Detecting abnormal electroencephalograms using deep convolutional networks.

Journal: Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology
Published Date: Nov 17, 2018

Abstract

OBJECTIVES: Electroencephalography (EEG) is a central part of the medical evaluation for patients with neurological disorders. Training an algorithm to label the EEG normal vs abnormal seems challenging, because of EEG heterogeneity and dependence of contextual factors, including age and sleep stage. Our objectives were to validate prior work on an independent data set suggesting that deep learning methods can discriminate between normal vs abnormal EEGs, to understand whether age and sleep stage information can improve discrimination, and to understand what factors lead to errors.

Authors

  • K G van Leeuwen
    Department of Neurology, Massachusetts General Hospital, Boston, MA, USA; University of Twente, Enschede, the Netherlands.
  • H Sun
    Department of Neurology, Massachusetts General Hospital, Boston, MA, USA.
  • M Tabaeizadeh
    Department of Neurology, Massachusetts General Hospital, Boston, MA, USA.
  • A F Struck
    Department of Neurology, Wisconsin Hospital and Clinics, Madison, WI, USA.
  • M J A M van Putten
    Clinical Neurophysiology, MIRA - Institute for Biomedical Technology and Technical Medicine, University of Twente, Hallenweg 15, 7522NB Enschede, The Netherlands; Departments of Neurology and Clinical Neurophysiology, Medisch Spectrum Twente, Koningsplein 1, 7512KZ Enschede, The Netherlands.
  • M B Westover
    Department of Neurology, Massachusetts General Hospital, Boston, MA, USA. Electronic address: mwestover@mgh.harvard.edu.

Keywords

External Resources

Popular Topics
Recent Journals