IBM Research has devised a way to use big data and analytics to identify potential sources of contamination in foods.
Researchers at IBM's Almaden research center in San Jose, Calif., found that analyzing retail scanner data from grocery stores in areas where there are confirmed cases of foodborne illnesses can speed up investigations and narrow down sources of contamination.
The Centers for Disease Control and Prevention (CDC) said foodborne illnesses such as salmonella, E. coli and norovirus infections affect more than one out of six Americans each year.
"In the US alone, the Centers for Disease Control and Prevention estimates that each year 76 million people get sick, more than 300,000 are hospitalized, and 5,000 die as a result of foodborne illnesses," IBM's researchers said in a paper on their findings.
IBM implemented a likelihood-based framework to study how such spatial data can be used to accelerate an investigation during the early stages of an outbreak.
"Our analysis shows that after receiving as few as 10 laboratory confirmed case reports it is possible to narrow the investigation to approximately 12 suspect products with the contaminated product included in this subset 90 percent of the time for approximately 80 percent of food products studied," the paper said.
Using their framework, IBM researchers demonstrated they could get down to the 12 suspected food products in a matter of hours, whereas a typical investigation can take weeks to months.
"When there's an outbreak of foodborne illness, the biggest challenge facing public health officials is the speed at which they can identify the contaminated food source and alert the public," said Kun Hu, a public health research scientist at IBM's Almaden research facility, in a statement. "While traditional methods like interviews and surveys are still necessary, analyzing big data from retail grocery scanners can significantly narrow down the list of contaminants in hours for further lab testing. Our study shows that big data and analytics can profoundly reduce investigation time and human error and have a huge impact on public health."
Meanwhile, also at IBM Research – Almaden, IBM and Stanford University researchers collaborated on a project to develop an inexpensive way to create plant-based biodegradable plastics. Although biodegradable forks and spoons already exist, IBM has come up with a chemical catalyst that can be used to create cheaper biodegradable plastics from plants such as palm trees and beets. The new inexpensive plastics can be used for making common consumer plasticware—not only eating utensils, but medical devices as well, IBM said.
"What's exciting about this discovery is that we now have a cheaper way to convert plants into common consumer plastics that decompose over time, providing an alternative to recycling plastics," said Gavin O. Jones, a computational chemist at IBM Research – Almaden, in a statement. "Making biodegradable plastics mainstream means less impact on our solid waste systems."
Jones explained that the current method of using plants to create biodegradable plastics involves heavy metals that do not fully decompose over time. With the new chemical catalyst identified by IBM, the use of heavy metals is not required.
IBM put its cognitive computing technology to use in achieving this discovery.
"In this study, we used a combination of predictive modeling and experimental lab work to make the discovery," said Xiangyi Zhang, a chemistry graduate student at Stanford University, in a statement. "This tag-team approach takes a lot of the guess work out of the process and helps us accelerate the materials discovery process."
IBM published its study in the Nature Chemistry journal. The National Science Foundation took part in funding IBM's collaborative effort with Stanford, the company said.
IBM announced these two innovations as part of its thirtieth anniversary celebration of the IBM Research – Almaden facility. IBM said the Almaden lab has spawned a host of technological innovations, including many that are critical to computing and technology today, including the hard disk drive, the relational database, DVD and Blu-ray encryption technology, and brain-inspired supercomputing chips.
"What sets us aside from other research operations in Silicon Valley is our novel interdisciplinary approach to innovation," said Dr. Jeff Welser, vice president and lab director at IBM Research – Almaden, in a statement. "Our most profound knowledge comes from non-traditional combinations of computer scientists, chemists, biologists, mathematicians, medical doctors or even artists from within our own lab ..."