Design‐Assisted Chemometric UV Spectrophotometric Determination of Candesartan Cilexetil, Chlorthalidone and Amlodipine Using Principal Component Regression, Partial Least Squares and Genetic Algorithm‐Partial Least Squares Models

ABSTRACT This study presents a sustainable chemometric‐assisted UV spectrophotometric strategy for the simultaneous determination of candesartan cilexetil (CAN), chlorthalidone (CTL) and amlodipine (AML) in laboratory‐prepared mixtures and commercial pharmaceutical formulations. Owing to the extensive spectral overlap of the three drugs in the UV region, conventional spectrophotometric methods are inadequate for their direct simultaneous analysis. To address this challenge, multivariate calibration models based on principal component regression (PCR), partial least squares (PLS) and genetic algorithm‐optimized partial least squares (GA‐PLS) were developed, enabling accurate quantification without prior separation or complex sample preparation. A design of experiments (DoE) approach was employed to construct the calibration set, while an independent validation set was generated using orthogonal array‐based Latin hypercube sampling (OALHS) to ensure robust external validation across the concentration domain. The GA‐PLS model enhanced predictive performance through effective wavelength selection, reducing spectral redundancy and improving model robustness. Furthermore, variable importance in projection (VIP) analysis was employed to identify the most influential spectral variables and provide insight into the spectral regions contributing to analyte quantification. The developed models exhibited excellent analytical performance, characterized by low calibration errors (root mean square error of calibration [RMSEC] < 0.30), strong predictive ability and satisfactory external validation results (RMSEP = 0.2278–0.4419; RRMSEP = 0.1558–0.3978), with recoveries ranging from 99.0% to 100.0%. The sustainability of the proposed methodology was assessed using the multi‐colour assessment (MA) tool according to white analytical chemistry principles, yielding a high whiteness score and demonstrating superior environmental performance compared with conventional chromatographic methods. In addition, the graphical layout tool for analytical chemistry evaluation (GLANCE) visualization framework provided a comprehensive graphical assessment of analytical performance and sustainability metrics. The proposed chemometric strategy offers a rapid, reliable, cost‐effective and environmentally friendly alternative for routine quality control of multicomponent pharmaceutical formulations.