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

• Published in: International journal of cardiology. Heart & vasculature Vol. 25; p. 100423
• Main Authors: Smith, Stephen W., Rapin, Jeremy, Li, Jia, Fleureau, Yann, Fennell, William, Walsh, Brooks M., Rosier, Arnaud, Fiorina, Laurent, Gardella, Christophe
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01-12-2019; Elsevier
• Subjects: Artificial intelligence; Atrial dysrhythmia; Atrial fibrillation; Deep neural network; Electrocardiogram; Original Paper; Atrial dysrhythmia; AD; AF; DNN; Atrial fibrillation; AFL; ECG; Deep neural network; AT; HCP; Electrocardiogram; Artificial intelligence; ED; DNN, deep neural network; AT, atrial tachycardia; AFL, atrial flutter; AD, atrial dysrhythmia; ED, emergency department; HCP, health care provider; AF, atrial fibrillation; ECG, electrocardiogram
• ISSN: 2352-9067; 2352-9067
• DOI: 10.1016/j.ijcha.2019.100423

Automated 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.
24,123 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.
Among 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 < 0.0001), and equal to Veritas® + physician (90.0%, CI:87.1–92.3) (p = 0.12). When Veritas® was incorrect, accuracy of Veritas® + physician was only 62% (CI 52–71); among those ECGs, Cardiologs® accuracy was 90% (CI: 82–94; p < 0.0001). The second database had 39 AF cases; sensitivity was 92% vs. 87% (p = 0.46) and specificity was 99.5% vs. 98.7% (p = 0.03) for Cardiologs® and Veritas® respectively.
Cardiologs® 12-lead ECG algorithm improves the interpretation of atrial fibrillation.