Artificial intelligence applications for strengthening global food safety systems

Abstract This review examines the application of artificial intelligence (AI) technologies in addressing limitations of traditional food safety systems in globalized supply chains. We analyzed current AI implementations including machine learning for pathogen detection, blockchain integration for supply chain traceability, and predictive analytics for outbreak forecasting. Key findings show AI-enabled biosensor networks achieve > 90% sensitivity for Salmonella and Listeria detection in controlled settings, while predictive models demonstrate up to 89% precision for E. coli contamination forecasting. However, significant equity challenges exist, with 78% of low- and middle-income countries lacking necessary cloud infrastructure for AI deployment. The review identifies critical gaps in data sovereignty, algorithmic bias, and implementation costs that may exacerbate global health disparities. Recommendations include developing open-access datasets, establishing ethical AI governance frameworks, and creating targeted capacity-building initiatives to ensure equitable access to AI-enhanced food safety technologies across diverse economic contexts.