Artificial intelligence is set to transform how health officials track illness outbreaks. The UK Health Security Agency (UKHSA) has announced it is exploring groundbreaking ways to use AI to detect and investigate outbreaks of foodborne illnesses – using data from online restaurant reviews.
The technology could transform how the agency spots illness outbreaks and prevent them from spreading.
Foodborne gastrointestinal illness – typically marked by vomiting, diarrhoea and stomach cramps – is a major public health threat in the UK, with millions affected each year.
According to the Food Standards Agency (FSA), norovirus is one of the most common causes of foodborne illness in the UK. It is a highly contagious virus that can spread by contaminated food, especially oysters, soft fruit and leafy greens, according to Professor Paul Hunter, Professor in Medicine at the University of East Anglia.
The NHS faced a “storm” of norovirus infections this winter as levels of the virus reached “all-time highs” in February. Health chiefs have warned that the virus spreads like “wildfire” through hospitals, putting intense pressure on the NHS.
The UKHSA warns that most cases of foodborne illness go undiagnosed, making it difficult to track the true scale of outbreaks. Now, scientists are using AI to dig through thousands of online restaurant reviews to find key symptoms that could indicate an outbreak of illness.
In a new study, UKHSA experts assessed various AI models to see how well they can scan reviews for mentions of symptoms like vomiting, diarrhoea, and abdominal pain, as well as the types of food that might be the culprit.
By doing this, the UKHSA could one day quickly identify early warning signs of foodborne illness outbreaks, before they become a widespread problem.
Professor Steven Riley, Chief Data Officer at UKHSA said: “We are constantly looking for new and effective ways to enhance our disease surveillance.
“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.”
The study goes beyond previous research by looking at a more detailed list of terms and language patterns that could offer deeper insights into the specific foods and ingredients tied to outbreaks, the UKHSA says.
However, more research is needed before this AI-powered approach becomes a regular part of health practices. If successful, this system could help fight outbreaks, save lives and improve public health safety.
Prof Riley added: “Further work is needed before we adopt these methods into our routine approach to tackling foodborne illness outbreaks.”
The UKHSA has announced plans to adopt AI in other aspects of public health: to understand patient experiences and to make public health guidance more consistent.
Gathering insights from patients is critical, but the agency says it has always been slow and expensive. However, AI-powered large language models (LLMs) are helping the UKHSA rapidly sift through thousands of responses.
Similarly, the agency is using LLMs to ensure consistent guidance in health emergencies. By scanning for inconsistencies in hundreds of guidance documents, early testing shows AI could ensure more than 90 per cent accuracy in health messaging.
Dr Nick Watkins, Deputy Director Data Science & Geospatial and Chief Data Scientist at UKHSA, said: “These projects demonstrate how, alongside human expertise, AI can enhance public health protection.
“As we continue to develop and refine these systems, we maintain a careful balance between embracing innovation and ensuring robust validation of AI outputs. This approach helps us harness AI’s potential while maintaining the high standards expected of a national public health agency.”
Read more at: https://www.manchestereveningnews.co.uk/
