The UK Health Security Agency (UKHSA) is exploring how the use of AI could play a role in helping scientists to detect and investigate foodborne illness outbreaks.
In a new study, experts at the agency assessed different types of AI for their ability to detect and classify text in online restaurant reviews.
The organisation said this could one day be used to identify and potentially target investigations into foodborne illness outbreaks.
The UKHSA said that foodborne gastrointestinal (GI) illness, which usually presents as vomiting and diarrhoea, causes millions of people to become unwell every year. However, most of these cases are not formally diagnosed.
The researchers looked at a range of large language models and investigated their ability to trawl thousands of online reviews for information about symptoms which might relate to GI illness including diarrhoea, vomiting and abdominal pain, as well as different food types people report eating.
Over 3,000 reviews were manually annotated by epidemiologists after being collected and filtered.
The UKHSA believes that gathering information in this way could become routine, providing more information on rates of GI illness which are not captured by current systems as well as vital clues around possible sources and causes in outbreaks.
The study also highlighted challenges around this approach which would need to be overcome such as access to real-time data, variations in spelling and the use of slang to describe symptoms.
“Using AI in this way could soon help us identify the likely source of more foodborne illness outbreaks, in combination with traditional epidemiological methods, to prevent more people becoming sick,” said professor Steven Riley, chief data officer at UKHSA. “Further work is needed before we adopt these methods into our routine approach to tackling foodborne illness outbreaks.”
