FDA is using AI to screen imported seafood

The project is just a pilot – but the initial results look very promising

Chuck Martin

September 15, 2020

2 Min Read

The project is just a pilot – but the initial results look very impressive

The US Food and Drug Administration (FDA) plans to leverage AI to screen imported foods that could pose a public health threat.

The agency has trained a machine learning modelusing years of historical data on seafood shipments that had been refused entry or required additional examination.

Now, it is being applied in the field, in a pilot focusing on imported seafood.

This is the second phase of the project, following a pilot program started in 2019 aimed at learning the benefits of machine learning in the FDA’s import-screening process.

Better fish through AI

The project is part of two FDA initiatives: New Era of Smarter Food Safety, and the Technology Modernization Action Plan (TMAP).

“The ultimate goal is to see if AI can improve our ability to quickly and efficiently identify products that may pose a threat to public health,” FDA Commissioner Stephen Hahn said in a blog post.

About 94 percent of the seafood consumed by Americans each year is imported, according to Hahn.

“We embarked on the proof of concept by training the ML screening tool, using years of retrospective data from past seafood shipments that were refused entry or subjected to additional scrutiny, such as a field exam, label exam, or laboratory analysis of a sample,” Hahn said.

“This gave us an idea of how much our surveillance efforts might be improved using these technologies. The proof of concept demonstrated that AI/ML could almost triple the likelihood that we will identify a shipment containing products of public health concern.”

The FDA said it screened nearly 15 million food shipments offered for import into the US in 2019.

“The FDA collects tens of millions of data points on imports alone, and we screen all the data associated with every shipment of food against the information in our internal databases,” Hahn said

“One of the major goals of our pilot is to assess the ability of AI/ML to more quickly, efficiently, and comprehensively take advantage of all the data and information residing in our systems.”

Stay Ahead of the Curve
Get the latest news, insights and real-world applications from the AI Business newsletter

You May Also Like