Quantification and Classification of Diclofenac Sodium Content in Dispersed Commercially Available Tablets by Attenuated Total Reflection Infrared Spectroscopy and Multivariate Data Analysis

Abstract

A new methodology, based on Fourier transform infrared spectroscopy equipped with an attenuated total reflectance accessory (ATR FT-IR), was developed for the determination of diclofenac sodium (DS) in dispersed commercially available tablets using chemometric tools such as partial least squares (PLS) coupled with discriminant analysis (PLS-DA). The results of PLS-DA depicted a perfect classification of the tablets into three different groups based on their DS concentrations, while the developed model with PLS had a sufficiently low root mean square error (RMSE) for the prediction of the samples' concentration (~5%) and therefore can be practically used for any tablet with an unknown concentration of DS. Comparison with ultraviolet/visible (UV/Vis) spectrophotometry as the reference method revealed no significant difference between the two methods. The proposed methodology exhibited satisfactory results in terms of both accuracy and precision while being rapid, simple and of low cost.

Keywords: ATR spectroscopy; Fourier transform infrared; chemometrics; diclofenac sodium; quantitative analysis.

Figure 1

Structure of diclofenac sodium molecule.

Figure 2

Second derivative transformation with Savitzky–Golay smoothing focusing on the 1600–1500 cm⁻¹ region of the spectra of the training set (blue: 1 g/L, red: 4 g/L, green: 7 g/L, cyan: 10 g/L, brown: 13 g/L of DS).

Figure 3

Boxplots (quantiles) of the training set. The maximum intensity deviation is observed in the region 1595–1575 cm⁻¹.

Figure 4

Scores plot of the training set (blue: 1 g/L, red: 4 g/L, green: 7 g/L, cyan: 10 g/L, brown: 13 g/L of DS). Each point corresponds to a different control batch consisting of three spectra for each concentration (N_total = 30 spectra).

Figure 5

Leave-one-out CV results (blue: training set, red: validation set).

Figure 6

Predicted content of DS in the test set alongside deviation (boxplots). The statistical outcomes of the PLS model are also shown.

Figure 7

ATR FT-IR spectrum of DS (standard compound) in powder form (abscissa units: wavenumber (cm⁻¹); ordinate units: absorbance).

Figure 8

ATR FT-IR spectrum of DS methanolic solution (20 g/L) after taking a methanol spectrum as background spectrum (abscissa units: wavenumber (cm⁻¹); ordinate units: absorbance).