Rapid and Simultaneous Determination of Montelukast, Fexofenadine and Cetirizine Using Partial Least Squares and Artificial Neural Networks Modeling

Simultaneous determination of pharmaceutical compounds and accurate quantitative prediction of them are of great interest in the clinical and laboratory-based investigations. This work has focused on a comprehensive comparison of Partial Least-Squares (PLS-1) and Artificial Neural Networks (ANN) as two powerful types of chemometric methods. For this purpose, montelukast (MONT), fexofenadine (FEXO) and cetirizine (CET) were studied as three pharmaceuticals whose UV-Vis absorption spectra highly overlap each other. The cross-validation leave-one-sample-out procedure was applied and the optimum number of factors was determined. The developed models were subsequently validated through testing with an independent dataset. Furthermore, a simple and fast method for wavelength selection (WS-PLS-1) in the calibration step was presented which involved the calculation of the Net Analyte Signal Regression Plot (NASRP) for each test sample. Highest prediction accuracies corresponded to WS-PLS-1 method with R2 values of 0.994, 0.982 and 0.999 for MONT, FEXO and CET, respectively. The best values of detection limit were also provided by WS-PLS-1 method which obtained to be 0.029, 0.049 and 0.054 mg/L for MONT, FEXO and CET, respectively. According to the results obtained, WS-PLS-1 method was shown to have the potential to be utilized as a promising tool in clinical and pharmaceutical applications.