2021 Attia, Zachi Dugan, Jennifer Pereira, Naveen Noseworthy, Peter A. Lopez Jimenez, Francisco Cruz, Jessica Carter, Rickey E. DeSimone, Daniel C. Signorino, John Halamka, John Chennaiah Gari, Nikhita R. Sekhar Madathala, Raja Platonov, Pyotr G. Gul, Fahad Janssens, Stefan P. Narayan, Sanjiv Upadhyay, Gaurav A. Alenghat, Francis J. Lahiri, Marc K. Dujardin, Karl Hermel, Melody Dominic, Paari Turk-Adawi, Karam Asaad, Nidal Svensson, Anneli Fernadez-Aviles, Francisco Esakof, Darryl D. Bartunek, Jozef Noheria, Amit Sridhar, Arun R. Lanza, Gaetano A. Cohoon, Kevin Padmanabhan, Deepak Alberto Pardo Gutierrez, Jose Sinagra, Giangranco Merlo, Marco Zagari, Domenico Rodriguez Escenaro, Brenda D. Pahlajani, Dev B. Lončar, Goran Vukomanović, Vladan Jensen, Henrik K. Farkouh, Michael E. Luescher, Thomas F. Lam Su Ping, Carolyn Peters, Nicholas S. Friedman, Paul A. Kapa, Suraj Discover Consortium - Digital and Noninvasive Screening for COVID-19 with AI ECG Repository eng https://unilib.phaidrabg.rs/o:2966 doi:10.1016/j.mayocp.2021.05.027 cobiss:125801225 ISSN: 1942-5546 Mayo Clinic Proceedings 96(8) Rapid exclusion of COVID infection with the artificial intelligence electrocardiogram Ključne reči: COVID, koronavirus, veštačka inteligencija, mašinsko učenje, respiratorne infekcije, elektrokardiogram All rights reserved OBJECTIVE: To rapidly exclude severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection using artificial intelligence applied to the electrocardiogram (ECG). METHODS: A 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. RESULTS: The 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 pre- dictive 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%. CONCLUSION: Infection 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. info:eu-repo/semantics/article application/pdf 1183438 bytes