Touch-Based Fingertip Blood-Free Reliable Glucose Monitoring: Personalized Data Processing for Predicting Blood Glucose Concentrations

ACS Sensors ◽  
2021 ◽  
Author(s):  
Juliane R. Sempionatto ◽  
Jong-Min Moon ◽  
Joseph Wang
Author(s):  
John C. Pickup

Blood glucose concentrations are measured in diabetes to detect hyper- and hypo-glycaemia. Health care professionals need this information to diagnose diabetes, or states of impaired glucose tolerance, to adjust therapy and correct hyper- and hypo-glycaemia in established diabetes, to interpret signs and symptoms in patients (e.g. is confusion due to hypoglycaemia or another cause?), and to assess the risk of tissue complications developing in the future (the severity and duration of hyperglycaemia is clearly related to microvascular disease). The patient with diabetes measures blood glucose concentrations to take corrective action with food and insulin, to maintain good control, to check the safety of everyday activities (e.g. not driving when hypoglycaemic), to assess the impact of events and lifestyle and on control (exercise, diet, illness, psychological stress), and to ensure a good quality of life and the ‘peace of mind’ that knowledge of the blood glucose concentration gives. Glucose monitoring has traditionally been performed by intermittent sampling of blood glucose concentrations, either in hospital or by the patient testing their own blood glucose concentrations at home using finger-prick capillary blood samples applied to reagent strips and inserted into portable glucose meters – self-monitoring of blood glucose (SMBG). In addition, in the last decade or so, continuous glucose monitoring (CGM) has entered clinical practice as a supplement to SMBG, albeit with limited uptake at present. CGM is based on the implantation of needle-type glucose sensors, or microdialysis probes, into the subcutaneous tissue for measurement of interstitial glucose concentrations.


2018 ◽  
Vol 11 (06) ◽  
pp. 1850038 ◽  
Author(s):  
Ryosuke Kasahara ◽  
Saiko Kino ◽  
Shunsuke Soyama ◽  
Yuji Matsuura

Noninvasive, glucose-monitoring technologies using infrared spectroscopy that have been studied typically require a calibration process that involves blood collection, which renders the methods somewhat invasive. We develop a truly noninvasive, glucose-monitoring technique using mid-infrared spectroscopy that does not require blood collection for calibration by applying domain adaptation (DA) using deep neural networks to train a model that associates blood glucose concentration with mid-infrared spectral data without requiring a training dataset labeled with invasive blood sample measurements. For realizing DA, the distribution of unlabeled spectral data for calibration is considered through adversarial update during training networks for regression to blood glucose concentration. This calibration improved the correlation coefficient between the true blood glucose concentrations and predicted blood glucose concentrations from 0.38 to 0.47. The result indicates that this calibration technique improves prediction accuracy for mid-infrared glucose measurements without any invasively acquired data.


2009 ◽  
Vol 3 (5) ◽  
pp. 1166-1167
Author(s):  
Bogdan Solnica

In this issue of Journal of Diabetes Science and Technology, Chang and colleagues present the analytical performance evaluation of the OneTouch® UltraVue™ blood glucose meter. This device is an advanced construction with a color display, used-strip ejector, no-button interface, and short assay time. Accuracy studies were performed using a YSI 2300 analyzer, considered the reference. Altogether, 349 pairs of results covering a wide range of blood glucose concentrations were analyzed. Patients with diabetes performed a significant part of the tests. Obtained results indicate good accuracy of OneTouch UltraVue blood glucose monitoring system, satisfying the International Organization for Standardization recommendations and thereby locating >95% of tests within zone A of the error grid. Results of the precision studies indicate good reproducibility of measurements. In conclusion, the evaluation of the OneTouch UltraVue meter revealed good analytical performance together with convenient handling useful for self-monitoring of blood glucose performed by elderly diabetes patients.


Diabetes ◽  
2018 ◽  
Vol 67 (Supplement 1) ◽  
pp. 944-P
Author(s):  
MASAKAZU AIHARA ◽  
NAOTO KUBOTA ◽  
TAKASHI KADOWAKI

Diabetes ◽  
2019 ◽  
Vol 68 (Supplement 1) ◽  
pp. 941-P
Author(s):  
LEI ZHANG ◽  
YAN GU ◽  
YUXIU YANG ◽  
NA WANG ◽  
WEIGUO GAO ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document