The U.S. Defense Threat Reduction Agency (DTRA) wants to know if U.S. service members are falling ill—at least 48 hours before the actually become ill. How could this be possible? DTRA has hooked up with the U.S. Defense Innovation Unit to leverage its purchasing ability outside of Federal Acquisition Regulations to partner with Royal Philips(PHG) to design the predictive algorithm.
Predicting Illness with 85%+ Accuracy
Philips will leverage its massive data sets to build a unique algorithm with the U.S. Defense Department. The Philips team capitalized on 165 distinct biomarkers across 41,000 cases to design a “Rapid Analysis of Threat Exposure” (RATE) algorithm which Philips declares can “predict infection 48 hours before clinical suspicion” with north of 85% accuracy.
To compare this performs is equal to a prostate cancer screening test.
Royal Philips Comments
Joe Frassica, chief medical officer and head of research for Philips North America reports “By coupling large-scale data with our experience in AI and remote patient monitoring with DTRA’s drive for innovation, we were able to develop a highly predictive early-warning algorithm based on non-invasively collected biomarkers.”
Intellectual Property Rights to U.S. Military
The U.S. military now maintains the intellectual property rights to this powerful new algorithm. Now DTRA can further develop the technology applying to service members—from back-office to the battlefield. The effort is led by Edward Argenta, science and technology manager for DTRA’s Joint Science and Technology Office. Aside from military benefits, imagine some of the commercialization scenarios possible now. How many companies worldwide could benefit if they were able to predict who would be absent and hence adjust and reallocate staff.
Edward Argenta, Science and Technology Manager for DTRA’s Joint Science and Technology Office