Personalized non-invasive continuous glucose monitoring via multiparameter-informed machine learning
Biosensors and Bioelectronics · 2026-10 · 310 · 118874
DOI: 10.1016/j.bios.2026.118874 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2026-10. Verfasst von Wangwang Zhu und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin, 300072, China. Hauptthemen laut MEDLINE: Biosensing Techniques, Blood Glucose, Continuous Glucose Monitoring, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Non-invasive continuous glucose monitoring (NCGM) based on reverse iontophoresis (RI) holds considerable promise for diabetes management; however, its clinical translation is constrained by limited predictive accuracy. This limitation primarily arises from the inter-individual differences and the dynamic variability during continuous monitoring. Here we present a multiparameter-informed machine learning framework using physiological factors of glucose, Na+, skin surface pH, temperature, and impedance to composite the effect and enable accurate and personalized NCGM. An accompanying flexible multimodal sensing platform is designed to simultaneously quantify glucose, Na+, and skin surface pH, together with skin temperature and impedance. A physics-based model first generates a physiologically grounded glucose estimate calibrated by Na+ and pH, which is subsequently refined using a CNN-LSTM-Attention architecture. Transfer learning is implemented to enable cross-individual generalization and personalized calibration. In-vivo studies in six healthy volunteers over 14 days demonstrate that the proposed multiparameter biosensing-informed machine learning approach achieves closer agreement with reference glucose profiles, reducing the overall mean absolute relative difference (MARD) from 19.01% to 14.47% and further to 10.51%. Clarke error grid analysis indicates enhanced clinical accuracy, with the highest proportion of data points located within zones A and B (99.45%). Shapley Additive Explanation (SHAP) analysis further reveals pronounced inter-individual variability in feature contributions, highlighting the model's capacity for adaptive, personalized weighting of physiological inputs. These results establish a multiparameter-informed strategy that improves the accuracy of RI-based glucose monitoring, providing a viable pathway toward precise and personalized NCGM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin, 300072, China.
- State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin, 300072, China. Electronic address: puzhihua@tju.edu.cn.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhu, W., Li, X., Hou, J., Li, W., Li, J., Zheng, H., Li, D., & Pu, Z. (2026). Personalized non-invasive continuous glucose monitoring via multiparameter-informed machine learning. Biosensors and Bioelectronics, 310, 118874. https://doi.org/10.1016/j.bios.2026.118874
Vancouver
Zhu W, Li X, Hou J, Li W, Li J, Zheng H, et al. Personalized non-invasive continuous glucose monitoring via multiparameter-informed machine learning. Biosensors and Bioelectronics. 2026;310:118874. doi:10.1016/j.bios.2026.118874
BibTeX
@article{Zhu2026,
author = {Zhu, Wangwang and Li, Xi and Hou, Jiaqi and Li, Wenjun and Li, Jingyun and Zheng, Hao and Li, Dachao and Pu, Zhihua},
title = {Personalized non-invasive continuous glucose monitoring via multiparameter-informed machine learning},
journal = {Biosensors and Bioelectronics},
year = {2026},
volume = {310},
pages = {118874},
doi = {10.1016/j.bios.2026.118874}
}
EUVIMED