Everything You Wanted to Know About Continuous Glucose Monitoring

Joshi, Amit M.; Jain, Prateek; Mohanty, Saraju P.

doi:10.1109/mce.2021.3073498

Cited by 23 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diabetes balancing has been explored through sensors with the system nominated as an artificial pancreas system. The minimally invasive techniques based designs are identified with some sort of limitations such as precision in glucose values and will have a shorter life span for monitoring [5].…”

Section: Prior Related Research Workmentioning

confidence: 99%

iGLU: An Intelligent Device for Accurate Noninvasive Blood Glucose-Level Monitoring in Smart Healthcare

Jain

Joshi

Mohanty

2020

IEEE Consumer Electron. Mag.

View full text Add to dashboard Cite

The conventional method of glucose measurement such as pricking blood from the body is prevalent which brings pain and trauma. Invasive methods of measurement sometimes raise the risk of blood infection to the patient. Sometimes, some of the physiological parameters such as body temperature and systolic blood pressure (SBP) are responsible for blood glucose level fluctuations. Moreover, diabetes for a long duration usually becomes a critical issue. In such situation, patients need to consult diabetologist frequently, which is not possible in normal life. Therefore, it is required to develop non-invasive glucose balancing paradigm, which measures blood glucose without pricking blood along with physiological parameters measurement and decision model. The proposed paradigm helps to doctor, who is even available at remote location. There won't be any need to consult frequently. In the way of optimized non-invasive system design, an NIRS technique with specific wavelengths along with physiological parameters is taken to predict the precise glucose value. The all parameters (glucose, Blood pressure and body temperature), food intake and insulin levels are parts of decision model, which would help to the doctor to take decision related to the further medicine doses and diet plan. The patients would have suggestions according to maintain their blood glucose level. The proposed system demonstrated an accurate model with MARD and AvgE 12.50% and 12.10% respectively using DNN model. Coefficient of determination R 2 has been found 0.97.

show abstract

Section: Prior Related Research Workmentioning

confidence: 99%

iGLU: An Intelligent Device for Accurate Noninvasive Blood Glucose-Level Monitoring in Smart Healthcare

Jain

Joshi

Mohanty

2020

IEEE Consumer Electron. Mag.

View full text Add to dashboard Cite

show abstract

“…The glucose concentrations increase in the human blood for the diabetic patients. The diabetes in humans can be classified into three parts, which are type-1, type-2 and gestational diabetes [2].…”

Section: Introductionmentioning

confidence: 99%

A non-invasive blood glucose detection using a slotted microstrip antenna sensor

Syamala,

Kumar,

Raju

2024

Phys. Scr.

View full text Add to dashboard Cite

A novel highly sensitive and compact slotted microstrip antenna sensor is designed consisting of slots with defected ground structure (DGS). The substrate used in the design of antenna is FR-4 of concise dimensions 30 × 30 × 1.6 mm3 and the developed antenna resonates at 3 GHz. The human finger consisting of several layers namely bone, blood, fat and skin is modelled in the EM simulation (CST) environment resulting in finger phantom. The finger phantom is situated at different locations on proposed antenna for evaluating the concentrations of glucose from 0 to 1000 mg/dL and the corresponding shift in frequencies are estimated. For detection of glucose concentration in human blood, the obtained frequency shifts in the proposed work are used. In this proposed work, at the top side of proposed antenna, the finger phantom is situated, an uttermost shift in frequency of 48 MHz, sensitivity of 48 KHz/(mg/dL) and a least possible shift in frequency of 24 MHz, sensitivity of 24 KHz/(mg/dL) are obtained.

show abstract

“…In diabetes, the glucose level in the blood increases. Diabetes can be divided in three parts mainly which includes type-1, type-2 and gestational diabetes [ 4 ]. Negligence in the treatment of diabetes can cause some serious health issues.…”

Section: Introductionmentioning

confidence: 99%

Machine learning models for non-invasive glucose measurement: towards diabetes management in smart healthcare

2022

Self Cite

View full text Add to dashboard Cite

The patients of diabetes require to observe and control their glycemic profile through continuous glucose level monitoring. The blood glucose measurement is possible through invasive, minimally invasive and non-invasive methods. Invasive method is traditional method for instant glucose measurement where glucose is measured by taking blood samples from the body. However, the repeated finger pricking increases the risk of blood-related infections and trauma. Hence, the development of non-invasive real time device is essential for smart healthcare to manage glucose-insulin balance. The paper presents machine learning models for non-invasive glucose measurement. So, various machine learning algorithms including Logistic Regression, KNN, Gaussian Naive Bayes, Linear Regression, Multi-polynomial Regression, Neural Network, XGBoost, Decision Tree, Random Forest and Support Vector Machine are applied on two dataset which are PIDD (UCI repository) and iGLU dataset (iGLU device). The comparative analysis is carried out where accuracy, training time, recall, precision, f-1 score and AUC curve is measured for classification algorithms. For regression algorithms, measures like accuracy, Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are used for comparison purpose. Random forest with 84% accuracy and 68% recall, 76% precision and 72% f1-score for PIDD and Decision tree with 70% accuracy, 8% mean absolute error (MAE) and 8.5% root mean square error (RMSE) for iGLU dataset gives best results. Clark grid analysis has also been done where all the values fall under zone A which gives 100% accuracy and the device is useful for medication purpose. The proposed work has been also compared with similar methods and the proposed work has excellent results in terms of MAD, mARD, RMSE and AvgE. The device would be ideal as non-invasive solution for continuous glucose monitoring. Graphical abstract

show abstract

Everything You Wanted to Know About Continuous Glucose Monitoring

Cited by 23 publications

References 17 publications

iGLU: An Intelligent Device for Accurate Noninvasive Blood Glucose-Level Monitoring in Smart Healthcare

iGLU: An Intelligent Device for Accurate Noninvasive Blood Glucose-Level Monitoring in Smart Healthcare

A non-invasive blood glucose detection using a slotted microstrip antenna sensor

Machine learning models for non-invasive glucose measurement: towards diabetes management in smart healthcare

Contact Info

Product

Resources

About