AI, EKG Technology Rapidly Exclude COVID-19 Infection

The EKG showed a negative predictive value of 99.2%.

A recent international, retrospective study, conducted by investigators from the Mayo Clinic and a global volunteer consortium from 14 countries, has discovered that artificial intelligence (AI) enhanced electrocardiography (EKG) can be used as a rapid and reliable screening method for ruling out an infection with COVID-19.

Findings from the study were published in the journal Mayo Clinic Proceedings.

"Accuracy is one of the biggest hurdles in determining the value of any test for COVID-19. Not only do we need to know the sensitivity and specificity of the test, but also the prevalence of the disease,” Zachi Attia, co-first author on the study said. "Adding the extra control EKG data was critical to demonstrating how a variable prevalence of the disease -- as we have encountered with regions having widely different rates of disease at different stages of the pandemic -- would impact how the test would perform."

For the study, the team of investigators analyzed EKG data from the time when an individual had a confirmed case of COVID-19, and matched them with a control from patients who were not infected.

They then used data from over 26,000 of the EKGs to train the AI, with an additional 4,000 other in order to validate the readings. They then tested the AI on nearly 8,000 EKGS that were not previously tested.

Findings from the study showed that the EKG was able to detect a COVID-19 infection with a positive predictive value of 37%, and a negative predictive value of 91%.

Additionally, when control subjects were added to reflect a real-world population, the negative predictive value increased to 99.2%.

"This study demonstrates the presence of a biological signal in the EKG consistent with COVID-19 infection, but it included many ill patients,” Paul Friedman, senior author on the study said. “While it is a hopeful signal, we must prospectively test this in asymptomatic people using smartphone-based electrodes to confirm that it can be practically used in the fight against the pandemic. Studies are underway now to address that question."