Researchers are learning to predict your chances of surviving COVID-19

COVID-19 patient in New York
(Image credit: Johannes Eisele/AFP/Getty Images)

Not everybody who gets COVID-19 has symptoms, and not all symptomatic patients get equally sick. Hospitalization rates have stabilized in hard-hit areas like northern Italy and New York City, but if the next wave is even bigger and more destructive — one of three scenarios envisioned by University of Minnesota epidemiologist Michael Osterholm and his colleagues — that "would absolutely take the health system down," Osterholm told Stat News. Two studies released last week offer tools that might help hospitals better triage patients.

Researchers in China reported in the journal Nature Machine Learning that an analysis of blood samples taken from 485 coronavirus patients in Wuhan discovered there biomarkers that can predict whether a coronavirus patient will die within 10 days, with more than 90 percent accuracy, Business Insider reports. A computer model the researchers developed looks for high levels of the enzyme lactic dehydrogenase (LDH), linked to lung damage; lymphopenia, or low levels of infection-fighting white blood cells; and a rise in inflammation-signaling high-sensitivity C-reactive proteins (hs-CRP).

Subscribe to The Week

Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

SUBSCRIBE & SAVE
https://cdn.mos.cms.futurecdn.net/flexiimages/jacafc5zvs1692883516.jpg

Sign up for The Week's Free Newsletters

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

Sign up
To continue reading this article...
Continue reading this article and get limited website access each month.
Get unlimited website access, exclusive newsletters plus much more.
Cancel or pause at any time.
Already a subscriber to The Week?
Not sure which email you used for your subscription? Contact us