Deep Learning Analysis of Sinus-Rhythm Echocardiography for the Identification of Patients with Atrial Fibrillation

Background and Aims Paroxysmal atrial fibrillation (AF) is underdiagnosed due to its intermittent and asymptomatic nature. We evaluated whether a deep neural network applied to transthoracic echocardiograms (TTEs) acquired in sinus rhythm can discriminate between patients with and without documented AF and identify individuals at increased risk for subsequent AF documentation and adverse outcomes. Methods We retrospectively analyzed 85,686 TTE studies (2009–2021). A deep neural network was applied to apical four-chamber and parasternal long-axis videos without Doppler. AF ground truth was based on ICD codes, ECG, Holter, or prior echocardiographic documentation of AF. The dataset was split into training (60%), validation (20%), and an independent test set (20%). In the test cohort, we assessed discrimination performance. Among patients without prior AF, we evaluated associations between model classification and subsequent AF documentation and a composite outcome of all-cause mortality, heart failure hospitalization, or stroke. Results The test set included 17,121 patients (median age 66 years [IQR 54–75]; 57.6% male), of whom 3,449 (20.1%) had prior AF. The model achieved an AUC of 0.85, with sensitivity 0.80 and specificity 0.72. At the selected threshold, 6,581 patients (38.4%) were classified as model-positive, including 3,832 (58.2%) without prior AF. Among patients without prior AF, model-positive classification was associated with subsequent AF documentation (adjusted HR 1.64; 95% CI 1.33–2.04) and with the composite outcome (adjusted HR 1.24; 95% CI 1.13–1.35). Conclusion Deep learning applied to sinus-rhythm TTE demonstrates discrimination for AF and identifies an imaging-derived signal associated with subsequent AF documentation and adverse outcomes.