tetano
Editor, Senior Moderator
Mayo Clin Proc
. 2021 Aug;96(8):2081-2094.
doi: 10.1016/j.mayocp.2021.05.027.
Rapid Exclusion of COVID Infection With the Artificial Intelligence Electrocardiogram
Zachi I Attia[SUP] 1 [/SUP], Suraj Kapa[SUP] 1 [/SUP], Jennifer Dugan[SUP] 1 [/SUP], Naveen Pereira[SUP] 1 [/SUP], Peter A Noseworthy[SUP] 1 [/SUP], Francisco Lopez Jimenez[SUP] 1 [/SUP], Jessica Cruz[SUP] 1 [/SUP], Rickey E Carter[SUP] 2 [/SUP], Daniel C DeSimone[SUP] 3 [/SUP], John Signorino[SUP] 4 [/SUP], John Halamka[SUP] 5 [/SUP], Nikhita R Chennaiah Gari[SUP] 6 [/SUP], Raja Sekhar Madathala[SUP] 7 [/SUP], Pyotr G Platonov[SUP] 8 [/SUP], Fahad Gul[SUP] 9 [/SUP], Stefan P Janssens[SUP] 10 [/SUP], Sanjiv Narayan[SUP] 11 [/SUP], Gaurav A Upadhyay[SUP] 12 [/SUP], Francis J Alenghat[SUP] 12 [/SUP], Marc K Lahiri[SUP] 13 [/SUP], Karl Dujardin[SUP] 14 [/SUP], Melody Hermel[SUP] 15 [/SUP], Paari Dominic[SUP] 16 [/SUP], Karam Turk-Adawi[SUP] 17 [/SUP], Nidal Asaad[SUP] 18 [/SUP], Anneli Svensson[SUP] 19 [/SUP], Francisco Fernandez-Aviles[SUP] 20 [/SUP], Darryl D Esakof[SUP] 21 [/SUP], Jozef Bartunek[SUP] 22 [/SUP], Amit Noheria[SUP] 23 [/SUP], Arun R Sridhar[SUP] 24 [/SUP], Gaetano A Lanza[SUP] 25 [/SUP], Kevin Cohoon[SUP] 26 [/SUP], Deepak Padmanabhan[SUP] 27 [/SUP], Jose Alberto Pardo Gutierrez[SUP] 28 [/SUP], Gianfranco Sinagra[SUP] 29 [/SUP], Marco Merlo[SUP] 29 [/SUP], Domenico Zagari[SUP] 30 [/SUP], Brenda D Rodriguez Escenaro[SUP] 31 [/SUP], Dev B Pahlajani[SUP] 32 [/SUP], Goran Loncar[SUP] 33 [/SUP], Vladan Vukomanovic[SUP] 34 [/SUP], Henrik K Jensen[SUP] 35 [/SUP], Michael E Farkouh[SUP] 36 [/SUP], Thomas F Luescher[SUP] 37 [/SUP], Carolyn Lam Su Ping[SUP] 38 [/SUP], Nicholas S Peters[SUP] 39 [/SUP], Paul A Friedman[SUP] 40 [/SUP], Discover Consortium (Digital and Noninvasive Screening for COVID-19 with AI ECG Repository)
Affiliations
Abstract
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 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%.
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.
. 2021 Aug;96(8):2081-2094.
doi: 10.1016/j.mayocp.2021.05.027.
Rapid Exclusion of COVID Infection With the Artificial Intelligence Electrocardiogram
Zachi I Attia[SUP] 1 [/SUP], Suraj Kapa[SUP] 1 [/SUP], Jennifer Dugan[SUP] 1 [/SUP], Naveen Pereira[SUP] 1 [/SUP], Peter A Noseworthy[SUP] 1 [/SUP], Francisco Lopez Jimenez[SUP] 1 [/SUP], Jessica Cruz[SUP] 1 [/SUP], Rickey E Carter[SUP] 2 [/SUP], Daniel C DeSimone[SUP] 3 [/SUP], John Signorino[SUP] 4 [/SUP], John Halamka[SUP] 5 [/SUP], Nikhita R Chennaiah Gari[SUP] 6 [/SUP], Raja Sekhar Madathala[SUP] 7 [/SUP], Pyotr G Platonov[SUP] 8 [/SUP], Fahad Gul[SUP] 9 [/SUP], Stefan P Janssens[SUP] 10 [/SUP], Sanjiv Narayan[SUP] 11 [/SUP], Gaurav A Upadhyay[SUP] 12 [/SUP], Francis J Alenghat[SUP] 12 [/SUP], Marc K Lahiri[SUP] 13 [/SUP], Karl Dujardin[SUP] 14 [/SUP], Melody Hermel[SUP] 15 [/SUP], Paari Dominic[SUP] 16 [/SUP], Karam Turk-Adawi[SUP] 17 [/SUP], Nidal Asaad[SUP] 18 [/SUP], Anneli Svensson[SUP] 19 [/SUP], Francisco Fernandez-Aviles[SUP] 20 [/SUP], Darryl D Esakof[SUP] 21 [/SUP], Jozef Bartunek[SUP] 22 [/SUP], Amit Noheria[SUP] 23 [/SUP], Arun R Sridhar[SUP] 24 [/SUP], Gaetano A Lanza[SUP] 25 [/SUP], Kevin Cohoon[SUP] 26 [/SUP], Deepak Padmanabhan[SUP] 27 [/SUP], Jose Alberto Pardo Gutierrez[SUP] 28 [/SUP], Gianfranco Sinagra[SUP] 29 [/SUP], Marco Merlo[SUP] 29 [/SUP], Domenico Zagari[SUP] 30 [/SUP], Brenda D Rodriguez Escenaro[SUP] 31 [/SUP], Dev B Pahlajani[SUP] 32 [/SUP], Goran Loncar[SUP] 33 [/SUP], Vladan Vukomanovic[SUP] 34 [/SUP], Henrik K Jensen[SUP] 35 [/SUP], Michael E Farkouh[SUP] 36 [/SUP], Thomas F Luescher[SUP] 37 [/SUP], Carolyn Lam Su Ping[SUP] 38 [/SUP], Nicholas S Peters[SUP] 39 [/SUP], Paul A Friedman[SUP] 40 [/SUP], Discover Consortium (Digital and Noninvasive Screening for COVID-19 with AI ECG Repository)
Affiliations
- PMID: 34353468
- DOI: 10.1016/j.mayocp.2021.05.027
Abstract
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 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%.
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.