IBM develops new system to improve food safety

US-based technology firm IBM has developed a new system, which will be used to identify contaminated food sources and accelerate the investigation of food-borne disease outbreaks.

Said to help food retailers, distributors and public health officials, the system will use information on the date and location of billions of supermarket food items by using novel algorithms, visualisation and statistical techniques to identify potentially "guilty" products within as few as ten outbreak case reports.

The IBM research team has built a system that identifies, contextualises and displays data from multiple sources to reduce the time to identify the most likely contaminated sources by a factor of days or weeks.

The new system incorporates petabytes of retail data with public health case reports to identify contaminated food sources, shorten intervention times and limit the spread of disease outbreaks.

The algorithm is said to effectively learn from every new report and re-calculate the probability of each food that might be causing the illness.

IBM scientists worked with the Department of Biological Safety of the German Federal Institute for Risk Assessment, to demonstrate the system’s effectiveness.

The scientists simulated 60,000 outbreaks of food-borne disease across 600 products by using real-world food sales data from Germany.

IBM Research public health research manager James Kaufman said: "Predictive analytics based on location, content and context are driving our ability to quickly discover hidden patterns and relationships from diverse public health and retail data.

"We are working with our public health clients and with retailers in the US to scale this research prototype and begin focusing on the 1.7 billion supermarket items sold each week in the US."