Dry film method with ytterbium as the internal standard for near infrared spectroscopic plasma glucose assay coupled with boosting support vector regression

A novel near infrared (NIR) spectroscopic measurement technique, dry film method, has been proposed for the determination of glucose in plasma. Rare earth element ytterbium (Yb) has been taken in the dry film method as the internal standard to compensate for the thickness variation of the dry films. This technique circumvents the interference from water absorption and requires only 50 µl of sample. Support vector regression (SVR) as a multivariate calibration method has been combined with boosting for the development of a boosting support vector regression (BSVR) method for the dry film measurement modeling. The introduction of boosting drastically enhances the performance of individual SVR model. The results show that the glucose in plasma can be determined over the 0.4–20 mmol/L concentration range with satisfactory accuracy using the dry film technique coupled with the BSVR method. Moreover, the performance of BSVR was compared favorably with that of the conventional SVR and PLS. Copyright © 2006 John Wiley & Sons, Ltd.

[1]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[2]  M A Arnold,et al.  Near-infrared spectroscopic measurement of physiological glucose levels in variable matrices of protein and triglycerides. , 1996, Analytical chemistry.

[3]  A. Belousov,et al.  Applicational aspects of support vector machines , 2002 .

[4]  J D Kruse-Jarres,et al.  Multivariate calibration for assays in clinical chemistry using attenuated total reflection infrared spectra of human blood plasma. , 1989, Analytical chemistry.

[5]  Harald Martens,et al.  A multivariate calibration problem in analytical chemistry solved by partial least-squares models in latent variables , 1983 .

[6]  Hiroshi Yamamoto,et al.  Biological Applications of Anti-Stokes Raman Spectroscopy: Quantitative Analysis of Glucose in Plasma and Serum by a Highly Sensitive Multichannel Raman Spectrometer , 1996 .

[7]  H Gin,et al.  Determination of glucose in dried serum samples by Fourier-transform infrared spectroscopy. , 1999, Clinical chemistry.

[8]  S. Wold,et al.  Wavelength interval selection in multicomponent spectral analysis by moving window partial least-squares regression with applications to mid-infrared and near-infrared spectroscopic data. , 2002, Analytical chemistry.

[9]  Y. Ozaki,et al.  Short-wave near-infrared spectroscopy of biological fluids. 1. Quantitative analysis of fat, protein, and lactose in raw milk by partial least-squares regression and band assignment. , 2001, Analytical chemistry.

[10]  G. W. Small,et al.  Calibration standardization algorithm for partial least-squares regression: application to the determination of physiological levels of glucose by near-infrared spectroscopy. , 2002, Analytical chemistry.

[11]  Wulfert,et al.  Correction of temperature-induced spectral variation by continuous piecewise direct standardization , 2000, Analytical chemistry.

[12]  D L Massart,et al.  Boosting partial least squares. , 2005, Analytical chemistry.

[13]  Yukihiro Ozaki,et al.  Selective removal of interference signals for near-infrared spectra of biomedical samples by using region orthogonal signal correction , 2004 .

[14]  G. W. Small,et al.  Multivariate calibration standardization across instruments for the determination of glucose by Fourier transform near-infrared spectrometry. , 2003, Analytical chemistry.

[15]  G. W. Small,et al.  Noninvasive glucose sensing. , 2005, Analytical chemistry.

[16]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[17]  L. Buydens,et al.  Comparing support vector machines to PLS for spectral regression applications , 2004 .

[18]  Yi-Zeng Liang,et al.  A generalized boosting algorithm and its application to two-class chemical classification problem , 2005 .

[19]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[20]  Jun Chen,et al.  Scattering and absorption effects in the determination of glucose in whole blood by near-infrared spectroscopy. , 2005, Analytical chemistry.

[21]  L. Buydens,et al.  Multivariate calibration with least-squares support vector machines. , 2004, Analytical chemistry.

[22]  J. Friedman.  Stochastic gradient boosting , 2002 .

[23]  Age K Smilde,et al.  Performance optimization of spectroscopic process analyzers. , 2004, Analytical chemistry.

[24]  R. V. Van Duyne,et al.  Toward a glucose biosensor based on surface-enhanced Raman scattering. , 2003, Journal of the American Chemical Society.

[25]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[26]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[27]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[28]  G. Cazorla,et al.  Plasma protein contents determined by Fourier-transform infrared spectrometry. , 2001, Clinical chemistry.

[29]  Yi-Ping Du,et al.  Simultaneous determination of human serum albumin, gamma-globulin, and glucose in a phosphate buffer solution by near-infrared spectroscopy with moving window partial least-squares regression. , 2003, The Analyst.

[30]  Vincent Baeten,et al.  Combination of support vector machines (SVM) and near‐infrared (NIR) imaging spectroscopy for the detection of meat and bone meal (MBM) in compound feeds , 2004 .