing system dynamics in a real T2D population, is extended to incorporate pharmacokinetics/pharmacodynamics (PK/PD) of a drug of interest. A graphical interface is developed on top of the simulator, allowing an easy design of in silico experiments: specifically, it is possible to select the population size to test, design the experiment (crossover or parallel), its duration and the sampling grid, choose glucose and insulin doses, and define treatment PK/PD and dose administered. The simulator also provides the outcome metrics requested by the user, and performs statistical comparisons among treatments and/or placebo.

RESULTS

To illustrate the potential of the simulator, we provided a case study using metformin and liraglutide. Literature-based PK/PD models of metformin and liraglutide have been incorporated in the simulator, by modulating key drug-sensitive model parameters. An in silico placebo-controlled trial has been done by simulating a three-arm meal tolerance test with subjects receiving placebo, metformin 850 mg, liraglutide 1.80 mg, respectively. The obtained results are in agreement with the clinical evidences, in terms of main glucose, insulin, and C-peptide outcome metrics.

CONCLUSIONS

We developed a user-friendly software interface for the T2D simulator to support the design and test of new antidiabetic drugs and treatments. This increases the simulator usability, making it suitable also for users who have low experience with computer programming.

A simulator with realistic and challenging scenarios for virtual T1D patients undergoing CSII and MDI therapy

In silico simulations have become essential for the development of diabetes treatments. However, currently available simulators are not challenging enough and often suffer from limitations in insulin and meal absorption variability, which is unable to realistically reflect the dynamics of people with type 1 diabetes (T1D). Additionally, T1D simulators are mainly designed for the testing of continuous subcutaneous insulin infusion (CSII) therapies. In this work, a simulator is presented that includes a generated virtual patient (VP) cohort and both fast- and long-acting Glargine-100 U/ml (Gla-100), Glargine-300 U/ml (Gla-300), and Degludec-100 U/ml (Deg-100) insulin models. Therefore, in addition to CSII therapies, multiple daily injections (MDI) therapies can also be tested. The Hovorka model and its published parameter probability distributions were used to generate cohorts of VPs that represent a T1D population. Valid patients are filtered through restrictions that guarantee that they are physiologically acceptable. To obtain more realistic scenarios, basal insulin profile patterns from the literature have been used to identify variability in insulin sensitivity. A library of mixed meals identified from real data has also been included. This work presents and validates a methodology for the creation of realistic VP cohorts that include physiological variability and a simulator that includes challenging and realistic scenarios for in silico testing. A cohort of 47 VPs has been generated and in silico simulations of both CSII and MDI therapies were performed in open-loop. The simulation outcome metrics were contrasted with literature results.

Two Decades of Research in Artificial Pancreas: Insights from a Bibliometric Analysis

BACKGROUND

Artificial pancreas is a well-known research topic devoted to achieving better glycemic outcomes that has been attracting increasing attention over the years. However, there is a lack of systematic, chronological, and synthesizing studies that show the background of the knowledge generation in this field. This study implements a bibliometric analysis to recognize the main documents, type of publications, research categories, countries, keywords, organizations, and authors related to this topic.

METHODS

Web of Science core collection database was accessed from 2000 to 2020 in order to select high-quality scientific documents based on a specific search query. Bibexcel, MS Excel, Power BI, R-Studio, VOSviewer, and CorText software were used for a descriptive and network analysis based on the local database obtained. Bibliometric parameters as the h-index, frequencies, co-authorship and co-ocurrences were computed.

RESULTS

A total of 756 documents were included that show a growing scientific production on this topic with an increasing contribution from engineering. Outstanding authors, organizations, and countries were identified. An analysis of trends in research was conducted according to the scientific categories of the Web of Science database to identify the main research interests of the last 2 decades and the emerging areas with greater prominence in the coming years. A keyword network analysis allowed to identify the main stages in the development of the AP research over time.

CONCLUSIONS

Results reveal a comprehensive background of the knowledge generation for the AP topic during the last 2 decades, which has been strengthened with international collaborations and a remarkable interdisciplinarity between endocrinology and engineering, giving rise to a growing number of research areas over time, where computer science and medical informatics stand out as the main emerging research areas.

Integrating Multiple Inputs Into an Artificial Pancreas System: Narrative Literature Review

Background

Type 1 diabetes (T1D) is a chronic autoimmune disease in which a deficiency in insulin production impairs the glucose homeostasis of the body. Continuous subcutaneous infusion of insulin is a commonly used treatment method. Artificial pancreas systems (APS) use continuous glucose level monitoring and continuous subcutaneous infusion of insulin in a closed-loop mode incorporating a controller (or control algorithm). However, the operation of APS is challenging because of complexities arising during meals, exercise, stress, sleep, illnesses, glucose sensing and insulin action delays, and the cognitive burden. To overcome these challenges, options to augment APS through integration of additional inputs, creating multi-input APS (MAPS), are being investigated.

Objective

The aim of this survey is to identify and analyze input data, control architectures, and validation methods of MAPS to better understand the complexities and current state of such systems. This is expected to be valuable in developing improved systems to enhance the quality of life of people with T1D.

Methods

A literature survey was conducted using the Scopus, PubMed, and IEEE Xplore databases for the period January 1, 2005, to February 10, 2020. On the basis of the search criteria, 1092 articles were initially shortlisted, of which 11 (1.01%) were selected for an in-depth narrative analysis. In addition, 6 clinical studies associated with the selected studies were also analyzed.

Results

Signals such as heart rate, accelerometer readings, energy expenditure, and galvanic skin response captured by wearable devices were the most frequently used additional inputs. The use of invasive (blood or other body fluid analytes) inputs such as lactate and adrenaline were also simulated. These inputs were incorporated to switch the mode of the controller through activity detection, directly incorporated for decision-making and for the development of intermediate modules for the controller. The validation of the MAPS was carried out through the use of simulators based on different physiological models and clinical trials.

Conclusions

The integration of additional physiological signals with continuous glucose level monitoring has the potential to optimize glucose control in people with T1D through addressing the identified limitations of APS. Most of the identified additional inputs are related to wearable devices. The rapid growth in wearable technologies can be seen as a key motivator regarding MAPS. However, it is important to further evaluate the practical complexities and psychosocial aspects associated with such systems in real life.

GLYFE: review and benchmark of personalized glucose predictive models in type 1 diabetes

Due to the sensitive nature of diabetes-related data, preventing them from being easily shared between studies, and the wide discrepancies in their data processing pipeline, progress in the field of glucose prediction is hard to assess. To address this issue, we introduce GLYFE (GLYcemia Forecasting Evaluation), a benchmark of machine learning-based glucose predictive models. We present the accuracy and clinical acceptability of nine different models coming from the literature, from standard autoregressive to more complex neural network-based models. These results are obtained on two different datasets, namely UVA/Padova Type 1 Diabetes Metabolic Simulator (T1DMS) and Ohio Type-1 Diabetes Mellitus (OhioT1DM), featuring artificial and real type 1 diabetic patients respectively. By providing extensive details about the data flow as well as by providing the whole source code of the benchmarking process, we ensure the reproducibility of the results and the usability of the benchmark by the community. Those results serve as a basis of comparison for future studies. In a field where data are hard to obtain, and where the comparison of results from different studies is often irrelevant, GLYFE gives the opportunity of gathering researchers around a standardized common environment.

Replay Simulations with Personalized Metabolic Model for Treatment Design and Evaluation in Type 1 Diabetes

BACKGROUND

The capacity to replay data collected in real life by people with type 1 diabetes mellitus (T1DM) would lead to individualized (vs population) assessment of treatment strategies to control blood glucose and possibly true personalization. Patek et al introduced such a technique, relying on regularized deconvolution of a population glucose homeostasis model to estimate a residual additive signal and reproduce the experimental data; therefore, allowing the subject-specific replay of what-if scenarios by altering the model inputs (eg, insulin). This early method was shown to have a limited domain of validity. We propose and test in silico a similar approach and extend the method applicability.

METHODS

A subject-specific model personalization of insulin sensitivity and meal-absorption parameters is performed. The University of Virginia (UVa)/Padova T1DM simulator is used to generate experimental scenarios and test the ability of the methodology to accurately reproduce changes in glucose concentration to alteration in meal and insulin inputs. Method performance is assessed by comparing true (UVa/Padova simulator) and replayed glucose traces, using the mean absolute relative difference (MARD) and the Clarke error grid analysis (CEGA).

RESULTS

Model personalization led to a 9.08 and 6.07 decrease in MARD over a prior published method of replaying altered insulin scenarios for basal and bolus changes, respectively. Replay simulations achieved high accuracy, with MARD <10% and more than 95% of readings falling in the CEGA A-B zones for a wide range of interventions.

CONCLUSIONS

In silico studies demonstrate that the proposed method for replay simulation is numerically and clinically valid over broad changes in scenario inputs, indicating possible use in treatment optimization.

Modeling Intraperitoneal Insulin Absorption in Patients with Type 1 Diabetes

Standard insulin therapy to treat type 1 diabetes (T1D) consists of exogenous insulin administration through the subcutaneous (SC) tissue. Despite recent advances in insulin formulations, the SC route still suffers from delays and large inter/intra-subject variability that limiting optimal glucose control. Intraperitoneal (IP) insulin administration, despite its higher invasiveness, was shown to represent a valid alternative to the SC one. To date, no mathematical model describing the absorption and distribution of insulin after IP administration is available. Here, we aim to fill this gap by using data from eight patients with T1D, treated by implanted IP pump, studied in a hospitalized setting, with frequent measurements of plasma insulin and glucose concentration. A battery of models describing insulin kinetics after IP administration were tested. Model comparison and selection were performed based on model ability to predict the data, precision of parameters and parsimony criteria. The selected model assumed that the insulin absorption from the IP space was described by a linear, two-compartment model, coupled with a two-compartment model of whole-body insulin kinetics with hepatic insulin extraction controlled by hepatic insulin. Future developments include model incorporation into the UVa/Padova T1D Simulator for testing open- and closed-loop therapies with IP insulin administration.

Modelling glucose dynamics during moderate exercise in individuals with type 1 diabetes

The artificial pancreas is a closed-loop insulin delivery system that automatically regulates glucose levels in individuals with type 1 diabetes. In-silico testing using simulation environments accelerates the development of better artificial pancreas systems. Simulation environments need an accurate model that captures glucose dynamics during exercise to simulate real-life scenarios. We proposed six variations of the Bergman Minimal Model to capture the physiological effects of moderate exercise on glucose dynamics in individuals with type 1 diabetes. We estimated the parameters of each model with clinical data using a Bayesian approach and Markov chain Monte Carlo methods. The data consisted of measurements of plasma glucose, plasma insulin, and oxygen consumption collected from a study of 17 adults with type 1 diabetes undergoing aerobic exercise sessions. We compared the models based on the physiological plausibility of their parameters estimates and the deviance information criterion. The best model features (i) an increase in glucose effectiveness proportional to exercise intensity, and (ii) an increase in insulin action proportional to exercise intensity and duration. We validated the selected model by reproducing results from two previous clinical studies. The selected model accurately simulates the physiological effects of moderate exercise on glucose dynamics in individuals with type 1 diabetes. This work offers an important tool to develop strategies for exercise management with the artificial pancreas.

Long-term use of the hybrid artificial pancreas by adjusting carbohydrate ratios and programmed basal rate: A reinforcement learning approach

BACKGROUND AND OBJECTIVES

The hybrid artificial pancreas regulates glucose levels in people with type 1 diabetes. It delivers (i) insulin boluses at meal times based on the meals' carbohydrate content and the carbohydrate ratios (CRs) and (ii) insulin basal, between meals and at night, continuously modulated around individual-specific programmed basal rate. The CRs and programmed basal rate significantly vary between individuals and within the same individual with type 1 diabetes, and using suboptimal values in the hybrid artificial pancreas may degrade glucose control. We propose a reinforcement learning algorithm to adaptively optimize CRs and programmed basal rate to improve the performance of the hybrid artificial pancreas.

METHODS

The proposed reinforcement learning algorithm was designed using the Q-learning approach. The algorithm learns the optimal actions (CRs and programmed basal rate) by applying them to the individual's state (previous day's glucose levels and insulin delivery) based on an exploration and exploitation trade-off. First, outcomes from our simulator were compared to those of a clinical study in 23 individuals with type 1 diabetes and have yielded similar results. Second, the learning algorithm was tested using the simulator with two scenarios. Scenario 1 has fixed meal sizes and ingestion times and scenario 2 has a more realistic eating behavior with random meal sizes, ingestion times, and carbohydrate counting errors.

RESULTS

After about five weeks, the reinforcement learning algorithm improved the percentage of time spent in target range from 67% to 86.7% in scenario 1 and 65.5% to 86% in scenario 2. The percentage of time spent below 4.0 mmol/L decreased from 9% to 0.9% in scenario 1 and 9.5% to 1.1% in scenario 2.

CONCLUSIONS

Results indicate that the proposed algorithm has the potential to improve glucose control in people with type 1 diabetes using the hybrid artificial pancreas. The proposed algorithm is a key in making the hybrid artificial pancreas adaptive for the long-term real life outpatient studies.

Mathematical Models of Meal Amount and Timing Variability With Implementation in the Type-1 Diabetes Patient Decision Simulator

BACKGROUND

In type 1 diabetes (T1D) research, in-silico clinical trials (ISCTs) have proven effective in accelerating the development of new therapies. However, published simulators lack a realistic description of some aspects of patient lifestyle which can remarkably affect glucose control. In this paper, we develop a mathematical description of meal carbohydrates (CHO) amount and timing, with the aim to improve the meal generation module in the T1D Patient Decision Simulator (T1D-PDS) published in Vettoretti et al.

METHODS

Data of 32 T1D subjects under free-living conditions for 4874 days were used. Univariate probability density function (PDF) parametric models with different candidate shapes were fitted, individually, against sample distributions of: CHO amounts of breakfast (CHOB), lunch (CHOL), dinner (CHOD), and snack (CHOS); breakfast timing (TB); and time between breakfast-lunch (TBL) and between lunch-dinner (TLD). Furthermore, a support vector machine (SVM) classifier was developed to predict the occurrence of a snack in future fixed-length time windows. Once embedded inside the T1D-PDS, an ISCT was performed.

RESULTS

Resulting PDF models were: gamma (CHOB, CHOS), lognormal (CHOL, TB), loglogistic (CHOD), and generalized-extreme-values (TBL, TLD). The SVM showed a classification accuracy of 0.8 over the test set. The distributions of simulated meal data were not statistically different from the distributions of the real data used to develop the models (α = 0.05).

CONCLUSIONS

The models of meal amount and timing variability developed are suitable for describing real data. Their inclusion in modules that describe patient behavior in the T1D-PDS can permit investigators to perform more realistic, reliable, and insightful ISCTs.

Development platform for artificial pancreas algorithms

BACKGROUND AND AIMS

Assessing algorithms of artificial pancreas systems is critical in developing automated and fault-tolerant solutions that work outside clinical settings. The development and evaluation of algorithms can be facilitated with a platform that conducts virtual clinical trials. We present in this paper a clinically validated cloud-based distributed platform that supports the development and comprehensive testing of single and dual-hormone algorithms for type 1 diabetes mellitus (T1DM).

METHODS

The platform is built on principles of object-oriented design and runs user algorithms in real-time virtual clinical trials utilizing a multi-threaded environment enabled by concurrent execution over a cloud infrastructure. The platform architecture isolates user algorithms located on personal machines from proprietary patient data running on the cloud. Users import a plugin into their algorithms (Matlab, Python, or Java) to connect to the platform. Once connected, users interact with a graphical interface to design experimental protocols for their trials. Protocols include trial duration in days, mealtimes and amounts, variability in mealtimes and amounts, carbohydrate counting errors, snacks, and onboard insulin levels.

RESULTS

The platform facilitates development by solving the ODE model in the cloud on large CPU-optimized machines, providing a 62% improvement in memory, speed and CPU utilization. Users can easily debug & modify code, test multiple strategies, and generate detailed clinical performance reports. We validated and integrated into the platform a glucoregulatory system of ordinary differential equations (ODEs) parameterized with clinical data to mimic the inter and intra-day variability of glucose responses of 15 T1DM patients.

CONCLUSION

The platform utilizes the validated patient model to conduct virtual clinical trials for the rapid development and testing of closed-loop algorithms for T1DM.

Data-Driven Robust Control for a Closed-Loop Artificial Pancreas

We present a fully closed-loop design for an artificial pancreas (AP) that regulates the delivery of insulin for the control of Type I diabetes. Our AP controller operates in a fully automated fashion, without requiring any manual interaction with the patient (e.g., in the form of meal announcements). A major obstacle to achieving closed-loop insulin control are the "unknown disturbances" related to various aspects of a patient's daily behavior, especially meals and physical activity. Such disturbances can significantly affect the patient's blood glucose levels. To handle such uncertainties, we present a data-driven, robust, model-predictive control framework in which we capture a wide range of individual meal and exercise patterns using uncertainty sets learned from historical data. These uncertainty sets are then used in the insulin controller to achieve automated, precise, and personalized insulin therapy. We provide an extensive in silico evaluation of our robust AP design, demonstrating the potential of the approach. In particular, without the benefit of explicit meal announcements, our approach can regulate glucose levels for large clusters of meal profiles learned from population-wide survey data and cohorts of virtual patients, even in the presence of high carbohydrate disturbances.

A Model-Based Insulin Dose Optimization Algorithm for People With Type 1 Diabetes on Multiple Daily Injections Therapy

OBJECTIVE

Multiple daily injections (MDI) therapy is the most common treatment for type 1 diabetes (T1D) including basal insulin doses to keep glucose levels constant during fasting conditions and bolus insulin doses with meals. Optimal insulin dosing is critical to achieving satisfactory glycemia but is challenging due to inter- and intra-individual variability. Here, we present a novel model-based iterative algorithm that optimizes insulin doses using previous-day glucose, insulin, and meal data.

METHODS

Our algorithm employs a maximum-a-posteriori method to estimate parameters of a model describing the effects of changes in basal-bolus insulin doses. Then, parameter estimates, their confidence intervals, and the goodness of fit, are combined to generate new recommendations. We assessed our algorithm in three ways. First, a clinical data set of 150 days (15 participants) were used to evaluate the proposed model and the estimation method. Second, 60-day simulations were performed to demonstrate the efficacy of the algorithm. Third, a sample 6-day clinical experiment is presented and discussed.

RESULTS

The model fitted the clinical data well with a root-mean-square-error of 1.75 mmol/L. Simulation results showed an improvement in the time in target (3.9-10 mmol/L) from 64% to 77% and a decrease in the time in hypoglycemia (< 3.9 mmol/L) from 8.1% to 3.8%. The clinical experiment demonstrated the feasibility of the algorithm.

CONCLUSION

Our algorithm has the potential to improve glycemic control in people with T1D using MDI.

SIGNIFICANCE

This work is a step forward towards a decision support system that improves their quality of life.

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.

Method to generate a large cohort in-silico for type 1 diabetes

BACKGROUND AND OBJECTIVE

In the last decade, several technological solutions have been proposed as artificial pancreas systems able to treat type 1 diabetes; most often they are built based on a control algorithm that needs to be validated before it is used with real patients. Control algorithms are usually tested with simulation tools that integrate mathematical models related mainly to the glucose-insulin dynamics, but other variables can be considered as well. In general, the simulators have a limited set of subjects. The main goal of this paper is to propose a new computational method to increase the number of virtual subjects, with physiological characteristics, included in the original mathematical models.

METHODS

A subject is defined by a set of parameters given by a mathematical model. From the available reduced number of subjects in the model, the covariance of each parameter of every subject is obtained to establish a mathematical relationship. Then, new sets of parameters are calculated using linear regression methods; this generates larger cohorts, which allows for testing insulin therapies in open-loop or closed-loop scenarios. The new method proposed here increases the number of subjects in a virtual cohort using two versions of Hovorka's mathematical model.

RESULTS

Two covariant cohorts are obtained with linear regression. Both cohorts are clustered to avoid overlapping in the glucose-insulin dynamics and are compared in terms of their qualitative and quantitative behaviours in the normoglycemic range. As a result, there have been generated two larger cohorts (256 subjects) than the original population, which contributes to improving the variability in in-silico tests. In addition, for analysing the characteristics of the covariant generation method, two random cohorts have been generated, where the parameters are obtained individually and independently from each other, exhibiting only distribution limitations so that these cohorts do not have physiological subjects.

CONCLUSIONS

The proposed methodology has enabled the generation of a large cohort of 256 subjects, with different characteristics that are plausible in the T1DM population, significantly increasing the number of available subjects in existing mathematical models. The proposed methodology does not limit the number of subjects that can be generated and thus, it can be used to increase the number of cohorts provided by other mathematical models in diabetes, or even other scientific problems.

Artificial Intelligence in Decision Support Systems for Type 1 Diabetes

Type 1 diabetes (T1D) is a chronic health condition resulting from pancreatic beta cell dysfunction and insulin depletion. While automated insulin delivery systems are now available, many people choose to manage insulin delivery manually through insulin pumps or through multiple daily injections. Frequent insulin titrations are needed to adequately manage glucose, however, provider adjustments are typically made every several months. Recent automated decision support systems incorporate artificial intelligence algorithms to deliver personalized recommendations regarding insulin doses and daily behaviors. This paper presents a comprehensive review of computational and artificial intelligence-based decision support systems to manage T1D. Articles were obtained from PubMed, IEEE Xplore, and ScienceDirect databases. No time period restrictions were imposed on the search. After removing off-topic articles and duplicates, 562 articles were left to review. Of those articles, we identified 61 articles for comprehensive review based on algorithm evaluation using real-world human data, in silico trials, or clinical studies. We grouped decision support systems into general categories of (1) those which recommend adjustments to insulin and (2) those which predict and help avoid hypoglycemia. We review the artificial intelligence methods used for each type of decision support system, and discuss the performance and potential applications of these systems.

Classification of postprandial glycemic patterns in type 1 diabetes subjects under closed-loop control: an in silico study

In this contribution we explore some alternatives in order to obtain filtered and low dimension CGM data to provide well processed CGM data to AP systems. The presented approach explores the possible association of certain patient behaviors with certain glucose patterns. We compare the classical clustering algorithms (K-means, and fuzzy C-means), which has shown some limitations for CGM data processing, with a new clustering algorithm (K-means ellipsoid algorithm) more suited to CGM data. We test this new algorithm in a variety of complex scenarios including variabilty in the amount of ingested carbohydrates, absorption time and intrapatient parameters. The new algorithm overcomes the perceived problems and is able to discriminate between normoglycaemic, moderate and severe hyperglycaemic post-prandial behaviour, even with similar amounts of carbohydrates contained in a meal.

Amount and Type of Dietary Fat, Postprandial Glycemia, and Insulin Requirements in Type 1 Diabetes: A Randomized Within-Subject Trial

OBJECTIVE

The American Diabetes Association recommends individuals with type 1 diabetes (T1D) adjust insulin for dietary fat; however, optimal adjustments are not known. This study aimed to determine 1) the relationship between the amount and type of dietary fat and glycemia and 2) the optimal insulin adjustments for dietary fat.

RESEARCH DESIGN AND METHODS

Adults with T1D using insulin pump therapy attended the research clinic on 9-12 occasions. On the first six visits, participants consumed meals containing 45 g carbohydrate with 0 g, 20 g, 40 g, or 60 g fat and either saturated, monounsaturated, or polyunsaturated fat. Insulin was dosed using individual insulin/carbohydrate ratio as a dual-wave 50/50% over 2 h. On subsequent visits, participants repeated the 20-60-g fat meals with the insulin dose estimated using a model predictive bolus, up to twice per meal, until glycemic control was achieved.

RESULTS

With the same insulin dose, increasing the amount of fat resulted in a significant dose-dependent reduction in incremental area under the curve for glucose (iAUC_glucose) in the early postprandial period (0-2 h; P = 0.008) and increase in iAUC_glucose in the late postprandial period (2-5 h; P = 0.004). The type of fat made no significant difference to the 5-h iAUC_glucose. To achieve glycemic control, on average participants required dual-wave insulin bolus: for 20 g fat, +6% insulin, 74/26% over 73 min; 40 g fat, +6% insulin, 63/37% over 75 min; and 60 g fat, +21% insulin, 49/51% over 105 min.

CONCLUSIONS

This study provides clinical guidance for mealtime insulin dosing recommendations for dietary fat in T1D.

Simulation Software for Assessment of Nonlinear and Adaptive Multivariable Control Algorithms: Glucose - Insulin Dynamics in Type 1 Diabetes

A simulator for testing automatic control algorithms for nonlinear systems with time-varying parameters, variable time delays, and uncertainties is developed. It is based on simulation of virtual patients with Type 1 diabetes (T1D). Nonlinear models are developed to describe glucose concentration (GC) variations based on user-defined scenarios for meal consumption, insulin administration, and physical activity. They compute GC values and physiological variables, such as heart rate, skin temperature, accelerometer, and energy expenditure, that are indicative of physical activities affecting GC dynamics. This is the first simulator designed for assessment of multivariable controllers that consider supplemental physiological variables in addition to GC measurements to improve glycemic control. Virtual patients are generated from distributions of identified model parameters using clinical data. The simulator will enable testing and evaluation of new control algorithms proposed for automated insulin delivery as well as various control algorithms for nonlinear systems with uncertainties, time-varying parameters and delays.

A statistical virtual patient population for the glucoregulatory system in type 1 diabetes with integrated exercise model

Purpose

We introduce two validated single (SH) and dual hormone (DH) mathematical models that represent an in-silico virtual patient population (VPP) for type 1 diabetes (T1D). The VPP can be used to evaluate automated insulin and glucagon delivery algorithms, so-called artificial pancreas (AP) algorithms that are currently being used to help people with T1D better manage their glucose levels. We present validation results comparing these virtual patients with true clinical patients undergoing AP control and demonstrate that the virtual patients behave similarly to people with T1D.

Methods

A single hormone virtual patient population (SH-VPP) was created that is comprised of eight differential equations that describe insulin kinetics, insulin dynamics and carbohydrate absorption. The parameters in this model that represent insulin sensitivity were statistically sampled from a normal distribution to create a population of virtual patients with different levels of insulin sensitivity. A dual hormone virtual patient population (DH-VPP) extended this SH-VPP by incorporating additional equations to represent glucagon kinetics and glucagon dynamics. The DH-VPP is comprised of thirteen differential equations and a parameter representing glucagon sensitivity, which was statistically sampled from a normal distribution to create virtual patients with different levels of glucagon sensitivity. We evaluated the SH-VPP and DH-VPP on a clinical data set of 20 people with T1D who participated in a 3.5-day outpatient AP study. Twenty virtual patients were matched with the 20 clinical patients by total daily insulin requirements and body weight. The identical meals given during the AP study were given to the virtual patients and the identical AP control algorithm that was used to control the glucose of the virtual patients was used on the clinical patients. We compared percent time in target range (70–180 mg/dL), time in hypoglycemia (<70 mg/dL) and time in hyperglycemia (>180 mg/dL) for both the virtual patients and the actual patients.

Results

The subjects in the SH-VPP performed similarly vs. the actual patients (time in range: 78.1 ± 5.1% vs. 74.3 ± 8.1%, p = 0.11; time in hypoglycemia: 3.4 ± 1.3% vs. 2.8 ± 1.7%, p = 0.23). The subjects in the DH-VPP also performed similarly vs. the actual patients (time in range: 75.6 ± 5.5% vs. 71.9 ± 10.9%, p = 0.13; time in hypoglycemia: 0.9 ± 0.8% vs. 1.3 ± 1%, p = 0.19). While the VPPs tended to over-estimate the time in range relative to actual patients, the difference was not statistically significant.

Conclusions

We have verified that a SH-VPP and a DH-VPP performed comparably with actual patients undergoing AP control using an identical control algorithm. The SH-VPP and DH-VPP may be used as a simulator for pre-evaluation of T1D control algorithms.

Assessing the efficacy, safety and utility of 6-month day-and-night automated closed-loop insulin delivery under free-living conditions compared with insulin pump therapy in children and adolescents with type 1 diabetes: an open-label, multicentre, multinational, single-period, randomised, parallel group study protocol

INTRODUCTION

Closed-loop systems titrate insulin based on sensor glucose levels, providing novel means to reduce the risk of hypoglycaemia while improving glycaemic control. We will assess effectiveness of 6-month day-and-night closed-loop insulin delivery compared with usual care (conventional or sensor-augmented pump therapy) in children and adolescents with type 1 diabetes.

METHODS AND ANALYSIS

The trial adopts an open-label, multicentre, multinational (UK and USA), randomised, single-period, parallel design. Participants (n=130) are children and adolescents (aged ≥6 and <19 years) with type 1 diabetes for at least 1 year, and insulin pump use for at least 3 months with suboptimal glycaemic control (glycated haemoglobin ≥58 mmol/mol (7.5%) and ≤86 mmol/mol (10%)). After a 2-3 week run-in period, participants will be randomised to 6-month use of hybrid closed-loop insulin delivery, or to usual care. Analyses will be conducted on an intention-to-treat basis. The primary outcome is glycated haemoglobin at 6 months. Other key endpoints include time in the target glucose range (3.9-10 mmol/L, 70-180 mg/dL), mean sensor glucose and time spent above and below target. Secondary outcomes include SD and coefficient of variation of sensor glucose levels, time with sensor glucose levels <3.5 mmol/L (63 mg/dL) and <3.0 mmol/L (54 mg/dL), area under the curve of glucose <3.5 mmol/L (63 mg/dL), time with glucose levels >16.7 mmol/L (300 mg/dL), area under the curve of glucose >10.0 mmol/L (180 mg/dL), total, basal and bolus insulin dose, body mass index z-score and blood pressure. Cognitive, emotional and behavioural characteristics of participants and caregivers and their responses to the closed-loop and clinical trial will be assessed. An incremental cost-effectiveness ratio for closed-loop will be estimated.

ETHICS AND DISSEMINATION

Cambridge South Research Ethics Committee and Jaeb Center for Health Research Institutional Review Office approved the study. The findings will be disseminated by peer-review publications and conference presentations.

TRIAL REGISTRATION NUMBER

NCT02925299; Pre-results.

Open-loop glucose control: Automatic IOB-based super-bolus feature for commercial insulin pumps

BACKGROUND AND OBJECTIVE

Although there has been significant progress towards closed-loop type 1 diabetes mellitus (T1DM) treatments, most diabetic patients still treat this metabolic disorder in an open-loop manner, based on insulin pump therapy (basal and bolus insulin infusion). This paper presents a method for automatic insulin bolus shaping based on insulin-on-board (IOB) as an alternative to conventional bolus dosing.

METHODS

The methodology presented allows the pump to generate the so-called super-bolus (SB) employing a two-compartment IOB dynamic model. The extra amount of insulin to boost the bolus and the basal cutoff time are computed using the duration of insulin action (DIA). In this way, the pump automatically re-establishes basal insulin when IOB reaches its basal level. Thus, detrimental transients caused by manual or a-priori computations are avoided.

RESULTS

The potential of this method is illustrated via in-silico trials over a 30 patients cohort in single meal and single day scenarios. In the first ones, improvements were found (standard treatment vs. automatic SB) both in percentage time in euglycemia (75g meal: 81.9 ± 15.59 vs. 89.51 ± 11.95, ρ ≃ 0; 100g meal: 75.12 ± 18.23 vs. 85.46 ± 14.96, ρ ≃ 0) and time in hypoglecymia (75g meal: 5.92 ± 14.48 vs. 0.97 ± 4.15, ρ=0.008; 100g meal: 9.5 ± 17.02 vs. 1.85 ± 7.05, ρ=0.014). In a single day scenario, considering intra-patient variability, the time in hypoglycemia was reduced (9.57 ± 14.48 vs. 4.21 ± 6.18, ρ=0.028) and improved the time in euglycemia (79.46 ± 17.46 vs. 86.29 ± 11.73, ρ=0.007).

CONCLUSIONS

The automatic IOB-based SB has the potential of a better performance in comparison with the standard treatment, particularly for high glycemic index meals with high carbohydrate content. Both glucose excursion and time spent in hypoglycemia were reduced.

A Neural-Network-Based Approach to Personalize Insulin Bolus Calculation Using Continuous Glucose Monitoring

BACKGROUND

In type 1 diabetes (T1D) therapy, the calculation of the meal insulin bolus is performed according to a standard formula (SF) exploiting carbohydrate intake, carbohydrate-to-insulin ratio, correction factor, insulin on board, and target glucose. Recently, some approaches were proposed to account for preprandial glucose rate of change (ROC) in the SF, including those by Scheiner and by Pettus and Edelman. Here, the aim is to develop a new approach, based on neural networks (NN), to optimize and personalize the bolus calculation using continuous glucose monitoring information and some easily accessible patient parameters.

METHOD

The UVa/Padova T1D Simulator was used to simulate data of 100 virtual adults in a single-meal noise-free scenario with different conditions in terms of meal amount and preprandial blood glucose and ROC values. An NN was trained to learn the optimal insulin dose using the SF parameters, ROC, body weight, insulin pump basal infusion rate and insulin sensitivity as features. The performance of the NN for meal bolus calculation was assessed by blood glucose risk index (BGRI) and compared to the methods by Scheiner and by Pettus and Edelman.

RESULTS

The NN approach brings to a small but statistically significant ( P < .001) reduction of BGRI value, equal to 0.37, 0.23, and 0.20 versus SF, Scheiner, and Pettus and Edelman, respectively.

CONCLUSION

This preliminary study showed the potentiality of using NNs for the personalization and optimization of the meal insulin bolus calculation. Future work will deal with more realistic scenarios including technological and physiological/behavioral sources of variability.

The UVA/Padova Type 1 Diabetes Simulator Goes From Single Meal to Single Day

BACKGROUND

A new version of the UVA/Padova Type 1 Diabetes (T1D) Simulator is presented which provides a more realistic testing scenario. The upgrades to the previous simulator, which was accepted by the Food and Drug Administration in 2013, are described.

METHOD

Intraday variability of insulin sensitivity (S_I) has been modeled, based on clinical T1D data, accounting for both intra- and intersubject variability of daily S_I. Thus, time-varying distributions of both subject's basal insulin infusion and insulin-to-carbohydrate ratio were calculated and made available to the user. A model of "dawn" phenomenon based on clinical T1D data has been also included. Moreover, the model of subcutaneous insulin delivery has been updated with a recently developed model of commercially available fast-acting insulin analogs. Models of both intradermal and inhaled insulin pharmacokinetics have been included. Finally, new models of error affecting continuous glucose monitoring and self-monitoring of blood glucose devices have been added.

RESULTS

One hundred in silico adults, adolescent, and children have been generated according to the above modifications. The new simulator reproduces the intraday glucose variability observed in clinical data, also describing the nocturnal glucose increase, and the simulated insulin profiles reflect real life data.

CONCLUSIONS

The new modifications introduced in the T1D simulator allow to extend its domain of validity from "single-meal" to "single-day" scenarios, thus enabling a more realistic framework for in silico testing of advanced diabetes technologies including glucose sensors, new insulin molecules and artificial pancreas.

Next-generation, personalised, model-based critical care medicine: a state-of-the art review of in silico virtual patient models, methods, and cohorts, and how to validation them

Critical care, like many healthcare areas, is under a dual assault from significantly increasing demographic and economic pressures. Intensive care unit (ICU) patients are highly variable in response to treatment, and increasingly aging populations mean ICUs are under increasing demand and their cohorts are increasingly ill. Equally, patient expectations are growing, while the economic ability to deliver care to all is declining. Better, more productive care is thus the big challenge. One means to that end is personalised care designed to manage the significant inter- and intra-patient variability that makes the ICU patient difficult. Thus, moving from current "one size fits all" protocolised care to adaptive, model-based "one method fits all" personalised care could deliver the required step change in the quality, and simultaneously the productivity and cost, of care. Computer models of human physiology are a unique tool to personalise care, as they can couple clinical data with mathematical methods to create subject-specific models and virtual patients to design new, personalised and more optimal protocols, as well as to guide care in real-time. They rely on identifying time varying patient-specific parameters in the model that capture inter- and intra-patient variability, the difference between patients and the evolution of patient condition. Properly validated, virtual patients represent the real patients, and can be used in silico to test different protocols or interventions, or in real-time to guide care. Hence, the underlying models and methods create the foundation for next generation care, as well as a tool for safely and rapidly developing personalised treatment protocols over large virtual cohorts using virtual trials. This review examines the models and methods used to create virtual patients. Specifically, it presents the models types and structures used and the data required. It then covers how to validate the resulting virtual patients and trials, and how these virtual trials can help design and optimise clinical trial. Links between these models and higher order, more complex physiome models are also discussed. In each section, it explores the progress reported up to date, especially on core ICU therapies in glycemic, circulatory and mechanical ventilation management, where high cost and frequency of occurrence provide a significant opportunity for model-based methods to have measurable clinical and economic impact. The outcomes are readily generalised to other areas of medical care.

Clinical Impact of Blood Glucose Monitoring Accuracy: An In-Silico Study

BACKGROUND

Patients with diabetes rely on blood glucose (BG) monitoring devices to manage their condition. As some self-monitoring devices are becoming more and more accurate, it becomes critical to understand the relationship between system accuracy and clinical outcomes, and the potential benefits of analytical accuracy.

METHODS

We conducted a 30-day in-silico study in type 1 diabetes mellitus (T1DM) patients using continuous subcutaneous insulin infusion (CSII) therapy and a variety of BG meters, using the FDA-approved University of Virginia (UVA)/Padova Type 1 Simulator. We used simulated meter models derived from the published characteristics of 43 commercial meters. By controlling random events in each parallel run, we isolated the differences in clinical performance that are directly associated with the meter characteristics.

RESULTS

A meter's systematic bias has a significant and inverse effect on HbA1c ( P < .01), while also affecting the number of severe hypoglycemia events. On the other hand, error, defined as the fraction of measurements beyond 5% of the true value, is a predictor of severe hypoglycemia events ( P < .01), but in the absence of bias has a nonsignificant effect on average glycemia (HbA1c). Both bias and error have significant effects on total daily insulin (TDI) and the number of necessary glucose measurements per day ( P < .01). Furthermore, these relationships can be accurately modeled using linear regression on meter bias and error.

CONCLUSIONS

Two components of meter accuracy, bias and error, clearly affect clinical outcomes. While error has little effect on HbA1c, it tends to increase episodes of severe hypoglycemia. Meter bias has significant effects on all considered metrics: a positive systemic bias will reduce HbA1c, but increase the number of severe hypoglycemia attacks, TDI use, and number of fingersticks per day.