AI is a 'key ally in the fight' against COVID-19, say Northwell researchers

Artificial intelligence and machine learning tools can be a vital aspect of the COVID-19 response, and some are already used by clinicians worldwide.

A team of researchers led by Theodoros Zanos, PhD, an assistant professor at the Northwell Health's Institute of Bioelectronic Medicine at Feinstein in New York City, wrote an article for the Springer Nature journal outlining the potential for critical care decision-making tools that include information based on collected vitals, laboratory results, medication orders and comorbidities.

"Researching patient data from the pandemic is key to creating cutting-edge AI tools that can provide our frontline clinicians with important information and assist them in making evidence-based recommendations," said Dr. Zanos in a health system press release.

The paper outlined key benefits of machine learning tools for Northwell's COVID-19 response, including in patient triaging. Information including first labs, presenting symptoms, available beds and staffing can be used to develop smarter triaging models, according to the article. It can also help healthcare providers have emotionally difficult conversations with patients and families about their care goals, providing essential information during the decision-making process.

Northwell's database includes outcomes from more than 5,700 hospitalized COVID-19 patients. "With the best possible data and analytics, the field of ML/AI can be a key ally in the fight to limit the devastating consequences of COVID-19," the study authors concluded.

More articles on artificial intelligence:
4 AI systems outperforming medical experts
How UC San Diego Health, AWS implemented an AI imaging algorithm to detect COVID-19 in 10 days
Harvard, Stanford researchers lead COVID-19 AI data initiative: 4 things to know


Copyright © 2022 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.


Featured Whitepapers

Featured Webinars