Expert-level sleep scoring with deep neural networks.

Journal: Journal of the American Medical Informatics Association : JAMIA

Published Date: Dec 1, 2018

Abstract

OBJECTIVES: Scoring laboratory polysomnography (PSG) data remains a manual task of visually annotating 3 primary categories: sleep stages, sleep disordered breathing, and limb movements. Attempts to automate this process have been hampered by the complexity of PSG signals and physiological heterogeneity between patients. Deep neural networks, which have recently achieved expert-level performance for other complex medical tasks, are ideally suited to PSG scoring, given sufficient training data.

Authors

Siddharth Biswal
Haoqi Sun

Neurology Department, Massachusetts General Hospital, Wang 720, Boston, MA, USA.
Balaji Goparaju

Neurology Department, Massachusetts General Hospital, Wang 720, Boston, MA, USA.
M Brandon Westover

Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts.
Jimeng Sun

College of Computing Georgia Institute of Technology Atlanta, GA, USA.
Matt T Bianchi

Neurology Department, Massachusetts General Hospital, Wang 720, Boston, MA, USA.

Keywords

Classification Datasets as Topic Electroencephalography Humans Machine Learning Models, Biological Neural Networks, Computer Polysomnography Sleep Sleep Apnea Syndromes Sleep Stages

External Resources

View on PubMed Access via DOI PubMed (30445569)

Expert-level sleep scoring with deep neural networks.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals