Spectrophotometric Multicomponent Analysis: from Classical and Chemometric Methods to Emerging Artificial Intelligence Approaches

Abstract

Fixed-dose combinations (FDCs) are increasingly utilized in modern therapeutics, as they incorporate multiple drugs to achieve synergistic effects while reducing the required dose and improving patient compliance. The accurate determination of these combinations in various matrices is essential for routine quality control. Among the available analytical techniques, spectrophotometry is routinely employed over chromatographic methods due to its simplicity, reliability, and low energy consumption, making it well aligned with green analytical chemistry principles. Despite these advantages, spectrophotometric determination of multicomponent drug mixtures faces significant challenges, particularly due to severe spectral overlap and the presence of minor components in fixed-dose formulations. These factors limit the direct application of conventional measurements and reduce analytical selectivity. To address these limitations, a wide range of chemometric methods have been introduced, enabling the accurate and selective resolution of complex mixtures without the need for prior separation. More recently, the integration of artificial intelligence (AI) techniques has further enhanced the capability of spectrophotometric analysis by improving data interpretation, accuracy, and handling of highly overlapping signals. In this review, classical and chemometric approaches, which remain the most established and widely validated tools multicomponent pharmaceutical analysis, are discussed in depth, while AI-assisted methods, representing an important but comparatively less mature area of adoption in pharmaceutical spectrophotometry, are critically examined with attention to their current scope, limitations, and validation requirements.