1. Rapid Exclusion of COVID Infection With the Artificial Intelligence Electrocardiogram
- Author
-
Zachi I. Attia, Naveen L. Pereira, Anneli Svensson, Francisco Fernández-Avilés, Thomas F Luescher, Raja Sekhar Madathala, Jozef Bartunek, John Halamka, Henrik Jensen, Francisco Lopez Jimenez, Paari Dominic, Pyotr G. Platonov, Domenico Zagari, Pahlajani Db, Nikhita R Chennaiah Gari, Marco Merlo, Darryl D Esakof, Vladan Vukomanovic, John Signorino, Daniel C. DeSimone, Gianfranco Sinagra, Stefan Janssens, Kevin P. Cohoon, Francis J. Alenghat, Jennifer L. Dugan, Karl Dujardin, Melody Hermel, Michael E. Farkouh, Goran Loncar, Sanjiv M. Narayan, Suraj Kapa, Deepak Padmanabhan, Karam Turk-Adawi, Rickey E. Carter, Paul A. Friedman, Carolyn Lam Su Ping, Fahad Gul, Amit Noheria, Nidal Asaad, Arun Sridhar, Gaetano Antonio Lanza, Peter A. Noseworthy, Nicholas S. Peters, Marc K. Lahiri, Jessica Cruz, Brenda D Rodriguez Escenaro, Gaurav A. Upadhyay, Jose Alberto Pardo Gutierrez, Attia, Z. I., Kapa, S., Dugan, J., Pereira, N., Noseworthy, P. A., Jimenez, F. L., Cruz, J., Carter, R. E., Desimone, D. C., Signorino, J., Halamka, J., Chennaiah Gari, N. R., Madathala, R. S., Platonov, P. G., Gul, F., Janssens, S. P., Narayan, S., Upadhyay, G. A., Alenghat, F. J., Lahiri, M. K., Dujardin, K., Hermel, M., Dominic, P., Turk-Adawi, K., Asaad, N., Svensson, A., Fernandez-Aviles, F., Esakof, D. D., Bartunek, J., Noheria, A., Sridhar, A. R., Lanza, G. A., Cohoon, K., Padmanabhan, D., Pardo Gutierrez, J. A., Sinagra, G., Merlo, M., Zagari, D., Rodriguez Escenaro, B. D., Pahlajani, D. B., Loncar, G., Vukomanovic, V., Jensen, H. K., Farkouh, M. E., Luescher, T. F., Su Ping, C. L., Peters, N. S., and Friedman, P. A.
- Subjects
COVID-19, coronavirus infectious disease 19 ,COVID-19/diagnosis ,Coronavirus disease 2019 (COVID-19) ,Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) ,Population ,Predictive Value of Test ,ACE2, angiotensin-converting enzyme 2 ,SARS-CoV-2, severe acute respiratory syndrome coronavirus 2 ,Sensitivity and Specificity ,WHO, World Health Organization ,AUC, area under the curve ,Electrocardiography ,COVID-19 ,Case-Control Studies ,Humans ,Predictive Value of Tests ,Artificial Intelligence ,PCR, polymerase chain reaction ,Medicine ,education ,Volunteer ,education.field_of_study ,medicine.diagnostic_test ,business.industry ,Area under the curve ,Case-control study ,AI-ECG, artificial intelligence–enhanced electrocardiogram ,REDCap, Research Electronic Data Capture ,General Medicine ,PPV, positive predictive value ,NPV, negative predictive value ,Predictive value of tests ,Screening ,Original Article ,AI, artificial intelligence ,Artificial intelligence ,business ,Case-Control Studie ,COVID 19 ,Human - 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.
- Published
- 2021