Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning

Blood glucose (BG) concentration monitoring is essential for controlling complications arising from diabetes, as well as digital management of the disease. At present, finger-prick glucometers are widely used to measure BG concentrations. In consideration of the challenges of invasive BG concentrati...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jianming Zhu, Yu Zhou, Junxiang Huang, Aojie Zhou, Zhencheng Chen
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/930e1634e73b4af28d1ff0e6af93973b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:930e1634e73b4af28d1ff0e6af93973b
record_format dspace
spelling oai:doaj.org-article:930e1634e73b4af28d1ff0e6af93973b2021-11-11T19:01:55ZNoninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning10.3390/s212169891424-8220https://doaj.org/article/930e1634e73b4af28d1ff0e6af93973b2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/6989https://doaj.org/toc/1424-8220Blood glucose (BG) concentration monitoring is essential for controlling complications arising from diabetes, as well as digital management of the disease. At present, finger-prick glucometers are widely used to measure BG concentrations. In consideration of the challenges of invasive BG concentration measurements involving pain, risk of infection, expense, and inconvenience, we propose a noninvasive BG concentration detection method based on the conservation of energy metabolism. In this study, a multisensor integrated detection probe was designed and manufactured by 3D-printing technology to be worn on the wrist. Two machine-learning algorithms were also applied to establish the regression model for predicting BG concentrations. The results showed that the back-propagation neural network model produced better performance than the multivariate polynomial regression model, with a mean absolute relative difference and correlation coefficient of 5.453% and 0.936, respectively. Here, about 98.413% of the predicted values were within zone A of the Clarke error grid. The above results proved the potential of our method and device for noninvasive glucose concentration detection from the human wrist.Jianming ZhuYu ZhouJunxiang HuangAojie ZhouZhencheng ChenMDPI AGarticlemultisensor fusiondiabetesmetabolic heat productionregression modelnoninvasive glucose concentration detectionwristChemical technologyTP1-1185ENSensors, Vol 21, Iss 6989, p 6989 (2021)
institution DOAJ
collection DOAJ
language EN
topic multisensor fusion
diabetes
metabolic heat production
regression model
noninvasive glucose concentration detection
wrist
Chemical technology
TP1-1185
spellingShingle multisensor fusion
diabetes
metabolic heat production
regression model
noninvasive glucose concentration detection
wrist
Chemical technology
TP1-1185
Jianming Zhu
Yu Zhou
Junxiang Huang
Aojie Zhou
Zhencheng Chen
Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning
description Blood glucose (BG) concentration monitoring is essential for controlling complications arising from diabetes, as well as digital management of the disease. At present, finger-prick glucometers are widely used to measure BG concentrations. In consideration of the challenges of invasive BG concentration measurements involving pain, risk of infection, expense, and inconvenience, we propose a noninvasive BG concentration detection method based on the conservation of energy metabolism. In this study, a multisensor integrated detection probe was designed and manufactured by 3D-printing technology to be worn on the wrist. Two machine-learning algorithms were also applied to establish the regression model for predicting BG concentrations. The results showed that the back-propagation neural network model produced better performance than the multivariate polynomial regression model, with a mean absolute relative difference and correlation coefficient of 5.453% and 0.936, respectively. Here, about 98.413% of the predicted values were within zone A of the Clarke error grid. The above results proved the potential of our method and device for noninvasive glucose concentration detection from the human wrist.
format article
author Jianming Zhu
Yu Zhou
Junxiang Huang
Aojie Zhou
Zhencheng Chen
author_facet Jianming Zhu
Yu Zhou
Junxiang Huang
Aojie Zhou
Zhencheng Chen
author_sort Jianming Zhu
title Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning
title_short Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning
title_full Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning
title_fullStr Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning
title_full_unstemmed Noninvasive Blood Glucose Concentration Measurement Based on Conservation of Energy Metabolism and Machine Learning
title_sort noninvasive blood glucose concentration measurement based on conservation of energy metabolism and machine learning
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/930e1634e73b4af28d1ff0e6af93973b
work_keys_str_mv AT jianmingzhu noninvasivebloodglucoseconcentrationmeasurementbasedonconservationofenergymetabolismandmachinelearning
AT yuzhou noninvasivebloodglucoseconcentrationmeasurementbasedonconservationofenergymetabolismandmachinelearning
AT junxianghuang noninvasivebloodglucoseconcentrationmeasurementbasedonconservationofenergymetabolismandmachinelearning
AT aojiezhou noninvasivebloodglucoseconcentrationmeasurementbasedonconservationofenergymetabolismandmachinelearning
AT zhenchengchen noninvasivebloodglucoseconcentrationmeasurementbasedonconservationofenergymetabolismandmachinelearning
_version_ 1718431659219484672