Premium
Simultaneous spectrophotometric determination of diclofenac potassium and methocarbamol in binary mixture using chemometric techniques and artificial neural networks
Author(s) -
Elkady Ehab F.
Publication year - 2011
Publication title -
drug testing and analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.065
H-Index - 54
eISSN - 1942-7611
pISSN - 1942-7603
DOI - 10.1002/dta.216
Subject(s) - principal component regression , partial least squares regression , chemistry , absorbance , matrix (chemical analysis) , artificial neural network , data matrix , principal component analysis , biological system , spectrophotometry , chromatography , analytical chemistry (journal) , artificial intelligence , computer science , machine learning , clade , biochemistry , biology , gene , phylogenetic tree
Abstract In this study, the simultaneous determination of diclofenac potassium (DP) and methocarbamol (MT) by chemometric approaches and artificial neural networks using UV spectrophotometry has been reported as a simple alternative to using separate models for each component. Three chemometric techniques—classical least‐squares (CLS), principal component regression (PCR), and partial least‐squares (PLS)—along with radial basis function‐artificial neural network (RBF‐ANN) were prepared by using the synthetic mixtures containing the two drugs in methanol. A set of synthetic mixtures of DP and MT was evaluated and the results obtained by the application of these methods were discussed and compared. In CLS, PCR, and PLS, the absorbance data matrix corresponding to the concentration data matrix was obtained by the measurements of absorbances in the range 260–310 nm in the intervals with Δλ = 0.2 nm in their zero‐order spectra. Then, calibration or regression was obtained by using the absorbance data matrix and concentration data matrix for the prediction of the unknown concentrations of DP and MT in their mixtures. In RBF‐ANN, the input layer consisting of 251 neurons, 9 neurons in the hidden layer, and 2 output neurons were found appropriate for the simultaneous determination of DP and MT. The accuracy and the precision of the four methods have been determined and they have been validated by analyzing synthetic mixtures containing the two drugs. The proposed methods were successfully applied to a pharmaceutical formulation containing the examined drugs. Copyright © 2010 John Wiley & Sons, Ltd.