scholarly journals Blood Glucose Prediction with Variance Estimation Using Recurrent Neural Networks

2019 ◽  
Vol 4 (1) ◽  
pp. 1-18 ◽  
Author(s):  
John Martinsson ◽  
Alexander Schliep ◽  
Björn Eliasson ◽  
Olof Mogren
Keyword(s):  
Neural Networks ◽  
Blood Glucose ◽  
Glucose Level ◽  
Recurrent Neural Networks ◽  
Mean Squared Error ◽  
Diabetic Patients ◽  
Peak Time ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
The Future

AbstractMany factors affect blood glucose levels in type 1 diabetics, several of which vary largely both in magnitude and delay of the effect. Modern rapid-acting insulins generally have a peak time after 60–90 min, while carbohydrate intake can affect blood glucose levels more rapidly for high glycemic index foods, or slower for other carbohydrate sources. It is important to have good estimates of the development of glucose levels in the near future both for diabetic patients managing their insulin distribution manually, as well as for closed-loop systems making decisions about the distribution. Modern continuous glucose monitoring systems provide excellent sources of data to train machine learning models to predict future glucose levels. In this paper, we present an approach for predicting blood glucose levels for diabetics up to 1 h into the future. The approach is based on recurrent neural networks trained in an end-to-end fashion, requiring nothing but the glucose level history for the patient. Our approach obtains results that are comparable to the state of the art on the Ohio T1DM dataset for blood glucose level prediction. In addition to predicting the future glucose value, our model provides an estimate of its certainty, helping users to interpret the predicted levels. This is realized by training the recurrent neural network to parameterize a univariate Gaussian distribution over the output. The approach needs no feature engineering or data preprocessing and is computationally inexpensive. We evaluate our method using the standard root-mean-squared error (RMSE) metric, along with a blood glucose-specific metric called the surveillance error grid (SEG). We further study the properties of the distribution that is learned by the model, using experiments that determine the nature of the certainty estimate that the model is able to capture.

scholarly journals Assessment of the salivary glucose as a non-invasive test for diabetic patients

2019 ◽  
Vol 6 (6) ◽  
pp. 2289
Author(s):  
Kajol Thapa ◽  
Saroj Kunwar ◽  
Sonu Thapa ◽  
Asmita Phuyal ◽  
Sahil Rupakheti
Keyword(s):  
Diabetes Mellitus ◽  
Blood Glucose ◽  
Glucose Level ◽  
Fasting Blood Glucose ◽  
Diabetic Patients ◽  
Glucose Levels ◽  
Non Invasive ◽  
Invasive Test ◽  
Blood Glucose Levels ◽  
Institutional Review

Background: Over the recent year there has been a startling rise in the number of people suffering from diabetes mellitus. Estimation of blood glucose levels has been an essential laboratory investigation for screening and monitoring of diabetes. Saliva is one of the secretions in human body whose collection is easy and non-invasive. Salivary glucose hence could serve as an easy and non-invasive tool.Methods: Institutional review committee of NHRC gave us permission to carry out this study. 105 subjects with Type 2 diabetes mellitus who attended the OPD at Star hospital, Sanepa, Lalitpur, Nepal and 106 healthy individuals were consented to participate in this study. Glucose was measured by the GOD-POD (Glucose oxidase peroxidase) methods using the semi-autoanalyser and salivary glucose was compared with corresponding blood glucose levels.Results: A significant positive correlation of fasting salivary glucose level and fasting blood glucose level was observed in healthy (r=0.241, p=0.001) and in diabetic patients (r=0.202, p=0.001).Conclusions: The study implies a potential for saliva in monitoring and screening of diabetes mellitus.

scholarly journals Yagya Therapy Treatment Reduced Blood Glucose Level in Diabetic Patients in 2 weeks - a Single Arm Study

2020 ◽  
Vol 3 (1) ◽  
pp. 30-36 ◽  
Author(s):  
Ajit Singh Saini ◽  
Saurabh Pal ◽  
Vandana Shrivastav
Keyword(s):  
Blood Glucose ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Diabetic Patients ◽  
Time Duration ◽  
Control Blood Glucose ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
The Impact ◽  
Therapy Treatment

Diabetes is a disease that occurs when blood glucose level is too high. To control blood glucose levels in diabetic patients, modern therapies with a healthy diet and regular physical activity has been a good approach for the management of the diabetes. However, the disease eventually becomes deepen in most of the patients with age, and current approaches are not sufficient, demanding supportive and alternative approaches. The present paper portrays a contextual analysis of the impact of Yagya Therapy on diabetic level (HbA1C) in 2 weeks, using an appropriate herbal formulation on 10 patients, who had been experiencing diabetes since recent years. 10 diabetic patients (5 males and 5 females) on allopathic medicine for past more than 1 year without any change in medication and dose in past 3 months participated in the study. They were given 13 days of Yagya Therapy twice a day and their pre and post blood level of fasting glucose, Post Prandial (PP) glucose, and HbA1C were measured. Among 10 patients only 6 had attended nearly all of the sessions. Among 6 Patient, all of them showed reduction in the HbA1c value. The four of the patients, it was remarkable HbA1c difference i.e. 0.4, 0.4, 0.3, 0.2 respectively indicating impressive results i.e. affecting 3 months glucose sugar average and producing reduction in them with just 26 sessions in 13 days. The present study indicated Yagya therapy as a potential supportive and alternative solution in the management of diabetes. The increase in the time duration of the Yagya Therapy for more than 3-6 months may give the desired results for managing the diabetes.

scholarly journals Noninvasive Self-monitoring of Blood Glucose at Your Fingertips, Literally!: Smartphone-Based Photoplethysmography

2020 ◽  
Vol 13 (02) ◽  
pp. 048-052
Author(s):  
Thiago Mazzu-Nascimento ◽  
Ângela Merice de Oliveira Leal ◽  
Carlos Alberto Nogueira-de-Almeida ◽  
Lucimar Retto da Silva de Avó ◽  
Emanuel Carrilho ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Biological Tissues ◽  
Diagnostic Methods ◽  
Diabetic Patients ◽  
Self Monitoring ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
The Impact

AbstractDiabetes is a chronic disease and one of the major public health problems worldwide. It is a multifactorial disease, caused by genetic factors and lifestyle habits. Brazil had ∼ 16.8 million individuals living with diabetes in 2019 and is expected to reach 26 million people by 2045. There are global increasing needs for the development of noninvasive diagnostic methods and use of mobile health, mainly in face of the pandemic caused by the coronavirus disease 2019 (COVID-19). For daily glycemic control, diabetic patients use a portable glucometer for glycemic self-monitoring and need to prick their fingertips three or more times a day, generating a huge discomfort throughout their lives. Our goal here is to present a review with very recent emerging studies in the field of noninvasive diagnosis and to emphasize that smartphone-based photoplethysmography (spPPG), powered by artificial intelligence, might be a trend to self-monitor blood glucose levels. In photoplethysmography, a light source travels through the tissue, interacts with the interstitium and with cells and molecules present in the blood. Reflection of light occurs as it passes through the biological tissues and a photodetector can capture these interactions. When using a smartphone, the built-in flashlight is a white light-emitting LED and the camera works as a photodetector. The higher the concentration of circulating glucose, the greater the absorbance and, consequently, the lesser the reflected light intensity will be. Due to these optical phenomena, the signal intensity captured will be inversely proportional to the blood glucose level. Furthermore, we highlight the microvascular changes in the progression of diabetes that can interfere in the signals captured by the photodetector using spPPG, due to the decrease of peripheral blood perfusion, which can be confused with high blood glucose levels. It is necessary to create strategies to filter or reduce the impact of these vascular changes in the blood glucose level analysis. Deep learning strategies can help the machine to solve these challenges, allowing an accurate blood glucose level and interstitial glucose prediction.

Nutritional Interventions and Considerations for the Development of Low Calorie or Sugar Free Foods

2020 ◽  
Vol 16 (4) ◽  
pp. 301-312 ◽  
Author(s):  
Jyoti Singh ◽  
Prasad Rasane ◽  
Sawinder Kaur ◽  
Vikas Kumar ◽  
Kajal Dhawan ◽  
...  
Keyword(s):  
Metabolic Disease ◽  
Blood Glucose ◽  
Human Population ◽  
Artificial Sweeteners ◽  
Diabetic Patients ◽  
Nutritional Interventions ◽  
Low Calorie ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Diet Plan

Diabetes is a globally prevalent chronic metabolic disease characterized by blood glucose levels higher than the normal levels. Sugar, a common constituent of diet, is also a major factor often responsible for elevating the glucose level in diabetic patients. However, diabetic patients are more prone to eat sweets amongst the human population. Therefore, we find a popular consumption of zero or low-calorie sweeteners, both natural and artificial. But, the uses of these sweeteners have proved to be controversial. Thus, the purpose of this review was to critically analyze and highlight the considerations needed for the development of sugar-free or low-calorie products for diabetic patients. For this purpose, various measures are taken such as avoiding sugary foods, using natural nectar, artificial sweeteners, etc. It cannot be ignored that many health hazards are associated with the overconsumption of artificial sweeteners only. These sweeteners are high-risk compounds and a properly balanced consideration needs to be given while making a diet plan for diabetic patients.

Effect of Corticosteroid Injections on Blood Glucose Levels in Diabetic Patients

2018 ◽  
pp. 1
Author(s):  
Sylvain Mathieu ◽  
Marion Couderc ◽  
Sandrine Malochet-Guinamand ◽  
Jean-Jacques Dubost ◽  
Anne Tournadre ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Diabetic Patients ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Corticosteroid Injections

Investigating the Efficacy of Using Hand Tremors for Early Detection of Hypoglycemic Events: A Scoping Literature Review

2018 ◽  
Vol 62 (1) ◽  
pp. 1211-1215 ◽  
Author(s):  
Karim Zahed ◽  
Farzan Sasangohar ◽  
Ranjana Mehta ◽  
Madhav Erraguntla ◽  
Mark Lawley ◽  
...  
Keyword(s):  
Blood Glucose ◽  
Early Detection ◽  
Diabetic Patients ◽  
Medium Frequency ◽  
Hand Tremor ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Scoping Literature Review ◽  
Continuous Glucose Monitors ◽  
The Relationship

Diabetes is a prevalent condition affecting millions of patients globally. Some diabetic patients suffer from a deadly condition called Hypoglycemia (sudden drop in blood glucose levels). Continuous Glucose Monitors (CGMs) have been the most pervasive tool used to track blood glucose levels but these tools are invasive and costly. While early detection of hypoglycemia has been studied, current approaches do not leverage tremors; which are a primary symptom of hypoglycemia. A scoping review was conducted to understand the relationship between tremors and hypoglycemia, and to document any efforts that utilized tremor signatures non-invasively to detect hypoglycemic events. Findings suggest that hypoglycemic tremors are a medium frequency tremor, more resistant to hypoglycemic impairment than other symptoms, and have not been fully explored yet. This paper also documents the work in progress to utilize a novel wearable device that predicts the onsets of hypoglycemia using hand tremor sensing.

scholarly journals Association between blood glucose levels and Glasgow Outcome Score in patients with traumatic brain injury: secondary analysis of a randomized trial

Trials ◽  
2022 ◽  
Vol 23 (1) ◽  
Author(s):  
Tao Yuan ◽  
Hongyu He ◽  
Yuepeng Liu ◽  
Jianwei Wang ◽  
Xin Kang ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Blood Glucose ◽  
Brain Injury ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Threshold Effect ◽  
Glasgow Outcome Score ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Average Blood Glucose

Abstract Background Blood glucose levels that are too high or too low after traumatic brain injury (TBI) negatively affect patient prognosis. This study aimed to demonstrate the relationship between blood glucose levels and the Glasgow Outcome Score (GOS) in TBI patients. Methods This study was based on a randomized, dual-center, open-label clinical trial. A total of 208 patients who participated in the randomized controlled trial were followed up for 5 years. Information on the disease, laboratory examination, insulin therapy, and surgery for patients with TBI was collected as candidate variables according to clinical importance. Additionally, data on 5-year and 6-month GOS were collected as primary and secondary outcomes, respectively. For multivariate analysis, a generalized additive model (GAM) was used to investigate relationships between blood glucose levels and GOS. The results are presented as odds ratios (ORs) with 95% confidence intervals (95% CIs). We further applied a two- piecewise linear regression model to examine the threshold effect of blood glucose level and GOS. Results A total of 182 patients were included in the final analysis. Multivariate GAM analysis revealed that a bell-shaped relationship existed between average blood glucose level and 5-year GOS score or 6-month GOS score. The inflection points of the average blood glucose level were 8.81 (95% CI: 7.43–9.48) mmol/L considering 5-year GOS as the outcome and were 8.88 (95% CI 7.43−9.74) mmol/L considering 6-month GOS score as the outcome. The same analysis revealed that there was also a bell relationship between average blood glucose levels and the favorable outcome group (GOS score ≥ 4) at 5 years or 6 months. Conclusion In a population of patients with traumatic brain injury, blood glucose levels were associated with the GOS. There was also a threshold effect between blood glucose levels and the GOS. A blood glucose level that is either too high or too low conveys a poor prognosis. Trial registration ClinicalTrials.gov NCT02161055. Registered on 11 June 2014.

Sign in / Sign up

Export Citation Format

Share Document