Modified locally weighted--partial least squares regression improving clinical predictions from infrared spectra of human serum samples.

Locally weighted partial least squares regression (LW-PLSR) has been applied to the determination of four clinical parameters in human serum samples (total protein, triglyceride, glucose and urea contents) by Fourier transform infrared (FTIR) spectroscopy. Classical LW-PLSR models were constructed using different spectral regions. For the selection of parameters by LW-PLSR modeling, a multi-parametric study was carried out employing the minimum root-mean square error of cross validation (RMSCV) as objective function. In order to overcome the effect of strong matrix interferences on the predictive accuracy of LW-PLSR models, this work focuses on sample selection. Accordingly, a novel strategy for the development of local models is proposed. It was based on the use of: (i) principal component analysis (PCA) performed on an analyte specific spectral region for identifying most similar sample spectra and (ii) partial least squares regression (PLSR) constructed using the whole spectrum. Results found by using this strategy were compared to those provided by PLSR using the same spectral intervals as for LW-PLSR. Prediction errors found by both, classical and modified LW-PLSR improved those obtained by PLSR. Hence, both proposed approaches were useful for the determination of analytes present in a complex matrix as in the case of human serum samples.

[1]  Despagne,et al.  Development of a robust calibration model for nonlinear in-line process data , 2000, Analytical chemistry.

[2]  Cyril Petibois,et al.  Applications of FT-IR spectrometry to plasma contents analysis and monitoring , 2003 .

[3]  S. Garrigues,et al.  Protein determination in serum and whole blood by attenuated total reflectance infrared spectroscopy , 2012, Analytical and Bioanalytical Chemistry.

[4]  Jing Wang,et al.  Comparison of different infrared measurement techniques in the clinical analysis of biofluids , 1996 .

[5]  K. Fujiwara,et al.  Development of correlation-based clustering method and its application to software sensing , 2010 .

[6]  W. Petrich.  MID-INFRARED AND RAMAN SPECTROSCOPY FOR MEDICAL DIAGNOSTICS , 2001 .

[7]  D L Massart,et al.  Optimization in locally weighted regression. , 1998, Analytical chemistry.

[8]  B. Lendl,et al.  On-Line Fermentation Monitoring by Mid-Infrared Spectroscopy , 2004, Applied spectroscopy.

[9]  T. Næs,et al.  The Effect of Multiplicative Scatter Correction (MSC) and Linearity Improvement in NIR Spectroscopy , 1988 .

[10]  D. Naumann,et al.  FT-IR and FT-NIR Raman spectroscopy in biomedical research , 1998 .

[11]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[12]  Angela Man,et al.  Reagent-free, simultaneous determination of serum cholesterol in HDL and LDL by infrared spectroscopy. , 2002, Clinical chemistry.

[13]  T. Isaksson,et al.  New approach for distance measurement in locally weighted regression , 1994 .

[14]  J Möcks,et al.  Comparison of mid-infrared and Raman spectroscopy in the quantitative analysis of serum. , 2005, Journal of biomedical optics.

[15]  Manabu Kano,et al.  Estimation of active pharmaceutical ingredients content using locally weighted partial least squares and statistical wavelength selection. , 2011, International journal of pharmaceutics.

[16]  B. Mizaikoff,et al.  Application of multivariate data-analysis techniques to biomedical diagnostics based on mid-infrared spectroscopy , 2008, Analytical and bioanalytical chemistry.

[17]  H. Heise,et al.  Nanoliter Serum Sample Analysis by Mid-Infrared Spectroscopy for Minimally Invasive Blood-Glucose Monitoring , 2005, Applied spectroscopy.

[18]  Andre J. Sommer,et al.  The Advantages of an Attenuated Total Internal Reflection Infrared Microspectroscopic Imaging Approach for Kidney Biopsy Analysis , 2010, Applied spectroscopy.

[19]  M. Amici,et al.  Determination of carbonate in marine solid samples by FTIR-ATR spectroscopy. , 2001, The Analyst.

[20]  Kevin H. Hazen,et al.  Measurement of glucose and other analytes in undiluted human serum with near-infrared transmission spectroscopy , 1998 .

[21]  Werner Mäntele,et al.  Clinical chemistry without reagents? An infrared spectroscopic technique for determination of clinically relevant constituents of body fluids , 2007, Analytical and bioanalytical chemistry.

[22]  J. Lademann,et al.  Two-wavelength carbon dioxide laser application for in-vitro blood glucose measurements. , 2008, Journal of biomedical optics.

[23]  Henry H. Mantsch,et al.  Vibrational spectroscopy and medicine: an alliance in the making , 2002 .

[24]  T. Næs,et al.  Locally weighted regression and scatter correction for near-infrared reflectance data , 1990 .

[25]  A Garrido-Varo,et al.  Non-linear regression methods in NIRS quantitative analysis. , 2007, Talanta.

[26]  Manabu Kano,et al.  Evaluation of infrared-reflection absorption spectroscopy measurement and locally weighted partial least-squares for rapid analysis of residual drug substances in cleaning processes. , 2012, Analytical chemistry.

[27]  Paolo Berzaghi,et al.  LOCAL Prediction with near Infrared Multi-Product Databases , 2000 .

[28]  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.

[29]  M. de la Guardia,et al.  Evaluation of infrared spectroscopy as a screening tool for serum analysis: Impact of the nature of samples included in the calibration set , 2013 .