A deep neural network learning algorithm outperforms a conventional algorithm for emergency department electrocardiogram interpretation.

Journal: Journal of electrocardiology
Published Date: Nov 16, 2018

Abstract

BACKGROUND: Cardiologs® has developed the first electrocardiogram (ECG) algorithm that uses a deep neural network (DNN) for full 12‑lead ECG analysis, including rhythm, QRS and ST-T-U waves. We compared the accuracy of the first version of Cardiologs® DNN algorithm to the Mortara/Veritas® conventional algorithm in emergency department (ED) ECGs.

Authors

  • Stephen W Smith
    Department of Emergency Medicine, University of Minnesota, Minneapolis, MN, USA.
  • Brooks Walsh
    Bridgeport Hospital, Bridgeport, CT, USA.
  • Ken Grauer
    College of Medicine, University of Florida, USA.
  • Kyuhyun Wang
    University of Minnesota, Department of Medicine, Division of Cardiology, USA.
  • Jeremy Rapin
    Cardiologs® Technologies, Paris, France.
  • Jia Li
    Zhongshan Institute for Drug Discovery, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Zhongshan Tsuihang New District, Guangdong, 528400, PR China; School of Pharmacy, Zunyi Medical University, Zunyi, 563000, PR China; National Center for Drug Screening, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai, 201203, PR China.
  • William Fennell
    Department of Cardiology, University College, Cork, Ireland.
  • Pierre Taboulet
    Cardiologs® Technologies, Paris, France; Department of Emergency Medicine, Hôpital Saint Louis, Assistance Publique-Hôpitaux de Paris, Paris, France.

Keywords

External Resources

Popular Topics
Recent Journals