Sign In

Communications of the ACM

ACM TechNews

Using Biomimicry to Detect Outbreaks Faster


The researchers are working to improve the U.S. biosurviellance system, which alerts authorities to disease outbreaks.

Sandia National Laboratories computer scientists Pat Finley (left) and Drew Levin (center), and University of New Mexico professor Melanie Moses (right) have taken inspiration from the immune system to improve how the U.S. detects emerging outbreaks.

Credit: Randy Montoya

Researchers at Sandia National Laboratories, the University of New Mexico (UNM), and the U.S. Centers for Disease Control and Prevention (CDC) have been working to improve the U.S. biosurviellance system, which alerts authorities to disease outbreaks.

Sandia's Pat Finley and Drew Levin have been working with collaborators at UNM and CDC to produce synthetic, mathematical "T-cells" that track multiple factors simultaneously, including the number of clinic visits, day of the year, and intake temperature. Levin ran the synthetic T-cell algorithms against past data gathered by the CDC and New Mexico Department of Health, comparing the algorithms and choosing the most accurate.

The researchers also devised a deep-learning algorithm for deciphering chief complaints.

Said Finley, "We are working closely with the CDC to test a number of our deep-learning approaches on a subset of the national data flow."

From Sandia Labs News
View Full Article

 

Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


 

No entries found