Transfer Learning for Improved Classification of Drivers in Atrial Fibrillation.

Journal: Computing in cardiology
Published Date: Dec 26, 2023

Abstract

"Drivers" are theorized mechanisms for persistent atrial fibrillation. Machine learning algorithms have been used to identify drivers, but the small size of current driver datasets limits their performance. We hypothesized that pretraining with unsupervised learning on a large dataset of unlabeled electrograms would improve classifier accuracy on a smaller driver dataset. In this study, we used a SimCLR-based framework to pretrain a residual neural network on a dataset of 113K unlabeled 64-electrode measurements and found weighted testing accuracy to improve over a non-pretrained network (78.6±3.9% vs 71.9±3.3%). This lays ground for development of superior driver detection algorithms and supports use of transfer learning for other datasets of endocardial electrograms.

Authors

  • Bram Hunt
    Department of Biomedical Engineering, University of Utah, SLC, UT, USA.
  • Eugene Kwan
    Department of Biomedical Engineering, University of Utah, SLC, UT, USA.
  • Tolga Tasdizen
    Scientific Computing and Imaging Institute, University of Utah, SLC, UT, USA.
  • Jake Bergquist
    Department of Biomedical Engineering, University of Utah, SLC, UT, USA.
  • Matthias Lange
    Nora Eccles Cardiovascular Research and Training Institute, University of Utah, SLC, UT, USA.
  • Benjamin Orkild
    Department of Biomedical Engineering, University of Utah, SLC, UT, USA.
  • Robert S MacLeod
    Department of Biomedical Engineering, University of Utah, SLC, UT, USA.
  • Derek J Dosdall
    Department of Biomedical Engineering, University of Utah, SLC, UT, USA.
  • Ravi Ranjan
    Nora Eccles Treadwell CVRTI, University of Utah, SLC, UT, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals