AI-assisted Python automation of mean-centering spectrophotometric methods with comprehensive sustainability...

The simultaneous spectrophotometric determination of drugs with overlapping spectra remains a challenging analytical task. In this study, a hybrid analytical strategy combining classical UV-Vis spectrophotometry with artificial intelligence (AI)-assisted Python automation is proposed for the simultaneous determination of amlodipine besylate (AMT) and hydrochlorothiazide (HYCD) in their combined dosage form. AMT was quantified using a zero-crossing method at 366 nm, while HYCD was determined using the mean-centering of ratio spectra (MCR) approach AI-assisted Python scripting was employed to automate spectral preprocessing, divisor selection, calibration, and validation, enabling systematic and reproducible evaluation of multiple divisor scenarios. The optimized mean spectrum divisor provided improved analytical performance, with strong linearity (R² ≥ 0.9998), low detection limits (LOD = 0.25 μg/mL for HYCD and 0.83 μg/mL for AMT), acceptable accuracy (mean recoveries of 99.8-100.1%), and good precision (RSD < 1.2%). The method was further evaluated using multiple sustainability assessment tools, including GAPI, WAC, Blueness, and AGREE, demonstrating favorable environmental performance. Compared to conventional chromatographic techniques, the proposed approach offers a simple, cost-effective, and reproducible alternative for routine pharmaceutical quality control. The results highlight the role of AI-assisted automation in enhancing workflow efficiency and reproducibility without altering the underlying analytical principles.