scholarly journals A Function Approximation Approach to the Prediction of Blood Glucose Levels

2021 ◽  
Vol 7 ◽  
Author(s):  
H. N. Mhaskar ◽  
S. V. Pereverzyev ◽  
M. D. van der Walt
Keyword(s):  
Blood Glucose ◽  
Unknown Function ◽  
Function Approximation ◽  
Real Life ◽  
Glucose Monitoring ◽  
Target Function ◽  
Training Data ◽  
Dimensional Euclidean Space ◽  
Glucose Levels ◽  
Prediction Horizon

The problem of real time prediction of blood glucose (BG) levels based on the readings from a continuous glucose monitoring (CGM) device is a problem of great importance in diabetes care, and therefore, has attracted a lot of research in recent years, especially based on machine learning. An accurate prediction with a 30, 60, or 90 min prediction horizon has the potential of saving millions of dollars in emergency care costs. In this paper, we treat the problem as one of function approximation, where the value of the BG level at time t+h (where h the prediction horizon) is considered to be an unknown function of d readings prior to the time t. This unknown function may be supported in particular on some unknown submanifold of the d-dimensional Euclidean space. While manifold learning is classically done in a semi-supervised setting, where the entire data has to be known in advance, we use recent ideas to achieve an accurate function approximation in a supervised setting; i.e., construct a model for the target function. We use the state-of-the-art clinically relevant PRED-EGA grid to evaluate our results, and demonstrate that for a real life dataset, our method performs better than a standard deep network, especially in hypoglycemic and hyperglycemic regimes. One noteworthy aspect of this work is that the training data and test data may come from different distributions.

scholarly journals Biomarker potential of real-world voice signals to predict abnormal blood glucose levels

2020 ◽  
Author(s):  
Jouhyun Jeon ◽  
Adam Palanica ◽  
Sarah Sarabadani ◽  
Michael Lieberman ◽  
Yan Fossat
Keyword(s):  
Blood Glucose ◽  
Real Life ◽  
Glucose Monitoring ◽  
Blood Glucose Monitoring ◽  
Funding Agency ◽  
Invasive Technique ◽  
Mixed Effect ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Significant Difference

SummaryBackgroundVoice signal analysis is an emerging non-invasive technique to examine health conditions, and is implemented in various real-life applications and devices. The purpose of this study was to evaluate the association of voice signals with blood glucose levels in healthy individuals. The study aimed to investigate the longitudinal stabilities of voice signals and identify voice biomarkers to predict abnormal blood glucose levels.MethodsWe created voice profiles composed of 17,552,688 voice signals from 44 participants and their 1,454 voice recordings. From each voice recording, 12,082 voice-features were extracted. Longitudinal stabilities of voice-features were quantified using linear mixed-effect modelling. Voice-features that showed significant difference between different blood glucose levels, strong intra-stability and the ability to make distinct choice in decision trees were selected as voice biomarker. Voice biomarkers were fed into a multi-class random forest classifier to predict high, normal, and low blood glucose levels.FindingsIn total, 196 voice biomarkers were characterized. Results showed a predictive model with an overall accuracy of 78.66%, overall AUC of 0.83 (95% confidence interval is 0.80 – 0.85), and 0.41 of Matthews Correlation Coefficient (MCC) to discriminate three different blood glucose levels in an independent test set.InterpretationOur voice biomarkers could serve as a noninvasive and conventional surrogate of blood glucose monitoring in daily life as well as a screening tool to estimate potential risk of poor glycemic control.FundingThis research was internally funded and received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.

scholarly journals Glycemic variability and cardiovascular disease in patients with type 2 diabetes

2021 ◽  
Vol 9 (1) ◽  
pp. e002032
Author(s):  
Marcela Martinez ◽  
Jimena Santamarina ◽  
Adrian Pavesi ◽  
Carla Musso ◽  
Guillermo E Umpierrez
Keyword(s):  
Type 2 Diabetes ◽  
Blood Glucose ◽  
Glycated Hemoglobin ◽  
Glucose Monitoring ◽  
Glycemic Variability ◽  
Cardiovascular Complications ◽  
Glucose Levels ◽  
Increased Risk ◽  
Patients With Diabetes

Glycated hemoglobin is currently the gold standard for assessment of long-term glycemic control and response to medical treatment in patients with diabetes. Glycated hemoglobin, however, does not address fluctuations in blood glucose. Glycemic variability (GV) refers to fluctuations in blood glucose levels. Recent clinical data indicate that GV is associated with increased risk of hypoglycemia, microvascular and macrovascular complications, and mortality in patients with diabetes, independently of glycated hemoglobin level. The use of continuous glucose monitoring devices has markedly improved the assessment of GV in clinical practice and facilitated the assessment of GV as well as hypoglycemia and hyperglycemia events in patients with diabetes. We review current concepts on the definition and assessment of GV and its association with cardiovascular complications in patients with type 2 diabetes.

scholarly journals A Review of Non-Invasive Optical Systems for Continuous Blood Glucose Monitoring

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6820
Author(s):  
Bushra Alsunaidi ◽  
Murad Althobaiti ◽  
Mahbubunnabi Tamal ◽  
Waleed Albaker ◽  
Ibraheem Al-Naib
Keyword(s):  
Blood Glucose ◽  
Glucose Monitoring ◽  
Daily Basis ◽  
Glucose Sensing ◽  
Blood Glucose Monitoring ◽  
Optical Systems ◽  
Glucose Levels ◽  
Non Invasive ◽  
Blood Glucose Levels ◽  
Continuous Blood Glucose Monitoring

The prevalence of diabetes is increasing globally. More than 690 million cases of diabetes are expected worldwide by 2045. Continuous blood glucose monitoring is essential to control the disease and avoid long-term complications. Diabetics suffer on a daily basis with the traditional glucose monitors currently in use, which are invasive, painful, and cost-intensive. Therefore, the demand for non-invasive, painless, economical, and reliable approaches to monitor glucose levels is increasing. Since the last decades, many glucose sensing technologies have been developed. Researchers and scientists have been working on the enhancement of these technologies to achieve better results. This paper provides an updated review of some of the pioneering non-invasive optical techniques for monitoring blood glucose levels that have been proposed in the last six years, including a summary of state-of-the-art error analysis and validation techniques.

Modern technologies in diabetes management - continuous glucose monitoring and insulin pump therapy

2021 ◽  
Vol 87 (1) ◽  
pp. 50-55
Author(s):  
E.Yu. Pyankova ◽  
◽  
L.A. Anshakova ◽  
I.A. Pyankov ◽  
S.V. Yegorova ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Diabetes Management ◽  
Insulin Pump ◽  
Glucose Monitoring ◽  
Insulin Pump Therapy ◽  
Pump Therapy ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
The Individual ◽  
Glucose Lowering Therapy

The problems of complications of diabetes mellitus cannot be solved without constant monitoring of blood glucose levels. The evolution of additional technologies for the determination of glucose in the blood of the last decades makes it possible to more accurately predict the risks of complications, both in the individual and in the patient population as a whole. The article provides an overview of the methods used in modern diabetology, facilitating control over the variability of blood glucose levels and helping in a more accurate selection of glucose-lowering therapy. All presented methods are currently working in real clinical practice in the Khabarovsk Krai

T1D Hypoglycemia Prediction Algorithms: A Systematic Review (Preprint)

2021 ◽  
Author(s):  
Stella Tsichlaki ◽  
Lefteris Koumakis ◽  
Manolis Tsiknakis
Keyword(s):  
Type 1 Diabetes ◽  
Blood Glucose ◽  
Digital Libraries ◽  
Predictive Models ◽  
Real Life ◽  
Blood Glucose Monitoring ◽  
Detection Techniques ◽  
Glucose Levels ◽  
Wide Range

BACKGROUND Diabetes is a chronic condition that necessitates regular monitoring and self-management of the patient's blood glucose levels. People with type 1 diabetes (T1D) can live a productive life if they receive proper diabetes care. Nonetheless, a loose glycemic control might increase the risk of developing hypoglycemia. This incident can occur due to a variety of causes, such as taking additional doses of insulin, skipping meals, or over-exercising. Mainly, the symptoms of hypoglycemia range from mild dysphoria to more severe conditions, if not detected in a timely manner. OBJECTIVE In this review, we report on innovative detection techniques and tactics for identifying and preventing hypoglycemic episodes, focusing on type 1 diabetes. METHODS A systematic literature search following the PRISMA guidelines was performed focusing on the “PUBMED”, “Google Scholar”, “IEEE Xplore” and “ACM” digital libraries to find articles about technologies related to hypoglycemia detection in type 1 diabetes patients. RESULTS The presented approaches have been utilized or devised to enhance blood glucose monitoring and boost its efficacy to forecast future glucose levels, which could aid the prediction of future episodes of hypoglycemia. We detected nineteen predictive models for hypoglycemia, specifically on type 1 diabetes, utilizing a wide range of algorithmic methodologies, spanning from statistics (10%) to machine learning (52%) and deep learning (38%). The algorithms employed most are the kalman filtering and classification models (SVM, KNN, random forests). The performance of the predictive models was found overall to be satisfactory, reaching accuracies between 70% and 99% which proves that such technologies are capable to facilitate the prediction of T1D hypoglycemia. CONCLUSIONS It is evident that CGM can improve the glucose control in diabetes but predictive models for hypo- and hyper- glycemia using only mainstream noninvasive sensors such as wristbands and smartwatches are foreseen to be the next step for mHealth in T1D. Prospective studies are required to demonstrate the value of such models in real-life mHealth interventions.

Online Prediction of Blood Glucose Levels using Genetic Algorithm

2014 ◽  
pp. 299-310
Author(s):  
Khaled Eskaf ◽  
Tim Ritchings ◽  
Osama Bedawy
Keyword(s):  
Blood Glucose ◽  
Glucose Monitoring ◽  
Simulation Software ◽  
Machine Learning Techniques ◽  
Diabetic Patients ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Learning Techniques ◽  
Preliminary Study ◽  
Online Prediction

Diabetes mellitus is one of the most common chronic diseases. The number of cases of diabetes in the world is likely to increase more than two fold in the next 30 years: from 115 million in 2000 to 284 million in 2030. This chapter is concerned with helping diabetic patients to manage themselves by developing a computer system that predicts their Blood Glucose Level (BGL) after 30 minutes on the basis of their current levels, so that they can administer insulin. This will enable the diabetic patient to continue living a normal daily life, as much as is possible. The prediction of BGLs based on the current levels BGLs become feasible through the advent of Continuous Glucose Monitoring (CGM) systems, which are able to sample patients' BGLs, typically 5 minutes, and computer systems that can process and analyse these samples. The approach taken in this chapter uses machine-learning techniques, specifically Genetic Algorithms (GA), to learn BGL patterns over an hour and the resulting value 30 minutes later, without questioning the patients about their food intake and activities. The GAs were invested using the raw BGLs as input and metadata derived from a Diabetic Dynamic Model of BGLs supplemented by the changes in patients' BGLs over the previous hour. The results obtained in a preliminary study including 4 virtual patients taken from the AIDA diabetes simulation software and 3 volunteers using the DexCom SEVEN system, show that the metadata approach gives more accurate predictions. Online learning, whereby new BGL patterns were incorporated into the prediction system as they were encountered, improved the results further.

scholarly journals Discrepancies Between Blood Glucose and Interstitial Glucose—Technological Artifacts or Physiology: Implications for Selection of the Appropriate Therapeutic Target

2017 ◽  
Vol 11 (4) ◽  
pp. 766-772 ◽  
Author(s):  
Thorsten Siegmund ◽  
Lutz Heinemann ◽  
Ralf Kolassa ◽  
Andreas Thomas
Keyword(s):  
Blood Glucose ◽  
Therapeutic Target ◽  
Diabetes Management ◽  
Glucose Monitoring ◽  
Blood Glucose Measurement ◽  
Glucose Measurement ◽  
Glucose Levels ◽  
Therapeutic Decisions ◽  
The Impact ◽  
Selection Of

Background: For decades, the major source of information used to make therapeutic decisions by patients with diabetes has been glucose measurements using capillary blood samples. Knowledge gained from clinical studies, for example, on the impact of metabolic control on diabetes-related complications, is based on such measurements. Different to traditional blood glucose measurement systems, systems for continuous glucose monitoring (CGM) measure glucose in interstitial fluid (ISF). The assumption is that glucose levels in blood and ISF are practically the same and that the information provided can be used interchangeably. Thus, therapeutic decisions, that is, the selection of insulin doses, are based on CGM system results interpreted as though they were blood glucose values. Methods: We performed a more detailed analysis and interpretation of glucose profiles obtained with CGM in situations with high glucose dynamics to evaluate this potentially misleading assumption. Results: Considering physical activity, hypoglycemic episodes, and meal-related differences between glucose levels in blood and ISF uncover clinically relevant differences that can make it risky from a therapeutic point of view to use blood glucose for therapeutic decisions. Conclusions: Further systematic and structured evaluation as to whether the use of ISF glucose is more safe and efficient when it comes to acute therapeutic decisions is necessary. These data might also have a higher prognostic relevance when it comes to long-term metabolic consequences of diabetes. In the long run, it may be reasonable to abandon blood glucose measurements as the basis for diabetes management and switch to using ISF glucose as the appropriate therapeutic target.

scholarly journals A Novel Five-Microlitre Capillary System for Home Glucose Monitoring

1981 ◽  
Vol 18 (5) ◽  
pp. 304-307 ◽  
Author(s):  
C P Williams ◽  
G K Davies ◽  
D F Child
Keyword(s):  
Blood Glucose ◽  
Capillary Tube ◽  
Glucose Monitoring ◽  
Diabetic Patients ◽  
Collection System ◽  
Patient Acceptability ◽  
Glucose Levels ◽  
Capillary System ◽  
Blood Glucose Levels ◽  
High Degree

Improvement in the control of diabetic patients is aided by a knowledge of blood glucose levels during a ‘normal’ (non-hospitalised) day. We have devised a 5 μl capillary tube collection system as a ‘kit’ for home use by diabetics. Blood collected into 5 μl capillary tubes is washed into a protein precipitant by the patient. The completed kit is posted to the laboratory for analysis. The technique has achieved a high degree of patient acceptability. Subsequent analysis involves the addition of a single reagent. Reagents, patient samples, and standards are stable, and the precision of the technique compares favourably with our routine glucose procedure.

Modeling continuous glucose monitoring (CGM) data during sleep

Biostatistics ◽  
2020 ◽  
Author(s):  
Irina Gaynanova ◽  
Naresh Punjabi ◽  
Ciprian Crainiceanu
Keyword(s):  
Blood Glucose ◽  
Sleep Onset ◽  
Glucose Monitoring ◽  
Model Parameters ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Continuous Glucose Monitors ◽  
Study Participants ◽  
Glucose Dynamics

Summary We introduce a multilevel functional Beta model to quantify the blood glucose levels measured by continuous glucose monitors for multiple days in study participants with type 2 diabetes mellitus. The model estimates the subject-specific marginal quantiles, quantifies the within- and between-subject variability, and produces interpretable parameters of blood glucose dynamics as a function of time from the actigraphy-estimated sleep onset. Results are validated via simulations and by studying the association between the estimated model parameters and hemoglobin A1c, the gold standard for assessing glucose control in diabetes.

Sign in / Sign up

Export Citation Format

Share Document