Deep learning algorithm for predicting left ventricular systolic dysfunction in atrial fibrillation with rapid ventricular response.

Abstract

Aims: Although evaluation of left ventricular ejection fraction (LVEF) is crucial for deciding the rate control strategy in patients with atrial fibrillation (AF), real-time assessment of LVEF is limited in outpatient settings. We aimed to investigate the performance of artificial intelligence-based algorithms in predicting LV systolic dysfunction (LVSD) in patients with AF and rapid ventricular response (RVR).

Methods and results: This study is an external validation of a pre-existing deep learning algorithm based on residual neural network architecture. Data were obtained from a prospective cohort of AF with RVR at a single centre between 2018 and 2023. Primary outcome was the detection of LVSD, defined as a LVEF ≤ 40%, assessed using 12-lead electrocardiography (ECG). Secondary outcome involved predicting LVSD using 1-lead ECG (Lead I). Among 423 patients, 241 with available echocardiography data within 2 months were evaluated, of whom 54 (22.4%) were confirmed to have LVSD. Deep learning algorithm demonstrated fair performance in predicting LVSD [area under the curve (AUC) 0.78]. Negative predictive value for excluding LVSD was 0.88. Deep learning algorithm resulted competent performance in predicting LVSD compared with N-terminal prohormone of brain natriuretic peptide (AUC 0.78 vs. 0.70, P = 0.12). Predictive performance of the deep learning algorithm was lower in Lead I (AUC 0.68); however, negative predictive value remained consistent (0.88).

Conclusion: Deep learning algorithm demonstrated competent performance in predicting LVSD in patients with AF and RVR. In outpatient setting, use of artificial intelligence-based algorithm may facilitate prediction of LVSD and earlier choice of drug, enabling better symptom control in AF patients with RVR.