Automated spectrographic seizure detection using convolutional neural networks.

Journal: Seizure
Published Date: Jul 8, 2019

Abstract

PURPOSE: Non-convulsive seizures are common in critically ill patients, and delays in diagnosis contribute to increased morbidity and mortality. Many intensive care units employ continuous EEG (cEEG) for seizure monitoring. Although cEEG is continuously recorded, it is often reviewed intermittently, which may delay seizure diagnosis and treatment. This may be mitigated with automated seizure detection. In this study, we develop and evaluate convolutional neural networks (CNN) to automate seizure detection on EEG spectrograms.

Authors

  • Peter Z Yan
    Department of Neurology, Weill Cornell Medicine, 525 E. 68(th) St F-610, New York, NY 10065, United States; Department of Health Policy & Research, Weill Cornell Medicine, 402 E. 67(th) St, New York, NY 10065, United States. Electronic address: PZY9001@med.cornell.edu.
  • Fei Wang
    Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, United States.
  • Nathaniel Kwok
    Weill Cornell Medical College, Weill Cornell Medicine, 1300 York Ave, New York, NY 10065, United States.
  • Baxter B Allen
    Department of Neurology, David Geffen School of Medicine at UCLA, 10833 Le Conte Ave, Los Angeles, CA 90095, United States.
  • Sotirios Keros
    Department of Pediatric Neurology, University of South Dakota Sanford School of Medicine, 1400 W 22nd St, Sioux Falls, SD 57105, United States.
  • Zachary Grinspan
    Department of Neurology, Weill Cornell Medicine, 525 E. 68(th) St F-610, New York, NY 10065, United States; Department of Pediatric Neurology, Weill Cornell Medicine, 505 E. 70(th) St, New York, NY 10021, United States.

Keywords

External Resources

Popular Topics
Recent Journals