A first-in-kind tool that collects and analyzes continuous physiologic data could provide early clinical indicators of COVID-19 decompensation.
Based on Phase I data, machine learning was used to develop and test a novel COVID-19 digital biomarker to be further validated in Phase II.
CHICAGO, IL– January 19, 2021 – The National Cancer Institute (NCI) and the National Institute of Biomedical Imaging and Bioengineering (NIBIB) of the National Institutes of Health (NIH), exercised their option to enter Phase II of a multi-phase contract to continuephysIQ’s development of an AI-based COVID-19 digital biomarker to address the rapid decompensation of high-risk COVID-19 patients. This exercise of Phase II by the NIH brings the total contract to $6.6 million.
In just 10 weeks, physIQ successfully enrolled and monitored 400 high-risk COVID-19 patients in Phase I of theDeCODe study. “The adoption of and enrollment in the platform by both patients and healthcare providers has been overwhelmingly positive. I believe this speaks to the demand for this type of program, as well as the ease of use and value to the both patient and provider,” said Karen Larimer PhD, ACNP-BC, study PI and physIQ’s Director of Clinical Development.
The DeCODe project, which is in collaboration with University of Illinois Hospital and Health Sciences System (UI Health), aimed to develop an early warning system allowing providers to intervene when a COVID-19 patient who is clinically surveilled from home begins to worsen. Rather than relying on periodic point measurements, such as temperature and pulse oximetry that are known to be lagging or insensitive indicators of COVID-19 decompensation, continuous multi-parameter vital signs and physiological features were used to establish a targeted biomarker, or COVID-19 Decompensation Index (CDI), for worsening COVID-19.
“Using Phase I data, we developed and tested a preliminary digital biomarker using state of the art machine learning algorithms that take advantage of our extensive library of wearable biosensor analytics as inputs,” said Stephan Wegerich, physIQ’s Chief Science Officer. “Furthermore, we were able to demonstrate performance levels that far exceeded our target performance criterion. We are looking forward to further validation in Phase II.”
Phase II begins January 2021 where 1,200 patients will be enrolled to validate the digital biomarker. During the validation phase, physIQ will continue to enroll ambulatory participants who are confirmed COVID-19 positive and evaluate the ability for the digital biomarker to predict decompensation severity remote from the hospital.
The study is designed to capture data from a large, diverse population to investigate the digital biomarker’s overall performance, as well as to identify any differences that may exist among subgroups based on age, sex/gender and racial/ethnic characteristics. Preliminary analysis has demonstrated that nearly half of the participants are Latinx and at least one third are Black. With this diverse representation of study participants, it may be possible to better understand how COVID-19 infection specifically impacts these populations.
"UI Health serves some of the most vulnerable, underserved communities in Illinois. These are the communities that COVID-19 has hit the hardest,” stated UI Health Chief Medical Officer, Terry Vanden Hoek MD. “We need to have a deep understanding of how and why COVID-19 is impacting people of color so dramatically. Then we’ll use this data to improve care everywhere.”
This biomarker will build on physIQ’s prior FDA-cleared, AI-based Multivariate Change IndexTM(MCI) that has amassed more than 2 million hours of physiologic data, supporting development of this targeted digital biomarker for COVID-19. This will enable new research and further insight into using digital health to advance the public health response.
This project has been funded in whole or in part with Federal funds from the National Institutes of Health, Department of Health and Human Services, under Contract No. 75N91020C00040.
PhysIQ is the leader in digital medicine, dedicated to generating unprecedented health insight using continuous wearable biosensor data and advanced analytics. Its enterprise-ready cloud platform continuously collects and processes data from any wearable biosensor using a deep portfolio of FDA-cleared analytics. The company has published one of the mostrigorous clinical studiesto date in digital medicine and are pioneers in developing, validating, and achieving regulatory approval of Artificial Intelligence-based analytics. With applications in both healthcare and clinical trial support, physIQ is transforming continuous physiological data into insight for health systems, payers, and pharmaceutical companies.