New AI model can predict COVID-19 patient outcomes

Data from basic blood work and other vitals can accurately project a COVID-19 patient's outcomes, according to a nearly three-year-long study led by Northwell Health's research arm, Feinstein Institutes for Medical Research. 

The study, published Nov. 10 in Nature Communications, took data sets of 34,912 COVID-19 patients from New Hyde Park, N.Y.-based Northwell Health between March 2020 and May 2022 and built an artificial intelligence tool to help inform front-line staff on a patient's prognosis and severity of the disease.

The data points the model used included age, serum urea nitrogen, lactate, serum albumin and red cell distribution width, which are all typically measured upon hospital admission, according to a Nov. 15 press release from Northwell Health

The researchers found that the AI-based model was accurate throughout the research period, even during surges and changing variants, and performs equally regardless of race, ethnicity or gender. 

Researchers said the model can also be applied to other dynamic diseases. 

The researchers published the validation methods and techniques used to build the tool and are also providing the medical community with the open-source code of the framework.


Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.


Featured Whitepapers

Featured Webinars