• Zachi I Attia, Suraj Kapa, Jennifer Dugan, Naveen Pereira, Peter A Noseworthy, Francisco Lopez Jimenez, Jessica Cruz, Rickey E Carter, Daniel C DeSimone, John Signorino, John Halamka, Nikhita R Chennaiah Gari, Raja Sekhar Madathala, Pyotr G Platonov, Fahad Gul, Stefan P Janssens, Sanjiv Narayan, Gaurav A Upadhyay, Francis J Alenghat, Marc K Lahiri, Karl Dujardin, Melody Hermel, Paari Dominic, Karam Turk-Adawi, Nidal Asaad, Anneli Svensson, Francisco Fernandez-Aviles, Darryl D Esakof, Jozef Bartunek, Amit Noheria, Arun R Sridhar, Gaetano A Lanza, Kevin Cohoon, Deepak Padmanabhan, Jose Alberto Pardo Gutierrez, Gianfranco Sinagra, Marco Merlo, Domenico Zagari, Brenda D Rodriguez Escenaro, Dev B Pahlajani, Goran Loncar, Vladan Vukomanovic, Henrik K Jensen, Michael E Farkouh, Thomas F Luescher, Carolyn Lam Su Ping, Nicholas S Peters, Paul A Friedman, and Discover Consortium (Digital and Noninvasive Screening for COVID-19 with AI ECG Repository).
• Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, MN.
• Mayo Clin. Proc. 2021 Aug 1; 96 (8): 2081-2094.

ObjectiveTo rapidly exclude severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection using artificial intelligence applied to the electrocardiogram (ECG).MethodsA global, volunteer consortium from 4 continents identified patients with ECGs obtained around the time of polymerase chain reaction-confirmed COVID-19 diagnosis and age- and sex-matched controls from the same sites. Clinical characteristics, polymerase chain reaction results, and raw electrocardiographic data were collected. A convolutional neural network was trained using 26,153 ECGs (33.2% COVID positive), validated with 3826 ECGs (33.3% positive), and tested on 7870 ECGs not included in other sets (32.7% positive). Performance under different prevalence values was tested by adding control ECGs from a single high-volume site.ResultsThe area under the curve for detection of acute COVID-19 infection in the test group was 0.767 (95% CI, 0.756 to 0.778; sensitivity, 98%; specificity, 10%; positive predictive value, 37%; negative predictive value, 91%). To more accurately reflect a real-world population, 50,905 normal controls were added to adjust the COVID prevalence to approximately 5% (2657/58,555), resulting in an area under the curve of 0.780 (95% CI, 0.771 to 0.790) with a specificity of 12.1% and a negative predictive value of 99.2%.ConclusionInfection with SARS-CoV-2 results in electrocardiographic changes that permit the artificial intelligence-enhanced ECG to be used as a rapid screening test with a high negative predictive value (99.2%). This may permit the development of electrocardiography-based tools to rapidly screen individuals for pandemic control.Copyright © 2021. Published by Elsevier Inc.

18 keywords...

hide…