An algorithm can identify COVID-19 cases and differentiate them from influenza cases with the same accuracy as a physician’s diagnosis, according to a study recently published in Nature Communications.
The research team trained an artificial intelligence algorithm to detect COVID-19 in lung scans of 1,280 patients from Japan, China and Italy. They tested it on 1,337 patients with lung diseases spanning from COVID-19 to pneumonia and cancer.
The algorithm was able to accurately diagnose 84 percent of positive COVID-19 cases and 93 percent of negative cases.
The study was conducted to explore alternatives to reverse transcription-polymerase chain reaction tests, which are often used to diagnose COVID-19. These tests often undergo delays during processing and have a high risk of producing false negatives.
“We demonstrated that a deep learning-based AI approach can serve as a standardized and objective tool to assist healthcare systems as well as patients,” Ulas Bagci, PhD, one of the study’s researchers, said in a Sept. 30 news release. “It can be used as a complementary test tool in very specific limited populations, and it can be used rapidly and at large scale in the unfortunate event of a recurrent outbreak.”
Register today for Becker’s HIT+RCM Virtual Event Oct. 6-9 for the best insights and big ideas in health IT!
More articles on artificial intelligence:
4 members of Congress demand research on racism within clinical algorithms
Defense Department, Philips expand AI research for early detection of infectious diseases
Bulk of clinical AI systems’ data comes from just 3 states, study finds
© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.