Wednesday, December 7, 2022

Newly Published physIQ and UI Health Study on the Efficacy of Novel COVID-19 Decompensation Index

COVID-19 Decompensation Index: A leader in digital medicine, physIQ announced the publication of a peer-reviewed paper describing the performance of a novel COVID-19 Decompensation Index (CDI) model in Phase I of a two-Phase NIH supported clinical study. The Wearable Sensor Derived Decompensation Index for Continuous Remote Monitoring of COVID-19 Diagnosed Patients article was published in npj Digital Medicine this week.

The DeCODe study proposed to develop and test a novel machine-learning CDI based on chest patch-derived continuous biosensor data in patients diagnosed with COVID-19. Performance of the physIQ CDI was retrospectively compared to standard of care (SOC) modalities to detect COVID-19 exacerbation. The study demonstrated that the CDI outperformed SOC modalities with a lower false alarm rate.

“Traditional remote monitoring systems involve `spot-check’ measurements taken by the patient, at most only a few times a day, which could lead to missing subtle and emerging indications of worsening health,” said Stephan Wegerich, physIQ Chief Science Officer. “At physIQ, we integrate artificial intelligence with wearable biosensing technology to enable continuous monitoring of patients during activities of daily living. These data provide rapid and continuous insights into physiology that may be impossible to gain from intermittent measurements. We have collected millions of hours of continuous biosensor data that our team has used with our CDI algorithms to detect early signs of possible decompensation due to COVID-19. We anticipate this approach may be applicable to other infectious diseases, as well.”

The DeCODe study was funded by the National Cancer Institute of the National Institutes of Health (NIH) in support of the Health and Human Services and NIH Digital Health Solutions for COVID-19 initiative. physIQ was awarded an NIH contract to develop an artificial intelligence (AI)-based CDI digital biomarker to detect a rapid decline of COVID-19 patients as well as to contribute to a digital data hub to support further research on COVID-19. The Phase I study enrolled 400 adults from the University of Illinois Health System (UI Health) diagnosed with COVID-19 in largely underserved Chicago areas. “We purposely collaborated with UI Health because of their mission to engage diverse communities. To that end, we were able to build this index using data from a truly representative population including Hispanic and non-Hispanic Black individuals who are the hardest hit by COVID-19,” Karen Larimer PhD, ACNP-BC, Study Principal Investigator, explained.

physIQ’s FDA-cleared AI analytics platform (pinpointIQ™) was used in the remote monitoring of COVID-positive study patients. The pinpointIQ solution continuously monitors a patient’s vital signs through a wearable biosensor, applies artificial intelligence analytics to the sensor data and alerts clinicians of any relevant physiologic changes. Clinicians review these signals and determine whether intervention is required.

“Up to one in five people who are infected with COVID-19 are at risk for severe worsening of the illness resulting in hospitalization. Novel digital health technologies hold the potential to expand our understanding of COVID-19, improve care delivery and produce better health outcomes. The Phase I results of the DeCODe study present a highly promising application of AI-driven personalized analytics within a continuous remote patient monitoring system,” added study co-author Dr. Terry Vanden Hoek, Chief Medical Officer at UI Health and Head of the Department of Emergency Medicine at the College of Medicine.

For the full study results published in npj Digital Medicine, visit: Identifier: NCT04575532 The pinpointIQ system continues to monitor patients in health systems across the country. An additional study of 1,000 patients has been completed and results are forthcoming.


By using this website you agree to accept Medical Device News Magazine Privacy Policy