Electrocardiogram screening for aortic valve stenosis using artificial intelligence

• Published in: European heart journal Vol. 42; no. 30; pp. 2885 - 2896
• Main Authors: Cohen-Shelly, Michal, Attia, Zachi I, Friedman, Paul A, Ito, Saki, Essayagh, Benjamin A, Ko, Wei-Yin, Murphree, Dennis H, Michelena, Hector I, Enriquez-Sarano, Maurice, Carter, Rickey E, Johnson, Patrick W, Noseworthy, Peter A, Lopez-Jimenez, Francisco, Oh, Jae K
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 07.08.2021
• Subjects: ECG; Aortic stenosis; Artificial intelligence; Convolutional neural network
• ISSN: 0195-668X; 1522-9645
• DOI: 10.1093/eurheartj/ehab153

Abstract Aims  Early detection of aortic stenosis (AS) is becoming increasingly important with a better outcome after aortic valve replacement in asymptomatic severe AS patients and a poor outcome in moderate AS. We aimed to develop artificial intelligence-enabled electrocardiogram (AI-ECG) using a convolutional neural network to identify patients with moderate to severe AS. Methods and results  Between 1989 and 2019, 258 607 adults [mean age 63 ± 16.3 years; women 122 790 (48%)] with an echocardiography and an ECG performed within 180 days were identified from the Mayo Clinic database. Moderate to severe AS by echocardiography was present in 9723 (3.7%) patients. Artificial intelligence training was performed in 129 788 (50%), validation in 25 893 (10%), and testing in 102 926 (40%) randomly selected subjects. In the test group, the AI-ECG labelled 3833 (3.7%) patients as positive with the area under the curve (AUC) of 0.85. The sensitivity, specificity, and accuracy were 78%, 74%, and 74%, respectively. The sensitivity increased and the specificity decreased as age increased. Women had lower sensitivity but higher specificity compared with men at any age groups. The model performance increased when age and sex were added to the model (AUC 0.87), which further increased to 0.90 in patients without hypertension. Patients with false-positive AI-ECGs had twice the risk for developing moderate or severe AS in 15 years compared with true negative AI-ECGs (hazard ratio 2.18, 95% confidence interval 1.90–2.50). Conclusion  An AI-ECG can identify patients with moderate or severe AS and may serve as a powerful screening tool for AS in the community. Graphical Abstract AI-ECG for Aortic Stenosis screening using convolutional neural network (CNN).