Communications of the ACM
Military Algorithm Can Predict Illness 48 Hours Before Symptoms Show
U.S. military researchers collaborated with a health IT company to develop an algorithm that can predict whether if a service member is falling ill up to 48 hours before any symptoms appear.
Credit: Dwayne Snader/U.S. Army
Researchers at the Defense Threat Reduction Agency (DTRA) and the Defense Innovation Unit, both within the U.S. Department of Defense, along with health IT company Royal Philips have developed a predictive algorithm that can determine if a service member is falling ill up to 48 hours before they start to show any symptoms.
The team used 165 distinct biomarkers across 41,000 cases to create the Rapid Analysis of Threat Exposure (RATE) algorithm, which can predict infection 48 hours before clinical suspicion, with better than 85% accuracy.
The algorithm relies on two data models: one using lab results and the other only using vitals obtained through non-invasive means.
Said DTRA researcher Edward Argenta, "We think this first, initial capability is really exciting, and it does open up the door for us to continue resourcing it and continue funding the research and development of it to see how far we can go."
From NextGov.com
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found