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

Abstract

The complementary use of partial least-squares (PLS) multivariate calibration and artificial neural networks (ANNs) for the simultaneous spectrophotometric determination of three active components in a pharmaceutical formulation has been explored. The presence of non-linearities caused by chemical interactions was confirmed by a recently discussed methodology based on Mallows augmented partial residual plots. Ternary mixtures of chlorpheniramine, naphazoline and dexamethasone in a matrix of excipients have been resolved by using PLS for the two major analytes (chlorpheniramine and naphazoline) and ANNs for the minor one (dexamethasone). Notwithstanding the large number of constituents, their high degree of spectral overlap and the occurrence of non-linearities, rapid and simultaneous analysis has been achieved, with reasonably good accuracy and precision. No extraction procedures using non-aqueous solvents are required.

A combined artificial neural network/residual bilinearization approach for obtaining the second‐order advantage from three‐way non‐linear data

“…Although on a different spectroscopic area, this behavior resembles that of the absorption spectra of pharmaceutical dexamethasone in mixtures with chlorpheniramine and naphazoline, which has been previously studied using an ANN approach [2]. However, in these latter pharmaceutical samples no unsuspected components occurred, and hence the second-order advantage issue was unimportant.…”

“…This phenomenon arises, for example, when significant interactions occur among sample components [1,2], or in fluorescence spectroscopy, due to the exponential relationship between emission and concentration [3]. They also appear in kinetic-spectroscopic systems, when a reaction product is followed which is the result of a pseudo first-order kinetics with respect to reagent [4], or when the analyte intervenes as a catalyst [5][6][7].…”

Recent Advances in the Analysis of Steroid Hormones and Related Drugs

“…20 Other 3-component formulations containing low quantities of dexamethasone resolved by partial least-squares regression analysis and other chemometric methods were Polymyxin B, trimethoprim, dexamethasone 21 and chlorpheniramine, naphazoline and dexamethasone. 22 In the latter case, the use of artificial neural network analysis was necessary for the determination of dexamethasone due to the non-linearity caused by interactions among the components.…”

Sustained modelling ability of artificial neural networks in the analysis of two pharmaceuticals (dextropropoxyphene and dipyrone) present in unequal concentrations

“…On the other hand, these methods are computationally more complex than linear methods, they have the limitation of being prone to over fitting, and they heavily depend on the amount and quality of data available [13]. We recently reported the application of ANNs to improve the prediction results for the analysis of dexamethasone in nasal solutions [19].…”