Artificial intelligence–enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial

• Published in: Nature medicine Vol. 27; no. 5; pp. 815 - 819
• Main Authors: Yao, Xiaoxi, Rushlow, David R., Inselman, Jonathan W., McCoy, Rozalina G., Thacher, Thomas D., Behnken, Emma M., Bernard, Matthew E., Rosas, Steven L., Akfaly, Abdulla, Misra, Artika, Molling, Paul E., Krien, Joseph S., Foss, Randy M., Barry, Barbara A., Siontis, Konstantinos C., Kapa, Suraj, Pellikka, Patricia A., Lopez-Jimenez, Francisco, Attia, Zachi I., Shah, Nilay D., Friedman, Paul A., Noseworthy, Peter A.
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.05.2021; Nature Publishing Group
• Subjects: 692/699/75/230; 692/700/228; Adolescent; Adult; Aged; Algorithms; Artificial Intelligence; Biomedical and Life Sciences; Biomedicine; Cancer Research; Clinical trials; Clusters; Congestive heart failure; Decision support systems; Decision Support Systems, Clinical - instrumentation; Diagnosis; Early Diagnosis; Echocardiography; Echocardiography - methods; Ejection fraction; EKG; Electrocardiogram; Electrocardiography; Electrocardiography - methods; Female; Health care; Heart failure; Heart Failure - diagnosis; Heart function; Heart function tests; Humans; Infectious Diseases; Intervention; Male; Metabolic Diseases; Methods; Middle Aged; Molecular Medicine; Neurosciences; Patients; Primary care; Stroke Volume - physiology; Young Adult; United States
• ISSN: 1078-8956; 1546-170X; 1546-170X
• DOI: 10.1038/s41591-021-01335-4

We have conducted a pragmatic clinical trial aimed to assess whether an electrocardiogram (ECG)-based, artificial intelligence (AI)-powered clinical decision support tool enables early diagnosis of low ejection fraction (EF), a condition that is underdiagnosed but treatable. In this trial ( NCT04000087 ), 120 primary care teams from 45 clinics or hospitals were cluster-randomized to either the intervention arm (access to AI results; 181 clinicians) or the control arm (usual care; 177 clinicians). ECGs were obtained as part of routine care from a total of 22,641 adults ( N  = 11,573 intervention; N  = 11,068 control) without prior heart failure. The primary outcome was a new diagnosis of low EF (≤50%) within 90 days of the ECG. The trial met the prespecified primary endpoint, demonstrating that the intervention increased the diagnosis of low EF in the overall cohort (1.6% in the control arm versus 2.1% in the intervention arm, odds ratio (OR) 1.32 (1.01–1.61), P  = 0.007) and among those who were identified as having a high likelihood of low EF (that is, positive AI-ECG, 6% of the overall cohort) (14.5% in the control arm versus 19.5% in the intervention arm, OR 1.43 (1.08–1.91), P  = 0.01). In the overall cohort, echocardiogram utilization was similar between the two arms (18.2% control versus 19.2% intervention, P  = 0.17); for patients with positive AI-ECGs, more echocardiograms were obtained in the intervention compared to the control arm (38.1% control versus 49.6% intervention, P  < 0.001). These results indicate that use of an AI algorithm based on ECGs can enable the early diagnosis of low EF in patients in the setting of routine primary care. In a pragmatic, cluster-randomized clinical trial, use of an AI algorithm for interpretation of electrocardiograms in primary care practices increased the frequency at which impaired heart function was diagnosed.