Deep Learning to Predict Cardiac Magnetic Resonance-Derived Left Ventricular Mass and Hypertrophy From 12-Lead ECGs.

Journal: Circulation. Cardiovascular imaging
Published Date: Jun 1, 2021

Abstract

BACKGROUND: Classical methods for detecting left ventricular (LV) hypertrophy (LVH) using 12-lead ECGs are insensitive. Deep learning models using ECG to infer cardiac magnetic resonance (CMR)-derived LV mass may improve LVH detection.

Authors

  • Shaan Khurshid
    Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts.
  • Samuel Friedman
    Data Sciences Platform (S.F., P.D.A., N.D., P.B., A.A.P.), Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge.
  • James P Pirruccello
    Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts.
  • Paolo Di Achille
    Data Sciences Platform, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.
  • Nathaniel Diamant
    Data Sciences Platform, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.
  • Christopher D Anderson
    Cardiovascular Disease Initiative, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.
  • Patrick T Ellinor
    Cardiovascular Disease Initiative, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.
  • Puneet Batra
    Data Sciences Platform, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.
  • Jennifer E Ho
    Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts.
  • Anthony A Philippakis
    Data Sciences Platform, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.
  • Steven A Lubitz
    Cardiovascular Disease Initiative, Broad Institute of Harvard and the Massachusetts Institute of Technology, Cambridge, Massachusetts.

Keywords

External Resources

Popular Topics
Recent Journals