Short-term diabetes blood glucose prediction based on blood glucose measurements

Blood Glucose Prediction from Nutrition Analytics in Type 1 Diabetes: A Review

INTRODUCTION

Type 1 Diabetes (T1D) affects over 9 million worldwide and necessitates meticulous self-management for blood glucose (BG) control. Utilizing BG prediction technology allows for increased BG control and a reduction in the diabetes burden caused by self-management requirements. This paper reviews BG prediction models in T1D, which include nutritional components.

METHOD

A systematic search, utilizing the PRISMA guidelines, identified articles focusing on BG prediction algorithms for T1D that incorporate nutritional variables. Eligible studies were screened and analyzed for model type, inclusion of additional aspects in the model, prediction horizon, patient population, inputs, and accuracy.

RESULTS

The study categorizes 138 blood glucose prediction models into data-driven (54%), physiological (14%), and hybrid (33%) types. Prediction horizons of ≤30 min are used in 36% of models, 31-60 min in 34%, 61-90 min in 11%, 91-120 min in 10%, and >120 min in 9%. Neural networks are the most used data-driven technique (47%), and simple carbohydrate intake is commonly included in models (data-driven: 72%, physiological: 52%, hybrid: 67%). Real or free-living data are predominantly used (83%).

CONCLUSION

The primary goal of blood glucose prediction in T1D is to enable informed decisions and maintain safe BG levels, considering the impact of all nutrients for meal planning and clinical relevance.

Glucose Oxidase Loading in Ordered Porous Aluminosilicates: Exploring the Potential of Surface Modification for Electrochemical Glucose Sensing

Enzymatic electrochemical sensors have become the leading glucose detection technology due to their rapid response, affordability, portability, selectivity, and sensitivity. However, the performance of these sensors is highly dependent on the surface properties of the electrode material used to store glucose oxidase and its ability to retain enzymatic activity under variable environmental conditions. Mesoporous thin films have recently attracted considerable attention as promising candidates for enzyme storage and activity preservation due to their well-defined nanoarchitecture and tunable surface properties. Herein, we systematically compare pathways for the immobilization of glucose oxidase (GOx) and their effectiveness in electrochemical glucose sensing, following modification protocols that lead to the electrostatic attraction (amino functionalization), covalent bonding (aldehyde functionalization), and electrostatic repulsion (oxygen plasma treatment) of the ordered porous aluminosilicate-coated electrodes. By direct comparison using a quartz crystal microbalance, we demonstrate that glucose oxidase can be loaded in a nanoarchitecture with a pore size of ∼50 nm and pore interconnections of ∼35 nm using the native aluminosilicate surface, as well as after amino or aldehyde surface modification, while oxygen plasma exposure of the native surface inhibits glucose oxidase loading. Despite a variety of routes for enzyme loading, quantitative electrochemical glucose sensing between 0 and 20 mM was only possible when the porous surface was functionalized with amino groups, which we relate to the role of surface chemistry in accessing the underlying substrate. Our results highlight the impact of rational surface modification on electrochemical biosensing performance and demonstrate the potential of tailoring porous nanoarchitecture surfaces for biosensing applications.

A Long-Term Model of the Glucose-Insulin Dynamics of Type 1 Diabetes

A new glucose-insulin model is introduced which fits with the clinical data from in- and outpatients for two days. Its stability property is consistent with the glycemia behavior for type 1 diabetes. This is in contrast to traditional glucose-insulin models. Prior models fit with clinical data for a few hours only or display some nonnatural equilibria. The parameters of this new model are identifiable from standard clinical data as continuous glucose monitoring, insulin injection, and carbohydrate estimate. Moreover, it is shown that the parameters from the model allow the computation of the standard tools used in functional insulin therapy as the basal rate of insulin and the insulin sensitivity factor. This is a major outcome as they are required in therapeutic education of type 1 diabetic patients.

A novel adaptive-weighted-average framework for blood glucose prediction

BACKGROUND

Blood glucose (BG) prediction plays a very important role in daily BG management of patients with diabetes mellitus. Several algorithms, such as autoregressive (AR) models and artificial neural networks, have been proposed for BG prediction. However, every algorithm has its own subject range (i.e., one algorithm might work well for one diabetes patient but poorly for another patient). Even for one individual patient, this algorithm might perform well during the preprandial period but poorly during the postprandial period.

MATERIALS AND METHODS

A novel framework was proposed to combine several BG prediction algorithms. The main idea of the novel framework is that an adaptive weight is given to each algorithm where one algorithm's weight is inversely proportional to the sum of the squared prediction errors. In general, this framework can be applied to combine any BG prediction algorithms.

RESULTS

As an example, the proposed framework was used to combine an AR model, extreme learning machine, and support vector regression. The new algorithm was compared with these three prediction algorithms on the continuous glucose monitoring system (CGMS) readings of 10 type 1 diabetes mellitus patients; the CGMS readings of each patient included 860 CGMS data points. For each patient, the algorithms were evaluated in terms of root-mean-square error, relative error, Clarke error-grid analysis, and J index. Of the 40 evaluations, the new adaptive-weighted algorithm achieved the best prediction performance in 37 (92.5%).

CONCLUSIONS

Thus, we conclude that the adaptive-weighted-average framework proposed in this study can give satisfactory predictions and should be used in BG prediction. The new algorithm has great robustness with respect to variations in data characteristics, patients, and prediction horizons. At the same time, it is universal.

Sensor calibration models for a non-invasive blood glucose measurement sensor

A calibration model was developed for a noninvasive blood glucose sensor, to determine how the blood glucose data measured by this sensor is related to blood glucose data measured with laboratory capillary finger sticks and to corrupting noise. The variability of calibration models for different patients was analyzed as well as the dynamics of the non-invasive blood glucose sensor according to reference blood glucose measurements and corrupting noise.

Analysis of the performance of the software/hardware product MyDiaBase+RxChecker for assessing treatment regimens

In 2008, the Action to Control Cardiovascular Risk in Diabetes trial was halted due to an unexpected number of deaths in the intensive treatment group (aiming for hemoglobin A1c levels less than 6%). Hypoglycemic episodes were thought by some to be a contributing cause, underscoring again the challenge of maintaining tight control while avoiding dangerous excursions into hypoglycemic territory. Albisser and colleagues present a set of articles in this issue of Journal of Diabetes Science and Technology that describe a clinical product developed specifically for this timeless clinical conundrum.