Detection and classification of arrhythmia using an explainable deep learning model.

Journal: Journal of electrocardiology
Published Date:

Abstract

BACKGROUND: Early detection and intervention is the cornerstone for appropriate treatment of arrhythmia and prevention of complications and mortality. Although diverse deep learning models have been developed to detect arrhythmia, they have been criticized due to their unexplainable nature. In this study, we developed an explainable deep learning model (XDM) to classify arrhythmia, and validated its performance using diverse external validation data.

Authors

  • Yong-Yeon Jo
    Medical research team, Medical AI, Seoul, South Korea.
  • Joon-Myoung Kwon
    Department of Emergency Medicine, Mediplex Sejong Hospital, Incheon, Korea.
  • Ki-Hyun Jeon
    Department of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, Korea.
  • Yong-Hyeon Cho
    Medical Research Team, Medical AI Co. Ltd., Seoul, South Korea.
  • Jae-Hyun Shin
    Medical Research Team, Medical AI Co. Ltd., Seoul, South Korea.
  • Yoon-Ji Lee
    Medical Research Team, Medical AI Co. Ltd., Seoul, South Korea.
  • Min-Seung Jung
    Medical Research Team, Medical AI Co. Ltd., Seoul, South Korea.
  • Jang-Hyeon Ban
    Medical R&D Center, Bodyfriend Co. Ltd., Seoul, South Korea.
  • Kyung-Hee Kim
    Department of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, Korea.
  • Soo Youn Lee
    Seoul National University Biomedical Informatics (SNUBI), Division of Biomedical Informatics, Seoul National University College of Medicine, Seoul 110799, South Korea.
  • Jinsik Park
    Department of Cardiology, Mediplex Sejong Hospital, Incheon, Korea.
  • Byung-Hee Oh
    Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, Republic of Korea.