Artificial Intelligence Can Now Predict Illness 48 Hours Before Symptoms

Sue Byamba
By Sue Byamba
October 25, 2019Science & Techshare
Artificial Intelligence Can Now Predict Illness 48 Hours Before Symptoms
The John Hopkins Hospital is seen at a area near the downtown of Baltimore, Maryland, on Nov. 4, 2015. (REUTERS/Carlos Barria/File Photo)

The project lead says that future troops may be deployed with watches or chest straps that could predict when they will get sick and how long it would take to recover.

When U.S. Service members get ill at the last minute, it could cause serious consequences in regards to executing critical duties.

To get ahead of the issues, the Defense Threat Reduction Agency (DTRA), leading health technology company Royal Phillips and the Defense Innovation Unit (DIU), launched a project to develop a technology that could predict whether a service member is getting sick 48 hours in advance.

The project was launched 18 months ago and announced its completion on Oct 22.

“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,” Joe Frassica, chief medical officer and head of research for Philips North America, said in the release.

Using 165 distinct biomarkers across 41,000 cases, the Phillips team created the Rapid Analysis of Threat Exposure (RATE) algorithm which is the “first large-scale empirical exploration of prediction of pre-symptomatic infection in humans.”

The algorithm uses two data models: lab results and non-invasive means. The non-invasive model uses biomarkers such as heart rate, a saturation of oxygen levels in the bloodstream, blood pressure, and temperature.

The DTRA told Netgov that they would only use the non-invasive means to develop the algorithm for clinical and military use further.

“The goal of my portfolio is to never prick or stick or take a sample out of you,” Edward Argenta, science and technology manager for DTRA’s Joint Science and Technology Office, told Nextgov. “If I can do everything remotely, digitally, from monitoring you with a wearable device that might sit on your body—like a watch-based one or a chest strap one—that’s where the portfolio has been focused on.”

While Philips holds onto its date, the military holds the intellectual property rights which would allow DTRA to develop further the program to work for all service members.

The solution procured through Philips is “the first step in that journey,” Argenta said. “At the end of the day, we do want to have it as a whole-forces, all-warfighter solution. But we started in a clinical setting to evaluate the state of the science and see if we could actually get there.”

Argenta told Nextgov that the program has another two to three years of testing in operational environments before deploying with forces.

The first field tests will be held at military hospitals and academies before being deployed in combat, according to Nextgov.

The technology could also be applied in a civilian scenario by helping to monitor hospital patients for infection before clinical symptoms arise.

ntd newsletter icon
Sign up for NTD Daily
What you need to know, summarized in one email.
Stay informed with accurate news you can trust.
By registering for the newsletter, you agree to the Privacy Policy.