Mount Sinai builds machine learning models to predict COVID-19 mortality

New York City-based Mount Sinai Health System researchers created machine learning-powered models that identify high risk and likelihood of mortality in COVID-19 patients.

The researchers used EHRs from more than 4,000 adult patients admitted to five Mount Sinai hospitals from March to May to develop the predictive models. Patient data analyzed included medical history, comorbidities, vital signs and lab results to predict critical events such as intubation and mortality.

Using the models, the researchers were able to predict a critical event or mortality at time windows of three, five, seven and 10 days from admission. The one-week mark performed best overall and correctly flagged the most critical events while simultaneously producing the fewest false positives.

"… We have created a method that identifies important health markers that drive likelihood estimates for acute care prognosis and can be used by health institutions across the world to improve care decisions, at both the physician and hospital level, and more effectively manage patients with COVID-19," said Girish Nadkarni, MD, clinical director of Mount Sinai's digital health institute, according to the Nov. 11 news release.

More articles on artificial intelligence:
Amgen, Japanese drugmaker join study using AI to improve COVID-19 treatment protocols
Google launches AI tools for healthcare to streamline document review, analysis
6 recent studies exploring AI in healthcare

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Webinars

Featured Whitepapers