Artificial pancreas: past, present, future

Deep reinforcement learning for Type 1 Diabetes: Dual PPO controller for personalized insulin management

BACKGROUND

Managing blood glucose levels in Type 1 Diabetes Mellitus (T1DM) is essential to prevent complications. Traditional insulin delivery methods often require significant patient involvement, limiting automation. Reinforcement Learning (RL)-based controllers offer a promising approach for improving automated insulin administration.

METHODS

We propose a Dual Proximal Policy Optimization (Dual PPO) controller for personalized insulin delivery in a hybrid closed-loop system. The controller optimizes patient-specific insulin bounds through a grid search on pre-trained models to manage both hyperglycemia and hypoglycemia. A safe-control mechanism prevents insulin administration when glucose levels drop below a predefined threshold. The system was evaluated on 10 in silico adult patients using the UVA/Padova simulator, with five-day randomized meal scenarios.

RESULTS

The Dual PPO controller significantly improved Time in Range (TIR) (69.30% ±1.61) compared to a single PPO model (61.69% ±1.54). The system effectively reduced severe hyperglycemia while maintaining a low incidence of severe hypoglycemia. Unlike conventional open-loop methods such as Basal-Bolus (BBC) and Proportional-Integral-Derivative (PIDC) controllers, our system requires minimal patient interaction, eliminating the need for carbohydrate estimation.

CONCLUSIONS

The Dual PPO controller enhances personalized insulin delivery in T1DM, improving glycemic control while reducing patient burden. This approach advances precision medicine in diabetes management, with potential for future real-world applications.

Personalized Blood Glucose Forecasting From Limited CGM Data Using Incrementally Retrained LSTM

For people with Type 1 diabetes (T1D), accurate blood glucose (BG) forecasting is crucial for the effective delivery of insulin by Artificial Pancreas (AP) systems. Deep learning frameworks like Long Short-Term-Memory (LSTM) have been widely used to predict BG using continuous glucose monitor (CGM) data. However, these methods usually require large amounts of training data for personalized forecasts. Moreover, individuals with diabetes exhibit diverse glucose variability (GV), resulting in varying forecast accuracy. To address these limitations, we propose a novel deep learning framework: Incrementally Retrained Stacked LSTM (IS-LSTM). This approach gradually adapts to individualsâ data and employs parameter-transfer for efficiency. We compare our method to three benchmarks using two CGM datasets from individuals with T1D: OpenAPS and Replace-BG. On both datasets, our approach significantly reduces root mean square error compared to the state of the art (Stacked LSTM): from 14.55 to 10.23 mg/dL (OpenAPS) and 17.15 to 13.41 mg/dL (Replace-BG) at 30-minute Prediction Horizon (PH). Clarke error grid analysis demonstrates clinical feasibility with at least 98.81% and 97.25% of predictions within the clinically safe zone at 30- and 60-minute PHs. Further, we demonstrate the effectiveness of our method in cold-start scenarios, which helps new CGM users obtain accurate predictions.

Unsupervised Retrospective Detection of Pressure Induced Failures in Continuous Glucose Monitoring Sensors for T1D Management

Continuous Glucose Monitoring sensors (CGMs) have revolutionized type 1 diabetes (T1D) management. In particular, in several cases, the retrospective analysis of CGM recordings allows clinicians to review and adjust patients' therapy. However, in this set-up, the artifacts that are often present in CGM data could lead to incorrect therapeutic actions. To mitigate this risk, we investigate how to detect one of the most common of these artifacts, the so-called pressure induced sensor attenuations, by means of anomaly detection algorithms. Specifically, these methods belong to the class of unsupervised techniques, which is particularly appealing since it does not require a labeled dataset, hardly available in practice. After having designed five features to highlight the anomalous state of the sensor, 8 different methods (e.g. Isolation Forest and Histogram-based Outlier Score) are assessed both in silico using the UVa/Padova Type 1 Diabetes Simulator and on real data of 36 subjects monitored for about 10 days. In the in silico scenario, the best results are achieved with Isolation Forest, which recognized the 74% of the failures generating on average only 2 false alerts during the whole monitoring time. In real data, Isolation Forest is confirmed to be effective in the detection of failures, achieving a recall of 55% and generating 3 false alarms in 10 days. By allowing to detect more than 50% of the artifacts while discarding only a few portions of correct data in several days of monitoring, the proposed approach could effectively improve the quality of CGM data used by clinicians to retrospectively evaluate and adjust T1D therapy.

Shortcomings in the Evaluation of Blood Glucose Forecasting

OBJECTIVE

Recent years have seen an increase in machine learning (ML)-based blood glucose (BG) forecasting models, with a growing emphasis on potential application to hybrid or closed-loop predictive glucose controllers. However, current approaches focus on evaluating the accuracy of these models using benchmark data generated under the behavior policy, which may differ significantly from the data the model may encounter in a control setting. This study challenges the efficacy of such evaluation approaches, demonstrating that they can fail to accurately capture an ML-based model's true performance in closed-loop control settings.

METHODS

Forecast error measured using current evaluation approaches was compared to the control performance of two forecasters - a ML-based model (LSTM) and a rule-based model (Loop) - in silico when the forecasters were utilized with a model-based controller in a hybrid closed-loop setting.

RESULTS

Under current evaluation standards, LSTM achieves a significantly lower (better) forecast error than Loop with a root mean squared error (RMSE) of vs. at the 30-minute prediction horizon. Yet in a control setting, LSTM led to significantly worse control performance with only 77.14% (IQR 66.57-84.03) time-in-range compared to 86.20% (IQR 78.28-91.21) for Loop.

CONCLUSION

Prevailing evaluation methods can fail to accurately capture the forecaster's performance when utilized in closed-loop settings.

SIGNIFICANCE

Our findings underscore the limitations of current evaluation standards and the need for alternative evaluation metrics and training strategies when developing BG forecasters for closed-loop control systems.

Digital twins for chronic lung diseases

Digital twins have recently emerged in healthcare. They combine advances in cyber-physical systems, modelling and computation techniques, and enable a bidirectional flow of information between the physical and virtual entities. In respiratory medicine, progress in connected devices and artificial intelligence make it technically possible to obtain digital twins that allow real-time visualisation of a patient's respiratory health. Advances in respiratory system modelling also enable the development of digital twins that could be used to predict the effectiveness of different therapeutic approaches for a patient. For researchers, digital twins could lead to a better understanding of the gene-environment-time interactions involved in the development of chronic respiratory diseases. For clinicians and patients, they could facilitate personalised and timely medicine, by enabling therapeutic adaptations specific to each patient and early detection of disease progression. The objective of this review is to allow the reader to explore the concept of digital twins, their feasibility in respiratory medicine, their potential benefits and the challenges to their implementation.

Reinforcement Learning: A Paradigm Shift in Personalized Blood Glucose Management for Diabetes

Background/Objectives: Managing blood glucose levels effectively remains a significant challenge for individuals with diabetes. Traditional methods often lack the flexibility needed for personalized care. This study explores the potential of reinforcement learning-based approaches, which mimic human learning and adapt strategies through ongoing interactions, in creating dynamic and personalized blood glucose management plans. Methods: We developed a mathematical model specifically for patients with type IVP diabetes, validated with data from 10 patients and 17 key parameters. The model includes continuous glucose monitoring (CGM) noise and random carbohydrate intake to simulate real-life conditions. A closed-loop system was designed to enable the application of reinforcement learning algorithms. Results: By implementing a Policy Optimization (PPO) branch, we achieved an average Time in Range (TIR) metric of 73%, indicating improved blood glucose control. Conclusions: This study presents a personalized insulin therapy solution using reinforcement learning. Our closed-loop model offers a promising approach for improving blood glucose regulation, with potential applications in personalized diabetes management.

Data-driven blood glucose level prediction in type 1 diabetes: a comprehensive comparative analysis

Accurate prediction of blood glucose level (BGL) has proven to be an effective way to help in type 1 diabetes management. The choice of input, along with the fundamental choice of model structure, is an existing challenge in BGL prediction. Investigating the performance of different data-driven time series forecasting approaches with different inputs for BGL prediction is beneficial in advancing BGL prediction performance. Limited work has been made in this regard, which has resulted in different conclusions. This paper performs a comprehensive investigation of different data-driven time series forecasting approaches using different inputs. To do so, BGL prediction is comparatively investigated from two perspectives; the model's approach and the model's input. First, we compare the performance of BGL prediction using different data-driven time series forecasting approaches, including classical time series forecasting, traditional machine learning, and deep neural networks. Secondly, for each prediction approach, univariate input, using BGL data only, is compared to a multivariate input, using data on carbohydrate intake, injected bolus insulin, and physical activity in addition to BGL data. The investigation is performed on two publicly available Ohio datasets. Regression-based and clinical-based metrics along with statistical analyses are performed for evaluation and comparison purposes. The outcomes show that the traditional machine learning model is the fastest model to train and has the best BGL prediction performance especially when using multivariate input. Also, results show that simply adding extra variables does not necessarily improve BGL prediction performance significantly, and data fusion approaches may be required to effectively leverage other variables' information.

Enhanced blood glucose levels prediction with a smartwatch

Ensuring stable blood glucose (BG) levels within the norm is crucial for potential long-term health complications prevention when managing a chronic disease like Type 1 diabetes (T1D), as well as body weight. Therefore, accurately forecasting blood sugar levels holds significant importance for clinicians and specific users, such as type one diabetic patients. In recent years, Continuous Glucose Monitoring (CGM) devices have been developed and are now in use. However, the ability to forecast future blood glucose values is essential for better management. Previous studies proposed the use of food intake documentation in order to enhance the forecasting accuracy. Unfortunately, these methods require the participants to manually record their daily activities such as food intake, drink and exercise, which creates somewhat inaccurate data, and is hard to maintain along time. To reduce the burden on participants and improve the accuracy of BG level predictions, as well as optimize training and prediction times, this study proposes a framework that continuously tracks participants' movements using a smartwatch. The framework analyzes sensor data and allows users to document their activities. We developed a model incorporating BG data, smartwatch sensor data, and user-documented activities. This model was applied to a dataset we collected from a dozen participants. Our study's results indicate that documented activities did not enhance BG level predictions. However, using smartwatch sensors, such as heart rate and step detector data, in addition to blood glucose measurements from the last sixty minutes, significantly improved the predictions.

Advancements in Insulin Pumps: A Comprehensive Exploration of Insulin Pump Systems, Technologies, and Future Directions

Insulin pumps have transformed the way diabetes is managed by providing a more accurate and individualized method of delivering insulin, in contrast to conventional injection routines. This research explores the progression of insulin pumps, following their advancement from initial ideas to advanced contemporary systems. The report proceeds to categorize insulin pumps according to their delivery systems, specifically differentiating between conventional, patch, and implantable pumps. Every category is thoroughly examined, emphasizing its unique characteristics and capabilities. A comparative examination of commercially available pumps is provided to enhance informed decision making. This section provides a thorough analysis of important specifications among various brands and models. Considered factors include basal rate and bolus dosage capabilities, reservoir size, user interface, and compatibility with other diabetes care tools, such as continuous glucose monitoring (CGM) devices and so on. This review seeks to empower healthcare professionals and patients with the essential information to improve diabetes treatment via individualized pump therapy options. It provides a complete assessment of the development, categorization, and full specification comparisons of insulin pumps.

Closed-loop automated drug infusion regulator: A clinically translatable, closed-loop drug delivery system for personalized drug dosing

BACKGROUND

Dosing of chemotherapies is often calculated according to the weight and/or height of the patient or equations derived from these, such as body surface area (BSA). Such calculations fail to capture intra- and interindividual pharmacokinetic variation, which can lead to order of magnitude variations in systemic chemotherapy levels and thus under- or overdosing of patients.

METHODS

We designed and developed a closed-loop drug delivery system that can dynamically adjust its infusion rate to the patient to reach and maintain the drug's target concentration, regardless of a patient's pharmacokinetics (PK).

FINDINGS

We demonstrate that closed-loop automated drug infusion regulator (CLAUDIA) can control the concentration of 5-fluorouracil (5-FU) in rabbits according to a range of concentration-time profiles (which could be useful in chronomodulated chemotherapy) and over a range of PK conditions that mimic the PK variability observed clinically. In one set of experiments, BSA-based dosing resulted in a concentration 7 times above the target range, while CLAUDIA keeps the concentration of 5-FU in or near the targeted range. Further, we demonstrate that CLAUDIA is cost effective compared to BSA-based dosing.

CONCLUSIONS

We anticipate that CLAUDIA could be rapidly translated to the clinic to enable physicians to control the plasma concentration of chemotherapy in their patients.

FUNDING

This work was supported by MIT's Karl van Tassel (1925) Career Development Professorship and Department of Mechanical Engineering and the Bridge Project, a partnership between the Koch Institute for Integrative Cancer Research at MIT and the Dana-Farber/Harvard Cancer Center.

Equivalent Electrical Circuit Approach to Enhance a Transducer for Insulin Bioavailability Assessment

The equivalent electrical circuit approach is explored to improve a bioimpedance-based transducer for measuring the bioavailability of synthetic insulin already presented in previous studies. In particular, the electrical parameter most sensitive to the variation of insulin amount injected was identified. Eggplants were used to emulate human electrical behavior under a quasi-static assumption guaranteed by a very low measurement time compared to the estimated insulin absorption time. Measurements were conducted with the EVAL-AD5940BIOZ by applying a sinusoidal voltage signal with an amplitude of 100 mV and acquiring impedance spectra in the range [1-100] kHz. 14 units of insulin were gradually administered using a Lilly's Insulin Pen having a 0.4 cm long needle. Modified Hayden's model was adopted as a reference circuit and the electrical component modeling the extracellular fluids was found to be the most insulin-sensitive parameter. The trnasducer achieves a state-of-the-art sensitivity of 225.90 ml1. An improvement of 223 % in sensitivity, 44 % in deterministic error, 7 % in nonlinearity, and 42 % in reproducibility was achieved compared to previous experimental studies. The clinical impact of the transducer was evaluated by projecting its impact on a Smart Insulin Pen for real-time measurement of insulin bioavailability. The wide gain in sensitivity of the bioimpedance-based transducer results in a significant reduction of the uncertainty of the Smart Insulin Pen. Considering the same improvement in in-vivo applications, the uncertainty of the Smart Insulin Pen is decreased from [Formula: see text]l to [Formula: see text]l.Clinical and Translational Impact Statement: A Smart Insulin Pen based on impedance spectroscopy and equivalent electrical circuit approach could be an effective solution for the non-invasive and real-time measurement of synthetic insulin uptake after subcutaneous administration.

Observer-based control for plasma glucose regulation in type 1 diabetes mellitus patients with unknown input delay

This article introduces an observer-based control strategy tailored for regulating plasma glucose in type 1 diabetes mellitus patients, addressing challenges like unknown time-varying delays and meal disturbances. This control strategy is based on an extended Bergman minimal model, a nonlinear glucose-insulin model to encompass unknown inputs, such as unplanned meals, exercise disturbances, or delays. The primary contribution lies in the design of an observer-based state feedback control in the presence of unknown long delays, which seeks to support and enhance the performance of the traditional artificial pancreas by considering realistic scenarios. The observer and control gains for the observer-based control are computed through linear matrix inequalities formulated from Lyapunov conditions that guarantee closed-loop stability. This design deploys a soft and gentle dynamic response, similar to a natural pancreas, despite meal disturbances and input delays. Numerical tests demonstrate the scheme's effectiveness in glycemic level regulation and hypoglycemic episode avoidance.

Orexin neurons track temporal features of blood glucose in behaving mice

Does the brain track how fast our blood glucose is changing? Knowing such a rate of change would enable the prediction of an upcoming state and a timelier response to this new state. Hypothalamic arousal-orchestrating hypocretin/orexin neurons (HONs) have been proposed to be glucose sensors, yet whether they track glucose concentration (proportional tracking) or rate of change (derivative tracking) is unknown. Using simultaneous recordings of HONs and blood glucose in behaving male mice, we found that maximal HON responses occur in considerable temporal anticipation (minutes) of glucose peaks due to derivative tracking. Analysis of >900 individual HONs revealed glucose tracking in most HONs (98%), with derivative and proportional trackers working in parallel, and many (65%) HONs multiplexed glucose and locomotion information. Finally, we found that HON activity is important for glucose-evoked locomotor suppression. These findings reveal a temporal dimension of brain glucose sensing and link neurobiological and algorithmic views of blood glucose perception in the brain's arousal orchestrators.

Predicting Blood Glucose Levels with Organic Neuromorphic Micro-Networks

Accurate glucose prediction is vital for diabetes management. Artificial intelligence and artificial neural networks (ANNs) are showing promising results for reliable glucose predictions, offering timely warnings for glucose fluctuations. The translation of these software-based ANNs into dedicated computing hardware opens a route toward automated insulin delivery systems ultimately enhancing the quality of life for diabetic patients. ANNs are transforming this field, potentially leading to implantable smart prediction devices and ultimately to a fully artificial pancreas. However, this transition presents several challenges, including the need for specialized, compact, lightweight, and low-power hardware. Organic polymer-based electronics are a promising solution as they have the ability to implement the behavior of neural networks, operate at low voltage, and possess key attributes like flexibility, stretchability, and biocompatibility. Here, the study focuses on implementing software-based neural networks for glucose prediction into hardware systems. How to minimize network requirements, downscale the architecture, and integrate the neural network with electrochemical neuromorphic organic devices, meeting the strict demands of smart implants for in-body computation of glucose prediction is investigated.

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.

Exploring the Impact of Glycemic Control on Diabetic Retinopathy: Emerging Models and Prognostic Implications

This review addresses the complexities of type 1 diabetes (T1D) and its associated complications, with a particular focus on diabetic retinopathy (DR). This review outlines the progression from non-proliferative to proliferative diabetic retinopathy and diabetic macular edema, highlighting the role of dysglycemia in the pathogenesis of these conditions. A significant portion of this review is devoted to technological advances in diabetes management, particularly the use of hybrid closed-loop systems (HCLSs) and to the potential of open-source HCLSs, which could be easily adapted to different patients' needs using big data analytics and machine learning. Personalized HCLS algorithms that integrate factors such as patient lifestyle, dietary habits, and hormonal variations are highlighted as critical to reducing the incidence of diabetes-related complications and improving patient outcomes.

Continuous glucose monitoring for automatic real-time assessment of eating events and nutrition: a scoping review

Background

Accurate dietary assessment remains a challenge, particularly in free-living settings. Continuous glucose monitoring (CGM) shows promise in optimizing the assessment and monitoring of ingestive activity (IA, i.e., consumption of calorie-containing foods/beverages), and it might enable administering dietary Just-In-Time Adaptive Interventions (JITAIs).

Objective

In a scoping review, we aimed to answer the following questions: (1) Which CGM approaches to automatically detect IA in (near-)real-time have been investigated? (2) How accurate are these approaches? (3) Can they be used in the context of JITAIs?

Methods

We systematically searched four databases until October 2023 and included publications in English or German that used CGM-based approaches for human (all ages) IA detection. Eligible publications included a ground-truth method as a comparator. We synthesized the evidence qualitatively and critically appraised publication quality.

Results

Of 1,561 potentially relevant publications identified, 19 publications (17 studies, total N = 311; for 2 studies, 2 publications each were relevant) were included. Most publications included individuals with diabetes, often using meal announcements and/or insulin boluses accompanying meals. Inpatient and free-living settings were used. CGM-only approaches and CGM combined with additional inputs were deployed. A broad range of algorithms was tested. Performance varied among the reviewed methods, ranging from unsatisfactory to excellent (e.g., 21% vs. 100% sensitivity). Detection times ranged from 9.0 to 45.0 min.

Conclusion

Several CGM-based approaches are promising for automatically detecting IA. However, response times need to be faster to enable JITAIs aimed at impacting acute IA. Methodological issues and overall heterogeneity among articles prevent recommending one single approach; specific cases will dictate the most suitable approach.

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.

In-human testing of a non-invasive continuous low-energy microwave glucose sensor with advanced machine learning capabilities

Continuous glucose monitoring schemes that avoid finger pricking are of utmost importance to enhance the comfort and lifestyle of diabetic patients. To this aim, we propose a microwave planar sensing platform as a potent sensing technology that extends its applications to biomedical analytes. In this paper, a compact planar resonator-based sensor is introduced for noncontact sensing of glucose. Furthermore, in vivo and in-vitro tests using a microfluidic channel system and in clinical trial settings demonstrate its reliable operation. The proposed sensor offers real-time response and a high linear correlation (R2 ∼ 0.913) between the measured sensor response and the blood glucose level (GL). The sensor is also enhanced with machine learning to predict the variation of body glucose levels for non-diabetic and diabetic patients. This addition is instrumental in triggering preemptive measures in cases of unusual glucose level trends. In addition, it allows for the detection of common artifacts of the sensor as anomalies so that they can be removed from the measured data. The proposed system is designed to noninvasively monitor interstitial glucose levels in humans, introducing the opportunity to create a customized wearable apparatus with the ability to learn.

Multivariable Automated Insulin Delivery System for Handling Planned and Spontaneous Physical Activities

BACKGROUND

Hybrid closed-loop control of glucose levels in people with type 1 diabetes mellitus (T1D) is limited by the requirements on users to manually announce physical activity (PA) and meals to the artificial pancreas system. Multivariable automated insulin delivery (mvAID) systems that can handle unannounced PAs and meals without any manual announcements by the user can improve glycemic control by modulating insulin dosing in response to the occurrence and intensity of spontaneous physical activities.

METHODS

An mvAID system is developed to supplement the glucose measurements with additional physiological signals from a wristband device, with the signals analyzed using artificial intelligence algorithms to automatically detect the occurrence of PA and estimate its intensity. This additional information gained from the physiological signals enables more proactive insulin dosing adjustments in response to both planned exercise and spontaneous unanticipated physical activities.

RESULTS

In silico studies of the mvAID illustrate the safety and efficacy of the system. The mvAID is translated to pilot clinical studies to assess its performance, and the clinical experiments demonstrate an increased time in range and reduced risk of hypoglycemia following unannounced PA and meals.

CONCLUSIONS

The mvAID systems can increase the safety and efficacy of insulin delivery in the presence of unannounced physical activities and meals, leading to improved lives and less burden on people with T1D.

Artificial intelligence in diabetes management: Advancements, opportunities, and challenges

The increasing prevalence of diabetes, high avoidable morbidity and mortality due to diabetes and diabetic complications, and related substantial economic burden make diabetes a significant health challenge worldwide. A shortage of diabetes specialists, uneven distribution of medical resources, low adherence to medications, and improper self-management contribute to poor glycemic control in patients with diabetes. Recent advancements in digital health technologies, especially artificial intelligence (AI), provide a significant opportunity to achieve better efficiency in diabetes care, which may diminish the increase in diabetes-related health-care expenditures. Here, we review the recent progress in the application of AI in the management of diabetes and then discuss the opportunities and challenges of AI application in clinical practice. Furthermore, we explore the possibility of combining and expanding upon existing digital health technologies to develop an AI-assisted digital health-care ecosystem that includes the prevention and management of diabetes.

A 2-dimensional model framework for blood glucose prediction based on iterative learning control architecture

The accurate, timely, and personalized prediction for future blood glucose (BG) levels is undoubtedly needed for further advancement of diabetes management technologies. Human inherent circadian rhythm and regular lifestyle resulting in similarity of daily glycemic dynamics play a positive role in the prediction of blood glucose. Inspired by the iterative learning control (ILC) method in the field of automatic control, a 2-dimensional (2-D) model framework is constructed to predict the future blood glucose levels by taking both the short-range information within a day (intra-day) and long-range information between days (inter-day) into account. In this framework, the radial basis function neural network was applied to capture nonlinear relationships in glycemic metabolism, that is, short-range temporal dependence and long-range contemporaneous dependence on previous days. We build models for each patient, and the models were tested on the in silico datasets at various prediction horizons (PHs). The learning model developed in the 2-D framework successfully increases the accuracy and reduces the delay of predictions. This modeling framework provides a new point of view for BG level prediction and contributes to the development of personalized glucose management, such as hypoglycemia warning and glycemic control.

Deep Multitask Learning by Stacked Long Short-Term Memory for Predicting Personalized Blood Glucose Concentration

The adverse glycemic events triggered by the inaccurate insulin infusion in Type I diabetes (T1D) can lead to fatal complications. Predicting blood glucose concentration (BGC) based on clinical health records is critical for control algorithms in the artificial pancreas (AP) and aiding in medical decision support. This paper presents a novel deep learning (DL) model incorporating multitask learning (MTL) for personalized blood glucose prediction. The network architecture consists of shared and clustered hidden layers. Two layers of stacked long short-term memory (LSTM) form the shared hidden layers that learn generalized features from all subjects. The clustered hidden layers comprise two dense layers adapting to the gender-specific variability in the data. Finally, the subject-specific dense layers offer additional fine-tuning to personalized glucose dynamics resulting in an accurate BGC prediction at the output. OhioT1DM clinical dataset is used for the training and performance evaluation of the proposed model. A detailed analytical and clinical assessment have been performed using root mean square (RMSE), mean absolute error (MAE), and Clarke error grid analysis (EGA), respectively, which demonstrates the robustness and reliability of the proposed method. Consistently leading performance has been achieved for 30- (RMSE = 16.06 $\pm$ 2.74, MAE = 10.64 $\pm$ 1.35), 60- (RMSE = 30.89 $\pm$ 4.31, MAE = 22.07 $\pm$ 2.96), 90- (RMSE = 40.51 $\pm$ 5.16, MAE = 30.16 $\pm$ 4.10), and 120-minute (RMSE = 47.39 $\pm$ 5.62, MAE = 36.36 $\pm$ 4.54) prediction horizon (PH). In addition, the EGA analysis confirms the clinical feasibility by maintaining more than 94% BGC predictions in the clinically safe zone for up to 120-minute PH. Moreover, the improvement is established by benchmarking against the state-of-the-art statistical, machine learning (ML), and deep learning (DL) methods.

Prediction of Blood Risk Score in Diabetes Using Deep Neural Networks

Improving the prediction of blood glucose concentration may improve the quality of life of people living with type 1 diabetes by enabling them to better manage their care. Given the anticipated benefits of such a prediction, numerous methods have been proposed. Rather than attempting to predict glucose concentration, a deep learning framework for prediction is proposed in which prediction is performed using a scale for hypo- and hyper-glycemia risk. Using the blood glucose risk score formula proposed by Kovatchev et al., models with different architectures were trained, including, a recurrent neural network (RNN), a gated recurrent unit (GRU), a long short-term memory (LSTM) network, and an encoder-like convolutional neural network (CNN). The models were trained using the OpenAPS Data Commons data set, comprising 139 individuals, each with tens of thousands of continuous glucose monitor (CGM) data points. The training set was composed of 7% of the data set, while the remaining was used for testing. Performance comparisons between the different architectures are presented and discussed. To evaluate these predictions, performance results are compared with the last measurement (LM) prediction, through a sample-and-hold approach continuing the last known measurement forward. The results obtained are competitive when compared to other deep learning methods. A root mean squared error (RMSE) of 16 mg/dL, 24 mg/dL, and 37 mg/dL were obtained for CNN prediction horizons of 15, 30, and 60 min, respectively. However, no significant improvements were found for the deep learning models compared to LM prediction. Performance was found to be highly dependent on architecture and the prediction horizon. Lastly, a metric to assess model performance by weighing each prediction point error with the corresponding blood glucose risk score is proposed. Two main conclusions are drawn. Firstly, going forward, there is a need to benchmark model performance using LM prediction to enable the comparison between results obtained from different data sets. Secondly, model-agnostic data-driven deep learning models may only be meaningful when combined with mechanistic physiological models; here, it is argued that neural ordinary differential equations may combine the best of both approaches. These findings are based on the OpenAPS Data Commons data set and are to be validated in other independent data sets.

Automated insulin delivery systems: from early research to routine care of type 1 diabetes

Automated insulin delivery (AID) systems, so-called closed-loop systems or artificial pancreas, are based upon the concept of insulin supply driven by blood glucose levels and their variations according to body glucose needs, glucose intakes and insulin action. They include a continuous glucose monitoring device which provides a signal to a control algorithm tuning insulin delivery from an infusion pump. The control algorithm is the key of the system since it commands insulin administration in order to maintain blood glucose in a predefined target range and close to a near-normal glucose level. The last two decades have shown dramatic advances toward the use in free life of AID systems for routine care of type 1 diabetes through step-by-step demonstrations of feasibility, safety and efficacy in successive hospital, transitional and outpatient trials. Because of the constraints of pharmacokinetics and dynamics of subcutaneous insulin delivery, the currently available AID systems are all 'hybrid' or 'semi-automated' insulin delivery systems with a need of meal and exercise announcements in order to anticipate rapid glucose variations through pre-meal bolus or pre-exercise reduction of infusion rate. Nevertheless, these AID systems significantly improve time spent in a near-normal range with a reduction of the risk of hypoglycemia and the mental load of managing diabetes in everyday life, representing a milestone in insulin therapy. Expected progression toward fully automated, further miniaturized and integrated, possibly implantable on long-term and more physiological closed-loop systems paves the way for a functional cure of type 1 diabetes.

Data-based modeling for hypoglycemia prediction: Importance, trends, and implications for clinical practice

Background and objective

Hypoglycemia is a key barrier to achieving optimal glycemic control in people with diabetes, which has been proven to cause a set of deleterious outcomes, such as impaired cognition, increased cardiovascular disease, and mortality. Hypoglycemia prediction has come to play a role in diabetes management as big data analysis and machine learning (ML) approaches have become increasingly prevalent in recent years. As a result, a review is needed to summarize the existing prediction algorithms and models to guide better clinical practice in hypoglycemia prevention.

Materials and methods

PubMed, EMBASE, and the Cochrane Library were searched for relevant studies published between 1 January 2015 and 8 December 2022. Five hypoglycemia prediction aspects were covered: real-time hypoglycemia, mild and severe hypoglycemia, nocturnal hypoglycemia, inpatient hypoglycemia, and other hypoglycemia (postprandial, exercise-related).

Results

From the 5,042 records retrieved, we included 79 studies in our analysis. Two major categories of prediction models are identified by an overview of the chosen studies: simple or logistic regression models based on clinical data and data-based ML models (continuous glucose monitoring data is most commonly used). Models utilizing clinical data have identified a variety of risk factors that can lead to hypoglycemic events. Data-driven models based on various techniques such as neural networks, autoregressive, ensemble learning, supervised learning, and mathematical formulas have also revealed suggestive features in cases of hypoglycemia prediction.

Conclusion

In this study, we looked deep into the currently established hypoglycemia prediction models and identified hypoglycemia risk factors from various perspectives, which may provide readers with a better understanding of future trends in this topic.

Recent progress and perspectives of continuous in vivo testing device

Devices for continuous in-vivo testing (CIVT) can detect target substances in real time, thus providing a valuable window into a patient's condition, their response to therapeutics, metabolic activities, and neurotransmitter transmission in the brain. Therefore, CIVT devices have received increased attention because they are expected to greatly assist disease diagnosis and treatment and research on human pathogenesis. However, CIVT has been achieved for only a few markers, and it remains challenging to detect many key markers. Therefore, it is important to summarize the key technologies and methodologies of CIVT, and to examine the direction of future development of CIVT. We review recent progress in the development of CIVT devices, with consideration of the structure of these devices, principles governing continuous detection, and nanomaterials used for electrode modification. This detailed and comprehensive review of CIVT devices serves three purposes: (1) to summarize the advantages and disadvantages of existing devices, (2) to provide a reference for development of CIVT equipment to detect additional important markers, and (3) to discuss future prospects with emphasis on problems that must be overcome for further development of CIVT equipment. This review aims to promote progress in research on CIVT devices and contribute to future innovation in personalized medical treatments.

Continuous Glucose Monitor, Insulin Pump, and Automated Insulin Delivery Therapies for Type 1 Diabetes: An Update on Potential for Cardiovascular Benefits

PURPOSE OF REVIEW

The incidence of type 1 diabetes (T1D) is rising in all age groups. T1D is associated with chronic microvascular and macrovascular complications but improving glycemic trends can delay the onset and slow the progression of these complications. Utilization of technological devices for diabetes management, such as continuous glucose monitors (CGM) and insulin pumps, is increasing, and these devices are associated with improvements in glycemic trends. Thus, device use may be associated with long-term prevention of T1D complications, yet few studies have investigated the direct impacts of devices on chronic complications in T1D. This review will describe common diabetes devices and combination systems, as well as review relationships between device use and cardiovascular outcomes in T1D.

RECENT FINDINGS

Findings from existing cohort and national registry studies suggest that pump use may aid in improving cardiovascular risk factors such as hypertension and dyslipidemia. Furthermore, pump users have been shown to have lower arterial stiffness and better measures of myocardial function. In registry and case-control longitudinal data, pump use has been associated with fewer cardiovascular events and reduction of cardiovascular disease (CVD) and all-cause mortality. CVD is the leading cause of morbidity and mortality in T1D. Consistent use of diabetes devices may protect against the development and progression of macrovascular complications such as CVD through improvement in glycemic trends. Existing literature is limited, but findings suggest that pump use may reduce acute cardiovascular risk factors as well as chronic cardiovascular complications and overall mortality in T1D.

The past, present, and future of chemotherapy with a focus on individualization of drug dosing

While there have been rapid advances in developing new and more targeted drugs to treat cancer, much less progress has been made in individualizing dosing. Even though the introduction of immunotherapies such as CAR T-cells and checkpoint inhibitors, as well as personalized therapies that target specific mutations, have transformed clinical treatment of cancers, chemotherapy remains a mainstay in oncology. Chemotherapies are typically dosed on either a body surface area (BSA) or weight basis, which fails to account for pharmacokinetic differences between patients. Drug absorption, distribution, metabolism, and excretion rates can vary between patients, resulting in considerable differences in exposure to the active drugs. These differences result in suboptimal dosing, which can reduce efficacy and increase side-effects. Therapeutic drug monitoring (TDM), genotype guided dosing, and chronomodulation have been developed to address this challenge; however, despite improving clinical outcomes, they are rarely implemented in clinical practice for chemotherapies. Thus, there is a need to develop interventions that allow for individualized drug dosing of chemotherapies, which can help maximize the number of patients that reach the most efficacious level of drug in the blood while mitigating the risks of underdosing or overdosing. In this review, we discuss the history of the development of chemotherapies, their mechanisms of action and how they are dosed. We discuss substantial intraindividual and interindividual variability in chemotherapy pharmacokinetics. We then propose potential engineering solutions that could enable individualized dosing of chemotherapies, such as closed-loop drug delivery systems and bioresponsive biomaterials.

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.

Data-Driven Supervised Compression Artifacts Detection on Continuous Glucose Sensors

Continuous Glucose Monitoring (CGM) sensors micro-invasively provide frequent glucose readings, improving the management of Type 1 diabetic patients' life and making available reach data-sets for retrospective analysis. Unlikely, CGM sensors are subject to failures, such as compression artifacts, that might impact on both real-time and respective CGM use. In this work is focused on retrospective detection of compression artifacts. An in-silico dataset is generated using the T1D UVa/Padova simulator and compression artifacts are subsequently added in known position, thus creating a dataset with perfectly accurate faulty/not-faulty labels. The problem of compression artifact detection is then faced with supervised data-driven techniques, in particular using Random Forest algorithm. The detection performance guaranteed by the method on in-silico data is satisfactory, opening the way for further analysis on real-data.

A Nonlinear State Observer for the Bi-Hormonal Intraperitoneal Artificial Pancreas

Currently, continuous glucose monitoring sensors are used in the artificial pancreas to monitor blood glucose levels. However, insulin and glucagon concentrations in different parts of the body cannot be measured in real-time, and determining body glucagon sensitivity is not feasible. Estimating these states provides more information about the current system status, facilitating improved decision-making by the model-based controller. In this regard, the aim of this paper is to design a nonlinear high-gain observer for a bi-hormonal artificial pancreas in the presence of measurement noises, model uncertainties, and disturbances. The model used in the observer is based on an existing intraperitoneal nonlinear animal model in the literature. This model is modified by assuming that insulin can directly transfer from the peritoneal cavity to the bloodstream. Based on a set of realistic assumptions, one model is considered after each hormone infusion, and two observers are separately designed. The model is divided into the insulin-phase and glucagon-phase models based on a set of realistic assumptions. Thereafter, two high-gain observers are designed separately for these phases contributing to estimating the non-measurable states. The observer error is proven to be locally uniformly ultimately bounded, and it is verified that any asymptotically stable control laws remain stable in the presence of the observer. The performance of the observers with different gains is evaluated for a scenario with multiple insulin and glucagon infusions. The proposed observer converges to a finite error, according to the results. Clinical relevance- In Type 1 diabetic patients, the developed observer can be employed in a closed-loop artificial pan-creas to improve the performance of model-based controllers. It estimates the key states, which are necessary for forecasting the body's response to insulin and glucagon boluses.

Practical constraint definition in safety schemes for artificial pancreas systems

Introduction:

Artificial pancreas systems usually define an insulin-on-board constraint ([Formula: see text]) for safety schemes to limit the insulin infusion and avoid hypoglycemia during the closed-loop performance. Several methods have been proposed with impractical considerations requiring information from the prandial events or complex procedures for ambulatory use.

Methods:

This paper presents a simple method that consists of two novel rules that allow finding an [Formula: see text] based only on common clinical parameters that do not require patient intervention. The method robustness was evaluated using a control system coupled to a safety layer under demanding scenarios implemented on the FDA-approved simulator for preclinical studies.

Results:

The method maintains a safe performance, even in the face of interpatient variability, hybrid and fully automatic implementations of an artificial pancreas system, and uncertain settings. Both proposed rules work as effectively or even better and without the patient intervention than other methods that have already been clinically validated.

Conclusion:

This method can be used to define a constant [Formula: see text] that ensures performance and safety of the control system, even under scenarios with incorrect clinical data. Unlike other methods, this method only requires reliable information that is easily obtained from the patient, such as their total daily dose of insulin or body mass.

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.

Switching from predictive low glucose suspend to advanced hybrid closed loop control: Effects on glucose control and patient reported outcomes

AIMS

Automated insulin delivery improves glucose control. Aim of this study was to compare in real life the effects on glucose control and patient reported outcomes of an advanced hybrid closed loop system (Control-IQ), versus a simpler system with predictive low glucose suspend function (Basal-IQ).

METHODS

Thirty-one type 1 diabetic subjects were studied during Basal-IQ and after switching to Control-IQ. Variables analyzed were time spent in range (70-180 mg/dL), in tight range (70-140 mg/dL), above range (>180 mg/dL), below range (<70 mg/dL), mean glucose, coefficient of variation and glycated hemoglobin. Questionnaires were administered regarding therapy satisfaction (Diabetes Treatment Satisfaction Questionnaire in status/change form), fear of hypoglycemia (Hypoglycemia Fear Survey), quality of sleep (Pittsburgh Sleep Quality Index).

RESULTS

After 12 weeks of Control-IQ, time in range increased from 62.7 to 74.0%, p < 0.0001, time in tight range increased from 37.1 to 44.6 %, p < 0.001, time above range decreased from 35.6 to 24.4% p < 0.0001. Improvements were observed in mean glucose and glucose variability. Glycated hemoglobin decreased from 7.0% (53 mmol/mol) to 6.6% (49 mmol/mol), p < 0.0001. Subjects using Control-IQ manifested greater satisfaction and less fear of hypoglycemia.

CONCLUSION

Compared to Basal-IQ, Control-IQ improves glucose control and therapy satisfaction.

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.

Blood Glucose Level Prediction: Advanced Deep-Ensemble Learning Approach

Optimal and sustainable control of blood glucose levels (BGLs) is the aim of type-1 diabetes management. The automated prediction of BGL using machine learning (ML) algorithms is considered as a promising tool that can support this aim. In this context, this paper proposes new advanced ML architectures to predict BGL leveraging deep learning and ensemble learning. The deep-ensemble models are developed with novel meta-learning approaches, where the feasibility of changing the dimension of a univariate time series forecasting task is investigated. The models are evaluated regression-wise and clinical-wise. The performance of the proposed ensemble models are compared with benchmark non-ensemble models. The results show the superior performance of the developed ensemble models over developed non-ensemble benchmark models and also show the efficacy of the proposed meta-learning approaches.

Artificial intelligence perspective in the future of endocrine diseases

In recent years, artificial intelligence (AI) shows promising results in the diagnosis, prediction, and management of diseases. The move from handwritten medical notes to electronic health records and a huge number of digital data commenced in the era of big data in medicine. AI can improve physician performance and help better clinical decision making which is called augmented intelligence. The methods applied in the research of AI and endocrinology include machine learning, artificial neural networks, and natural language processing. Current research in AI technology is making major efforts to improve decision support systems for patient use. One of the best-known applications of AI in endocrinology was seen in diabetes management, which includes prediction, diagnosis of diabetes complications (measuring microalbuminuria, retinopathy), and glycemic control. AI-related technologies are being found to assist in the diagnosis of other endocrine diseases such as thyroid cancer and osteoporosis. This review attempts to provide insight for the development of prospective for AI with a focus on endocrinology.

From insulin injections to islet transplantation: An overview of the journey

When, in 1869, Paul Langerhans detected the "islands of tissue" in the pancreas, he took the first step on a journey towards islet transplantation as a treatment for type 1 diabetes. The route has embraced developments across biosciences, surgery, gene therapy and clinical research. This review highlights major milestones along that journey involving whole pancreas transplantation, islet transplantation, the creation of surrogate insulin-secreting cells and novel islet-like structures using genetic and bio-engineering technologies. To obviate the paucity of human tissue, pluripotent stem cells and non-β-cells within the pancreas have been modified to create physiologically responsive insulin-secreting cells. Before implantation, these can be co-cultured with endothelial cells to promote vascularisation and with immune defence cells such as placental amnion cells to reduce immune rejection. Scaffolds to contain grafts and facilitate surgical placement provide further opportunities to achieve physiological insulin delivery. Alternatively, xenotransplants such as porcine islets might be reconsidered as opportunities exist to circumvent safety concerns and immune rejection. Thus, despite a long and arduous journey, the prospects for increased use of tissue transplantation to provide physiological insulin replacement are drawing ever closer.

Designing biomaterials for the modulation of allogeneic and autoimmune responses to cellular implants in Type 1 Diabetes

The effective suppression of adaptive immune responses is essential for the success of allogeneic cell therapies. In islet transplantation for Type 1 Diabetes, pre-existing autoimmunity provides an additional hurdle, as memory autoimmune T cells mediate both an autoantigen-specific attack on the donor beta cells and an alloantigen-specific attack on the donor graft cells. Immunosuppressive agents used for islet transplantation are generally successful in suppressing alloimmune responses, but dramatically hinder the widespread adoption of this therapeutic approach and fail to control memory T cell populations, which leaves the graft vulnerable to destruction. In this review, we highlight the capacity of biomaterials to provide local and nuanced instruction to suppress or alter immune pathways activated in response to an allogeneic islet transplant. Biomaterial immunoisolation is a common approach employed to block direct antigen recognition and downstream cell-mediated graft destruction; however, immunoisolation alone still permits shed donor antigens to escape into the host environment, resulting in indirect antigen recognition, immune cell activation, and the creation of a toxic graft site. Designing materials to decrease antigen escape, improve cell viability, and increase material compatibility are all approaches that can decrease the local release of antigen and danger signals into the implant microenvironment. Implant materials can be further enhanced through the local delivery of anti-inflammatory, suppressive, chemotactic, and/or tolerogenic agents, which serve to control both the innate and adaptive immune responses to the implant with a benefit of reduced systemic effects. Lessons learned from understanding how to manipulate allogeneic and autogenic immune responses to pancreatic islets can also be applied to other cell therapies to improve their efficacy and duration. STATEMENT OF SIGNIFICANCE: This review explores key immunologic concepts and critical pathways mediating graft rejection in Type 1 Diabetes, which can instruct the future purposeful design of immunomodulatory biomaterials for cell therapy. A summary of immunological pathways initiated following cellular implantation, as well as current systemic immunomodulatory agents used, is provided. We then outline the potential of biomaterials to modulate these responses. The capacity of polymeric encapsulation to block some powerful rejection pathways is covered. We also highlight the role of cellular health and biocompatibility in mitigating immune responses. Finally, we review the use of bioactive materials to proactively modulate local immune responses, focusing on key concepts of anti-inflammatory, suppressive, and tolerogenic agents.

A comparison among three maximal mathematical models of the glucose-insulin system

The most well-known and widely used mathematical representations of the physiology of a diabetic individual are the Sorensen and Hovorka models as well as the UVAPadova Simulator. While the Hovorka model and the UVAPadova Simulator only describe the glucose metabolism of a subject with type 1 diabetes, the Sorensen model was formulated to simulate the behaviour of both normal and diabetic individuals. The UVAPadova model is the most known model, accepted by the FDA, with a high level of complexity. The Hovorka model is the simplest of the three models, well documented and used primarily for the development of control algorithms. The Sorensen model is the most complete, even though some modifications were required both to the model equations (adding useful compartments for modelling subcutaneous insulin delivery) and to the parameter values. In the present work several simulated experiments, such as IVGTTs and OGTTs, were used as tools to compare the three formulations in order to establish to what extent increasing complexity translates into richer and more correct physiological behaviour. All the equations and parameters used for carrying out the simulations are provided.

Engineered insulin-polycation complexes for glucose-responsive delivery with high insulin loading

Glucose-responsive insulin delivery systems have the potential to improve quality of life for individuals with diabetes by improving blood sugar control and limiting the risk of hypoglycemia. However, systems with desirable insulin release kinetics and high loading capacities have proven difficult to achieve. Here, we report the development of electrostatic complexes (ECs) comprised of insulin, a polycation, and glucose oxidase (GOx). Under normoglycemic physiological conditions, insulin carries a slight negative charge and forms a stable EC with the polycation. In hyperglycemia, the encapsulated glucose-sensing enzyme GOx converts glucose to gluconic acid and lowers the pH of the microenvironment, causing insulin to adopt a positive charge. Thus, the electrostatic interactions are disrupted, and insulin is released. Using a model polycation, we conducted molecular dynamics simulations to model these interactions, synthesized ECs with > 50% insulin loading capacity, and determined in vitro release kinetics. We further showed that a single dose of ECs can provide a glycemic profile in streptozotocin-induced diabetic mice that mimics healthy mice over a 9 h period with 2 glucose tolerance tests.

A review of biosensor technology and algorithms for glucose monitoring

Diabetes mellitus (DM) has become a serious illness in the whole world. Until now, there is no effective cure for patients with DM. It is well known that the glucose level is one key factor to determine the progress of DM. It is also an important reference to carry out the accurate and timely treatment for patients with DM. In this article, the related biosensors technology that can be utilized to identify and predict glucose level are reviewed in detail, including the algorithms that can help to achieve numerical value of glucose level. Firstly, the biosensor technology based on the physiological fluids are illustrated, including blood, sweat, interstitial fluid, ocular fluid, and other available fluids. Secondly, the algorithms for achieving numerical value of glucose level are investigated, including the physiological model-based method and the machine learning-based method. Finally, the future development trend and challenges of glucose level monitoring are given and the conclusions are drawn.

Multifunctional Biosensors Made with Self-Healable Silk Fibroin Imitating Skin

We report on robust silk fibroin (SF) gels fabricated by incorporating cellulose nanocrystals (SF/CNC) as a "tough" unit and photopolymerization of acrylamide as an "elastic" segment. The addition of CNC affects the refolding process of SF molecules controlled by nucleation via templating, resulting in a stable mesoscopic structure. The gel shows robust mechanical stability (88.8% of initial stress after 1000 compression cycles) and excellent adhesion to various materials. The connected gel can recover its ionic conductivity within 20 s and be stretched to a maximum strain of 498% after healing for 10 h with an efficiency of 95.2%. This multifunctional gel sensor can sensitively detect different toxic gases and small-scale and large-scale human motions in real-time. Its sensitivity is calculated as GF = 3.84 at 0-200% strain. Especially, the gel with 5 wt % thermochromic pigments as a visual temperature indicator can quickly reflect abnormal human body temperature according to the color change. Therefore, the strategy shows potential applications in flexible electrodes, biomimetic sensors, and visual biosensors.

Modulating the foreign body response of implants for diabetes treatment

Diabetes Mellitus is a group of diseases characterized by high blood glucose levels due to patients' inability to produce sufficient insulin. Current interventions often require implants that can detect and correct high blood glucose levels with minimal patient intervention. However, these implantable technologies have not reached their full potential in vivo due to the foreign body response and subsequent development of fibrosis. Therefore, for long-term function of implants, modulating the initial immune response is crucial in preventing the activation and progression of the immune cascade. This review discusses the different molecular mechanisms and cellular interactions involved in the activation and progression of foreign body response (FBR) and fibrosis, specifically for implants used in diabetes. We also highlight the various strategies and techniques that have been used for immunomodulation and prevention of fibrosis. We investigate how these general strategies have been applied to implants used for the treatment of diabetes, offering insights on how these devices can be further modified to circumvent FBR and fibrosis.

Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study

BACKGROUND

Closed-loop insulin delivery systems, which integrate continuous glucose monitoring (CGM) and algorithms that continuously guide insulin dosing, have been shown to improve glycaemic control. The ability to predict future glucose values can further optimize such devices. In this study, we used machine learning to train models in predicting future glucose levels based on prior CGM and accelerometry data.

METHODS

We used data from The Maastricht Study, an observational population-based cohort that comprises individuals with normal glucose metabolism, prediabetes, or type 2 diabetes. We included individuals who underwent >48h of CGM (n = 851), most of whom (n = 540) simultaneously wore an accelerometer to assess physical activity. A random subset of individuals was used to train models in predicting glucose levels at 15- and 60-minute intervals based on either CGM data or both CGM and accelerometer data. In the remaining individuals, model performance was evaluated with root-mean-square error (RMSE), Spearman's correlation coefficient (rho) and surveillance error grid. For a proof-of-concept translation, CGM-based prediction models were optimized and validated with the use of data from individuals with type 1 diabetes (OhioT1DM Dataset, n = 6).

RESULTS

Models trained with CGM data were able to accurately predict glucose values at 15 (RMSE: 0.19mmol/L; rho: 0.96) and 60 minutes (RMSE: 0.59mmol/L, rho: 0.72). Model performance was comparable in individuals with type 2 diabetes. Incorporation of accelerometer data only slightly improved prediction. The error grid results indicated that model predictions were clinically safe (15 min: >99%, 60 min >98%). Our prediction models translated well to individuals with type 1 diabetes, which is reflected by high accuracy (RMSEs for 15 and 60 minutes of 0.43 and 1.73 mmol/L, respectively) and clinical safety (15 min: >99%, 60 min: >91%).

CONCLUSIONS

Machine learning-based models are able to accurately and safely predict glucose values at 15- and 60-minute intervals based on CGM data only. Future research should further optimize the models for implementation in closed-loop insulin delivery systems.

Current treatment options and challenges in patients with Type 1 diabetes: Pharmacological, technical advances and future perspectives

Type 1 diabetes mellitus imposes a significant burden of complications and mortality, despite important advances in treatment: subjects affected by this disease have also a worse quality of life-related to disease management. To overcome these challenges, different new approaches have been proposed, such as new insulin formulations or innovative devices. The introduction of insulin pumps allows a more physiological insulin administration with a reduction of HbA1c level and hypoglycemic risk. New continuous glucose monitoring systems with better accuracy have allowed, not only better glucose control, but also the improvement of the quality of life. Integration of these devices with control algorithms brought to the creation of the first artificial pancreas, able to independently gain metabolic control without the risk of hypo- and hyperglycemic crisis. This approach has revolutionized the management of diabetes both in terms of quality of life and glucose control. However, complete independence from exogenous insulin will be obtained only by biological approaches that foresee the replacement of functional beta cells obtained from stem cells: this will be a major challenge but the biggest hope for the subjects with type 1 diabetes. In this review, we will outline the current scenario of innovative diabetes management both from a technological and biological point of view, and we will also forecast some cutting-edge approaches to reduce the challenges that hamper the definitive cure of diabetes.

Wearable patch delivery system for artificial pancreas health diagnostic-therapeutic application: A review

The advanced stimuli-responsive approaches for on-demand drug delivery systems have received tremendous attention as they have great potential to be integrated with sensing and multi-functional electronics on a flexible and stretchable single platform (all-in-one concept) in order to develop skin-integration with close-loop sensation for personalized diagnostic and therapeutic application. The wearable patch pumps have evolved from reservoir-based to matrix patch and drug-in-adhesive (single-layer or multi-layer) type. In this review, we presented the basic requirements of an artificial pancreas, surveyed the design and technologies used in commercial patch pumps available on the market and provided general information about the latest wearable patch pump. We summarized the various advanced delivery strategies with their mechanisms that have been developed to date and representative examples. Mechanical, electrical, light, thermal, acoustic and glucose-responsive approaches on patch form have been successfully utilized in the controllable transdermal drug delivery manner. We highlighted key challenges associated with wearable transdermal delivery systems, their research direction and future development trends.