Researchers at the University of Central Florida (UCF) and the U.S. National Institutes of Health have developed an artificial intelligence (AI) algorithm that is almost as accurate as a physician in diagnosing Covid-19 in the lungs and distinguishing Covid-19 cases from influenza.
The researchers trained the algorithm to recognize Covid-19 in computed tomography (CT) scans of 1,280 patients, then tested the algorithm on CT scans of 1,337 patients with various lung diseases.
They found the algorithm could be trained to classify Covid-19 pneumonia in CT scans with up to 90% accuracy, and to correctly identify positive cases 84% of the time and negative cases 93% of the time.
Said UCF's Ulas Bagci, "We showed that robust AI models can achieve up to 90% accuracy in independent test populations, maintain high specificity in non-Covid-19 related pneumonias, and demonstrate sufficient generalizability to unseen patient populations and centers."
From University of Central Florida
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA