Artificial Intelligence Enhances Microbial Safety in Aquatic Products Supply Chain

Researchers from Zhejiang University, in Jiaxing, Zhejiang, People's Republic of China, have published a comprehensive review on the use of artificial intelligence in enhancing microbial safety in aquatic products. The study points out that aquatic products are a critical source of dietary protein, but their expanded global trade has increased the risk of microbial contamination. This review examines the role of traceability technologies in improving microbial safety and proposes the integration of genome sequencing, artificial intelligence, and digital monitoring systems within the traceability framework. The evaluation considers specific performance indicators such as detection sensitivity, source attribution resolution, and time-to-result in outbreak scenarios.

Key Takeaways:

• The study highlights the significance of aquatic products as a source of dietary protein, particularly in regions with abundant marine resources.
• The expansion of global trade has increased the risk of microbial contamination in aquatic products, leading to serious public health concerns and significant economic losses.
• The review systematically examines the role of traceability technologies, emphasizing the integration of genome sequencing, artificial intelligence, and digital monitoring systems within the traceability framework.
• Specific performance indicators considered in the evaluation include detection sensitivity, source attribution resolution, and time-to-result in outbreak scenarios.
• The study introduces the application of artificial intelligence in integrating WGS-derived genomic fingerprints for rapid and highly sensitive microbial source prediction.
• The research emphasizes the need for future efforts to develop cost-effective and user-friendly traceability tools, promoting global standardization, strengthening regulatory frameworks, and increasing public engagement.
• Innovative approaches involving big data analytics and AI hold great promise for advancing microbial safety and ensuring the integrity of aquatic product supply chains.

Statistics:

• 20 core-genome SNP differences or unique wgMLST allelic profiles are considered as the minimum limit for source attribution resolution.
• 20 core-genome SNP differences or unique wgMLST allelic profiles can accurately identify corresponding microbial sources.
• WGS-derived genomic fingerprints transformed into machine learning models for rapid and highly sensitive microbial source prediction.
• Artificial intelligence enhances detection speed and accuracy, contributing to improved food safety management.
• 40% of aquatic products are traded internationally, making them a crucial aspect of global food safety.

Sources:

• Tracing microbial hazards in the aquatic supply chain: challenges, technologies, and future directions. Frontiers in Nutrition, 2025,12. (Frontiers in Nutrition - http://www.frontiersin.org/nutrition).
• Jiayi Zhang, Future Food Laboratory, Innovation Center of Yangtze River Delta, Zhejiang University, Jiaxing, Zhejiang, People's Republic of China.
• Tian Ding, Juhee Ahn, Zhaohuan Zhang, Xinyu Liao, Zhejiang University, Jiaxing, Zhejiang, People's Republic of China.