A deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation

摘要

BackgroundAutomated electrocardiogram (ECG) interpretations may be erroneous, and lead to erroneous overreads, including for atrial fibrillation (AF). We compared the accuracy of the first version of a new deep neural network 12-Lead ECG algorithm (Cardiologs?) to the conventional Veritas algorithm in interpretation of AF.Methods24,123 consecutive 12-lead ECGs recorded over 6?months were interpreted by 1) the Veritas? algorithm, 2) physicians who overread Veritas? (Veritas??+?physician), and 3) Cardiologs? algorithm. We randomly selected 500 out of 858 ECGs with a diagnosis of AF according to either algorithm, then compared the algorithms' interpretations, and Veritas??+?physician, with expert interpretation. To assess sensitivity for AF, we analyzed a separate database of 1473 randomly selected ECGs interpreted by both algorithms and by blinded experts.ResultsAmong the 500 ECGs selected, 399 had a final classification of AF; 101 (20.2%) had ≥1 false positive automated interpretation. Accuracy of Cardiologs? (91.2%; CI: 82.4–94.4) was higher than Veritas? (80.2%; CI: 76.5–83.5) (p?