The Food and Drug Administration reports that the third phase of its artificial intelligence imported seafood pilot program was launched Aug. 15 and is scheduled to run through late fiscal year 2023. The first phase of the pilot, an analytical proof of concept launched in 2019, demonstrated the potential for AI to assist the FDA in ensuring the security and safety of imported seafood, while the second phase was designed to integrate machine learning into existing import data systems to inform decisions about sampling by entry reviewers while gaining more experience with training of the ML model.
According to the FDA, the third phase will help determine the feasibility of deploying in-house AI/ML models using the intelligence that the agency extracts from data collected reviewing millions of import entries per year. For example, there have been enhancements made that determine how ML algorithms can best complement field operations and improve the FDA’s ability to identify products posing a threat quickly and efficiently. Additionally, the FDA is looking at its seafood project portfolio to expand the use of ML to better protect consumers.
The FDA notes that it has incorporated data from a related shrimp pilot into the third phase of the AI imported seafood pilot program in an effort to achieve a more robust and larger targeted sample. In the shrimp pilot, the FDA has begun to focus on areas of increased risk, such as shrimp contaminated by aquaculture drugs, for foreign inspections. This includes increased importer inspections, higher rates of sampling and examination, and use of non-traditional tools (such as third-party audits) specific to this commodity.
Copyright © 2023 Sandler, Travis & Rosenberg, P.A.; WorldTrade Interactive, Inc. All rights reserved.