Bolus calculators

Culturally adapted mobile application for optimizing metabolic control in type 1 diabetes: a pilot study

Objective

To evaluate whether use of a culturally adapted mobile application (app) for adolescents with type 1 diabetes is associated with improved metabolic control.

Methods

The Dominican Republic's National Institute of Diabetes, Endocrinology, and Nutrition and the Learning to Live clinic recruited 23 pediatric participants for the study. Blood tests were performed before and after use of the app for a period of 3 months. Based on the user profile, participants were encouraged to use the app's bolus insulin calculator after each meal. The app included a list of regionally and culturally specific foods, color-coded to indicate a high glycemic index (GI) as red; medium GI as yellow; and low GI as green. The color-coding was designed to assist participants in making healthier eating choices.

Results

There were statistically significant improvements in lipid profile. Mean high-density lipoprotein values rose to acceptable levels, while low-density lipoproteins and triglyceride levels fell to the recommended values. The overall quality of life increased, although glycated hemoglobin levels showed no statistically significant changes.

Conclusion

The findings of this study suggest that using this culturally tailored app can help young patients with type 1 diabetes to improve metabolic health.

Assessing Carbohydrate Counting Accuracy: Current Limitations and Future Directions

Diabetes mellitus is a prevalent chronic autoimmune disease with a high impact on global health, affecting millions of adults and resulting in significant morbidity and mortality. Achieving optimal blood glucose levels is crucial for diabetes management to prevent acute and long-term complications. Carbohydrate counting (CC) is widely used by patients with type 1 diabetes to adjust prandial insulin bolus doses based on estimated carbohydrate content, contributing to better glycemic control and improved quality of life. However, accurately estimating the carbohydrate content of meals remains challenging for patients, leading to errors in bolus insulin dosing. This review explores the current limitations and challenges in CC accuracy and emphasizes the importance of personalized educational programs to enhance patients' abilities in carbohydrate estimation. Existing tools for assessing patient learning outcomes in CC are discussed, highlighting the need for individualized approaches tailored to each patient's needs. A comprehensive review of the relevant literature was conducted to identify educational programs and assessment tools dedicated to training diabetes patients on carbohydrate counting. The research aims to provide insights into the benefits and limitations of existing tools and identifies future research directions to advance personalized CC training approaches. By adopting a personalized approach to CC education and assessment, healthcare professionals can empower patients to achieve better glycemic control and improve diabetes management. Moreover, this review identifies potential avenues for future research, paving the way for advancements in personalized CC training and assessment approaches and further enhancing diabetes management strategies.

A strategy based on integer programming for optimal dosing and timing of preventive hypoglycemic treatments in type 1 diabetes management

BACKGROUND AND OBJECTIVES

One of the major problems related to type 1 diabetes (T1D) management is hypoglycemia, a condition characterized by low blood glucose levels and responsible for reduced quality of life and increased mortality. Fast-acting carbohydrates, also known as hypoglycemic treatments (HT), can counteract this event. In the literature, dosage and timing of HT are usually based on heuristic rules. In the present work, we propose an algorithm for mitigating hypoglycemia by suggesting preventive HT consumption, with dosages and timing determined by solving an optimization problem.

METHODS

By leveraging integer programming and linear inequality constraints, the algorithm can bind the amount of suggested carbohydrates to standardized quantities (i.e., those available in "off-the-shelf" HT) and the minimal distance between consecutive suggestions (to reduce the nuisance for patients).

RESULTS

The proposed method was tested in silico and compared with competitor algorithms using the UVa/Padova T1D simulator. At the cost of a slight increase of HT consumed per day, the proposed algorithm produces the lowest median and interquartile range of the time spent in hypoglycemia, with a statistically significant improvement over most competitor algorithms. Also, the average number of hypoglycemic events per day is reduced to 0 in median.

CONCLUSIONS

Thanks to its positive performances and reduced computational burden, the proposed algorithm could be a candidate tool for integration in a DSS aimed at improving T1D management.

The effect of bolus advisors on glycaemic parameters in adults with diabetes on intensive insulin therapy: A systematic review with meta-analysis

AIM

To conduct a systematic review with meta-analysis to provide a comprehensive synthesis of randomized controlled trials (RCTs) and prospective cohort studies investigating the effects of currently available bolus advisors on glycaemic parameters in adults with diabetes.

MATERIALS AND METHODS

An electronic search of PubMed, Embase, CINAHL, Cochrane Library and ClinicalTrials.gov was conducted in December 2022. The risk of bias was assessed using the revised Cochrane Risk of Bias tool. (Standardized) mean difference (MD) was selected to determine the difference in continuous outcomes between the groups. A random-effects model meta-analysis and meta-regression were performed. This systematic review was registered on PROSPERO (CRD42022374588).

RESULTS

A total of 18 RCTs involving 1645 adults (50% females) with a median glycated haemoglobin (HbA1c) concentration of 8.45% (7.95%-9.30%) were included. The majority of participants had type 1 diabetes (N = 1510, 92%) and were on multiple daily injections (N = 1173, 71%). Twelve of the 18 trials had low risk of bias. The meta-analysis of 10 studies with available data on HbA1c showed that the use of a bolus advisor modestly reduced HbA1c compared to standard treatment (MD -011%, 95% confidence interval -0.22 to -0.01; I2 = 0%). This effect was accompanied by small improvements in low blood glucose index and treatment satisfaction, but not with reductions in hypoglycaemic events or changes in other secondary outcomes.

CONCLUSION

Use of a bolus advisor is associated with slightly better glucose control and treatment satisfaction in people with diabetes on intensive insulin treatment. Future studies should investigate whether personalizing bolus advisors using artificial intelligence technology can enhance these effects.

Shining the Spotlight on Multiple Daily Insulin Therapy: Real-World Evidence of the InPen Smart Insulin Pen

Objective: Connected insulin pens are creating opportunities for the millions of individuals with diabetes using multiple daily injections (MDI) therapy across the globe. Continuous glucose monitoring (CGM) data from connected insulin pens are revealing gaps and opportunities to significantly improve care for this population. In this article, we report real-world findings of the InPen™ smart insulin pen paired with CGM (InPen system), used by persons with type 1 diabetes (T1D) and type 2 diabetes (T2D). Methods: A retrospective cohort analysis was conducted with the real-world data collected from the InPen system of individuals (N = 3793 with T1D, N = 552 with T2D, and N = 808 unidentified) who used the system from January 01, 2020, to December 31, 2021. Diabetes management (e.g., missed and mistimed insulin dosing, mismatched food intake, and correction dose delivery) and glycemic outcomes were assessed. Results: In the overall and T1D populations, a dosing frequency of ≥3 doses per day and a missed dose frequency of <20% was associated with improved glycemia. In adults with T2D, missing <20% of doses was the significant factor determining improved glycemia. Conclusion: This analysis, integrating data from a smart insulin pen and CGM, provides insights into the impact of dosing behavior on glycemic outcomes and informs counseling strategies for the diabetes care team, through technologically advanced insulin management for those using MDI therapy.

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.

Adaptive bolus calculators for people with type 1 diabetes: A systematic review

AIM

To conduct a systematic review of studies assessing adaptive insulin bolus calculators for people with type 1 diabetes (T1D).

METHODS

Electronic databases (Medline, Embase and Web of Science) were systematically searched from date of inception to 13 October 2022 for single-arm or randomized controlled studies assessing adaptive bolus calculators only, in children or adults with T1D on multiple daily injections or insulin pumps with glycaemic outcomes reported. The Clinicaltrials.gov registry was searched for recently completed studies evaluating decision support in T1D. The quality of extracted studies was assessed using the Standard Quality Assessment criteria and the Cochrane Risk of Bias assessment tool.

RESULTS

Six studies were identified. Extracted data were synthesized in a descriptive review because of heterogeneity. All the studies were small feasibility studies or were not suitably powered, and all were deemed to be at a high risk of performance and detection bias because they were unblinded. Overall, these studies did not show a significant glycaemic improvement. Two studies showed a reduction in postprandial time below range or an incremental change in blood glucose concentration; however, these were in controlled environments over a short duration.

CONCLUSIONS

There are limited clinical trials evaluating adaptive bolus calculators. Although results from small trials or in-silico data are promising, further studies are required to support personalized and adaptive management of T1D.

Advantages and disadvantages of connected insulin pens in diabetes management

Insulin administration remains vital to the treatment of diabetes and although there have been advances in insulin delivery, evidence suggests that many people with diabetes on insulin therapy have suboptimal glycemic management. Recent advancements in insulin administration techniques include connected insulin devices, such as connected insulin pens and pen caps. In this review, we provide an overview of the literature on the use of connected insulin pens and pen caps to further elucidate the clinical benefits and drawbacks of these devices. We discuss the development of these devices, outlining the characteristics of insulin pens and pen caps with regulatory approvals. These devices have different features that can ease the burden of diabetes management, including automatic recording of insulin dose information, tracking of insulin-on-board, bolus calculators, and missed dose alerts. Despite the advantages of connected pens and pen caps, a small percentage of insulin users are currently using these devices, due to many factors, including lack of health-care professional awareness, initial training for prescribers, and setup of the device. Overcoming these barriers and publishing more data demonstrating the glycemic outcomes associated with these systems could improve diabetes management for people living with diabetes. As health-care systems become increasingly digital, connected insulin pens have the potential to allow a data-driven approach to diabetes management for people who are not interested in, cannot afford, or do not have intensive insulin regimens that might warrant use of insulin pumps or automated insulin delivery systems.

Performance Effect of Adjusting Insulin Sensitivity for Model-Based Automated Insulin Delivery Systems

BACKGROUND

Model predictive control (MPC) has become one of the most popular control strategies for automated insulin delivery (AID) in type 1 diabetes (T1D). These algorithms rely on a prediction model to determine the best insulin dosing every sampling time. Although these algorithms have been shown to be safe and effective for glucose management through clinical trials, managing the ever-fluctuating relationship between insulin delivery and resulting glucose uptake (aka insulin sensitivity, IS) remains a challenge. We aim to evaluate the effect of informing an AID system with IS on the performance of the system.

METHOD

The University of Virginia (UVA) MPC control-based hybrid closed-loop (HCL) and fully closed-loop (FCL) system was used. One-day simulations at varying levels of IS were run with the UVA/Padova T1D Simulator. The AID system was informed with an estimated value of IS obtained through a mixed meal glucose tolerance test. Relevant controller parameters are updated to inform insulin dosing of IS. Performance of the HCL/FCL system with and without information of the changing IS was assessed using a novel performance metric penalizing the time outside the target glucose range.

RESULTS

Feedback in AID systems provides a certain degree tolerance to changes in IS. However, IS-informed bolus and basal dosing improve glycemic outcomes, providing increased protection against hyperglycemia and hypoglycemia according to the individual's physiological state.

CONCLUSIONS

The proof-of-concept analysis presented here shows the potentially beneficial effects on system performance of informing the AID system with accurate estimates of IS. In particular, when considering reduced IS, the informed controller provides increased protection against hyperglycemia compared with the naïve controller. Similarly, reduced hypoglycemia is obtained for situations with increased IS. Further tailoring of the adaptation schemes proposed in this work is needed to overcome the increased hypoglycemia observed in the more resistant cases and to optimize the performance of the adaptation method.

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.

Offline Deep Reinforcement Learning and Off-Policy Evaluation for Personalized Basal Insulin Control in Type 1 Diabetes

Recent advancements in hybrid closed-loop systems, also known as the artificial pancreas (AP), have been shown to optimize glucose control and reduce the self-management burdens for people living with type 1 diabetes (T1D). AP systems can adjust the basal infusion rates of insulin pumps, facilitated by real-time communication with continuous glucose monitoring. Deep reinforcement learning (DRL) has introduced new paradigms of basal insulin control algorithms. However, all the existing DRL-based AP controllers require extensive random online interactions between the agent and environment. While this can be validated in T1D simulators, it becomes impractical in real-world clinical settings. To this end, we propose an offline DRL framework that can develop and validate models for basal insulin control entirely offline. It comprises a DRL model based on the twin delayed deep deterministic policy gradient and behavior cloning, as well as off-policy evaluation (OPE) using fitted Q evaluation. We evaluated the proposed framework on an in silico dataset generated by the UVA/Padova T1D simulator, and the OhioT1DM dataset, a real clinical dataset. The performance on the in silico dataset shows that the offline DRL algorithm significantly increased time in range while reducing time below range and time above range for both adult and adolescent groups. Then, we used the OPE to estimate model performance on the clinical dataset, where a notable increase in policy values was observed for each subject. The results demonstrate that the proposed framework is a viable and safe method for improving personalized basal insulin control in T1D.

Offline reinforcement learning for safer blood glucose control in people with type 1 diabetes

The widespread adoption of effective hybrid closed loop systems would represent an important milestone of care for people living with type 1 diabetes (T1D). These devices typically utilise simple control algorithms to select the optimal insulin dose for maintaining blood glucose levels within a healthy range. Online reinforcement learning (RL) has been utilised as a method for further enhancing glucose control in these devices. Previous approaches have been shown to reduce patient risk and improve time spent in the target range when compared to classical control algorithms, but are prone to instability in the learning process, often resulting in the selection of unsafe actions. This work presents an evaluation of offline RL for developing effective dosing policies without the need for potentially dangerous patient interaction during training. This paper examines the utility of BCQ, CQL and TD3-BC in managing the blood glucose of the 30 virtual patients available within the FDA-approved UVA/Padova glucose dynamics simulator. When trained on less than a tenth of the total training samples required by online RL to achieve stable performance, this work shows that offline RL can significantly increase time in the healthy blood glucose range from 61.6±0.3% to 65.3±0.5% when compared to the strongest state-of-art baseline (p<0.001). This is achieved without any associated increase in low blood glucose events. Offline RL is also shown to be able to correct for common and challenging control scenarios such as incorrect bolus dosing, irregular meal timings and compression errors. The code for this work is available at: https://github.com/hemerson1/offline-glucose.

Maximizing Glycemic Benefits of Using Faster Insulin Formulations in Type 1 Diabetes: In Silico Analysis Under Open- and Closed-Loop Conditions

Background: Ultrarapid-acting insulin analogs that could improve or even prevent postprandial hyperglycemia are now available for both research and clinical care. However, clear glycemic benefits remain elusive, especially when combined with automated insulin delivery (AID) systems. In this work, we study two insulin formulations in silico and highlight adjustments of both open-loop and closed-loop insulin delivery therapies as a critical step to achieve clinically meaningful improvements. Methods: Subcutaneous insulin transport models for two faster analogs, Fiasp (Novo Nordisk, Bagsværd, Denmark) and AT247 (Arecor, Saffron Walden, United Kingdom), were identified using data collected from prior clamp experiments, and integrated into the UVA/Padova type 1 diabetes simulator (adult cohort, N = 100). Pump therapy parameters and the aggressiveness of our full closed-loop algorithm were adapted to the new insulin pharmacokinetic and pharmacodynamic profiles through a sequence of in silico studies. Finally, we assessed these analogs' glycemic impact with and without modified therapy parameters in simulated conditions designed to match clinical trial data. Results: Simply switching to faster insulin analogs shows limited improvements in glycemic outcomes. However, when insulin acceleration is accompanied by therapy adaptation, clinical significance is found comparing time-in-range (70-180 mg/dL) with Aspart versus AT247 in open-loop (+5.1%); and Aspart versus Fiasp (+5.4%) or AT247 (+10.6%) in full closed-loop with no clinically significant differences in the exposure to hypoglycemia. Conclusion: In silico results suggest that properly adjusting intensive insulin therapy profiles, or AID tuning, to faster insulin analogs is necessary to obtain clinically significant improvements in glucose control.

Manual and Application-Based Carbohydrate Counting and Glycemic Control in Type 1 Diabetes Subjects: A Narrative Review

Type 1 diabetes (T1DM) is the most common chronic disease in young adults and children, which is treated with insulin, usually given as basal and boluses. Carbohydrate counting (CHOC) helps patients to determine the correct meal doses. The aim of this review is to study the effect of CHOC on glucose control, body weight, insulin dose and quality of life (QoL). The literature search was conducted using PubMed from January 2010 to October 2022. Studies included in this review are limited to randomized controlled studies involving an intervention group undergoing CHOC and a control group following the usual practice, measuring glycosylated hemoglobin (HbA1c) as a parameter of glucose control and involving only T1DM subjects. A total of ten articles were found to fulfill the criteria involving 1034 patients. Most of the studies showed a positive impact of CHOC on glucose control, especially in adults, where five out of six studies were statistically positive. However, in pediatrics, only two out of four showed a positive outcome. In all four studies using mobile applications, CHOC was better at controlling glucose. No difference was seen between the CHOC group and the control regarding the risk of severe hypoglycemia. In fact, two studies have shown lower hypoglycemia rates. No change in weight was observed in most of the studies (six out of eight). In subjects with T1DM, CHOC might provide better glucose control than traditional care without a significant increment in severe hypoglycemia or weight gain. Mobile application-based models showed promising results in glucose control.

A Review of Precision Insulin Management With Smart Insulin Pens: Opening Up the Digital Door to People on Insulin Injection Therapy

Although advances in insulin therapy and delivery have been made, global evidence indicates sub-optimal glycemic management in people on insulin therapy with either type 1 diabetes (T1D) or type 2 diabetes (T2D). In this review, we discuss connected insulin pens that include tracking insulin pens (TIPs) and smart insulin pens (SIPs) and caps, as approaches to improving mean glucose or time in range while minimizing exposure to hypoglycemia or time below range (TBR) in people with diabetes (PwD) on multiple daily injection (MDI) therapy. We discuss various factors offered by SIPs that can facilitate precision insulin management, that is, delivering the right dose at the right time. These factors include the automatic recording of insulin dose size and delivery time; differentiating prime from therapy doses; active insulin tracking; dose calculators that provide individualized dosing recommendations; alerts for missed doses (ie, rapid-acting or long-acting insulin), insulin temperature, and insulin age monitoring; and integrated data reports for the clinical care team. A data-driven approach to care is critical to precision insulin management and includes helping PwD make informed choices regarding their preferred method of insulin delivery and ensuring insulin delivery technology tools are configured for their personal therapy plan. The data-driven approach involves developing a plan for ongoing collaborative use of the resulting data with their care team that may include adjusting insulin regimen and optimizing the care plan on a timely basis. We conclude with a list of practice protocols that are needed to support data-driven precision insulin management. This review includes a summary of research including various stages of connected insulin pens and caps.

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.

Impact of Carbohydrate Counting Error on Glycemic Control in Open-Loop Management of Type 1 Diabetes: Quantitative Assessment Through an In Silico Trial

BACKGROUND

In the management of type 1 diabetes (T1D), systematic and random errors in carb-counting can have an adverse effect on glycemic control. In this study, we performed an in silico trial aiming at quantifying the impact of different levels of carb-counting error on glycemic control.

METHODS

The T1D patient decision simulator was used to simulate 7-day glycemic profiles of 100 adults using open-loop therapy. The simulation was repeated for different values of systematic and random carb-counting errors, generated with Gaussian distribution varying the error mean from -10% to +10% and standard deviation (SD) from 0% to 50%. The effect of the error was evaluated by computing the difference of time inside (∆TIR), above (∆TAR) and below (∆TBR) the target glycemic range (70-180mg/dl) compared to the reference case, that is, absence of error. Finally, 3 linear regression models were developed to mathematically describe how error mean and SD variations result in ∆TIR, ∆TAR, and ∆TBR changes.

RESULTS

Random errors globally deteriorate the glycemic control; systematic underestimations lead to, on average, up to 5.2% more TAR than the reference case, while systematic overestimation results in up to 0.8% more TBR. The different time in range metrics were linearly related with error mean and SD (R²>0.95), with slopes of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msub><mml:mi>β</mml:mi><mml:mrow><mml:mi>M</mml:mi><mml:mi>E</mml:mi><mml:mi>A</mml:mi><mml:mi>N</mml:mi></mml:mrow></mml:msub><mml:mo>=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>21</mml:mn></mml:mrow></mml:math>, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msub><mml:mi>β</mml:mi><mml:mrow><mml:mi>S</mml:mi><mml:mi>D</mml:mi></mml:mrow></mml:msub><mml:mo>=</mml:mo><mml:mo>-</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>07</mml:mn></mml:mrow></mml:math> for ∆TIR, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msub><mml:mi>β</mml:mi><mml:mrow><mml:mi>M</mml:mi><mml:mi>E</mml:mi><mml:mi>A</mml:mi><mml:mi>N</mml:mi></mml:mrow></mml:msub><mml:mo>=</mml:mo><mml:mo>-</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>25</mml:mn></mml:mrow></mml:math>, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msub><mml:mi>β</mml:mi><mml:mrow><mml:mi>S</mml:mi><mml:mi>D</mml:mi></mml:mrow></mml:msub><mml:mo>=</mml:mo><mml:mo>+</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>06</mml:mn></mml:mrow></mml:math> for ∆TAR, and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msub><mml:mi>β</mml:mi><mml:mrow><mml:mi>M</mml:mi><mml:mi>E</mml:mi><mml:mi>A</mml:mi><mml:mi>N</mml:mi></mml:mrow></mml:msub><mml:mo>=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>05</mml:mn></mml:mrow></mml:math>, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msub><mml:mi>β</mml:mi><mml:mrow><mml:mi>S</mml:mi><mml:mi>D</mml:mi></mml:mrow></mml:msub><mml:mo>=</mml:mo><mml:mo>+</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>01</mml:mn></mml:mrow></mml:math> for ∆TBR.

CONCLUSIONS

The quantification of carb-counting error impact performed in this work may be useful understanding causes of glycemic variability and the impact of possible therapy adjustments or behavior changes in different glucose metrics.

Building a Data-Driven Multiple Daily Insulin Therapy Model Using Smart Insulin Pens

A growing suite of connected devices including Bluetooth or cellular-enabled glucose monitoring devices, smart insulin pens, pumps, fitness trackers, blood pressure, and heart rate and weight monitors present a golden opportunity to build a data-driven clinical practice model including remote monitoring capability and virtual care. This paper will discuss this approach using diabetes as a case study and smart insulin pens as a use case. As payment and practice approaches evolve, there is growing interest from both patients and their health care teams in virtual care made possible by remote monitoring capability. Here, we will define the category of smart insulin pens, describe the hallmarks of a data-driven practice model, and delineate the steps to take to incorporate remote monitoring capability with smart insulin pens into diabetes care for injection therapy patients.

Smart Insulin Pens: Advancing Digital Transformation and a Connected Diabetes Care Ecosystem

With the first commercially available smart insulin pens, the predominant insulin delivery device for millions of people living with diabetes is now coming into the digital age. Smart insulin pens (SIPs) have the potential to reshape a connected diabetes care ecosystem for patients, providers, and health systems. Existing SIPs are enhanced with real-time wireless connectivity, digital dose capture, and integration with personalized dosing decision support. Automatic dose capture can promote effective retrospective review of insulin dose data, particularly when paired with glucose data. Patients, providers, and diabetes care teams will be able to make increasingly data-driven decisions and recommendations, in real time, during scheduled visits, and in a more continuous, asynchronous care model. As SIPs continue to progress along the path of digital transformation, we can expect additional benefits: iteratively improving software, machine learning, and advanced decision support. Both these technological advances, and future care delivery models with asynchronous interactions, will depend on easy, open, and continuous data exchange between the growing number of diabetes devices. SIPs have a key role in modernizing diabetes care for a large population of people living with diabetes.

Self-Monitoring of Blood Glucose as an Integral Part in the Management of People with Type 2 Diabetes Mellitus

For decades, self-monitoring of blood glucose (SMBG) has been considered a cornerstone of adequate diabetes management. Structured SMBG can follow different monitoring patterns, and it results in improved glycemic control, reduced hypoglycemia, and a better quality of life of people with diabetes. The technology, usability, and accuracy of SMBG systems have advanced markedly since their introduction a few decades ago. Current SMBG systems are small and easy to use, require small (capillary) blood sample volumes, and provide measurement results within seconds. In addition, devices are increasingly equipped with features such as connectivity to other devices and/or digital diaries and diabetes management tools. Although measurement quality can come close to or equal that of the glucose monitoring systems used by healthcare professionals, several available SMBG systems still do not meet internationally accepted accuracy standards, such as the International Organization for Standardization 15197 standard. Reports from China, India, and Brazil based on local experience suggest that in addition of the accuracy issues of SMBG systems, other obstacles also need to be overcome to optimize SMBG usage. Nonetheless, adequate usage of SMBG data is of high relevance for the management of people with type 2 diabetes mellitus.

Automated Bolus Calculators and Connected Insulin Pens: A Smart Combination for Multiple Daily Injection Insulin Therapy

Although automated bolus calculators (ABCs) have become a mainstay in insulin pump therapy, they have not achieved similar levels of adoption by persons with diabetes (PWD) using multiple daily injections of insulin (MDI). Only a small number of blood glucose meters (BGMs) have incorporated ABC functionality and the proliferation of unregulated ABC smartphone apps raised safety concerns and eventually led to Food and Drug Administration (FDA)-mandated regulatory oversight for these types of apps. With the recent introduction of smartphone-connected insulin pens, manufacturer-supported companion ABC apps may offer an ideal solution for PWD and health care professionals that reduces errors of mental math when calculating bolus insulin dosing, increases the quality of diabetes data reporting, and improves glycemic outcomes.

Towards the Integration of an Islet-Based Biosensor in Closed-Loop Therapies for Patients With Type 1 Diabetes

In diabetes mellitus (DM) treatment, Continuous Glucose Monitoring (CGM) linked with insulin delivery becomes the main strategy to improve therapeutic outcomes and quality of patients' lives. However, Blood Glucose (BG) regulation with CGM is still hampered by limitations of algorithms and glucose sensors. Regarding sensor technology, current electrochemical glucose sensors do not capture the full spectrum of other physiological signals, i.e., lipids, amino acids or hormones, relaying the general body status. Regarding algorithms, variability between and within patients remains the main challenge for optimal BG regulation in closed-loop therapies. This work highlights the simulation benefits to test new sensing and control paradigms which address the previous shortcomings for Type 1 Diabetes (T1D) closed-loop therapies. The UVA/Padova T1DM Simulator is the core element here, which is a computer model of the human metabolic system based on glucose-insulin dynamics in T1D patients. That simulator is approved by the US Food and Drug Administration (FDA) as an alternative for pre-clinical testing of new devices and closed-loop algorithms. To overcome the limitation of standard glucose sensors, the concept of an islet-based biosensor, which could integrate multiple physiological signals through electrical activity measurement, is assessed here in a closed-loop insulin therapy. This investigation has been addressed by an interdisciplinary consortium, from endocrinology to biology, electrophysiology, bio-electronics and control theory. In parallel to the development of an islet-based closed-loop, it also investigates the benefits of robust control theory against the natural variability within a patient population. Using 4 meal scenarios, numerous simulation campaigns were conducted. The analysis of their results then introduces a discussion on the potential benefits of an Artificial Pancreas (AP) system associating the islet-based biosensor with robust algorithms.

The Review of Insulin Pens-Past, Present, and Look to the Future

Currently, there are about 150-200 million diabetic patients treated with insulin globally. The year 2021 is special because the 100th anniversary of the insulin discovery is being celebrated. It is a good occasion to sum up the insulin pen technology invention and improvement which are nowadays the leading mode of an insulin delivery. Even though so many years have passed, insulin is still administered subcutaneously, that is why devices to deliver it are of great importance. Insulin pens have evolved only through the last decades (the reusable, durable pens, and the disposable, prefilled pens) and modern smart insulin pens have been developed in the last few years, and both types of the devices compared to traditional syringes and vials are more convenient, discrete in use, have better dosing accuracy, and improve adherence. In this review, we will focus on the history of insulin pens and their improvement over the previous decades.

Flash glucose monitoring and automated bolus calculation in type 1 diabetes treated with multiple daily insulin injections: a 26 week randomised, controlled, multicentre trial

AIMS/HYPOTHESIS

We aimed to compare the effects of intermittently scanned continuous glucose monitoring (isCGM) and carbohydrate counting with automated bolus calculation (ABC) with usual care.

METHODS

In a randomised, controlled, open-label trial carried out at five diabetes clinics in the Capital Region of Denmark, 170 adults with type 1 diabetes for ≥1 year, multiple daily insulin injections and HbA_1c > 53 mmol/mol (7.0%) were randomly assigned 1:1:1:1 with centrally prepared envelopes to usual care (n = 42), ABC (n = 41), isCGM (n = 48) or ABC+isCGM (n = 39). Blinded continuous glucose monitoring data, HbA_1c and patient-reported outcomes were recorded at baseline and after 26 weeks. The primary outcome was change in time in range using isCGM vs usual care.

RESULTS

Baseline characteristics were comparable across arms: mean age 47 (SD 13.7) years, median (IQR) diabetes duration 18 (10-28) years and HbA_1c 65 (61-72) mmol/mol (8.1% [7.7-8.7%]). Change in time in range using isCGM was comparable to usual care (% difference of 3.9 [-12-23], p = 0.660). The same was true for the ABC and ABC+isCGM arms and for hypo- and hyperglycaemia. Also compared with usual care, using ABC+isCGM reduced HbA_1c (4 [95% CI 1, 8] mmol/mol) (0.4 [0.1, 0.7] %-point) and glucose CV (11% [4%, 17%]) and improved treatment satisfaction, psychosocial self-efficacy and present life quality. Treatment satisfaction also improved by using isCGM alone vs usual care. Statistical significance was maintained after multiple testing adjustment concerning glucose CV and treatment satisfaction with ABC+isCGM, and treatment satisfaction with isCGM. Discontinuation was most common among ABC only users, and among completers the ABC was used 4 (2-5) times/day and the number of daily isCGM scans was 5 (1-7) at study end.

CONCLUSIONS/INTERPRETATION

isCGM alone did not improve time in range, but treatment satisfaction increased in technology-naive people with type 1 diabetes and suboptimal HbA_1c. The combination of ABC+isCGM appears advantageous regarding glycaemic variables and patient-reported outcomes, but many showed resistance towards ABC.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03682237.

FUNDING

The study is investigator initiated and financed by the Capital Region of Denmark.

A Correction Insulin Bolus Delivery Strategy for Decision Support Systems in Type 1 Diabetes

Management of type 1 diabetes (T1D) requires affected individuals to perform multiple daily actions to keep their blood glucose levels within the safe rage and avoid adverse hypo-/hyperglycemic episodes. Decision support systems (DSS) for T1D are composite tools that implement multiple software modules aiming to ease such a burden and to improve glucose control. At the University of Padova, we are developing a new DSS that currently integrate a smart insulin bolus calculator for optimal insulin dosing and a rescue carbohydrate intake advisor to tackle hypoglycemia. However, a module specifically targeting hyperglycemia, that suggests the administration of corrective insulin boluses (CIB), is still missing. For such a scope, this work aims to assess a recent literature methodology, proposed by Aleppo et al., which provides a simple strategy for dealing with hyperglycemia. The methodology is tested retrospectively on clinical data of individuals with T1D. In particular, here we leveraged a novel in silico tool that first identifies a non-linear model of glucose-insulin dynamics on data, then uses such model to simulate and compare the glucose trace obtained by "replaying" the recorded scenario and the glucose trace obtained using the CIB delivery strategy under evaluation. Results show that the CIB delivery strategy significantly reduce the percentage of time spent in hyperglycemia (-15.63%) without inducing any hypoglycemic episode, demonstrating both safety and efficacy of its use. These preliminary results suggest that the CIB delivery strategy proposed by Aleppo et al. is a promising candidate to be included in our system to counteract hyperglycemia. Future work will extensively evaluate the methodology and will compare it against other competing approaches.

An Ensemble Learning Algorithm Based on Dynamic Voting for Targeting the Optimal Insulin Dosage in Type 1 Diabetes Management

People with type 1 diabetes (T1D) need exogenous insulin administrations several times a day. The amount of injected insulin is key for maintaining the concentration of blood glucose (BG) within a physiological safe range. According to well-established clinical guidelines, insulin dosing at mealtime is calculated through an empirical formula which, however, does not take advantage of the knowledge of BG trend provided in real-time by continuous glucose monitoring (CGM) sensors. To overcome suboptimal insulin dosage, we recently used machine learning techniques to build two new models, one linear and one nonlinear, which incorporate BG trend information.In this work, we propose an ensemble learning method for mealtime insulin bolus estimation based on dynamic voting, which combines the two models by taking advantage of where each alternative performs better. Being the resulting model black-box, a tool that enables its interpretability was applied to evaluate the contribution of each feature. The proposed model was trained using a synthetic dataset having information on 100 virtual subjects with different mealtime conditions, and its performance was evaluated within a simulated environment.The benefit given by the ensemble method compared to the single models was confirmed by the high time within the target glycemic range, and the trade-off reached in terms of time spent below and above this range. Moreover, the model interpretation pointed out the key role played by the information on BG dynamics in the estimation of insulin dosage.

A New Decision Support System for Type 1 Diabetes Management

Type 1 diabetes (T1D) is a chronic life-threatening metabolic condition which needs to be accurately and continuously managed with care by multiple daily exogenous insulin injections, frequent blood glucose concentration monitoring, ad-hoc diet, and physical activity. In the last decades, new technologies, such as continuous glucose monitoring sensors, eased the burden for T1D patients and opened new therapy perspectives by fostering the development of decision support systems (DSS). A DSS for T1D should be able to provide patients with advice aimed at improving metabolic control and reducing the number of actions related to therapy handling. Major challenges are the vast intra-/inter-subject physiological variability and the many factors that impact glucose metabolism. The present work illustrates a new DSS for T1D management. The algorithmic core includes a module for optimal, personalized, insulin dose calculation and a module that triggers the assumption of rescue carbohydrates to avoid/mitigate impending hypoglycemic events. The algorithms are integrated within a prototype communication platform that comprises a mobile app, a real-time telemonitoring interface, and a cloud server to safely store patients' data. Tests made in silico show that the use of the new algorithms lead to metabolic control indices significantly better than those obtained by the standard care for T1D. The preliminary test of the prototype platform suggests that it is robust, performant, and well-accepted by both patients and clinicians. Future work will focus on the refinement of the communication platform and the design of a clinical trial to assess the system effectiveness in real-life conditions.Clinical Relevance- The presented DSS is a promising tool to facilitate T1D daily management and improve therapy efficacy.

Linear Model Identification for Personalized Prediction and Control in Diabetes

OBJECTIVE

Type-1 diabetes (T1D) is a metabolic disease, characterized by impaired blood glucose (BG) regulation, which forces patients to multiple daily therapeutic actions, the most critical of which is exogenous insulin administration. T1D management can considerably benefit of mathematical models enabling accurate BG predictions and effective/safe automated insulin delivery. In building these models, dealing with large inter- and intra-patient variability in glucose-insulin dynamics represents a major challenge. The aim of the present work is to assess linear black-box methods, including a novel non-parametric methodology, for learning individualized models of glucose response to insulin and meal, suitable for model-based prediction and control.

METHODS

We focus on data-driven techniques for linear model-learning and compare the state-of-art parametric pipeline, exploring all its degrees of freedom (including population vs. individualized parameter identification, model class chosen among ARX/ARMAX/ARIMAX/Box-Jenkins, model order selection criteria, etc.), with a novel non-parametric approach based on Gaussian regression and stable spline kernel. By using data collected in 11 T1D individuals, we evaluate effectiveness of the different models by measuring root mean squared error (RMSE), coefficient of determination (COD), and time gain of the associated BG predictors.

RESULTS

Among the tested approaches, the non-parametric technique results in the best prediction performance: median RMSE=29.8mg/dL, and median COD=57.4%, for a prediction horizon (PH) of 60 min. With respect to the state-of-the-art parametric techniques, the non-parametric approach grants a COD improvement of about 2%, 7%, 21%, and 41% for PH = 30, 60, 90, and 120 min (paired-sample t-test p 0.001, p=0.003, p=0.03, and p=0.07 respectively).

CONCLUSION

Non-parametric linear model-learning grants statistically significant improvement with respect to the state-of-art parametric approach. The higher PH, the more pronounced the improvement.

SIGNIFICANCE

The use of a linear non-parametric model-learning approach for model-based prediction and control could bring to a more prompt, safe and effective T1D management.

Satisfaction of Healthcare Professionals and People With Diabetes With an Insulin Bolus Calculator Mobile Application

People with diabetes (PWD) who need to take mealtime insulin to help control their blood sugar often have difficulty correctly calculating their dose due to consideration of many factors such as current blood glucose, carbohydrate consumption, active insulin duration, insulin-to-carb ratio, and insulin sensitivity. The Insulin Mentor, a bolus calculator tool in the OneTouch Reveal diabetes management app, uses an algorithm to automate many of these calculations and contains a link to a food diary to help estimate carbohydrate intake. In the current study, healthcare professionals and PWD from United States and Germany responded favorably to simulations of this calculator tool and compared it positively with other apps on the market. The Insulin Mentor may simplify the difficult process of correctly calculating mealtime insulin doses for PWD.

Basal Glucose Control in Type 1 Diabetes Using Deep Reinforcement Learning: An In Silico Validation

People with Type 1 diabetes (T1D) require regular exogenous infusion of insulin to maintain their blood glucose concentration in a therapeutically adequate target range. Although the artificial pancreas and continuous glucose monitoring have been proven to be effective in achieving closed-loop control, significant challenges still remain due to the high complexity of glucose dynamics and limitations in the technology. In this work, we propose a novel deep reinforcement learning model for single-hormone (insulin) and dual-hormone (insulin and glucagon) delivery. In particular, the delivery strategies are developed by double Q-learning with dilated recurrent neural networks. For designing and testing purposes, the FDA-accepted UVA/Padova Type 1 simulator was employed. First, we performed long-term generalized training to obtain a population model. Then, this model was personalized with a small data-set of subject-specific data. In silico results show that the single and dual-hormone delivery strategies achieve good glucose control when compared to a standard basal-bolus therapy with low-glucose insulin suspension. Specifically, in the adult cohort (n = 10), percentage time in target range 70, 180 mg/dL improved from 77.6% to 80.9% with single-hormone control, and to 85.6% with dual-hormone control. In the adolescent cohort (n = 10), percentage time in target range improved from 55.5% to [Formula: see text] with single-hormone control, and to 78.8% with dual-hormone control. In all scenarios, a significant decrease in hypoglycemia was observed. These results show that the use of deep reinforcement learning is a viable approach for closed-loop glucose control in T1D.

Efficacy of Bolus Calculation and Advanced Carbohydrate Counting in Type 2 Diabetes: A Randomized Clinical Trial

Background: Carbohydrate counting and use of automated bolus calculators (ABCs) can help reduce HbA_1c in type 1 diabetes but only limited evidence exists in type 2 diabetes. We evaluated the efficacy of advanced carbohydrate counting (ACC) and use of an ABC compared with manual insulin bolus calculation (MC) in persons with type 2 diabetes. Materials and Methods: A 24-week open-label, randomized clinical study was conducted in 79 persons with type 2 diabetes treated with basal-bolus insulin (mean age 62.5 ± 9.6 years, HbA_1c 8.7% ± 1.0% [72 ± 11 mmol/mol], diabetes duration 18.7 ± 7.6 years). Participants were randomized 1:1 into two groups: ABC group received training in ACC and use of an ABC; MC group received training in ACC and manual calculation of insulin bolus. Participants wore blinded continuous glucose monitors for 6 days at baseline and at study end. Primary endpoint was change in HbA_1c. Results: After 24 weeks, HbA_1c decreased 0.8% (8.8 mmol/mol) in ABC group and 0.8% (9.0 mmol/mol) in MC group with no between-group difference (P = 0.96) and without increase in time in hypoglycemic range (sensor glucose <3.9 mmol/L). Glycemic variability decreased significantly in both groups, whereas the total insulin dose and body mass index (BMI) remained unchanged during the study. Treatment satisfaction increased significantly in both groups after 24 weeks. Conclusion: ACC is an effective, low-cost tool to reduce HbA_1c and glycemic variability in persons with basal-bolus insulin-treated type 2 diabetes without increase in hypoglycemia or BMI. Similar effects were seen with use of an ABC and with use of manual bolus calculation. Trial registration: ClinicalTrials.gov NCT02887898.

Nonlinear Machine Learning Models for Insulin Bolus Estimation in Type 1 Diabetes Therapy

Type 1 diabetes (T1D) therapy requires multiple daily insulin injections to compensate the lack of endogenous insulin production due to β-cells destruction. An empirical standard formula (SF) is commonly used for such a task. Unfortunately, SF does not include information on glucose dynamics, e.g. the glucose rate-of-change (ROC) provided by continuous glucose monitoring (CGM) sensor. Hence, SF can sometimes lead to under/overestimations that can cause critical hypo/hyperglycemic episodes during/after the meal. Recently, to overcome this limitation, we proposed new linear regression models, integrating ROC information and personalized features. Despite the first encouraging results, the nonlinear nature of the problem calls for the application of nonlinear models. In this work, random forest (RF) and gradient boosting tree (GBT), nonlinear machine learning methodologies, were investigated. A dataset of 100 virtual subjects, opportunely divided into training and testing sets, was used. For each individual, a single-meal scenario with different meal conditions (preprandial ROC, BG and meal amounts) was simulated. The assessment was performed both in terms of accuracy in estimating the optimal bolus and glycemic control. Results were compared to the best performing linear model previously developed. The two tree-based models proposed lead to a statistically significant improvement of glycemic control compared to the linear approach, reducing the time spent in hypoglycemia (from 32.49% to 27.57-25.20% for RF and GBT, respectively). These results represent a preliminary step to prove that nonlinear machine learning techniques can improve the estimation of insulin bolus in T1D therapy. Particularly, RF and GBT were shown to outperform the previously linear models proposed.Clinical Relevance- Insulin bolus estimation with nonlinear machine learning techniques reduces the risk of adverse events in T1D therapy.

Modeling Carbohydrate Counting Error in Type 1 Diabetes Management

Background: The error in estimating meal carbohydrates (CHO) amount is a critical mistake committed by type 1 diabetes (T1D) subjects. The aim of this study is both to investigate which factors, related to meals and subjects, affect the CHO counting error most and to develop a mathematical model of CHO counting error embeddable in T1D patient decision simulators to conduct in silico clinical trials. Methods: A published dataset of 50 T1D adults is used, which includes a patient's CHO count of 692 meals, dietitian's estimates of meal composition (used as reference), and several potential explanatory factors. The CHO counting error is modeled by multiple linear regression, with stepwise variable selection starting from 10 candidate predictors, that is, education level, insulin treatment duration, age, body weight, meal type, CHO, lipid, energy, protein, and fiber content. Inclusion of quadratic and interaction terms is also evaluated. Results: Larger errors correspond to larger meals, and most of the large meals are underestimated. The linear model selects CHO (P < 0.00001), meal type (P < 0.00001), and body weight (P = 0.047), whereas its extended version embeds a quadratic term of CHO (P < 0.00001) and interaction terms of meal type with CHO (P = 0.0001) and fiber amount (P = 0.001). The extended model explains 34.9% of the CHO counting error variance. Comparison with the CHO counting error description previously used in the T1D patient decision simulator shows that the proposed models return more credible realizations. Conclusions: The most important predictors of CHO counting errors are CHO and meal type. The mathematical models proposed improve the description of patients' behavior in the T1D patient decision simulator.

An Insulin Bolus Advisor for Type 1 Diabetes Using Deep Reinforcement Learning

(1) Background: People living with type 1 diabetes (T1D) require self-management to maintain blood glucose (BG) levels in a therapeutic range through the delivery of exogenous insulin. However, due to the various variability, uncertainty and complex glucose dynamics, optimizing the doses of insulin delivery to minimize the risk of hyperglycemia and hypoglycemia is still an open problem. (2) Methods: In this work, we propose a novel insulin bolus advisor which uses deep reinforcement learning (DRL) and continuous glucose monitoring to optimize insulin dosing at mealtime. In particular, an actor-critic model based on deep deterministic policy gradient is designed to compute mealtime insulin doses. The proposed system architecture uses a two-step learning framework, in which a population model is first obtained and then personalized by subject-specific data. Prioritized memory replay is adopted to accelerate the training process in clinical practice. To validate the algorithm, we employ a customized version of the FDA-accepted UVA/Padova T1D simulator to perform in silico trials on 10 adult subjects and 10 adolescent subjects. (3) Results: Compared to a standard bolus calculator as the baseline, the DRL insulin bolus advisor significantly improved the average percentage time in target range (70-180 mg/dL) from 74.1%±8.4% to 80.9%±6.9% (p<0.01) and 54.9%±12.4% to 61.6%±14.1% (p<0.01) in the the adult and adolescent cohorts, respectively, while reducing hypoglycemia. (4) Conclusions: The proposed algorithm has the potential to improve mealtime bolus insulin delivery in people with T1D and is a feasible candidate for future clinical validation.

Advanced Diabetes Management Using Artificial Intelligence and Continuous Glucose Monitoring Sensors

Wearable continuous glucose monitoring (CGM) sensors are revolutionizing the treatment of type 1 diabetes (T1D). These sensors provide in real-time, every 1-5 min, the current blood glucose concentration and its rate-of-change, two key pieces of information for improving the determination of exogenous insulin administration and the prediction of forthcoming adverse events, such as hypo-/hyper-glycemia. The current research in diabetes technology is putting considerable effort into developing decision support systems for patient use, which automatically analyze the patient's data collected by CGM sensors and other portable devices, as well as providing personalized recommendations about therapy adjustments to patients. Due to the large amount of data collected by patients with T1D and their variety, artificial intelligence (AI) techniques are increasingly being adopted in these decision support systems. In this paper, we review the state-of-the-art methodologies using AI and CGM sensors for decision support in advanced T1D management, including techniques for personalized insulin bolus calculation, adaptive tuning of bolus calculator parameters and glucose prediction.

Preventing undesirable behavior of intelligent machines

Intelligent machines using machine learning algorithms are ubiquitous, ranging from simple data analysis and pattern recognition tools to complex systems that achieve superhuman performance on various tasks. Ensuring that they do not exhibit undesirable behavior-that they do not, for example, cause harm to humans-is therefore a pressing problem. We propose a general and flexible framework for designing machine learning algorithms. This framework simplifies the problem of specifying and regulating undesirable behavior. To show the viability of this framework, we used it to create machine learning algorithms that precluded the dangerous behavior caused by standard machine learning algorithms in our experiments. Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.

Reinforcement Learning-Based Adaptive Insulin Advisor for Individuals with Type 1 Diabetes Patients under Multiple Daily Injections Therapy

The existing adaptive basal-bolus advisor (ABBA) was further developed to benefit patients under insulin therapy with multiple daily injections (MDI). Three different in silico experiments were conducted with the DMMS.R simulator to validate the approach of combined use of self-monitoring of blood glucose (SMBG) and insulin injection devices, e.g. insulin pen, as are used by the majority of type 1 diabetes patients under insulin therapy. The proposed approach outperforms the conventional method, as it increases the time spent within the target range and simultaneously reduces the risks of hyperglycaemic and hypoglycaemic events.

Study protocol for optimising glycaemic control in type 1 diabetes treated with multiple daily insulin injections: intermittently scanned continuous glucose monitoring, carbohydrate counting with automated bolus calculation, or both? A randomised controlled trial

INTRODUCTION

There are beneficial effects of advanced carbohydrate counting with an automatic bolus calculator (ABC) and intermittently scanned continuous glucose monitoring (isCGM) in persons with type 1 diabetes. We aim to compare the effects of isCGM, training in carbohydrate counting with ABC and the combination of the two concepts with standard care.

METHODS AND ANALYSIS

A multi-centre randomised controlled trial with inclusion criteria: ≥18 years, type 1 diabetes ≥1 year, injection therapy, HbA1c >53 mmol/mol, whereas daily use of carbohydrate counting and/or CGM/isCGM wear are exclusion criteria. Inclusion was initiated in October 2018 and is ongoing. Eligible persons are randomised into four groups: standard care, ABC, isCGM or ABC+isCGM. Devices used are FreeStyle Libre Flash and smart phone diabetes application mySugr. Participants attend group courses according to treatment allocation with different educational contents. Participants are followed for 26 weeks with clinical visits and telephone consultations. At baseline and at study end, participants wear blinded CGM, have blood samples performed and fill in questionnaires on person-related outcomes, and at baseline also on personality traits and hypoglycaemia awareness. The primary outcome is the difference in time spent in normoglycaemia (4-10 mmol/L) at study end versus baseline between the isCGM group and the standard care group. Secondary outcomes will also be analysed. Results are expected in 2020.

ETHICS AND DISSEMINATION

Regional Scientific Ethics Committee approval (H-17040573). Results will be sought disseminated at conferences and in high impact journals.Trial registration numberClinicalTrial.gov registry (NCT03682237).

Insulin Pump Settings During Breastfeeding in Women with Type 1 Diabetes

Background: We aimed to explore insulin pump settings in breastfeeding women with type 1 diabetes. Methods: Thirteen unselected breastfeeding women with type 1 diabetes on insulin pump therapy were included consecutively from April 2016 to October 2017. Blinded continuous glucose monitoring (CGM) for 6 days was applied at 1, 2, and 6 months after delivery. Recommendations were intake of 210 g carbohydrate daily while aiming for glucose target range 4.0-10.0 mmol/L and avoiding hypoglycemia. Immediately after delivery a reduction of total insulin dose by 30% of the prepregnancy dose was recommended. Insulin pump target glucose was 5.8 mmol/L. Results: Median diabetes duration was 22 (range 13-36) years. At 1, 2, and 6 months, 13, 11, and 8 women, respectively, were breastfeeding and spent ≥70.8% (25%-99%) of time in the glucose target range and ≤3.8% (0%-15.5%) of time with CGM <4.0 mmol/L at night-time and for 24 h. None of the women experienced severe hypoglycemia. HbA1c was 58 (47-72) mmol/mol and 52 (44-60) at 6 months and prepregnancy, respectively, P = 0.18. At 1, 2, and 6 months, the insulin pump settings remained almost stable with basal insulin rates (at 03.00, 08.00, 12.00, and 18.00) 14% lower and the carbohydrate-to-insulin ratios 10% higher than the prepregnancy settings. Conclusions: In breastfeeding women with type 1 diabetes who consumed sufficient amounts of carbohydrates and obtained appropriate glycemic control, the basal insulin rates were 14% lower and carbohydrate-to-insulin ratios 10% higher than before pregnancy. These data are useful when recommending insulin pump settings after delivery.

Smartphone-Based Technology in Diabetes Management

Diabetes is a group of metabolic disorders characterized by elevated levels of blood glucose which leads over time to serious complications and significant morbidity and mortality worldwide. Self-management tasks in diabetes may be quite challenging because of lack of training, difficulties in sustaining lifestyle modifications, and limited access to specialized healthcare. Nowadays, the evolution of mobile technology provides a large number of health-related smartphone applications (apps), aiming to increase the self-management skills of the patient in chronic diseases, to facilitate the communication between the patient and healthcare providers, and to increase also the patient's compliance with the treatment. In the field of diabetes there are also many diabetes-related mobile apps mainly focusing on self-management of diabetes, lifestyle modification, and medication adherence motivation. The aim of this paper is to review the most important diabetes-related mobile smartphone applications, including only those supported by prospective randomized controlled trials.

Intelligent Data-Driven Model for Diabetes Diurnal Patterns Analysis

In type 1 diabetes, diurnal activity routines are influential factors in insulin dose calculations. Bolus advisors have been developed to more accurately suggest doses of meal-related insulin based on carbohydrate intake, according to pre-set insulin to carbohydrate levels and insulin sensitivity factors. These parameters can be varied according to the time of day and their optimal setting relies on identifying the daily time periods of routines accurately. The main issues with reporting and adjustments of daily activity routines are the reliance on self-reporting which is prone to inaccuracy and within bolus calculators, the keeping of default settings for daily time periods, such as within insulin pumps, glucose meters, and mobile applications. Moreover, daily routines are subject to change over periods of time which could go unnoticed. Hence, forgetting to change the daily time periods in the bolus calculator could contribute to sub-optimal self-management. In this paper, these issues are addressed by proposing a data-driven model for identification of diabetes diurnal patterns based on self-monitoring data. The model uses time-series clustering to achieve a meaningful separation of the patterns which is then used to identify the daily time periods and to advise of any time changes required. Further improvements in bolus advisor settings are proposed to include week/weekend or even modifiable daily time settings. The proposed model provides a quick, granular, more accurate, and personalized daily time setting profile while providing a more contextual perspective to glycemic pattern identification to both patients and clinicians.

A Modular Safety System for an Insulin Dose Recommender: A Feasibility Study

BACKGROUND

Delivering insulin in type 1 diabetes is a challenging, and potentially risky, activity; hence the importance of including safety measures as part of any insulin dosing or recommender system. This work presents and clinically evaluates a modular safety system that is part of an intelligent insulin dose recommender platform developed within the EU-funded PEPPER project.

METHODS

The proposed safety system is composed of four modules which use a novel glucose forecasting algorithm. These modules are predictive glucose alerts and alarms; a predictive low-glucose basal insulin suspension module; an advanced rescue carbohydrate recommender for resolving hypoglycemia; and a personalized safety constraint applied to insulin recommendations. The technical feasibility of the proposed safety system was evaluated in a pilot study including eight adult subjects with type 1 diabetes on multiple daily injections over a duration of six weeks. Glycemic control and safety system functioning were compared between the two-weeks run-in period and the end point at eight weeks. A standard insulin bolus calculator was employed to recommend insulin doses.

RESULTS

Overall, glycemic control improved over the evaluated period. In particular, percentage time in the hypoglycemia range (<3.0 mmol/l) significantly decreased from 0.82% (0.05-4.79) at run-in to 0.33% (0.00-0.93) at endpoint (P = .02). This was associated with a significant increase in percentage time in target range (3.9-10.0 mmol/l) from 52.8% (38.3-61.5) to 61.3% (47.5-71.7) (P = .03). There was also a reduction in number of carbohydrate recommendations.

CONCLUSION

A safety system for an insulin dose recommender has been proven to be a viable solution to reduce the number of adverse events associated to glucose control in type 1 diabetes.

Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes-An In Silico Proof-of-Concept

In the daily management of type 1 diabetes (T1D), determining the correct insulin dose to be injected at meal-time is fundamental to achieve optimal glycemic control. Wearable sensors, such as continuous glucose monitoring (CGM) devices, are instrumental to achieve this purpose. In this paper, we show how CGM data, together with commonly recorded inputs (carbohydrate intake and bolus insulin), can be used to develop an algorithm that allows classifying, at meal-time, the post-prandial glycemic status (i.e., blood glucose concentration being too low, too high, or within target range). Such an outcome can then be used to improve the efficacy of insulin therapy by reducing or increasing the corresponding meal bolus dose. A state-of-the-art T1D simulation environment, including intraday variability and a behavioral model, was used to generate a rich in silico dataset corresponding to 100 subjects over a two-month scenario. Then, an extreme gradient-boosted tree (XGB) algorithm was employed to classify the post-prandial glycemic status. Finally, we demonstrate how the XGB algorithm outcome can be exploited to improve glycemic control in T1D through real-time adjustment of the meal insulin bolus. The proposed XGB algorithm obtained good accuracy at classifying post-prandial glycemic status (AUROC = 0.84 [0.78, 0.87]). Consequently, when used to adjust, in real-time, meal insulin boluses obtained with a bolus calculator, the proposed approach improves glycemic control when compared to the baseline bolus calculator. In particular, percentage time in target [70, 180] mg/dL was improved from 61.98 (±13.89) to 67.00 (±11.54; p < 0.01) without increasing hypoglycemia.

Artificial Intelligence/Machine Learning in Diabetes Care

Artificial intelligence/Machine learning (AI/ML) is transforming all spheres of our life, including the healthcare system. Application of AI/ML has a potential to vastly enhance the reach of diabetes care thereby making it more efficient. The huge burden of diabetes cases in India represents a unique set of problems, and provides us with a unique opportunity in terms of potential availability of data. Harnessing this data using electronic medical records, by all physicians, can put India at the forefront of research in this area. Application of AI/ML would provide insights to our problems as well as may help us to devise tailor-made solutions for the same.

Comprehensive Analysis of the Real Lifestyles of T1D Patients for the Purpose of Designing a Personalized Counselor for Prandial Insulin Dosing

Post-prandial hyperglycemia is still a challenging issue in intensified insulin therapy. Data of 35 T1D patients during a four-week period were analyzed: RT-CGM (real time continuous glucose monitoring) record, insulin doses, diet (including meal photos), energy expenditure, and other relevant conditions. Patients made significant errors in carbohydrate counting (in 56% of cooked and 44% of noncooked meals), which resulted in inadequate insulin doses. Subsequently, a mobile application was programmed to provide individualized advice on prandial insulin dose. When using the application, a patient chooses only the type of categorized situation (e.g., meals with other relevant data) without carbohydrates counting. The application significantly improved postprandial glycemia as normoglycemia was reached in 95/105 testing sessions. Other important findings of the study include: A high intake of saturated fat (median: 162% of recommended intake); a low intake of fiber and vitamin C (median: 42% and 37%, respectively, of recommended intake); an increase in overweight/obesity status (according to body fat measurement), especially in women (median of body fat: 30%); and low physical activity (in 16/35 patients). The proposed individualized approach without carbohydrate counting may help reach postprandial normoglycemia but it is necessary to pay attention to the lifestyle habits of T1D patients too.

A mobile health monitoring-and-treatment system based on integration of the SSN sensor ontology and the HL7 FHIR standard

BACKGROUND

Mobile health (MH) technologies including clinical decision support systems (CDSS) provide an efficient method for patient monitoring and treatment. A mobile CDSS is based on real-time sensor data and historical electronic health record (EHR) data. Raw sensor data have no semantics of their own; therefore, a computer system cannot interpret these data automatically. In addition, the interoperability of sensor data and EHR medical data is a challenge. EHR data collected from distributed systems have different structures, semantics, and coding mechanisms. As a result, building a transparent CDSS that can work as a portable plug-and-play component in any existing EHR ecosystem requires a careful design process. Ontology and medical standards support the construction of semantically intelligent CDSSs.

METHODS

This paper proposes a comprehensive MH framework with an integrated CDSS capability. This cloud-based system monitors and manages type 1 diabetes mellitus. The efficiency of any CDSS depends mainly on the quality of its knowledge and its semantic interoperability with different data sources. To this end, this paper concentrates on constructing a semantic CDSS based on proposed FASTO ontology.

RESULTS

This realistic ontology is able to collect, formalize, integrate, analyze, and manipulate all types of patient data. It provides patients with complete, personalized, and medically intuitive care plans, including insulin regimens, diets, exercises, and education sub-plans. These plans are based on the complete patient profile. In addition, the proposed CDSS provides real-time patient monitoring based on vital signs collected from patients' wireless body area networks. These monitoring include real-time insulin adjustments, mealtime carbohydrate calculations, and exercise recommendations. FASTO integrates the well-known standards of HL7 fast healthcare interoperability resources (FHIR), semantic sensor network (SSN) ontology, basic formal ontology (BFO) 2.0, and clinical practice guidelines. The current version of FASTO includes 9577 classes, 658 object properties, 164 data properties, 460 individuals, and 140 SWRL rules. FASTO is publicly available through the National Center for Biomedical Ontology BioPortal at https://bioportal.bioontology.org/ontologies/FASTO .

CONCLUSIONS

The resulting CDSS system can help physicians to monitor more patients efficiently and accurately. In addition, patients in rural areas can depend on the system to manage their diabetes and emergencies.