Optimizing Analysis of Donepezil HCl and Memantine HCl Using Multivariate Analysis as a Data Mining Tool in HPTLC Methodology

AI can be used to develop predictive models, identify patterns, and detect anomalies in data, which can be useful in method validation as a part of data mining. Data mining is useful in analysis validation as it is the technique of finding patterns and more valuable information from huge data sets. In the context of high-performance thin-layer chromatographic (HPTLC), data mining can be used to analyze patterns and trends in the data that can be used to upgrade the accuracy and robustness of the analysis. A HPTLC technique for simultaneous detection of Donepezil HCl and Memantine HCl was developed and validated according to ICH recommendations. Post-chromatographic derivatization with eosin Y reagent was needed to identify Memantine HCl without chromophoric groups and Donepezil HCl. Component separation in HPTLC was done on aluminum plates precoated with silica gel 60F254 with chloroform: cyclohexane: methanol: ammonia (4.25: 4.25: 1.5: 0.1, % v/v) as optimized mobile phase at 547 nm. Donepezil HCl had an Rf of 0.67, while Memantine had 0.36. Methanol concentration in the total mobile phase, wavelength, chamber saturation duration, and solvent front were tested for robustness using a fractional factorial design (24–1). From all four factors, the amount of methanol in the mobile phase has a possible significant influence on the Rf of Memantine HCl than Donepezil HCl; therefore, it was crucial to manage. In conclusion, a simple, novel, reproducible, accurate, and resilient high-performance thin-layer chromatographic method for pharmaceutical formulation quality control was developed.