Finding the source of foodborne outbreaks
When consumers get sick from eating contaminated food, finding the “true” food culprit can be a complicated task because it might be an ingredient that was incorporated into a variety of finished products. But discovering the problem may be easier now thanks to IBM. The high-tech giant has designed a system to help food retailers, distributors, and public health officials predict the most likely contaminated food sources and accelerate the investigation of foodborne disease outbreaks.
Using novel algorithms, visualization, and statistical techniques, the tool can use information on the date and location of billions of supermarket food items sold each week to quickly identify with high probability a set of potentially “guilty” products within as few as 10 outbreak case reports. The research was published in the peer-reviewed journal PLOS Computational Biology together with collaborators from Johns Hopkins University, Purdue University, and the German Federal Institute for Risk Assessment (BfR).
When a foodborne disease outbreak is detected, identifying the contaminated food quickly is vital to minimize the spread of illness and limit economic losses. However, the time required to detect it may range from days to weeks, creating extensive strain on the public health system. Surprisingly, the petabytes of retail sales data have never before been used to accelerate the identification of contaminated food. In fact, this data already exists as part of the inventory systems used by retailers and distributors today, which manage up to 30,000 food items at any given time with nearly 3,000 of them being perishable.
Recognizing this issue, IBM scientists built a system that automatically identifies, contextualizes, and displays data from multiple sources to help reduce the time to identify the mostly likely contaminated sources by a factor of days or weeks. It integrates pre-computed retail data with geocoded public health data to allow investigators to see the distribution of suspect foods and, selecting an area of the map, view public health case reports and lab reports from clinical encounters. The algorithm effectively learns from every new report and re-calculates the probability of each food that might be causing the illness.
“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 United States to scale this research prototype and begin focusing on the 1.7 billion supermarket items sold each week in the U.S.”
To demonstrate the system’s effectiveness, IBM scientists worked with the Dept. of Biological Safety of the BfR. In this demonstration, the scientists simulated 60,000 outbreaks of foodborne disease across 600 products using realworld food sales data from Germany.
Consumer perceptions of food technology
Despite the controversy of mandatory labeling of foods produced through biotechnology, a significant majority of consumers support the U.S. Food and Drug Administration’s (FDA) current labeling policy for foods produced using biotechnology, according to the 2014 International Food Information Council (IFIC) “Consumer Perceptions of Food Technology” Survey. Consistent with previous study years, nearly two-thirds (63%) of consumers support the FDA’s current labeling policy for foods produced using biotechnology, which calls for labeling only when biotechnology substantially changes the food’s nutritional content or composition, or when a potential safety issue (such as a food allergen) is identified. However, there is a slight increase in consumers indicating opposition to the policy (19%) compared to 2012 (14%).
More than seven in 10 consumers agree that modern agriculture (i.e., conventional farming using today’s modern tools and equipment) can be sustainable (74%), produce high-quality foods (72%), and produce nutritious foods (71%). More than two-thirds also agree that modern agriculture produces safe foods (68%). Slightly more than half agree that modern agriculture farms are still primarily family-run (52%), highlighting a lack of awareness of the family-run nature of most of today’s small- and large-scale farms.
Only one-quarter (26%) of consumers are willing to pay more for foods that fit their perception of sustainability, down from 33% in 2012. This number goes up when looking at Millennials: 43% would be willing to pay more for sustainable foods and beverages. However, two-thirds of consumers (66%) say it is important that the foods they purchase or consume are produced in a sustainable way, with sustainability being defined as “meeting long-term food needs by producing more food affordably with the same or fewer resources, in a way that is better for the environment and keeps food affordable and accessible for consumers.”
If you are working on or know of some cutting edge technology that you would like to be featured in this column, please send an email to [email protected].