Identifying food safety risks with a novel digitally-driven food safety early warning tool – A retrospective study on the pesticide ethylene oxide
Sina Röhrs, Kornél Nagy, Martin Kreutzer, Richard H. Stadler, Sascha Rohn, Yvonne Pfeifer
Abstract
Foodborne diseases present a major global health challenge, with 600 million annual cases and 420,000 deaths worldwide in 2023 reported by the World Health Organization , underscoring the critical need for early risk detection and swift measures. Novel solutions for early risk detection in food are emerging due to artificial intelligence-based data models. By applying diverse algorithms and ontologies in data processing, the continually expanding amount of available data can be harnessed in a precise manner. To assess the efficacy of such technologies in early risk detection, we evaluated whether the risk to exceed a legal limit for ethylene oxide – specifically in sesame seeds – could have been identified sooner with the assistance of a commercially available Artificial Intelligence (AI)-based platform. The non-compliance of sesame seeds led to various product recalls in the year 2020. The result of this retrospective case study shows that the first indirect indications of the issue started to emerge from the year 2018 with initial Rapid Alert System for Food and Feed (RASFF) notification of ethylene oxide limit value exceedances in black pepper powder. Based on these promising findings, the subsequent challenge is to develop a methodology for systematically categorizing and evaluating similar risks in the light of the exponentially growing volume of accessible data. • A new platform was tested in a retrospective study on the “ethylene oxide issue”. • The tool covers contaminant regulations and text is translated into English. • An underlying ontology helps to recognize food safety issues via horizon scanning. • First sign of “ethylene oxide issue” could have been detected 2.5+ years earlier.