Format

Send to

Choose Destination
Nat Commun. 2018 Dec 6;9(1):5229. doi: 10.1038/s41467-018-07229-3.

Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy.

Author information

1
Center for Sleep Science and Medicine, Stanford University, Stanford, 94304, CA, USA.
2
Department of Electrical Engineering, Technical University of Denmark, Kongens Lyngby, 2800, Denmark.
3
Danish Center for Sleep Medicine, Rigshospitalet, Glostrup, 2600, Denmark.
4
Department of Pulmonary Medicine, Peking University People's Hospital, Beijing, 100044, China.
5
Sleep-Wake Disorders Center, Department of Neurology, Gui-de-Chauliac Hospital, CHU Montpellier, 34295, France.
6
INSERM, U1061, Université Montpellier 1, Montpellier, 34090, France.
7
Department of Neurology, Innsbruck Medical University, Innsbruck, 6020, Austria.
8
Department of Psychiatry, St. Vincent's Hospital, The Catholic University of Korea, Seoul, 16247, Korea.
9
Department of Biomedical and Neuromotor Sciences, University of Bologna, Bologna, 40123, Italy.
10
IRCCS Istituto delle Scienze Neurologiche di Bologna, Bologna, 40139, Italy.
11
School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, 4001, Australia.
12
Department of Medicine and Center for Sleep and Circadian Neurobiology, University of Pennsylvania, Philadelphia, 19104, PA, USA.
13
Sleep Medicine and Research Center, St. Luke's Hospital, Chesterfield, 63017, MO, USA.
14
Department of Population Health Sciences, University of Wisconsin-Madison, Madison, 53726, WI, USA.
15
Center for Sleep Science and Medicine, Stanford University, Stanford, 94304, CA, USA. mignot@stanford.edu.

Abstract

Analysis of sleep for the diagnosis of sleep disorders such as Type-1 Narcolepsy (T1N) currently requires visual inspection of polysomnography records by trained scoring technicians. Here, we used neural networks in approximately 3,000 normal and abnormal sleep recordings to automate sleep stage scoring, producing a hypnodensity graph-a probability distribution conveying more information than classical hypnograms. Accuracy of sleep stage scoring was validated in 70 subjects assessed by six scorers. The best model performed better than any individual scorer (87% versus consensus). It also reliably scores sleep down to 5 s instead of 30 s scoring epochs. A T1N marker based on unusual sleep stage overlaps achieved a specificity of 96% and a sensitivity of 91%, validated in independent datasets. Addition of HLA-DQB1*06:02 typing increased specificity to 99%. Our method can reduce time spent in sleep clinics and automates T1N diagnosis. It also opens the possibility of diagnosing T1N using home sleep studies.

PMID:
30523329
PMCID:
PMC6283836
DOI:
10.1038/s41467-018-07229-3
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center