DoD, Philips Use Artificial Intelligence to Monitor COVID-19

The US Defense Threat Reduction Agency (DTRA), the Defense Innovation Unit (DIU), and Philips have partnered to expand their artificial intelligence-based early warning system to monitor and contain COVID-19.

For more coronavirus updates, visit our resource page, updated twice daily by Xtelligent Healthcare Media.

The new system prototype will be an application of the Rapid Analysis of Threat Exposure (RATE) technology and part of DoD’s COVID-19 response. The accelerated research includes COVID-19 detection among a dozen different cohorts in clinical trials, using wearable technologies that can capture vital sign and biomarker information.

With the spread of COVID-19, the RATE project’s goal of facilitating faster diagnosis and treatment of infection is even more important. Through RATE, researchers discovered that exposure to infectious agents changes people’s physiology before they experience symptoms.

Identifying these changes early in the infection is critical to containing the spread, because asymptomatic and pre-symptomatic people don’t yet show signs of infection and can unknowingly spread the disease to others.

With an early warning solution, individuals could be alerted to their possible infection, allowing them to quarantine and avoid infecting others.

“RATE would allow us to non-invasively monitor a service member’s health and provide early alerts to potential infection that will help us to ensure troop readiness, better support their health and protect against the threat of further spread of the disease,” said Edward Argenta, Science and Technology Manager at DTRA. “Unlike other more narrow approaches, this solution is designed to recognize a wide variety of infections and can help identify future novel threats.”

RATE integrates with consumer off-the-shelf wearables to measure biomarkers. The biomarker data is processed in the cloud as part of a software as a service model and enables users to see their hourly RATE score through a secure website. The RATE-COVID system began deployment with US military units on June 16, 2020, and over the next few weeks the study is expected to grow to several thousand participants.

RATE-COVID is designed to eventually work with any and all variables, and the system will be able to deploy in a bring-your-own-device approach in the future.

“By combining commercial technology, a rich data source and simple to use wearables, we are effectively providing a check-engine light on the military service member and getting that alert before they’re broken down with a disease. In military speak, we’re targeting left-of-cough awareness,” said Christian Whitchurch, PhD, DIU Human Systems Portfolio Director.

The RATE approach uses large-scale machine learning tools and trade-space analyses across 165 different biomarkers from a Philips dataset of over 41,000 cases of hospital acquired infection. The risk score also works other general types of infection, including COVID-19. Philips researchers are now looking for ways the solution can be used to detect the next unknown infectious agent.

The technology could be further applied in hospitals and healthcare organizations by helping to monitor patients for infection prior to clinical symptoms. The early warning system could also help organizations manage COVID-19 return-to-work activities by helping with the early identification of individuals who may be infected and who should self-isolate and work from home.

“The RATE science shows that physiological response to infection has similarities across different types of infectious agents, and we anticipate that this will also apply to RATE-COVID, giving us a useful early warning solution,” said Dr. Joe Frassica, Chief Medical Officer and Head of Philips Research North America.

“As we continue to get new data from monitored cases of COVID-19, we will be able to refine the RATE-COVID algorithm in the near future. We hope that this will not only allow us to protect people from contracting the disease, but to also intervene early and treat those who are infected.”

This effort adds to DoD’s use of AI to track and reduce the spread of coronavirus. In April, the organization announced that it would be using artificial intelligence, machine learning, and data visualization tools to look for patterns or identify potential hotspots during the COVID-19 pandemic.

“We have a favorable position and relative advantage. One of our competitive advantages against any threat is the quality of the force we have, and educating them with the complexity of the environment that they're in,” said Marine Corps Lt. Gen. Daniel O'Donohue at the time.

“Education is a key component of our strategic competitive advantage. Expediency in response to COVID got us out of the classroom. I think many of the things we've learned will be retained and take us where we need to go for the future fight.”