UK Health Agency to Use AI for Tracking Foodborne Illness Outbreaks

UKHSA is testing AI models to monitor online restaurant reviews for mentions of symptoms such as vomiting, diarrhea, and abdominal pain.

The UK Health Security Agency (UKHSA) has announced plans to use artificial intelligence (AI) to enhance the tracking and investigation of foodborne illness outbreaks. 

The initiative involves analyzing data from online restaurant reviews to identify early signs of gastrointestinal illness, which could help prevent widespread outbreaks and improve public health response.

Foodborne illnesses, typically characterized by symptoms such as vomiting, diarrhea, and stomach cramps, are a significant public health challenge in the UK. 

Millions of cases occur each year, with many going undiagnosed, making it difficult for health authorities to track the full scale of the problem. According to the Food Standards Agency (FSA), norovirus is one of the most common causes of foodborne illness in the UK, often linked to contaminated food like oysters, soft fruits, and leafy greens.

Professor Paul Hunter, Professor in Medicine at the University of East Anglia, highlighted that norovirus spreads rapidly, particularly in hospitals, putting pressure on the National Health Service (NHS). 

In February, the NHS reported record-high levels of norovirus infections, with health officials describing its spread as moving like "wildfire" through healthcare facilities.

AI-Powered Approach to Disease Detection

To address this challenge, UKHSA is testing AI models to monitor online restaurant reviews for mentions of symptoms such as vomiting, diarrhea, and abdominal pain. 

The AI system is designed to detect patterns in language and specific references to food items that could indicate an outbreak.

Professor Steven Riley, Chief Data Officer at UKHSA, explained the importance of early detection, "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 from becoming sick."

The study involved evaluating various AI models to determine how accurately they could identify signs of foodborne illness. 

The AI system scans large volumes of online reviews, searching for terms linked to gastrointestinal issues and cross-referencing them with the types of food mentioned. By identifying clusters of reports, health authorities could intervene more quickly to contain potential outbreaks.

Building on Existing Research

UKHSA's AI project builds on previous research by expanding the list of terms and language patterns used for detection. This could provide deeper insights into the specific foods and ingredients linked to outbreaks, improving the accuracy of the tracking system.

The agency cautioned that further research is required before the system becomes routine for public health surveillance. Prof Riley noted that while initial findings are promising, the AI models must be rigorously tested and validated to ensure reliability in real-world settings.

"Further work is needed before we adopt these methods into our routine approach to tackling foodborne illness outbreaks," he said.

Expanding AI Use in Public Health

UKHSA has also outlined broader plans to integrate AI into other areas of public health. One key focus is using AI to analyze patient experiences and improve public health guidance.

Traditionally, gathering insights from patients has been time-consuming and costly. AI-powered large language models (LLMs) are now helping UKHSA process large volumes of patient feedback more quickly and accurately. Dr Nick Watkins, Deputy Director of Data Science and Geospatial and Chief Data Scientist at UKHSA, explained:

"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."

LLMs are also being tested to ensure consistency in public health guidance during emergencies. Early tests have shown that AI could improve accuracy in health messaging by more than 90%, helping to avoid confusion and ensure the public receives clear, reliable advice.

Stay tuned for more such updates on Digital Health News.