Emerging technologies for antimicrobial resistance detection in clinical microbiology

from conventional testing to artificial intelligence

Resumen

Objective: to critically evaluate emerging technologies for antimicrobial resistance (AMR) detection in clinical microbiology, highlighting their applications, advantages, and limitations. Methodology: a systematic literature review was conducted following PRISMA guidelines. Searches were performed in the PubMed/MEDLINE and Scopus databases using terms related to antimicrobial resistance and diagnostic methods. Results: a total of 4,131 records were identified, and 38 studies published between 2020 and 2026 met the eligibility criteria and were included in the final review. The selected studies were categorized into four major groups: molecular diagnostics, genomic technologies, rapid phenotypic antimicrobial susceptibility testing (AST), and computational approaches incorporating artificial intelligence. The reviewed evidence demonstrated substantial advances in reducing diagnostic time, improving pathogen and resistance gene detection, and supporting earlier optimization of antimicrobial therapy. However, challenges related to standardization, multicenter clinical validation, result interpretation, operational costs, and workflow integration continue to limit widespread implementation. Conclusion: the future of AMR diagnostics will depend on the integration of molecular, phenotypic, genomic, and computational approaches capable of providing faster, more accurate, and clinically relevant information to support patient management and antimicrobial stewardship programs.