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

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5058 ◽  
Author(s):  
Taiyu Zhu ◽  
Kezhi Li ◽  
Lei Kuang ◽  
Pau Herrero ◽  
Pantelis Georgiou
Keyword(s):  
Type 1 Diabetes ◽  
Reinforcement Learning ◽  
Glucose Monitoring ◽  
Insulin Delivery ◽  
Target Range ◽  
Average Percentage ◽  
Learning Framework ◽  
Policy Gradient ◽  
Bolus Insulin

(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.

scholarly journals Analysis of continuous glucose tracking data in people with Type 1 Diabetes (T1DM) after Covid-19 Vaccination reveals unexpected link between immune and metabolic response, augmented by adjunctive oral medication

2021 ◽  
Author(s):  
Adrian Heald ◽  
Rustam Rea ◽  
Linda Horne ◽  
Ann Metters ◽  
Tom Steele ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Metabolic Response ◽  
Glucose Monitoring ◽  
Primary Outcome Measure ◽  
Target Range ◽  
Older Individuals ◽  
Oral Hypoglycaemic Agents ◽  
Before And After ◽  
Bolus Insulin

Introduction The COVID-19 vaccination programme is under way. Anecdotal evidence is increasing that some people with Type 1 Diabetes Mellitus (T1DM) experience temporary instability of blood glucose (BG) levels post-vaccination which normally settles within 2-3 days. We report an analysis of BG profiles of 20 individuals before and after vaccination. Methods We examined the BG profile of 20 consecutive adults (18 years of age or more) with T1DM using the FreeStyle® Libre flash glucose monitor in the period immediately before and after COVID-19 vaccination. The primary outcome measure was percentage(%) BG readings in the designated target range 3.9-10mmmol/L as reported on the LibreView portal for 7 days prior to the vaccination (week -1) and the 7 days after the vaccination (week +1). Results There was a significant decrease in the %BG on target following the COVID-vaccination for the 7 days following vaccination (mean 45.2% ±se 4.2%) vs pre-COVID-19 vaccination (mean 52.6% ±se 4.5%). This was mirrored by an increase in the proportion of readings in other BG categories 10.1-13.9%/ ≥14%. There was no significant change in BG variability in the 7days post COVID-19 vaccination. This change in BG proportion on target in the week following vaccination was most pronounced for people taking Metformin/Dapagliflozin+basal bolus insulin (-23%) vs no oral hypoglycaemic agents (-4%), and median age <53 vs ≥53 years (greater reduction in %BG in target for older individuals (-18% vs -9%)). Conclusion In T1DM, we have shown that COVID-19 vaccination can cause temporary perturbation of BG, with this effect more pronounced in patients talking oral hypoglycaemic medication plus insulin, and in older individuals. This may have consequences for patients with T2DM who are currently not supported by flash glucose monitoring.

136-OR: Nocturnal Hypoglycemia Prevention Strategies Used by People with Type 1 Diabetes According to Their Insulin Delivery and Blood Glucose Monitoring Technology

Diabetes ◽  
2021 ◽  
Vol 70 (Supplement 1) ◽  
pp. 136-OR
Author(s):  
MERYEM K. TALBO ◽  
VIRGINIE MESSIER ◽  
KATHERINE DESJARDINS ◽  
RÉMI RABASA-LHORET ◽  
ANNE-SOPHIE BRAZEAU ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Blood Glucose ◽  
Glucose Monitoring ◽  
Insulin Delivery ◽  
Blood Glucose Monitoring ◽  
Prevention Strategies ◽  
Monitoring Technology ◽  
Nocturnal Hypoglycemia

scholarly journals Liraglutide as additional treatment for type 1 diabetes

2011 ◽  
Vol 165 (1) ◽  
pp. 77-84 ◽  
Author(s):  
Ajay Varanasi ◽  
Natalie Bellini ◽  
Deepti Rawal ◽  
Mehul Vora ◽  
Antoine Makdissi ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Glycemic Control ◽  
Insulin Dose ◽  
Glucose Monitoring ◽  
Glycemic Variability ◽  
Additional Treatment ◽  
The Body ◽  
The Mean ◽  
Bolus Insulin

ObjectiveTo determine whether the addition of liraglutide to insulin to treat patients with type 1 diabetes leads to an improvement in glycemic control and diminish glycemic variability.Subjects and methodsIn this study, 14 patients with well-controlled type 1 diabetes on continuous glucose monitoring and intensive insulin therapy were treated with liraglutide for 1 week. Of the 14 patients, eight continued therapy for 24 weeks.ResultsIn all the 14 patients, mean fasting and mean weekly glucose concentrations significantly decreased after 1 week from 130±10 to 110±8 mg/dl (P<0.01) and from 137.5±20 to 115±12 mg/dl (P<0.01) respectively. Glycemic excursions significantly improved at 1 week. The mean s.d. of glucose concentrations decreased from 56±10 to 26±6 mg/dl (P<0.01) and the coefficient of variation decreased from 39.6±10 to 22.6±7 (P<0.01). There was a concomitant fall in the basal insulin from 24.5±6 to 16.5±6 units (P<0.01) and bolus insulin from 22.5±4 to 15.5±4 units (P<0.01).In patients who continued therapy with liraglutide for 24 weeks, mean fasting, mean weekly glucose concentrations, glycemic excursions, and basal and bolus insulin dose also significantly decreased (P<0.01). HbA1c decreased significantly at 24 weeks from 6.5 to 6.1% (P=0.02), as did the body weight by 4.5±1.5 kg (P=0.02).ConclusionLiraglutide treatment provides an additional strategy for improving glycemic control in type 1 diabetes. It also leads to weight loss.

scholarly journals Improved Glycemic Outcomes With Medtronic MiniMed Advanced Hybrid Closed-Loop Delivery: Results From a Randomized Crossover Trial Comparing Automated Insulin Delivery With Predictive Low Glucose Suspend in People With Type 1 Diabetes

2021 ◽  
Author(s):  
Olivia J Collyns ◽  
Renee A Meier ◽  
Zara L Betts ◽  
Denis SH Chan ◽  
Chris Frampton ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Closed Loop ◽  
Insulin Delivery ◽  
Target Range ◽  
Study Phase ◽  
Pump Therapy ◽  
Set Point ◽  
Sensor Glucose ◽  
Low Glucose

Objective:<br><p> To study the MiniMed™ Advanced Hybrid Closed-Loop system (AHCL) which includes an algorithm with individualised basal target set points, automated correction bolus function, and improved Auto Mode stability.<br> Research design and Methods:</p> <p>This dual-centre, randomized, open-label, two-sequence cross-over study in automated insulin delivery naïve participants with type 1 diabetes (aged 7-80yrs), compared AHCL to Sensor Augmented Pump therapy with Predictive Low Glucose Management (SAP+PLGM). Each study phase was 4 weeks, preceded by a 2-4 week run-in, and separated by 2-week washout.</p> <p><a>Results:<b> </b><br> 59/60 people completed the study (mean age 23.3±14.4yrs). Time in target range (TIR) 3.9-10mmol/L (70-180 mg/dL) favoured AHCL over SAP+PLGM (</a>70.4±8.1 vs 57.9±11.7) by 12.5±8.5% (p<0.001), with greater improvement overnight (18.8±12.9%, p<0.001). All age groups (children (7 – 13 years), adolescents (14 – 21 years), and adults (>22 years) demonstrated improvement, with adolescents showing the largest improvement (14.4±8.4%). Mean sensor glucose (SG) at run in was 9.3±0.9 mmol/L (167±16.2mg/dL) and improved with AHCL (8.5±0.7mmol/L (153±12.6mg/dL) (p < 0.001)), but deteriorated during PLGM (9.5±1.1mmol/L (17±19.8mg/dL), (p<0.001)).. TIR was optimal when the algorithm set point was 5.6 mmol/L (100 mg/dL) compared to 6.7 mmol/L (120 mg/dL), 72.0±7.9% vs 64.6±6.9% respectively with no additional hypoglycemia. Auto Mode was active 96.4±4.0% of the time. <a>The percentage of hypoglycemia at baseline (<3.9mmol/L (70mg/dl) and </a> £ 3.0mmol/L(54mg/dl)) was 3.1±2.1% and 0.5±0.6% respectively. During AHCL percentage time <3.9mmol/L (70mg/dl) improved to 2.1±1.4% (p=0.034) (70mg/dl), and was statistically but not clinically reduced for £ 3.0mmol/L(54mg/dl) (0.5±0.5%, p = 0.025) There was one episode of mild diabetic ketoacidosis attributed to an infusion set failure in combination with an intercurrent illness, which occurred during the SAP+PLGM arm.</p> <p>Conclusions</p> <p>AHCL with automated correction bolus demonstrated significant improvement in glucose control compared to SAP+PLGM. A lower algorithm sensor glucose set point during AHCL resulted in greater TIR, with no increase in hypoglycemia.</p>

scholarly journals Technology for Augmenting Type 1 Diabetes Mellitus Management

2019 ◽  
Vol 24 (2) ◽  
pp. 99-106
Author(s):  
Michelle Condren ◽  
Samie Sabet ◽  
Laura J. Chalmers ◽  
Taylor Saley ◽  
Jenna Hopwood
Keyword(s):  
Diabetes Mellitus ◽  
Type 1 Diabetes ◽  
Type 1 Diabetes Mellitus ◽  
Continuous Glucose Monitoring ◽  
Diabetes Management ◽  
Insulin Pump ◽  
Glucose Monitoring ◽  
Insulin Delivery ◽  
Diabetes Mellitus Management

Type 1 diabetes mellitus has witnessed significant progress in its management over the past several decades. This review highlights technologic advancements in type 1 diabetes management. Continuous glucose monitoring systems are now available at various functionality and cost levels, addressing diverse patient needs, including a recently US Food and Drug Administration (FDA)–approved implantable continuous glucose monitoring system (CGMS). Another dimension to these state-of-the-art technologies is CGMS and insulin pump integration. These integrations have allowed for CGMS-based adjustments to basal insulin delivery rates and suspension of insulin delivery when a low blood glucose event is predicted. This review also includes a brief discussion of upcoming technologies such as patch-based CGMS and insulin-glucagon dual-hormonal delivery.

scholarly journals Progress with Closed-loop Systems in Type 1 Diabetes

2010 ◽  
Vol 06 (01) ◽  
pp. 58
Author(s):  
Lalantha Leelarathna ◽  
Roman Hovorka ◽  
◽  
Keyword(s):  
Type 1 Diabetes ◽  
Closed Loop ◽  
Diabetes Management ◽  
Insulin Delivery ◽  
Glucose Measurement ◽  
Target Range ◽  
Advantages And Disadvantages ◽  
Closed Loop Systems ◽  
Interstitial Glucose

Automated insulin delivery by means of a glucose-responsive closed-loop system has often been cited as the ‘holy grail’ of type 1 diabetes management. Reflecting the technological advances in interstitial glucose measurements and wider use of continuous glucose monitoring, recent research in closed-loop glucose control has focused on the subcutaneous route for glucose measurements and insulin delivery. The primary aim of such systems is to keep blood glucose within the target range while minimizing the risk of hypoglycemia with minimal input from the user. This article examines recent developments in the field of interstitial glucose measurement, limitations of the current generation of devices and implications on the performance of closed-loop systems. Clinical results and the advantages and disadvantages of different closed-loop configurations are summarized. Potential future advances in closed-loop systems are highlighted.

Type 1 diabetes glycemic management: Insulin therapy, glucose monitoring, and automation

Science ◽  
2021 ◽  
Vol 373 (6554) ◽  
pp. 522-527
Author(s):  
Bruce A. Perkins ◽  
Jennifer L. Sherr ◽  
Chantal Mathieu
Keyword(s):  
Type 1 Diabetes ◽  
Insulin Therapy ◽  
Glucose Monitoring ◽  
Insulin Delivery ◽  
Clinical Implementation ◽  
Delivery Methods ◽  
Insulin Effect ◽  
Future Challenges ◽  
Delivery Routes

Despite innovations in insulin therapy since its discovery, most patients living with type 1 diabetes do not achieve sufficient glycemic control to prevent complications, and they experience hypoglycemia, weight gain, and major self-care burden. Promising pharmacological advances in insulin therapy include the refinement of extremely rapid insulin analogs, alternate insulin-delivery routes, liver-selective insulins, add-on drugs that enhance insulin effect, and glucose-responsive insulin molecules. The greatest future impact will come from combining these pharmacological solutions with existing automated insulin delivery methods that integrate insulin pumps and glucose sensors. These systems will use algorithms enhanced by machine learning, supplemented by technologies that include activity monitors and sensors for other key metabolites such as ketones. The future challenges facing clinicians and researchers will be those of access and broad clinical implementation.

Progress with Closed-loop Systems in Type 1 Diabetes

2010 ◽  
Vol 6 (2) ◽  
pp. 31
Author(s):  
Lalantha Leelarathna ◽  
Roman Hovorka ◽  
◽  
Keyword(s):  
Type 1 Diabetes ◽  
Closed Loop ◽  
Diabetes Management ◽  
Insulin Delivery ◽  
Glucose Measurement ◽  
Target Range ◽  
Advantages And Disadvantages ◽  
Closed Loop Systems ◽  
Interstitial Glucose

Automated insulin delivery by means of a glucose-responsive closed-loop system has often been cited as the ‘holy grail’ of type 1 diabetes management. Reflecting the technological advances in interstitial glucose measurements and wider use of continuous glucose monitoring, recent research in closed-loop glucose control has focused on the subcutaneous route for glucose measurements and insulin delivery. The primary aim of such systems is to keep blood glucose within the target range while minimising the risk of hypoglycaemia with minimal input from the user. This article examines recent developments in the field of interstitial glucose measurement, limitations of the current generation of devices and implications on the performance of closed-loop systems. Clinical results and the advantages and disadvantages of different closed-loop configurations are summarised. Potential future advances in closed-loop systems are highlighted.

Sign in / Sign up

Export Citation Format

Share Document