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

Simple item page
dc.contributor.authorSmith, Stephen W.
dc.contributor.authorRapin, Jeremy
dc.contributor.authorLi, Jia
dc.contributor.authorFleureau, Yann
dc.contributor.authorFennell, William
dc.contributor.authorWalsh, Brooks M.
dc.contributor.authorRosier, Arnaud
dc.contributor.authorFiorina, Laurent
dc.contributor.authorGardella, Christophe
dc.contributor.funderCardiologs® technologiesen
dc.date.accessioned2019-10-15T06:06:00Z
dc.date.available2019-10-15T06:06:00Z
dc.date.issued2019-09-08
dc.description.abstractBackground: 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. Methods: 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. Results: 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. Conclusion: Cardiologs® 12-lead ECG algorithm improves the interpretation of atrial fibrillation.en
dc.description.statusPeer revieweden
dc.description.versionPublished Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.articleid100423en
dc.identifier.citationSmith, S. W., Rapin, J., Li, J., Fleureau, Y., Fennell, W., Walsh, B. M., Rosier, A., Fiorina, L. and Gardella, C. (2019) 'A deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation', IJC Heart & Vasculature, 25,100423 (6pp.). DOI: 10.1016/j.ijcha.2019.100423en
dc.identifier.doi10.1016/j.ijcha.2019.100423en
dc.identifier.endpage6en
dc.identifier.issn2352-9067
dc.identifier.journaltitleIJC Heart and Vasculatureen
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/8771
dc.identifier.volume25en
dc.language.isoenen
dc.publisherElsevier Ireland Ltden
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S2352906719301241?via%3Dihub
dc.rights©2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).Contents lists available atScienceDirectIJC Heart & Vasculaturejournal homepage:http://www.journals.elsevier.com/ijc-heart-and-vasculatureen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectDeep neural networken
dc.subjectArtificial intelligenceen
dc.subjectArtificial fibrillationen
dc.subjectAtrial dysrhythmiaen
dc.subjectElectrocardiogramen
dc.titleA deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillationen
dc.typeArticle (peer-reviewed)en
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S2352906719301241-main.pdf
Size:
501.03 KB
Format:
Adobe Portable Document Format
Description:
Published version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Medicine - Journal Articles