rtificial intelligence (AI) may offer a way to accurately determine that a person is not infected with COVID-19. An international retrospective study

Artificial Intelligence for Rapid Exclusion of COVID-19 Infection

submited by

Style Pass

2021-06-15 13:30:05

rtificial intelligence (AI) may offer a way to accurately determine that a person is not infected with COVID-19. An international retrospective study finds that infection with SARS-CoV-2, the virus that causes COVID-19, creates subtle electrical changes in the heart. An AI-enhanced EKG can detect these changes and potentially be used as a rapid, reliable COVID-19 screening test to rule out COVID-19 infection.

The AI-enhanced EKG was able to detect COVID-19 infection in the test with a positive predictive value — people infected — of 37% and a negative predictive value — people not infected — of 91%. When additional normal control subjects were added to reflect a 5% prevalence of COVID-19 — similar to a real-world population — the negative predictive value jumped to 99.2%. The findings are published in Mayo Clinic Proceedings.

COVID-19 has a 10- to 14-day incubation period, which is long compared to other common viruses. Many people do not show symptoms of infection, and they could unknowingly put others at risk. Also, the turnaround time and clinical resources needed for current testing methods are substantial, and access can be a problem.