IBM announced yesterday that it developed a “first-of-a-kind” system that can predict the sources of contaminated foods and facilitate the investigation in outbreaks of food-borne illnesses. Through using “novel” computer algorithms, visualisation, and statistical techniques, the tech giant believes that its system can help grocers and distributors, as well as public health officials.

“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,” said James Kaufman, Manager of Public Health Research for IBM Research, “We are working with our public health clients and with retailers in the U.S. to scale this research prototype and begin focusing on the 1.7B supermarket items sold each week in the United States.”

Food-borne disease outbreaks in the United States burdens the country, economically, by nearly $80 billion; it is the cause of 128,000 hospitalizations, and 3,000 deaths each year. To combat this, IBM says that the petabytes of retail sales data that has never been used could greatly accelerate the identification of contaminated food.

IBM said that after looking at as few as 10 cases it could make informed predictions about the source of a food poisoning outbreak. Its confidence that the culprit food will be in its list of suspect foods at that stage in an outbreak is about 95 percent, reported VentureBeat. To demonstrate the system’s effectiveness, IBM scientists worked with the Department of Biological Safety of the German Federal Institute for Risk Assessment. In this demonstration, the scientists simulated 60,000 outbreaks of food-borne disease across 600 products using real-world food sales data from Germany.

As VentureBeat note, “when a food-borne illness such as E.coli bacteria infections is detected, identifying the culprit food is essential to minimizing the spread of the illness”…“but the time required to detect a problem may be days or weeks, straining the public health system. In 2011, an E.coli outbreak in Germany made more than 4,000 people sick and left 50 dead. In that case, it took two months to track down the source of the contamination, and German retailers suffered losses of more than 150 million euros, or $205 million.”

The recent announcement from IBM is just one example of how the company is using big data and predicative analytics in the public domain. It has already used its algorithms and analytic capabilities to solve problems with irrigation issues for farmers as well as malaria outbreaks.

“People are getting sick, and commercial retailers need to know what is coming from where,” Kaufman told VentureBeat in an interview.

Read more here

Interested in more content like this? Sign up to our newsletter, and you wont miss a thing!


(Image Credit: Ryan Kitko)

Previous post

The History of BI: The 1980's and 90's

Next post

Survey Shows Cloud Computing Has Grown by 61% in 4 Years