Application of Artificial Intelligence and Molecular Docking in Early Detection of Antimicrobial Resistance: A Systematic Review

Abstract

Antimicrobial resistance (AMR) poses a growing global health threat, resulting in increased morbidity, mortality, and increased cost of health care. Traditional diagnostic methods for AMR, relying on phenotypic culture and susceptibility testing, are time-consuming and often fail to provide rapid insights necessary for effective treatment decisions. Computational approaches, particularly artificial intelligence (AI) and molecular docking, offer promising alternatives for early detection of resistance by analyzing genomic, proteomic, a paradigm shift by enabling rapid target identification, ligand screening, drug optimization and structural data. This systematic review examines recent advances in AI algorithms and molecular docking techniques applied to AMR detection, evaluates their predictive performances and discusses integration challenges into clinical workflows. Findings suggest that AI-driven models can accurately predict resistance patterns, while molecular docking provides mechanistic insights into drug-target interactions and resistance mutations. Hybrid AI-docking approaches demonstrate enhanced predictive capacity, offering potential for early intervention and personalized antimicrobial therapy. Future research should focus on multi-omics integration, standardization of data pipelines, and real-world validation.