News

 Artificial Intelligence (AI) is increasingly applied in food safety management, offering new capabilities in data analysis, predictive modelling, and risk-based decision-making.

A review of the literature identifies three primary areas of application: scientific advice, inspection and border control, and operational activities of food safety competent authorities.

Five country examples with the real-world use cases illustrate diverse uses of AI tools, including pathogen detection, import sampling prioritization, and language models for regulatory data processing.

Regulatory frameworks, as well as voluntary governance, addressing AI in the public sector are emerging worldwide. National and international initiatives often highlight the importance of data governance, transparency, ethical considerations, and human oversight. Challenges such as biased data, explainability, and data governance gaps appear across different contexts, along with potential risks from deploying AI systems prematurely. Access to high-quality, interoperable data and collaboration among stakeholders can support effective integration of AI technologies.

AI readiness often depends on understanding specific problems to be addressed, current capacities, and the quality of available data. Human oversight and continuous evaluation contribute to maintaining trust in AI systems.

Collaborative efforts involving academia, the private sector, and international organizations help build shared knowledge and resources for AI development in food safety. Overall, AI presents opportunities to enhance resilience, efficiency, and responsiveness in food safety systems. Careful consideration of governance, data management, and multi-stakeholder cooperation can shape AI’s contribution to achieving sustainable and equitable outcomes in agrifood systems.

Read full report here: https://openknowledge.fao.org/handle/20.500.14283/cd7242en

There are a large number of both commercial and in-house-written digital tools that attempt to classify and predict food safety risks based upon historic records in the EU Rapid Alert Service in Food and Feeds (RASFF) database.  With all such tools, it is important to remember that RASFF records are not a representative sample of either tests or results, and were never intended as a source of trends; the purpose of RASFF is rather to share specific individual alerts which may require regulatory action  on a cross-border basis.  Official tests are highly targeted, and often informed by previous RASFF alerts, so more alerts about a specific issue drives more official tests which drives more alerts (i.e. a feedback mechanism).  Also, RASFF only records the “positive” results, so there is no denominator; no indication of the number of “negative” results or the % incidence of an issue.  And finally, RASFF only records issues with a food safety concern so most food authenticity test results are excluded.

Despite these caveats, RASFF is still one of the most extensive and systematic public databases of food safety incidents and is likely to form the basis of many AI risk-prediction systems for years to come.

This paper (purchase required) evaluated the effectiveness of the Machine Learning models that sit behind such systems. The authors report that transformer-based models significantly outperform traditional machine learning methods, with RoBERTa achieving the highest classification accuracy. SHAP analysis highlights key hazards salmonella, aflatoxins, listeria and sulphites as primary factors in serious risk classification, while procedural attributes like certification status and temperature control are less impactful.

They conclude that despite improvements in accuracy, computational efficiency and scalability remain challenges for real-world deployment of AI risk-scoring and prediction systems.

Photo by Clarisse Croset on Unsplash

The Joint Research Centre (JRC) of the European Commission have published a report that includes an overview of food fraud information sharing networks and incident data held around the world.  (including both the Food Industry Intelligence Network, Fiin, and the 2022 Defra report FA0175 into food fraud drivers and mitigation tools).

The report recommends the funding of a new predictive analytics model to try and prioritise future fraud risks based on historic patterns of reported incidents.  This would be predicated on improved data sharing between different countries and between industry and governments.  The report recommends a public-private partnership model to develop the concept.