acm-header
Sign In

Communications of the ACM

ACM TechNews

AI Tool Predicts Which Patients with Pandemic Virus Will Develop Serious Respiratory Disease


View as: Print Mobile App Share:
The artificial intelligence tool weighs many factors.

An experimental artificial intelligence tool predicted, with as much as 80% accuracy, which patients in a small test group who were newly infected with the COVID-19 virus would develop severe respiratory disease.

Credit: metamorworks/Getty Images

Researchers at New York University and China's Wenzhou Central Hospital and Cangnan People's Hospital developed an experimental artificial intelligence (AI) tool that accurately predicted which patients newly infected with the COVID-19 virus would develop severe respiratory disease.

The researchers collected demographic, laboratory, and radiological findings from 53 patients who tested positive in January for the virus at the two Chinese hospitals.

The AI applies decision trees that monitor decisions between options, and models the potential impacts of choices at each step in a pathway.

The tool determined that changes in three factors—alanine aminotransferase levels, reported myalgia, and hemoglobin levels—were most accurately predictive of subsequent severe disease, and could ultimately predict the risk of Acute Respiratory Distress Syndrome with up to 80% accuracy.

From New York University
View Full Article

 

Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account