D-optimal candexch algorithm-enhanced machine learning UV-spectrophotometry for five-analyte determination in novel anti-glaucoma formulations and ocular fluids: four-color sustainability framework with NQS assessment and UN-SDG integration.

The novel anti-glaucoma ophthalmic preparation containing latanoprost, netarsudil, and benzalkonium chloride has posed a significant challenge due to its complexity and the lack of environmentally sustainable quantification methods, with only a single published method available for its quantification that lacks environmental consideration. This study aims to address this crucial gap by presenting a novel and sustainable approach using machine learning-enhanced UV-spectrophotometric chemometric models for the concurrent quantification of latanoprost, netarsudil, benzalkonium chloride, and two related compounds in ophthalmic preparations and aqueous humour. A strategic multi-level, multi-factor experimental design creates a 25-mixture calibration set for four models (PLS, GA-PLS, PCR, and MCR-ALS). The key novelty was using the D-optimal design generated by MATLAB's candexch algorithm to construct a robust validation set, overcoming random data splitting limitations in machine learning chemometric methods and ensuring unbiased evaluation across concentrations. The optimized MCR-ALS model outperforms in predictive ability, with recovery percentages of 98-102%, low root mean square errors of calibration and prediction, favorable bias-corrected mean square error of prediction, relative root mean square error within acceptable limits, and adequate limits of detection for pharmaceutical analysis. The Greenness Index Spider Charts and the Green Solvents Selection Tool were applied to replace hazardous solvents. A total of seven advanced evaluation tools were employed to assess the method's greenness, blueness, violetness, and whiteness, highlighting its eco-friendly profile, practical relevance, and innovation potential. Additionally, the method's environmental and societal benefits were further validated using the Need, Quality, Sustainability (NQS) index. Overall, this machine learning-based framework contributes meaningfully to ten United Nations Sustainable Development Goals (UN-SDGs), underscoring its value for future-oriented pharmaceutical research.