Be Prepared: Machine Learning is Equipping Us for the Unknown

Courtesy Photo | Researchers work on a new COVID-19 detection technology. DTRA-JSTO is applying the commercial technology for early detection of the severe acute respiratory syndrome coronavirus 2, which causes the COVID-19 disease. Photo courtesy of Philips Research North America.  

FORT. BELVOIR, VA, UNITED STATES

01.12.2021

Courtesy Story

Defense Threat Reduction Agency's Chemical and Biological Technologies Department

In the midst of the COVID-19 pandemic, the Department of Defense (DoD) offers a glimmer of hope: the ability to warn of an infection up to 48 hours before overt symptoms appear. This infection-warning capability is the Rapid Analysis of Threat Exposure (RATE), and its development was conceptualized and spearheaded by DoD’s Defense Threat Reduction Agency’s (DTRA) Chemical and Biological Technologies Department, in its role as the Joint Science and Technology Office (JSTO). RATE has the potential to disrupt the early, invisible progression of disease, and the tool has been publicized by the media. National Public Radio discussed the impact of the new capability on the military. Federal News Network focused on the global, public health effects of learning presymptomatic signs of an infection 48 hours in advance.¹ The Wall Street Journal highlighted the significance of RATE in identifying infections due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2),² the virus that causes COVID-19; and Fox 5 Good Day DC explored the commercial potential of RATE.

RATE is a machine-learning algorithm that can explore a large set of data for patterns in how the human body changes when it acquires an infection. RATE is threat agnostic by design, which means the algorithm can identify signs of an infection regardless of the type of pathogen (bacterium or virus) causing the infection. The algorithm is demonstrating that it can analyze data collected by wearable technologies, such as smart watches, to identify individuals who are about to develop overt symptoms due to an exposure to SARS-CoV-2. If military personnel were outfitted with a wearable technology, then RATE’s threat-agnostic, infection-warning capability could help DoD better prepare for surprises in biological warfare.

DTRA-JSTO sought to develop an early infection-warning system that is grounded on the clinical fact that when a person is exposed to a pathogen, that person undergoes certain measurable changes in the body before symptoms the potential to change behavior to mitigate the effects of a disease. For example, military personnel armed with this knowledge can seek medical help and self-quarantine to prevent disease transmission. “While RATE isn’t preventing disease, it informs of an illness about to overwhelm the body, in turn promoting behavior that can assure a quicker return to wellness,” says Dr. John Hannan, Chief of Digital Battlespace Management Division at DTRA-JSTO.

Although RATE was developed using data from patients who developed hospital-acquired infections, it is now being assessed for its ability to indicate early signs of infection in active and otherwise healthy military personnel. The assessment is making use of wearable devices and SARS-CoV-2 as the infection-causing pathogen of interest, the latter because the assessment coincided with the COVID-19 pandemic. As mentioned earlier, RATE uses biomarkers that are collected noninvasively, which are also the type of data gathered by readily available, commercial wearable devices. Through the ongoing RATE COVID-19 Demonstration, DTRA-JSTO is evaluating the algorithm’s ability to utilize data gathered in nonclinical settings from wearable technologies, such as the Garmin Fenix 6 smart watch and the Oura Ring, to warn of an infection while maintaining confidentiality of personal identity and physical location.

RATE is the first machine-learning, infection-warning algorithm of its kind, offering DoD a novel opportunity to get ahead of illness among its military personnel. A 48-hour warning of an infection, regardless of the type of pathogen causing it, enables military personnel to initiate self-care, seek medical help, and self-quarantine. After all, with knowledge, action is possible. As the current pandemic continues to incite fear, RATE offers the hope of good health, even after an infection has begun.

1. Temin T. 2020. DoD components team with industry partner on AI project for an infectious disease warning system. Federal News Network website. https://federalnewsnetwork.com/artificial-intelligence/2020/09/dod-components-team-with-industry-partner-on-ai-project-for-an-infectious-disease-warning-system/. Accessed November 6, 2020.

2. Kesling B, Youssef NA. 2020. Thousands of American troops to take part in COVID-19 early-detection study. Wall Street Journal website. https://www.wsj.com/articles/thousands-of-american-troops-to-take-part-in-covid-19-early-detection-study-11600772402. Accessed November 6, 2020.

3. Campos M. 2017. Heart rate variability: A new way to track well-being. Harvard Health Blog. Harvard Health Publishing website. https://www.health.harvard.edu/blog/heart-rate-variability-new-way-track-well-2017112212789. Accessed November 6, 2020.

POCs: John Hannan, Ph.D., [e-mail]; Christopher Kiley, Ph.D., [e-mail]

• Date Taken: 01.12.2021
• Date Posted: 01.12.2021 16:57
• Story ID: 386801
• Location: FORT. BELVOIR, VA, US