AbstractBackgroundThere is an increasing interest of the scientific community in developing innovative methodologies for their analysis needs within a green analytical chemistry framework. UV spectrophotometry is one of the most promising eco-friendly methods, which is integrated with advanced chemometric tools to enhance the selectivity of the analysis of complex mixtures with severe overlapped signals.ObjectiveSimultaneous determination of a triple-combination of pseudoephedrine hydrochloride (PSE), carbinoxamine maleate (CRX), and paracetamol (PAR) using an artificial intelligence system and multivariate calibration methods. This combination has been recently recommended for COVID-19 home-treated patients as part of a symptomatic treatment.MethodsNamely, the suggested models are artificial neural networks, partial least-squares, and principal component regression. The proposed algorithms were optimized and developed with the aid of a five-level, three-factor experimental design.ResultsThe investigated methods were applied over the concentration range of 100–180 μg/mL, 18–16 μg/mL, and 4–12 μg/mL for PSE, CRX, and PAR, respectively. The models’ validation results demonstrated excellent recoveries (around 98 to 102%), signaling the approaches’ outstanding resolution capacity for the cited compounds in the presence of common excipients. The outcomes of the studied methods were statistically compared to the official approaches, and no significant difference was found.ConclusionsThe suggested models were efficiently employed to determine the selected drugs in their combined tablets without any initial separation steps. The impact of these methods on the environment was evaluated via greenness tools: namely, the National Environmental Method Index, Raynie and Driver’s green assessment method, Analytical Eco-Scale, Green Analytical Procedure Index, and Analytical Greenness Metric.HighlightsGreen chemometric quality assessment of PSE, CRX, and PAR in their pure and pharmaceutical dosage forms. The established approaches are innovative, sustainable, smart, fast, selective, and cost-effective. These models are potential green nominees for routine analysis of the investigated mixture in quality control laboratories.