Digital Twins in Type 1 Diabetes: A Systematic Review.

Digital twin is a new concept that is rapidly gaining recognition especially in the medical field. Indeed, being a virtual representation of real-world entities and processes, a digital twin can be used to accurately represent the patients' disease, clarify the treatment target, and realize personalized and precise therapies. However, despite being a revolutionary concept, the diffusion of digital twins in type 1 diabetes (T1D) is still limited. In this systematic review, we analyzed structure, operating conditions, and characteristics of digital twins being developed for T1D. Our search covered published documents until March 2024: 220 publications were identified, 37 of which were duplicated entries; in addition, 173 publications were removed after inspection of titles, abstracts, and keywords; and finally, 11 publications were fully reviewed, of which 8 were deemed eligible for inclusion. We found that all eight methodologies are not comprehensive multi-scale virtual replicas of the individual with T1D, but they all focus on describing glucose-insulin metabolism, aiming to simulate glucose concentration resultant from therapeutic interventions. In this review, we will compare and analyze different factors characterizing these digital twins, such as operating principles (mathematical model, twinning procedure, validation and assessment) and the key aspects for practical adoption (inclusion of physical activity, data required for twinning, open-source availability). We will conclude the paper listing which, in our opinion, are the current limitations and future directives of digital twins in T1D, hoping that this article can be helpful to researchers working on diabetes technologies to further develop the use of such an important instrument.

Supervised and Unsupervised Approaches for the Real-Time Detection of Undesired Insulin Suspension Caused by Malfunctions.

BACKGROUND: Automated insulin delivery (AID) systems, permit improved treatment of type 1 diabetes (T1D). Unfortunately, malfunctioning in the insulin pump or in the infusion set can prevent insulin from being administered, reducing the AID efficacy and posing the patient at risk. Different data-driven methods available in the literature can be used to deal with the problem of automatically detecting complete insulin suspension in real-time. This article investigates both supervised and unsupervised strategies and proposes a fair comparison under either population or personalized settings. METHODS: Several algorithms are compared using data generated through the UVA/Padova T1D simulator, a computer simulator widely used to test control strategies in silico and accepted by the Food and Drugs Administration (FDA) as a substitute to animal pre-clinical trials. Two synthetic data sets, each consisting of 100 virtual subjects monitored for 1 month, were generated. Occasional faults of the insulin pump are simulated as complete occlusions by suspending the therapy administration. Personalized algorithms are investigated with unsupervised approaches only, since personalized labels are hardly available. RESULTS: In the population scenario, the supervised approach outperforms the unsupervised strategy. In particular, logistic regression and random forest achieves a recall of 72% and 82%, with 0.12 and 0.21 false positives (FP) per day, respectively. In the personalized setting scenario, the unsupervised algorithms are tailored on each patient and outperform the population ones, in particular isolation forest achieves a recall 80% and 0.06 FPs per day. CONCLUSIONS: This article suggests that unsupervised personalized approach, by addressing the large variability in glucose response among individuals with T1D, is superior to other one-fits-all approaches in detecting insulin suspensions caused by malfunctioning. Population methodologies can be effectively used while waiting to collect sufficient patient data, when the system is installed on a new patient.

Risk of hypoglycemia in type 1 diabetes management: An in-silico sensitivity analysis to assess and rank the quantitative impact of different behavioral factors.

BACKGROUND AND OBJECTIVE: In type 1 diabetes (T1D), a quantitative evaluation of the impact on hypoglycemia of suboptimal therapeutic decision (e.g. incorrect estimation of the ingested carbohydrates, inaccurate insulin timing, etc) is unavailable. Clinical trials to measure sensitivity to patient actions would be expensive, exposed to confounding factors and risky for the participants. In this work, a T1D patient decision simulator (T1D-PDS), realistically reproducing blood glucose dynamics in a large virtual population, is used to perform extensive in-silico trials and the so-derived data employed to implement a sensitivity analysis that ranks different behavioral factors based on their impact on a clinically meaningful parameter, the time below range (TBR). METHODS: Eleven behavioral factors impacting on hypoglycemia are considered. The T1D-PDS was used to perform multiple 2-week simulations involving 100 adults, by testing about 3500 different perturbations for nominal behavior. A local linear approximation of the function linking the TBR and the factors were computed to derive sensitivity indices (SIs), quantifying the impact of each factor on TBR variations. RESULTS: The obtained ranking quantifies importance of factors w.r.t. the others. Factors apparently related to hypoglycemia were correctly placed on the top of the ranking, including systematic (SI=2.05%) and random (SI=1.35%) carb-counting error, hypotreatment dose (SI=-1.21%), insulin bolus time w.r.t. mealtime (SI=1.09%). CONCLUSIONS: The obtained SIs allowed to rank behavioral factors based on their impact on TBR. The behavioral factors identified as most influential can be prioritized in patient training.

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.

High intensity interval training as a novel treatment for impaired awareness of hypoglycaemia in people with type 1 diabetes (HIT4HYPOS): a randomised parallel-group study.

AIMS/HYPOTHESIS: Impaired awareness of hypoglycaemia (IAH) in type 1 diabetes may develop through a process referred to as habituation. Consistent with this, a single bout of high intensity interval exercise as a novel stress stimulus improves counterregulatory responses (CRR) to next-day hypoglycaemia, referred to as dishabituation. This longitudinal pilot study investigated whether 4 weeks of high intensity interval training (HIIT) has sustained effects on counterregulatory and symptom responses to hypoglycaemia in adults with type 1 diabetes and IAH. METHODS: HIT4HYPOS was a single-centre, randomised, parallel-group study. Participants were identified using the Scottish Diabetes Research Network (SDRN) and from diabetes outpatient clinics in NHS Tayside, UK. The study took place at the Clinical Research Centre, Ninewells Hospital and Medical School, Dundee, UK. Participants were aged 18-55 years with type 1 diabetes of at least 5 years' duration and HbA1c levels <75 mmol/mol (<9%). They had IAH confirmed by a Gold score ≥4, modified Clarke score ≥4 or Dose Adjustment For Normal Eating [DAFNE] hypoglycaemia awareness rating of 2 or 3, and/or evidence of recurrent hypoglycaemia on flash glucose monitoring. Participants were randomly allocated using a web-based system to either 4 weeks of real-time continuous glucose monitoring (RT-CGM) or RT-CGM+HIIT. Participants and investigators were not masked to group assignment. The HIIT programme was performed for 20 min on a stationary exercise bike three times a week. Hyperinsulinaemic-hypoglycaemic (2.5 mmol/l) clamp studies with assessment of symptoms, hormones and cognitive function were performed at baseline and after 4 weeks of the study intervention. The predefined primary outcome was the difference in hypoglycaemia-induced adrenaline (epinephrine) responses from baseline following RT-CGM or RT-CGM+HIIT. RESULTS: Eighteen participants (nine men and nine women) with type 1 diabetes (median [IQR] duration 27 [18.75-32] years) and IAH were included, with nine participants randomised to each group. Data from all study participants were included in the analysis. During the 4 week intervention there were no significant mean (SEM) differences between RT-CGM and RT-CGM+HIIT in exposure to level 1 (28 [7] vs 22 [4] episodes, p=0.45) or level 2 (9 [3] vs 4 [1] episodes, p=0.29) hypoglycaemia. The CGM-derived mean glucose level, SD of glucose and glucose management indicator (GMI) did not differ between groups. During the hyperinsulinaemic-hypoglycaemic clamp studies, mean (SEM) change from baseline was greater for the noradrenergic responses (RT-CGM vs RT-CGM+HIIT: -988 [447] vs 514 [732] pmol/l, p=0.02) but not the adrenergic responses (-298 [687] vs 1130 [747] pmol/l, p=0.11) in those participants who had undergone RT-CGM+HIIT. There was a benefit of RT-CGM+HIIT for mean (SEM) change from baseline in the glucagon CRR to hypoglycaemia (RT-CGM vs RT-CGM+HIIT: 1 [4] vs 16 [6] ng/l, p=0.01). Consistent with the hormone response, the mean (SEM) symptomatic response to hypoglycaemia (adjusted for baseline) was greater following RT-CGM+HIIT (RT-CGM vs RT-CGM+HIIT: -4 [2] vs 0 [2], p<0.05). CONCLUSIONS/INTERPRETATION: In this pilot clinical trial in people with type 1 diabetes and IAH, we found continuing benefits of HIIT for overall hormonal and symptomatic CRR to subsequent hypoglycaemia. Our findings also suggest that HIIT may improve the glucagon response to insulin-induced hypoglycaemia. TRIAL REGISTRATION: ISRCTN15373978. FUNDING: Sir George Alberti Fellowship from Diabetes UK (CMF) and the Juvenile Diabetes Research Foundation.

Bayesian denoising algorithm dealing with colored, non-stationary noise in continuous glucose monitoring timeseries.

Introduction: The retrospective analysis of continuous glucose monitoring (CGM) timeseries can be hampered by colored and non-stationary measurement noise. Here, we introduce a Bayesian denoising (BD) algorithm to address both autocorrelation of measurement noise and temporal variability of its variance. Methods: BD utilizes adaptive, a-priori models of signal and noise, whose unknown variances are derived on partially-overlapped CGM windows, via smoothing approach based on linear mean square estimation. The CGM signal and noise variability profiles are then reconstructed using a kernel smoother. BD is first assessed on two simulated datasets, DS1 and DS2. On DS1, the effectiveness of accounting for colored noise is evaluated by comparison against a literature algorithm; on DS2, the effectiveness of accounting for the noise variance temporal variability is evaluated by comparison against a Butterworth filter. BD is then evaluated on 15 CGM timeseries measured by the Dexcom G6 (DR). Results: On DS1, BD allows reducing the root-mean-square-error (RMSE) from 8.10 [6.79-9.24] mg/dL to 6.28 [5.47-7.27] mg/dL (median [IQR]); on DS2, RMSE decreases from 6.85 [5.50-8.72] mg/dL to 5.35 [4.48-6.49] mg/dL. On DR, BD performs a reasonable tracking of noise variance variability and a satisfactory denoising. Discussion: The new algorithm effectively addresses the nature of CGM measurement error, outperforming existing denoising algorithms.

drCORRECT: An Algorithm for the Preventive Administration of Postprandial Corrective Insulin Boluses in Type 1 Diabetes Management.

BACKGROUND: In type 1 diabetes therapy, precise tuning of postprandial corrective insulin boluses (CIBs) is crucial to mitigate hyperglycemia without inducing dangerous hypoglycemic events. Several heuristic formulas accounting for continuous glucose monitoring (CGM) trend have been proposed in the literature. However, these formulas suggest a lot of quantized CIB adjustments, and they lack personalization. METHOD: drCORRECT algorithm proposed in this work employs a patient-specific time parameter and the "dynamic risk" (DR) measure to determine postprandial CIB suggestion. The expected benefits include the reduction of time in hyperglycemia, thanks to the preventive action exploited through DR. drCORRECT has been assessed retrospectively vs the literature methods proposed by Aleppo et al (AL), Bruttomesso et al (BR), and Ziegler et al (ZI) using a data set of 49 CGM daily traces recorded in free-living conditions. Retrospective evaluation of the algorithms is made possible by the use of ReplayBG, a digital twin-based tool that allows assessing alternative insulin therapies on already collected glucose data. Efficacy in terms of glucose control was measured by temporal, risk indicators, and dedicated hyperglycemic/hypoglycemic events metrics. RESULTS: drCORRECT significantly reduces time spent in hyperglycemia when compared with AL and BR (33.52 [24.16, 39.89]% vs 39.76 [22.54, 48.15]% and 36.32 [26.91, 45.93]%, respectively); significantly reduces daily injected insulin (5.97 [3.80, 8.06] U vs 7.5 [5.21, 10.34] U), glycemia risk index (38.78 [26.58, 55.39] vs 40.78 [27.95, 70.30]), and time spent in hypoglycemia (0.00 [0.00, 1.74]% vs 0.00 [0.00, 10.23]%) when compared with ZI, resulting overall in a safer strategy. CONCLUSIONS: The proposed drCORRECT algorithm allows preventive actions thanks to the personalized timing configuration and the introduction of the innovative DR-based CIB threshold, proving to be a valid alternative to the available heuristic literature methods.

Design and Usability Assessment of a User-Centered, Modular Platform for Real-World Data Acquisition in Clinical Trials involving Post-bariatric Surgery Patients.

BACKGROUND: Clinical trials often face challenges in efficient data collection and participant monitoring. To address these issues, we developed the IMPACT platform, comprising a real-time mobile application for data collection and a web-based dashboard for remote monitoring and management. METHODS: This article presents the design, development, and usability assessment of the IMPACT platform customized for patients with post-bariatric surgery hypoglycemia (PBH). We focus on adapting key IMPACT components, including continuous glucose monitoring (CGM), symptom tracking, and meal logging, as crucial elements for user-friendly and efficient PBH monitoring. RESULTS: The adapted IMPACT platform demonstrated effectiveness in data collection and remote participant monitoring. The mobile application allowed patients to easily track their data, while the clinician dashboard provided a comprehensive overview of enrolled patients, featuring filtering options and alert mechanisms for identifying data collection issues. The platform incorporated various visual representations, including time plots and category-based visualizations, which greatly facilitated data interpretation and analysis. The System Usability Scale questionnaire results indicated a high level of usability for the web dashboard, with an average score of 86.3 out of 100. The active involvement of clinicians throughout the development process ensured that the platform allowed for the collection and visualization of clinically meaningful data. CONCLUSIONS: By leveraging IMPACT's existing features and infrastructure, the adapted version streamlined data collection, analysis, and trial customization for PBH research. The platform's high usability underscores its alignment with the requirements for conducting research using continuous real-world data in PBH patients and other populations of interest.

A model to forecast the two-year variation of subjective wellbeing in the elderly population.

BACKGROUND: The ageing global population presents significant public health challenges, especially in relation to the subjective wellbeing of the elderly. In this study, our aim was to investigate the potential for developing a model to forecast the two-year variation of the perceived wellbeing of individuals aged over 50. We also aimed to identify the variables that predict changes in subjective wellbeing, as measured by the CASP-12 scale, over a two-year period. METHODS: Data from the European SHARE project were used, specifically the demographic, health, social and financial variables of 9422 subjects. The subjective wellbeing was measured through the CASP-12 scale. The study outcome was defined as binary, i.e., worsening/not worsening of the variation of CASP-12 in 2 years. Logistic regression, logistic regression with LASSO regularisation, and random forest were considered candidate models. Performance was assessed in terms of accuracy in correctly predicting the outcome, Area Under the Curve (AUC), and F1 score. RESULTS: The best-performing model was the random forest, achieving an accuracy of 65%, AUC = 0.659, and F1 = 0.710. All models proved to be able to generalise both across subjects and over time. The most predictive variables were the CASP-12 score at baseline, the presence of depression and financial difficulties. CONCLUSIONS: While we identify the random forest model as the more suitable, given the similarity of performance, the models based on logistic regression or on logistic regression with LASSO regularisation are also possible options.

The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP.

Machine learning has become a popular tool for learning models of complex dynamics from biomedical data. In Type 1 Diabetes (T1D) management, these models are increasingly been integrated in decision support systems (DSS) to forecast glucose levels and provide preventive therapeutic suggestions, like corrective insulin boluses (CIB), accordingly. Typically, models are chosen based on their prediction accuracy. However, since patient safety is a concern in this application, the algorithm should also be physiologically sound and its outcome should be explainable. This paper aims to discuss the importance of using tools to interpret the output of black-box models in T1D management by presenting a case-of-study on the selection of the best prediction algorithm to integrate in a DSS for CIB suggestion. By retrospectively "replaying" real patient data, we show that two long-short term memory neural networks (LSTM) (named p-LSTM and np-LSTM) with similar prediction accuracy could lead to different therapeutic decisions. An analysis with SHAP-a tool for explaining black-box models' output-unambiguously shows that only p-LSTM learnt the physiological relationship between inputs and glucose prediction, and should therefore be preferred. This is verified by showing that, when embedded in the DSS, only p-LSTM can improve patients' glycemic control.

A Markov Model of Gap Occurrence in Continuous Glucose Monitoring Data for Realistic in Silico Clinical Trials.

BACKGROUND AND OBJECTIVE: Continuous glucose monitoring (CGM) sensors measure interstitial glucose concentration every 1-5 min for days or weeks. New CGM-based diabetes therapies are often tested in in silico clinical trials (ISCTs) using diabetes simulators. Accurate models of CGM sensor inaccuracies and failures could help improve the realism of ISCTs. However, the modeling of CGM failures has not yet been fully addressed in the literature. This work aims to develop a mathematical model of CGM gaps, i.e., occasional portions of missing data generated by temporary sensor errors (e.g., excessive noise or artifacts). METHODS: Two datasets containing CGM traces collected in 167 adults and 205 children, respectively, using the Dexcom G6 sensor (Dexcom Inc., San Diego, CA) were used. Four Markov models, of increasing complexity, were designed to describe three main characteristics: number of gaps for each sensor, gap distribution in the monitoring days, and gap duration. Each model was identified on a portion of each dataset (training set). The remaining portion of each dataset (real test set) was used to evaluate model performance through a Monte Carlo simulation approach. Each model was used to generate 100 simulated test sets with the same size as the real test set. The distributions of gap characteristics on the simulated test sets were compared with those observed on the real test set, using the two-sample Kolmogorov-Smirnov test and the Jensen-Shannon divergence. RESULTS: A six-state Markov model, having two states to describe normal sensor operation and four states to describe gap occurrence, achieved the best results. For this model, the Kolmogorov-Smirnov test found no significant differences between the distribution of simulated and real gap characteristics. Moreover, this model obtained significantly lower Jensen-Shannon divergence values than the other models. CONCLUSIONS: A Markov model describing CGM gaps was developed and validated on two real datasets. The model describes well the number of gaps for each sensor, the gap distribution over monitoring days, and the gap durations. Such a model can be integrated into existing diabetes simulators to realistically simulate CGM gaps in ISCTs and thus enable the development of more effective and robust diabetes management strategies.

Relationship Between Symptom Perception and Postprandial Glycemic Profiles in Patients With Postbariatric Hypoglycemia After Roux-en-Y Gastric Bypass Surgery.

OBJECTIVE: Post-bariatric surgery hypoglycemia (PBH) is a metabolic complication of Roux-en-Y gastric bypass (RYGB). Since symptoms are a key component of the Whipple's triad to diagnose nondiabetic hypoglycemia, we evaluated the relationship between self-reported symptoms and postprandial sensor glucose profiles. RESEARCH DESIGN AND METHODS: Thirty patients with PBH after RYGB (age: 50.1 [41.6-60.6] years, 86.7% female, BMI: 26.5 [23.5-31.2] kg/m2; median [interquartile range]) wore a blinded Dexcom G6 sensor while recording autonomic, neuroglycopenic, and gastrointestinal symptoms over 50 days. Symptoms (overall and each type) were categorized into those occurring in postprandial periods (PPPs) without hypoglycemia, or in the preceding dynamic or hypoglycemic phase of PPPs with hypoglycemia (nadir sensor glucose <3.9 mmol/L). We further explored the relationship between symptoms and the maximum negative rate of sensor glucose change and nadir sensor glucose levels. RESULTS: In 5,851 PPPs, 775 symptoms were reported, of which 30.6 (0.0-59.9)% were perceived in PPPs without hypoglycemia, 16.7 (0.0-30.1)% in the preceding dynamic phase and 45.0 (13.7-84.7)% in the hypoglycemic phase of PPPs with hypoglycemia. Per symptom type, 53.6 (23.8-100.0)% of the autonomic, 30.0 (5.6-80.0)% of the neuroglycopenic, and 10.4 (0.0-50.0)% of the gastrointestinal symptoms occurred in the hypoglycemic phase of PPPs with hypoglycemia. Both faster glucose dynamics and lower nadir sensor glucose levels were related with symptom perception. CONCLUSIONS: The relationship between symptom perception and PBH is complex, challenging clinical judgement and decision-making in this population.

Nutritional strategies for correcting low glucose values in patients with postbariatric hypoglycaemia: A randomized controlled three-arm crossover trial.

AIM: To evaluate the efficacy of nutritional hypoglycaemia correction strategies in postbariatric hypoglycaemia (PBH) after Roux-en-Y gastric bypass (RYGB). MATERIALS AND METHODS: In a randomized, controlled, three-arm crossover trial, eight post-RYGB adults (mean [SD] 7.0 [1.4] years since surgery) with PBH ingested a solid mixed meal (584 kcal, 85 g carbohydrates, 21 g fat, 12 g protein) to induce hypoglycaemia on three separate days. Upon reaching plasma glucose of less than 3.0 mmol/L, hypoglycaemia was corrected with 15 g of glucose (G15), 5 g of glucose (G5) or a protein bar (P10, 10 g of protein) in random order. The primary outcome was percentage of time spent in the target plasma glucose range (3.9-5.5 mmol/L) during 40 minutes after correction. RESULTS: Postcorrection time spent in the target glucose range did not differ significantly between the interventions (P = .161). However, postcorrection time with glucose less than 3.9 mmol/L was lower after G15 than P10 (P = .007), whereas time spent with glucose more than 5.5 mmol/L, peak glucose and insulin 15 minutes postcorrection were higher after G15 than G5 and P10 (P < .001). Glucagon 15 minutes postcorrection was higher after P10 than after G15 and G5 (P = .002 and P = .003, respectively). G15 resulted in rebound hypoglycaemia (< 3.0 mmol/L) in three of eight cases (38%), while no rebound hypoglycaemia occurred with G5 and P10. CONCLUSIONS: Correcting hypoglycaemia with 15 g of glucose should be reconsidered in post-RYGB PBH. A lower dose appears to sufficiently increase glucose levels outside the critical range in most cases, and complementary nutrients (e.g. proteins) may provide glycaemia-stabilizing benefits. REGISTRATION NUMBER OF CLINICAL TRIAL: NTC05250271 (ClinicalTrials.gov).

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.

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.

Randomized, Double-Blind, Placebo-Controlled Crossover Trial of Once Daily Empagliflozin 25 mg for the Treatment of Postprandial Hypoglycemia After Roux-en-Y Gastric Bypass.

Aims: To investigate the effect of empagliflozin on glucose dynamics in individuals suffering from postbariatric hypoglycemia (PBH) after Roux-en-Y gastric bypass (RYGB). Methods: Twenty-two adults with PBH after RYGB were randomized to empagliflozin 25 mg or placebo once daily over 20 days in a randomized, double-blind, placebo-controlled, crossover trial. The primary efficacy outcome was the amplitude of plasma glucose excursion (peak to nadir) during a mixed-meal tolerance test (MMTT). Outcomes of the outpatient period were assessed using continuous glucose monitoring (CGM) and an event-tracking app. Results: The amplitude of glucose excursion during the MMTT was 8.1 ± 2.4 mmol/L with empagliflozin versus 8.1 ± 2.6 mmol/L with placebo (mean ± standard deviation, P = 0.807). CGM-based mean amplitude of glucose excursion during the 20-day period was lower with empagliflozin than placebo (4.8 ± 1.3 vs. 5.2 ± 1.6. P = 0.028). Empagliflozin reduced the time spent with CGM values >10.0 mmol/L (3.8 ± 3.5% vs. 4.7 ± 3.8%, P = 0.009), but not the time spent with CGM values <3.0 mmol/L (1.7 ± 1.6% vs. 1.5 ± 1.5%, P = 0.457). No significant difference was observed in the quantity and quality of recorded symptoms. Eleven adverse events occurred with empagliflozin (three drug-related) and six with placebo. Conclusions: Empagliflozin 25 mg reduces glucose excursions but not hypoglycemia in individuals with PBH. Clinical Trial Registration: Clinicaltrials.gov: NCT05057819.

A Personalized and Adaptive Insulin Bolus Calculator Based on Double Deep Q- Learning to Improve Type 1 Diabetes Management.

Mealtime insulin dosing is a major challenge for people living with type 1 diabetes (T1D). This task is typically performed using a standard formula that, despite containing some patient-specific parameters, often leads to sub-optimal glucose control due to lack of personalization and adaptation. To overcome the previous limitations here we propose an individualized and adaptive mealtime insulin bolus calculator based on double deep Q-learning (DDQ), which is tailored to the patient thanks to a personalization procedure relying on a two-step learning framework. The DDQ-learning bolus calculator was developed and tested using the UVA/Padova T1D simulator modified to reliably mimic real-world scenarios by introducing multiple variability sources impacting glucose metabolism and technology. The learning phase included a long-term training of eight sub-population models, one for each representative subject, selected thanks to a clustering procedure applied to the training set. Then, for each subject of the testing set, a personalization procedure was performed, by initializing the models based on the cluster to which the patient belongs. We evaluated the effectiveness of the proposed bolus calculator on a 60-day simulation, using several metrics representing the goodness of glycemic control, and comparing the results with the standard guidelines for mealtime insulin dosing. The proposed method improved the time in target range from 68.35% to 70.08% and significantly reduced the time in hypoglycemia (from 8.78% to 4.17%). The overall glycemic risk index decreased from 8.2 to 7.3, indicating the benefit of our method when applied for insulin dosing compared to standard guidelines.

Performance of the Dexcom G6 Continuous Glucose Monitoring System During Cardiac Surgery Using Hypothermic Extracorporeal Circulation.

OBJECTIVE: Continuous glucose monitoring (CGM) may be challenged by extreme conditions during cardiac surgery using hypothermic extracorporeal circulation (ECC). RESEARCH DESIGN AND METHODS: We evaluated the Dexcom G6 sensor in 16 subjects undergoing cardiac surgery with hypothermic ECC, of whom 11 received deep hypothermic circulatory arrest (DHCA). Arterial blood glucose, quantified by the Accu-Chek Inform II meter, served as reference. RESULTS: Intrasurgery mean absolute relative difference (MARD) of 256 paired CGM/reference values was 23.8%. MARD was 29.1% during ECC (154 pairs) and 41.6% immediately after DHCA (10 pairs), with a negative bias (signed relative difference: -13.7%, -26.6%, and -41.6%). During surgery, 86.3% pairs were in Clarke error grid zones A or B and 41.0% of sensor readings fulfilled the International Organization for Standardization (ISO) 15197:2013 norm. Postsurgery, MARD was 15.0%. CONCLUSIONS: Cardiac surgery using hypothermic ECC challenges the accuracy of the Dexcom G6 CGM although recovery appears to occur thereafter.

AGATA: A Toolbox for Automated Glucose Data Analysis.

BACKGROUND: Analyzing continuous glucose monitoring (CGM) data is a mandatory step for multiple purposes spanning from reporting clinical trial outcomes to developing new algorithms for diabetes management. This task is repetitive, and scientists struggle in computing literature glucose control metrics and waste time in reproducing possibly complex plots and reports. For this reason, to provide the diabetes technology community a unified tool, here we present Automated Glucose dATa Analysis (AGATA), an automated glucose data analysis toolbox developed in MATLAB/Octave. METHODS: Automated Glucose dATa Analysis is an open-source software program to visualize and preprocess CGM data, compute glucose control metrics, detect adverse events, evaluate the effectiveness of users' prediction algorithms, and compare study arms. Automated Glucose dATa Analysis can be used as a standalone computer application accessible through a dedicated graphical user interface, particularly suitable for clinicians, or by integrating its functionalities in user-defined MATLAB/Octave scripts, which fits the need of researchers and developers. To demonstrate its features, we used AGATA to analyze CGM data of two subjects extracted from a publicly available data set of individuals with type one diabetes. Finally, AGATA's features are compared against those of 12 noncommercial software programs for CGM data analysis. RESULTS: Using AGATA, we easily preprocessed, analyzed, and visualized CGM data in a handy way, in compliance with the requirements and the standards defined in the literature. Compared to the other considered software programs, AGATA offers more functionalities and capabilities. CONCLUSION: Automated Glucose dATa Analysis is easy to use and reduces the burden of CGM data analysis. It is freely available in GitHub at https://github.com/gcappon/agata.

Methods for Insulin Bolus Adjustment Based on the Continuous Glucose Monitoring Trend Arrows in Type 1 Diabetes: Performance and Safety Assessment in an In Silico Clinical Trial.

BACKGROUND: Providing real-time magnitude and direction of glucose rate-of-change (ROC) via trend arrows represents one of the major strengths of continuous glucose monitoring (CGM) sensors in managing type 1 diabetes (T1D). Several literature methods were proposed to adjust the standard formula (SF) used for insulin bolus calculation by accounting for glucose ROC, but each of them provides different suggestions, making it difficult to understand which should be applied in practice. This work aims at performing an extensive in-silico assessment of their performance and safety. METHODS: The methods of Buckingham (BU), Scheiner (SC), Pettus/Edelman (PE), Klonoff/Kerr (KL), Aleppo/Laffel (AL), Ziegler (ZI), and Bruttomesso (BR) were evaluated using the UVa/Padova T1D simulator, in single-meal scenarios, where ROC and glucose at mealtime varied between [-2,+2] mg/dL/min and [80,200] mg/dL, respectively. Efficacy of postprandial glucose control was quantitatively assessed by time in, above and below range (TIR, TAR, and TBR, respectively). RESULTS: For negative ROCs, all methods proved to increase TIR and decrease TAR and TBR vs SF, with KL, PE, and BR being the most effective. For positive ROCs, a general worsening of the performances is present, only BR improved the glycemic control when mealtime glucose was close to hypoglycemia, while SC resulted the safest in the other conditions. CONCLUSIONS: Insulin bolus adjustment methods are effective for negative ROCs, but they generally appear to overdose for positive ROCs, calling for safer strategies in such a scenario. These results can be useful in outlining guidelines to identify which adjustment to apply based on the mealtime condition.