Artificial intelligence in veterinary diagnostic microbiology: Applications, opportunities and challenges in the one health era

Artificial intelligence (AI) has emerged as a transformative tool in veterinary diagnostic microbiology, enabling the analysis of complex datasets generated by modern laboratory technologies. This study aimed to review current applications of AI in veterinary microbiology, with emphasis on its relevance within the One Health framework. A narrative literature review was conducted using PubMed, Scopus, Web of Science, and Google Scholar. Studies addressing machine learning and deep learning applications in microbial identification, antimicrobial resistance detection, genomic analysis, and infectious disease surveillance were included following structured screening and eligibility criteria. The findings indicate that AI is increasingly applied across multiple domains of veterinary diagnostic microbiology. Key applications include automated microbial identification using MALDI-TOF mass spectrometry, image-based diagnostics through deep learning, genomic and metagenomic analysis for pathogen detection, and prediction of antimicrobial resistance. AI has also demonstrated value in clinical decision support and in integrating microbiological, epidemiological, and environmental data for disease surveillance within the One Health context.However, important limitations persist, including limited availability of standardized veterinary datasets, heterogeneity across species and diagnostic systems, and challenges related to model interpretability, infrastructure, and regulatory frameworks.In conclusion, AI represents a promising tool to enhance diagnostic accuracy, optimize laboratory workflows, and strengthen disease surveillance. Addressing current limitations will be essential to support its effective and responsible implementation in veterinary microbiology.