Complementary use of partial least-squares and artificial neural networks for the non-linear spectrophotometric analysis of pharmaceutical samples

MS COLLADO,; ML SATUF,; GOICOECHEA, HÉCTOR C; AC OLIVIERI,

ANALYTICAL AND BIOANALYTICAL CHEMISTRY

SPRINGER HEIDELBERG

Año: 2002 vol. 374 p. 460 - 465

1618-2642

The complementary use partial least-squares (PLS) multivariate calibration and artificial neural networks (ANNs) for the simultaneous spectrophotometric determination of three active components in nasal solutions is presented. The resolution of ternary mixtures of chlorpheniramine, naphazoline and dexamethasone in a matrix of excipients has been accomplished by using PLS-1 for the two major analytes (chlorpheniramine and naphazoline) and ANNs for dexamethasone. Notwithstanding the presence of a large number of constituents, their high degree of spectral overlap and the occurrence of non-linearities caused by the high concentrations of the main components, they have been rapidly and simultaneously determined with reasonably good accuracy and precision, with no interference, and without resorting to extraction procedures using non-aqueous solvents. The presence of non-linearities was studied with a recently discussed methodology based on Mallows augmented partial residual plots (APaRP)