Scholarlink

Abstract <p>Currently, non-invasive continuous blood glucose monitoring technology remains insufficient in terms of clinical validation data. Existing approaches predominantly depend on statistical models to predict blood glucose levels, which often suffer from limited data samples. This leads to significant individual differences in non-invasive continuous glucose monitoring, limiting its scope and promotion. We propose a neural network that uses metabolic characteristics as inputs to predict the rate of insulin-facilitated glucose uptake by cells and postprandial glucose gradient changes (glucose gradient: the rate of change of blood glucose concentration within a unit of time (dG/dt), with the unit of mg/(dL × min), reflects the dynamic change trend of blood glucose levels). This neural network utilises non-invasive continuous glucose monitoring method based on the Bergman minimal model (BM-NCGM) while considering the effects of the glucose gradient, insulin action, and the digestion process on glucose changes, achieving non-invasive continuous glucose monitoring. This work involved 161 subjects in a controlled clinical trial, collecting over 15,000 valid data sets. The predictive results of BM-NCGM for glucose showed that the CEG A area accounted for 77.58% and the A + B area for 99.57%. The correlation coefficient (0.85), RMSE (1.48&#xa0;mmol/L), and MARD (11.51%) showed an improvement of over 32% compared to the non-use of BM-NCGM. The dynamic time warping algorithm was used to calculate the distance between the predicted blood glucose spectrum and the reference blood glucose spectrum, with an average distance of 21.80, demonstrating the excellent blood glucose spectrum tracking ability of BM-NCGM. This study is the first to apply the Bergman minimum model to non-invasive continuous blood glucose monitoring research, supported by a large amount of clinical trial data, bringing non-invasive continuous blood glucose monitoring closer to its true application in daily blood glucose monitoring. &#xa0;</p> Clinical trial registry number <p>ChiCTR1900028100.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A non-invasive continuous glucose monitoring method based on the Bergman minimal model

  • 期刊论文

  • 发表日期：

    2025年8月5日

查看全文
  • Ang Li,
  • Long Zhao,
  • Chenyang Wu,
  • Zhanxiao Geng,
  • Lihui Yang,
  • Fei Tang

摘要

Abstract

Currently, non-invasive continuous blood glucose monitoring technology remains insufficient in terms of clinical validation data. Existing approaches predominantly depend on statistical models to predict blood glucose levels, which often suffer from limited data samples. This leads to significant individual differences in non-invasive continuous glucose monitoring, limiting its scope and promotion. We propose a neural network that uses metabolic characteristics as inputs to predict the rate of insulin-facilitated glucose uptake by cells and postprandial glucose gradient changes (glucose gradient: the rate of change of blood glucose concentration within a unit of time (dG/dt), with the unit of mg/(dL × min), reflects the dynamic change trend of blood glucose levels). This neural network utilises non-invasive continuous glucose monitoring method based on the Bergman minimal model (BM-NCGM) while considering the effects of the glucose gradient, insulin action, and the digestion process on glucose changes, achieving non-invasive continuous glucose monitoring. This work involved 161 subjects in a controlled clinical trial, collecting over 15,000 valid data sets. The predictive results of BM-NCGM for glucose showed that the CEG A area accounted for 77.58% and the A + B area for 99.57%. The correlation coefficient (0.85), RMSE (1.48 mmol/L), and MARD (11.51%) showed an improvement of over 32% compared to the non-use of BM-NCGM. The dynamic time warping algorithm was used to calculate the distance between the predicted blood glucose spectrum and the reference blood glucose spectrum, with an average distance of 21.80, demonstrating the excellent blood glucose spectrum tracking ability of BM-NCGM. This study is the first to apply the Bergman minimum model to non-invasive continuous blood glucose monitoring research, supported by a large amount of clinical trial data, bringing non-invasive continuous blood glucose monitoring closer to its true application in daily blood glucose monitoring.  

Clinical trial registry number

ChiCTR1900028100.

Graphical Abstract