scholarly journals Long-Term Glucose Forecasting Using a Physiological Model and Deconvolution of the Continuous Glucose Monitoring Signal

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4338 ◽  
Author(s):  
Chengyuan Liu ◽  
Josep Vehí ◽  
Parizad Avari ◽  
Monika Reddy ◽  
Nick Oliver ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Continuous Glucose Monitoring ◽  
Latent Variable ◽  
Prediction Accuracy ◽  
Insulin Dose ◽  
Artificial Pancreas ◽  
Glucose Monitoring ◽  
Physiological Model ◽  
The Impact

(1) Objective: Blood glucose forecasting in type 1 diabetes (T1D) management is a maturing field with numerous algorithms being published and a few of them having reached the commercialisation stage. However, accurate long-term glucose predictions (e.g., >60 min), which are usually needed in applications such as precision insulin dosing (e.g., an artificial pancreas), still remain a challenge. In this paper, we present a novel glucose forecasting algorithm that is well-suited for long-term prediction horizons. The proposed algorithm is currently being used as the core component of a modular safety system for an insulin dose recommender developed within the EU-funded PEPPER (Patient Empowerment through Predictive PERsonalised decision support) project. (2) Methods: The proposed blood glucose forecasting algorithm is based on a compartmental composite model of glucose–insulin dynamics, which uses a deconvolution technique applied to the continuous glucose monitoring (CGM) signal for state estimation. In addition to commonly employed inputs by glucose forecasting methods (i.e., CGM data, insulin, carbohydrates), the proposed algorithm allows the optional input of meal absorption information to enhance prediction accuracy. Clinical data corresponding to 10 adult subjects with T1D were used for evaluation purposes. In addition, in silico data obtained with a modified version of the UVa-Padova simulator was used to further evaluate the impact of accounting for meal absorption information on prediction accuracy. Finally, a comparison with two well-established glucose forecasting algorithms, the autoregressive exogenous (ARX) model and the latent variable-based statistical (LVX) model, was carried out. (3) Results: For prediction horizons beyond 60 min, the performance of the proposed physiological model-based (PM) algorithm is superior to that of the LVX and ARX algorithms. When comparing the performance of PM against the secondly ranked method (ARX) on a 120 min prediction horizon, the percentage improvement on prediction accuracy measured with the root mean square error, A-region of error grid analysis (EGA), and hypoglycaemia prediction calculated by the Matthews correlation coefficient, was 18.8 % , 17.9 % , and 80.9 % , respectively. Although showing a trend towards improvement, the addition of meal absorption information did not provide clinically significant improvements. (4) Conclusion: The proposed glucose forecasting algorithm is potentially well-suited for T1D management applications which require long-term glucose predictions.

scholarly journals Continuous Glucose Monitoring (CGM) or Blood Glucose Monitoring (BGM): Interactions and Implications

2018 ◽  
Vol 12 (4) ◽  
pp. 873-879 ◽  
Author(s):  
Lutz Heinemann
Keyword(s):  
Blood Glucose ◽  
Continuous Glucose Monitoring ◽  
Patient Management ◽  
Glucose Monitoring ◽  
Blood Glucose Monitoring ◽  
Advanced Technologies ◽  
Patients With Diabetes ◽  
The Impact ◽  
Annual International Conference

At the 2017 10th annual International Conference on Advanced Technologies and Treatments for Diabetes (ATTD) in Paris, France, four speakers presented their perspectives on the roles of continuous glucose monitoring (CGM) and of blood glucose monitoring (BGM) in patient management within one symposium. These presentations included discussions of the differences in the accuracy of CGM and BGM, a clinical perspective on the physiological reasons behind differences in CGM and BGM values, and an overview of the impact of variations in device accuracy on patients with diabetes. Subsequently a short summary of these presentations is given, highlighting the value of good accuracy of BGM or CGM systems and the ongoing need for standardization. The important role of both BGM and CGM in patient management was a theme across all presentations.

scholarly journals Toward Long-Term Implantable Glucose Biosensors for Clinical Use

2019 ◽  
Vol 9 (10) ◽  
pp. 2158 ◽  
Author(s):  
Yun Jung Heo ◽  
Seong-Hyok Kim
Keyword(s):  
Continuous Glucose Monitoring ◽  
Artificial Pancreas ◽  
Glucose Monitoring ◽  
Blood Glucose Monitoring ◽  
New Era ◽  
Glucose Testing ◽  
Sensor Fabrication ◽  
Technical Refinement ◽  
Implantable Sensor

Continuous glucose monitoring (CGM) sensors have led a paradigm shift to painless, continuous, zero-finger pricking measurement in blood glucose monitoring. Recent electrochemical CGM sensors have reached two-week lifespans and no calibration with clinically acceptable accuracy. The system with the recent CGM sensors is identified as an “integrated glucose monitoring system,” which can replace finger-pricking glucose-testing for diabetes treatment decisions. Although such innovation has brought CGM technology closer to realizing the artificial pancreas, discomfort and infection problems have arisen from short lifespans and open wounds. A fully implantable sensor with a longer-term lifespan (90 days) is considered as an alternative CGM sensor with high comfort and low running cost. However, it still has barriers, including surgery for applying and replacing and frequent calibration. If technical refinement is conducted (e.g., stability and reproducibility of sensor fabrication), fully implantable, long-term CGM sensors can open the new era of continuous glucose monitoring.

scholarly journals Interstitium versus Blood Equilibrium in Glucose Concentration and its Impact on Subcutaneous Continuous Glucose Monitoring Systems

2010 ◽  
Vol 10 (1) ◽  
pp. 36 ◽  
Author(s):  
Cosimo Scuffi ◽  
Keyword(s):  
Blood Glucose ◽  
Continuous Glucose Monitoring ◽  
Glucose Concentration ◽  
Interstitial Fluid ◽  
Glucose Monitoring ◽  
Foreign Body Response ◽  
Monitoring Systems ◽  
Glucose Levels ◽  
Consequent Reduction ◽  
The Impact

The relationship between both interstitial and blood glucose remains a debated topic, on which there is still no consensus. The experimental evidence suggests that blood and interstitial fluid glucose levels are correlated by a kinetic equilibrium, which as a consequence has a time and magnitude gradient in glucose concentration between blood and interstitium. Furthermore, this equilibrium can be perturbed by several physiological effects (such as foreign body response, wound-healing effect, etc.), with a consequent reduction of interstitial fluid glucose versus blood glucose correlation. In the present study, the impact of operating in the interstitium on continuous glucose monitoring systems (CGMs) will be discussed in depth, both for the application of CGMs in the management of diabetes and in other critical areas, such as tight glycaemic control in critically ill patients.

scholarly journals A Neural-Network-Based Approach to Personalize Insulin Bolus Calculation Using Continuous Glucose Monitoring

2018 ◽  
Vol 12 (2) ◽  
pp. 265-272 ◽  
Author(s):  
Giacomo Cappon ◽  
Martina Vettoretti ◽  
Francesca Marturano ◽  
Andrea Facchinetti ◽  
Giovanni Sparacino
Keyword(s):  
Blood Glucose ◽  
Continuous Glucose Monitoring ◽  
Insulin Pump ◽  
Risk Index ◽  
Insulin Dose ◽  
Glucose Monitoring ◽  
Rate Of Change ◽  
Single Meal ◽  
Ratio Correction ◽  
Future Work

Background: In type 1 diabetes (T1D) therapy, the calculation of the meal insulin bolus is performed according to a standard formula (SF) exploiting carbohydrate intake, carbohydrate-to-insulin ratio, correction factor, insulin on board, and target glucose. Recently, some approaches were proposed to account for preprandial glucose rate of change (ROC) in the SF, including those by Scheiner and by Pettus and Edelman. Here, the aim is to develop a new approach, based on neural networks (NN), to optimize and personalize the bolus calculation using continuous glucose monitoring information and some easily accessible patient parameters. Method: The UVa/Padova T1D Simulator was used to simulate data of 100 virtual adults in a single-meal noise-free scenario with different conditions in terms of meal amount and preprandial blood glucose and ROC values. An NN was trained to learn the optimal insulin dose using the SF parameters, ROC, body weight, insulin pump basal infusion rate and insulin sensitivity as features. The performance of the NN for meal bolus calculation was assessed by blood glucose risk index (BGRI) and compared to the methods by Scheiner and by Pettus and Edelman. Results: The NN approach brings to a small but statistically significant ( P < .001) reduction of BGRI value, equal to 0.37, 0.23, and 0.20 versus SF, Scheiner, and Pettus and Edelman, respectively. Conclusion: This preliminary study showed the potentiality of using NNs for the personalization and optimization of the meal insulin bolus calculation. Future work will deal with more realistic scenarios including technological and physiological/behavioral sources of variability.

Sign in / Sign up

Export Citation Format

Share Document