Evaluation of nonlinear model building strategies for the determination ofglucose in biological matrices by near-infrared spectroscopy

Nonlinear model building techniques are applied to near-infrared spectra to predict glucose concentrations in samples containing an aqueous matrix of varied concentrations of bovine serum albumin (BSA) and triacetin. The tria cetin is used to model triglycerides in human blood, and the BSA is used to model blood proteins. The non-linear model building techniques included in this study are quadratic partial least-squares regression (QPLS), stepwise QPLS, and PLS followed by artificial neural networks (PLS-ANN). The optima l models obtained for glucose provide standard errors of prediction of 0.53 mM, 0.54 mM, and 0.48 mM for the QPLS, stepwise QPLS and PLS-ANN models, r espectively, over the clinically relevant concentration range of 1-20 mM. T hese results indicate significant improvement in, prediction performance re lative to that obtained with linear PLS models. This improvement is confirm ed through the use of F-tests at the 95% confidence level. The significant quadratic terms included in the stepwise QPLS models also confirm that nonl inear information exists in the data set studied. This suggests that there is a need to develop suitable nonlinear model building strategies for nonin vasive blood glucose determinations. (C) 1999 Elsevier Science B.V. All rig hts reserved.