Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram. / Sridhar, Arun R.; Chen (Amber), Zih Hua; Mayfield, Jacob J.; Fohner, Alison E.; Arvanitis, Panagiotis; Atkinson, Sarah; Braunschweig, Frieder; Chatterjee, Neal A.; Zamponi, Alessio Falasca; Johnson, Gregory; Joshi, Sanika A.; Lassen, Mats C.H.; Poole, Jeanne E.; Rumer, Christopher; Skaarup, Kristoffer G.; Biering-Sørensen, Tor; Blomstrom-Lundqvist, Carina; Linde, Cecilia M.; Maleckar, Mary M.; Boyle, Patrick M.
In: Cardiovascular Digital Health Journal, Vol. 3, No. 2, 04.2022, p. 62-74.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Identifying risk of adverse outcomes in COVID-19 patients via artificial intelligence–powered analysis of 12-lead intake electrocardiogram
AU - Sridhar, Arun R.
AU - Chen (Amber), Zih Hua
AU - Mayfield, Jacob J.
AU - Fohner, Alison E.
AU - Arvanitis, Panagiotis
AU - Atkinson, Sarah
AU - Braunschweig, Frieder
AU - Chatterjee, Neal A.
AU - Zamponi, Alessio Falasca
AU - Johnson, Gregory
AU - Joshi, Sanika A.
AU - Lassen, Mats C.H.
AU - Poole, Jeanne E.
AU - Rumer, Christopher
AU - Skaarup, Kristoffer G.
AU - Biering-Sørensen, Tor
AU - Blomstrom-Lundqvist, Carina
AU - Linde, Cecilia M.
AU - Maleckar, Mary M.
AU - Boyle, Patrick M.
N1 - Publisher Copyright: © 2021 Heart Rhythm Society
PY - 2022/4
Y1 - 2022/4
N2 - Background: Adverse events in COVID-19 are difficult to predict. Risk stratification is encumbered by the need to protect healthcare workers. We hypothesize that artificial intelligence (AI) can help identify subtle signs of myocardial involvement in the 12-lead electrocardiogram (ECG), which could help predict complications. Objective: Use intake ECGs from COVID-19 patients to train AI models to predict risk of mortality or major adverse cardiovascular events (MACE). Methods: We studied intake ECGs from 1448 COVID-19 patients (60.5% male, aged 63.4 ± 16.9 years). Records were labeled by mortality (death vs discharge) or MACE (no events vs arrhythmic, heart failure [HF], or thromboembolic [TE] events), then used to train AI models; these were compared to conventional regression models developed using demographic and comorbidity data. Results: A total of 245 (17.7%) patients died (67.3% male, aged 74.5 ± 14.4 years); 352 (24.4%) experienced at least 1 MACE (119 arrhythmic, 107 HF, 130 TE). AI models predicted mortality and MACE with area under the curve (AUC) values of 0.60 ± 0.05 and 0.55 ± 0.07, respectively; these were comparable to AUC values for conventional models (0.73 ± 0.07 and 0.65 ± 0.10). There were no prominent temporal trends in mortality rate or MACE incidence in our cohort; holdout testing with data from after a cutoff date (June 9, 2020) did not degrade model performance. Conclusion: Using intake ECGs alone, our AI models had limited ability to predict hospitalized COVID-19 patients’ risk of mortality or MACE. Our models’ accuracy was comparable to that of conventional models built using more in-depth information, but translation to clinical use would require higher sensitivity and positive predictive value. In the future, we hope that mixed-input AI models utilizing both ECG and clinical data may be developed to enhance predictive accuracy.
AB - Background: Adverse events in COVID-19 are difficult to predict. Risk stratification is encumbered by the need to protect healthcare workers. We hypothesize that artificial intelligence (AI) can help identify subtle signs of myocardial involvement in the 12-lead electrocardiogram (ECG), which could help predict complications. Objective: Use intake ECGs from COVID-19 patients to train AI models to predict risk of mortality or major adverse cardiovascular events (MACE). Methods: We studied intake ECGs from 1448 COVID-19 patients (60.5% male, aged 63.4 ± 16.9 years). Records were labeled by mortality (death vs discharge) or MACE (no events vs arrhythmic, heart failure [HF], or thromboembolic [TE] events), then used to train AI models; these were compared to conventional regression models developed using demographic and comorbidity data. Results: A total of 245 (17.7%) patients died (67.3% male, aged 74.5 ± 14.4 years); 352 (24.4%) experienced at least 1 MACE (119 arrhythmic, 107 HF, 130 TE). AI models predicted mortality and MACE with area under the curve (AUC) values of 0.60 ± 0.05 and 0.55 ± 0.07, respectively; these were comparable to AUC values for conventional models (0.73 ± 0.07 and 0.65 ± 0.10). There were no prominent temporal trends in mortality rate or MACE incidence in our cohort; holdout testing with data from after a cutoff date (June 9, 2020) did not degrade model performance. Conclusion: Using intake ECGs alone, our AI models had limited ability to predict hospitalized COVID-19 patients’ risk of mortality or MACE. Our models’ accuracy was comparable to that of conventional models built using more in-depth information, but translation to clinical use would require higher sensitivity and positive predictive value. In the future, we hope that mixed-input AI models utilizing both ECG and clinical data may be developed to enhance predictive accuracy.
KW - 12-lead ECG
KW - Arrhythmia
KW - Artificial intelligence
KW - COVID-19
KW - Deep learning
KW - Heart failure prognosis
KW - Mortality
KW - Risk factors
UR - http://www.scopus.com/inward/record.url?scp=85128248818&partnerID=8YFLogxK
U2 - 10.1016/j.cvdhj.2021.12.003
DO - 10.1016/j.cvdhj.2021.12.003
M3 - Journal article
C2 - 35005676
AN - SCOPUS:85128248818
VL - 3
SP - 62
EP - 74
JO - Cardiovascular Digital Health Journal
JF - Cardiovascular Digital Health Journal
SN - 2666-6936
IS - 2
ER -
ID: 343130132