A Review on Application of Artificial Intelligence and Machine Learning in Liquid Chromatography-Tandem Mass Spectrometry Method Development and Validation of Anti-cancer Agents by Analytical Quality by Design

Abstract

The development of robust and reliable analytical methods is essential for the quality assessment of anticancer drugs. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) has become a preferred analytical
technique due to its high sensitivity, selectivity, and capability for accurate quantitative analysis. However, conventional method development approaches often rely on trial-and-error experimentation, resulting in
increased time, cost, and variability. Analytical quality by design (AQbD) has emerged as a systematic and science-based approach that enhances method understanding and robustness throughout the analytical lifecycle.
AQbD involves the establishment of an analytical target profile, identification of critical analytical attributes and critical method parameters, risk assessment, and optimization using design of experiments. These elements facilitate the development of reliable LC-MS/MS methods with improved performance, reproducibility, and regulatory compliance. The establishment of a method operable design region and appropriate control strategies further ensures consistent analytical performance during routine application. This review provides a
comprehensive overview of AQbD-based stability-indicating LC-MS/MS method development and validation for anticancer drugs. Key aspects, including risk assessment, experimental design, optimization strategies, design space establishment, method validation, and lifecycle management are discussed. The review also highlights the emerging role of artificial intelligence (AI) and machine learning in chromatographic optimization, predictive modeling, and analytical data interpretation. The integration of AQbD, LC-MS/MS, and AI offers a modern framework for developing efficient, robust, and regulatory-compliant analytical methods. These advancements are expected to improve analytical efficiency, enhance method reliability, and support future innovations in pharmaceutical analysis.