Improved stability of blood glucose measurement in humans using near infrared spectroscopy

C. F. SO, Wai Yee Joanne CHUNG, Maggie S. M. SIU, Thomas K. S. WONG

Research output: Contribution to journalArticles

3 Citations (Scopus)

Abstract

Near infrared (NIR) spectroscopy has become a promising technique for blood glucose monitoring. However, an appropriate model of spectral response in humans is yet to be determined because of the reliability problem. In this study, 48 subjects were recruited. The subjects' left forearms were scanned using near infrared spectroscopy to obtain NIR spectra. Simultaneously, a blood sample of glucose was drawn. A new method based on Monte Carlo approach is applied for partial least squares (PLS), named as PLSMC, is proposed. A large numbers of models are built from calibration subsets which are randomly selected from the whole calibration set in order to minimize the noises. It is then determining the mean value over the models with high correlation and small prediction errors. The results show that the method can enhance the stability of PLS model. Also, the performance of the PLSMC shows more accurate prediction results as compared with conventional PLS. Copyright © 2011 - IOS Press and the authors.
Original languageEnglish
Pages (from-to)137-145
JournalSpectroscopy
Volume25
Issue number3-4
DOIs
Publication statusPublished - Apr 2011

Citation

So, C. F., Chung, J. W. Y., Siu, M. S. M., & Wong, T. K. S. (2011). Improved stability of blood glucose measurement in humans using near infrared spectroscopy. Spectroscopy, 25(3-4), 137-145.

Keywords

  • Blood glucose
  • Near infrared
  • Partial least squares
  • Prediction model
  • Spectroscopy

Fingerprint Dive into the research topics of 'Improved stability of blood glucose measurement in humans using near infrared spectroscopy'. Together they form a unique fingerprint.