Deep Learning-Based Noninvasive Blood Glucose Estimation

Estimating blood glucose levels (BGLs) noninvasively is a rapidly advancing field driven by the need for effective and painless glucose monitoring solutions for diabetic patients. This study explores deep learning (DL) models applied to noninvasive techniques for accurate BGL estimation. Thermal ima...

Full description

Saved in:
Bibliographic Details
Main Authors: Shatha M. Ali, Younis M. Abbosh, Dia M. Ali
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Engineering
Online Access:http://dx.doi.org/10.1155/je/1134023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850148211535118336
author Shatha M. Ali
Younis M. Abbosh
Dia M. Ali
author_facet Shatha M. Ali
Younis M. Abbosh
Dia M. Ali
author_sort Shatha M. Ali
collection DOAJ
description Estimating blood glucose levels (BGLs) noninvasively is a rapidly advancing field driven by the need for effective and painless glucose monitoring solutions for diabetic patients. This study explores deep learning (DL) models applied to noninvasive techniques for accurate BGL estimation. Thermal images were collected for Type I diabetes after confirming BGLs using a glucometer. DL techniques were then employed to classify the thermal images into three BGL classes (low, high, and normal). DarkNet and ShuffleNet convolutional neural networks (CNNs) are used to classify the thermal image and get the best performance, with an overall accuracy of 98% for DarkNet and 100% for ShuffleNet CNN.
format Article
id doaj-art-1a582d2a4c7045cd8679f8d45cb2aacc
institution OA Journals
issn 2314-4912
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Engineering
spelling doaj-art-1a582d2a4c7045cd8679f8d45cb2aacc2025-08-20T02:27:19ZengWileyJournal of Engineering2314-49122025-01-01202510.1155/je/1134023Deep Learning-Based Noninvasive Blood Glucose EstimationShatha M. Ali0Younis M. Abbosh1Dia M. Ali2Communication EngineeringBiomedical EngineeringBiomedical EngineeringEstimating blood glucose levels (BGLs) noninvasively is a rapidly advancing field driven by the need for effective and painless glucose monitoring solutions for diabetic patients. This study explores deep learning (DL) models applied to noninvasive techniques for accurate BGL estimation. Thermal images were collected for Type I diabetes after confirming BGLs using a glucometer. DL techniques were then employed to classify the thermal images into three BGL classes (low, high, and normal). DarkNet and ShuffleNet convolutional neural networks (CNNs) are used to classify the thermal image and get the best performance, with an overall accuracy of 98% for DarkNet and 100% for ShuffleNet CNN.http://dx.doi.org/10.1155/je/1134023
spellingShingle Shatha M. Ali
Younis M. Abbosh
Dia M. Ali
Deep Learning-Based Noninvasive Blood Glucose Estimation
Journal of Engineering
title Deep Learning-Based Noninvasive Blood Glucose Estimation
title_full Deep Learning-Based Noninvasive Blood Glucose Estimation
title_fullStr Deep Learning-Based Noninvasive Blood Glucose Estimation
title_full_unstemmed Deep Learning-Based Noninvasive Blood Glucose Estimation
title_short Deep Learning-Based Noninvasive Blood Glucose Estimation
title_sort deep learning based noninvasive blood glucose estimation
url http://dx.doi.org/10.1155/je/1134023
work_keys_str_mv AT shathamali deeplearningbasednoninvasivebloodglucoseestimation
AT younismabbosh deeplearningbasednoninvasivebloodglucoseestimation
AT diamali deeplearningbasednoninvasivebloodglucoseestimation