Communications of the ACM
Can AI Predict How Sick You'll Get From COVID? San Diego Scientists Think So
A team of San Diego scientists is harnessing artificial intelligence to understand why COVID-19 symptoms can vary dramatically from one person to the next.
Credit: Alissa Eckert, Dan Higgins/CDC
Researchers at the University of California San Diego (UCSD), Scripps Research, and the La Jolla Institute for Immunology used artificial intelligence to determine why COVID-19 symptoms can vary among patients.
The researchers downloaded 45,000 samples from a wide array of viral infections to find a shared response pattern to these viruses.
They determined that 166 genes were activated consistently during infection, and 20 genes separated patients with mild and severe symptoms.
This was found to be true for the novel coronavirus as well.
UCSD's Debashis Sahoo said, "It seemed to work in every dataset we used. It was hard to believe."
The researchers also observed distinct gene activation patterns in people with prolonged coronavirus symptoms.
From The San Diego Union-Tribune
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found