We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
Comen Medical

Download Mobile App

AI Supported Predictors of Cardiac-Related COVID-19 Mortality Revealed in New Study

By HospiMedica International staff writers
Posted on 20 May 2021
Print article
Image: EchoGo Core (Photo courtesy of Ultromics Limited)
Image: EchoGo Core (Photo courtesy of Ultromics Limited)
New research has revealed key insights into the varying international use of cardiac ultrasound on COVID-19 patients, and how artificial intelligence (AI) derived heart measurements were able to predict COVID-19 mortality.

Ultromics Limited’s (Oxford, UK) cloud-based, AI platform was tapped to speedily review data from 13 medical centers in nine countries in an international effort supported in partnership by the American Society of Echocardiography (ASE), MedStar Health, and University of Chicago. In the World Alliance Societies of Echocardiography (WASE-COVID) Study, the researchers studied the crossover between COVID-19 and cardiac measurements among 870 patients from 13 medical centers in Asia, Europe, the US, and Latin America. Compared to previous studies that have identified coronary artery disease, hypertension, and diabetes as cardiovascular comorbidities, the new study validated those findings and identified which cardiac measurements and biomarkers were the best predictor of adverse outcomes.

The study revealed that 10 of the 13 medical centers performed limited cardiac exams as their primary COVID in-patient practice, and just three out of the 13 centers performed comprehensive exams. The researchers found that in-hospital mortality rates varied by region, 11% in Asia, 19% in Europe, 27% in Latin America, and 26% in the US. Left ventricular longitudinal strain (LV LS), right ventricle free wall strain (RV FWS), in addition to age at presentation, lactic dehydrogenase (LDH), and previous lung disease were independently associated with mortality, while left ventricle ejection fraction (LVEF) was not. The study also found that fully automated quantification of LVEF and LVLS using AI minimized variability, and AI-based LV analyses, but not manual, were significant predictors of in-hospital and follow-up mortality.

"Our original WASE Study first set out to see the state of healthy Normal hearts across the world. It took us a few years to manually review all of that data," said Dr. Federico Asch, Director of the Cardiovascular and Echo Core Labs at MedStar Health Research Institute. "When the pandemic began, we knew that the clinical urgency to learn as much as possible about the cardiovascular connection to COVID-19 was incredibly high, and that we had to find a better way of securely and consistently reviewing all of this information in a timely manner."

"Knowing we had to move quickly to figure out if there was anything about heart health that we could associate with COVID-19 outcomes, we were motivated to secure an industry partner to help accelerate our analysis timeline," said Dr. Roberto Lang, Director of the University of Chicago's Noninvasive Cardiac Imaging Laboratory. "Using Ultromics' software to anonymize echocardiograms, upload them to a cloud platform, and use artificial intelligence to quickly and accurately analyze each exam was hugely beneficial in bringing this report forward while the world is still fighting this virus."

"Global health equity is an issue that COVID-19 has highlighted, and this study has helped further demonstrate this while investigating the predictive power of cardiac markers," said Ross Upton, Ultromics CEO. "As we continue to study the significance of cardiac involvement in COVID, we can use these critical findings to optimize cardiac care for patients going forwards."

Related Links:
Ultromics Limited

Print article


Copyright © 2000-2021 Globetech Media. All rights reserved.