The globalization of food systems has increased the risk of foodborne pathogens like Salmonella and Listeria, and antimicrobial resistance (AMR). Traditional methods are labor-intensive and low-throughput, and relying on individual machine learning models limits predictive robustness. A systematic review of 13 studies using ML algorithms showed predictive accuracies up to 99% and AUROC scores above 0.90. However, limitations like small sample sizes and inconsistent metadata hinder real-world implementation.
Machine learning-based predictive modeling of foodborne pathogens and antimicrobial resistance in food microbiomes using omics techniques: A systematic review
Subscribe to
disAMR Matters
Receive newly released thought leadership articles and news in your inbox twice a month.