- Tech Improves Detection of Food-Borne Pathogens
- A combination of high-tech lasers and sophisticated computing is allowing machines to automatically detect bacteria in food samples. The system can even identify previously unknown pathogens.Current approaches to food testing lack the technology and the efficiency to screen large samples for bacteria. Even with the FDA's many regulations, food-borne pathogens kill thousands of people in the United States each year—hundreds of thousands more are sickened.
Salmonella bacteria are one of the more common causes of food-borne illness.Deadly bacteria like E. coli lurk unseen in everything from eggs to spinach to peanut butter. These bacteria can cause violent illnesses and even death. A new bacteria detection method from scientists at the School of Science at Indiana University-Purdue University Indianapolis (IUPUI) and the Bindley Bioscience Center at Purdue University could improve the rapid detection of pathogens—thereby saving lives and improving our food supply.
The scientists have developed an innovative, automated way to detect and classify the dangerous bacteria found in food. Their sophisticated statistical approach enables computers to improve their abilities to test samples. With complex new formulas, technological progress called "machine-learning" occurs: Computers can identify even unknown classes of food pathogens. The computers are also highly capable of detecting known pathogens, such as listeria, staphylococcus, salmonella, vibrio and E. coli.
"The sheer number of existing bacterial pathogens and their high mutation rate make it extremely difficult to automate their detection," says M. Murat Dundar, Ph.D., assistant professor of computer science in the School of Science at IUPUI, and the leader of the research team. "There are thousands of different bacteria subtypes, and you can't collect enough subsets to add to a computer's memory so it can identify them when it sees them in the future. Unless we enable our equipment to modify detection and identification based on what it has already seen, we may miss discovering isolated or even major outbreaks."
The team of researchers has created a prototype laser scanner. The light-scattering sensor is used by the formula-trained computers to detect and classify bacteria—even types not specifically programmed into the machines.
"We are very excited because this new machine-learning approach is a major step toward a fully automated identification of known and emerging pathogens in real time, hopefully circumventing full-blown, food-borne illness outbreaks in the near future," Dundar explains. "Ultimately we would like to see this deployed to tens of centers as part of a national bio-warning system."
"Our work is not based on any particular property of light scattering detection, and therefore it can potentially be applied to other label-free techniques for classification of pathogenic bacteria, such as various forms of vibrational spectroscopy," states Bartek Rajwa, Ph.D., the Purdue research leader.
The researchers hope that their novel approach could be applied to the analysis of blood and other biological samples. Their research, which was funded by the National Institute of Allergy and Infectious Disease, appears in the October issue of the journal "Statistical Analysis and Data Mining." Other members of the team include Ferit Akova, a graduate student at the School of Science at IUPUI, and Purdue University researchers V. Jo Davisson, E. Daniel Hirleman, Arun K. Bhunia and J. Paul Robinson.