A Feasibility Study on Noninvasive Blood Glucose Estimation Using Machine Learning Analysis of Near-Infrared Spectroscopy Data
Biosensors · 2025
DOI: 10.3390/bios15110711 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors, 2025. Verfasst von Tae Wuk Bae und 3 weiteren Autor:innen. Beteiligte Einrichtung: Daegu-Gyeongbuk Research Center, Electronics and Telecommunications Research Institute, Daegu 42994, Republic of Korea. Hauptthemen laut MEDLINE: Blood Glucose, Machine Learning, Biosensing Techniques. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Electronics and Telecommunications Research Institute.
Abstract (Originalsprache)
This study explored the feasibility of noninvasive blood glucose (BG) estimation using near-infrared (NIR) spectroscopy with dog blood samples. A sensor module employing three representative wavelengths (770 nm, 850 nm, and 970 nm) was tested on an artificial blood vessel (ABV) and a thin pig skin (TPS) model. BG concentrations were adjusted through dilution and enrichment with injection-grade water and glucose solution, and reference values were obtained from three commercial invasive glucometers. Correlations between NIR spectral responses and glucose variations were quantitatively evaluated using linear, multiple, partial least squares (PLS), logistic regression, regularized linear models, and multilayer perceptron (MLP) analysis. The results revealed distinct negative correlations at 850 nm and 970 nm, identifying these wavelengths as promising candidates for noninvasive glucose sensing. Furthermore, an NIR–glucose database generated from actual dog blood was established, which may serve as a valuable resource for the development of future noninvasive glucose monitoring systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Daegu-Gyeongbuk Research Center, Electronics and Telecommunications Research Institute, Daegu 42994, Republic of Korea.
- Electronic Advanced Development Team, AJIN Industrial Co., Ltd., Gyeongsan 38462, Republic of Korea.
ORCID-Profile: Tae Wuk Bae, Kee Koo Kwon
Förderung
- Electronics and Telecommunications Research Institute
Zitieren
APA
Bae, T. W., Kim, B. I., Kwon, K. K., & Kim, K. Y. (2025). A Feasibility Study on Noninvasive Blood Glucose Estimation Using Machine Learning Analysis of Near-Infrared Spectroscopy Data. Biosensors. https://doi.org/10.3390/bios15110711
Vancouver
Bae TW, Kim BI, Kwon KK, Kim KY. A Feasibility Study on Noninvasive Blood Glucose Estimation Using Machine Learning Analysis of Near-Infrared Spectroscopy Data. Biosensors. 2025. doi:10.3390/bios15110711
BibTeX
@article{Bae2025,
author = {Bae, Tae Wuk and Kim, Byoung Ik and Kwon, Kee Koo and Kim, Kwang Yong},
title = {A Feasibility Study on Noninvasive Blood Glucose Estimation Using Machine Learning Analysis of Near-Infrared Spectroscopy Data},
journal = {Biosensors},
year = {2025},
doi = {10.3390/bios15110711}
}
EUVIMED