scholarly journals A Deep Learning Framework for Automatic Meal Detection and Estimation in Artificial Pancreas Systems

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 466
Author(s):  
John Daniels ◽  
Pau Herrero ◽  
Pantelis Georgiou
Keyword(s):  
Deep Learning ◽  
Quantile Regression ◽  
Glucose Control ◽  
Closed Loop ◽  
Artificial Pancreas ◽  
Postprandial Glucose ◽  
User Engagement ◽  
Frequent User ◽  
Learning Framework ◽  
Closed Loop Systems

Current artificial pancreas (AP) systems are hybrid closed-loop systems that require manual meal announcements to manage postprandial glucose control effectively. This poses a cognitive burden and challenge to users with T1D since this relies on frequent user engagement to maintain tight glucose control. In order to move towards fully automated closed-loop glucose control, we propose an algorithm based on a deep learning framework that performs multitask quantile regression, for both meal detection and carbohydrate estimation. Our proposed method is evaluated in silico on 10 adult subjects from the UVa/Padova simulator with a Bio-inspired Artificial Pancreas (BiAP) control algorithm over a 2 month period. Three different configurations of the AP are evaluated -BiAP without meal announcement (BiAP-NMA), BiAP with meal announcement (BiAP-MA), and BiAP with meal detection (BiAP-MD). We present results showing an improvement of BiAP-MD over BiAP-NMA, demonstrating 144.5 ± 6.8 mg/dL mean blood glucose level (−4.4 mg/dL, p< 0.01) and 77.8 ± 6.3% mean time between 70 and 180 mg/dL (+3.9%, p< 0.001). This improvement in control is realised without a significant increase in mean in hypoglycaemia (+0.1%, p= 0.4). In terms of detection of meals and snacks, the proposed method on average achieves 93% precision and 76% recall with a detection delay time of 38 ± 15 min (92% precision, 92% recall, and 37 min detection time for meals only). Furthermore, BiAP-MD handles hypoglycaemia better than BiAP-MA based on CVGA assessment with fewer control errors (10% vs. 20%). This study suggests that multitask quantile regression can improve the capability of AP systems for postprandial glucose control without increasing hypoglycaemia.

scholarly journals The challenges of achieving postprandial glucose control using closed‐loop systems in patients with type 1 diabetes

2017 ◽  
Vol 20 (2) ◽  
pp. 245-256 ◽  
Author(s):  
Véronique Gingras ◽  
Nadine Taleb ◽  
Amélie Roy‐Fleming ◽  
Laurent Legault ◽  
Rémi Rabasa‐Lhoret
Keyword(s):  
Type 1 Diabetes ◽  
Glucose Control ◽  
Closed Loop ◽  
Postprandial Glucose ◽  
Closed Loop Systems

scholarly journals Closed-loop management of inpatient hyperglycaemia

2019 ◽  
Vol 80 (11) ◽  
pp. 665-669
Author(s):  
CK Boughton ◽  
R Hovorka
Keyword(s):  
Health Care ◽  
Insulin Therapy ◽  
Health Care Professionals ◽  
Glucose Control ◽  
Closed Loop ◽  
Diabetes Management ◽  
Inpatient Setting ◽  
Glucose Levels ◽  
Closed Loop Systems ◽  
Inpatient Diabetes

The prevalence of diabetes in the inpatient setting is increasing, and suboptimal glucose control in hospital is associated with increased morbidity and mortality. Attaining the recommended glucose levels is challenging with standard insulin therapy. Hypoglycaemia and hyperglycaemia are common and diabetes management in hospital can be a considerable workload burden for health-care professionals. Fully automated insulin delivery (closed-loop) has been shown to be safe, and achieves superior glucose control than standard insulin therapy in the hospital, including in those patients receiving haemodialysis and enteral or parenteral nutrition where glucose control can be particularly challenging. Evidence that the improved glucose control achieved using closed-loop systems can translate into improved clinical outcomes for patients is key to support widespread adoption of this technology. The closed-loop approach has the potential to provide a paradigm shift in the management of inpatient diabetes, particularly in the most challenging inpatient populations, and may reduce staff work burden and the health-care costs associated with inpatient diabetes.

Impact of macronutrient content of meals on postprandial glucose control in the context of closed‐loop insulin delivery: A randomized cross‐over study

2018 ◽  
Vol 20 (11) ◽  
pp. 2695-2699 ◽  
Author(s):  
Véronique Gingras ◽  
Lisa Bonato ◽  
Virginie Messier ◽  
Amélie Roy‐Fleming ◽  
Mohamed R. Smaoui ◽  
...  
Keyword(s):  
Glucose Control ◽  
Closed Loop ◽  
Insulin Delivery ◽  
Postprandial Glucose ◽  
Macronutrient Content

scholarly journals Women’s Experiences of Day-and-Night Closed-Loop Insulin Delivery During Type 1 Diabetes Pregnancy

2018 ◽  
Vol 12 (6) ◽  
pp. 1125-1131 ◽  
Author(s):  
Conor Farrington ◽  
Zoe Stewart ◽  
Roman Hovorka ◽  
Helen Murphy
Keyword(s):  
Type 1 Diabetes ◽  
Glucose Control ◽  
Closed Loop ◽  
Insulin Delivery ◽  
Peace Of Mind ◽  
Women’S Experiences ◽  
Closed Loop Systems ◽  
Women's Experiences

Aims: Closed-loop insulin delivery has the potential to improve day-to-day glucose control in type 1 diabetes pregnancy. However, the psychosocial impact of day-and-night usage of automated closed-loop systems during pregnancy is unknown. Our aim was to explore women’s experiences and relationships between technology experience and levels of trust in closed-loop therapy. Methods: We recruited 16 pregnant women with type 1 diabetes to a randomized crossover trial of sensor-augmented pump therapy compared to automated closed-loop therapy. We conducted semistructured qualitative interviews at baseline and follow-up. Findings from follow-up interviews are reported here. Results: Women described benefits and burdens of closed-loop systems during pregnancy. Feelings of improved glucose control, excitement and peace of mind were counterbalanced by concerns about technical glitches, CGM inaccuracy, and the burden of maintenance requirements. Women expressed varied but mostly high levels of trust in closed-loop therapy. Conclusions: Women displayed complex psychosocial responses to day-and-night closed-loop therapy in pregnancy. Clinicians should consider closed-loop therapy not just in terms of its potential impact on biomedical outcomes but also in terms of its impact on users’ lives.

scholarly journals Survey about do-it-yourself closed loop systems in the treatment of diabetes in Germany

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0243465
Author(s):  
Anna Laura Herzog ◽  
Jonas Busch ◽  
Christoph Wanner ◽  
Holger K. von Jouanne-Diedrich
Keyword(s):  
Blood Glucose ◽  
Glucose Control ◽  
Closed Loop ◽  
Artificial Pancreas ◽  
Direct Interaction ◽  
Loop System ◽  
Closed Loop System ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Do It Yourself

Continuous glucose monitoring (CGM) improves treatment with lower blood glucose levels and less patient effort. In combination with continuous insulin application, glycemic control improves and hypoglycemic episodes should decrease. Direct feedback of CGM to continuous subcutaneous insulin application, using an algorithm is called a closed-loop (CL) artificial pancreas system. Commercial devices stop insulin application by predicting hypoglycemic blood glucose levels through direct interaction between the sensor and pump. The prediction is usually made for about 30 minutes and insulin delivery is restarted at the previous level if a rise in blood glucose is predicted within the next 30 minutes (hybrid closed loop system, HCL this is known as a predictive low glucose suspend system (PLGS)). In a fully CL system, sensor and pump communicate permanently with each other. Hybrid closed-loop (HCL) systems, which require the user to estimate the meal size and provide a meal insulin basis, are commercially available in Germany at the moment. These systems result in fewer hyperglycemic and hypoglycemic episodes with improved glucose control. Open source initiatives have provided support by building do-it-yourself CL (DIYCL) devices for automated insulin application since 2014, and are used by a tech-savvy subgroup of patients. The first commercial hybrid CL system has been available in Germany since September 2019. We surveyed 1054 patients to determine which devices are currently used, which features would be in demand by potential users, and the benefits of DIYCL systems. 9.7% of these used a DIYCL system, while 50% would most likely trust these systems but more than 85% of the patients would use a commercial closed loop system, if available. The DIYCL users had a better glucose control regarding their time in range (TIR) and glycated hemoglobin (HbA1c).

Sign in / Sign up

Export Citation Format

Share Document