Deep Learning and Insomnia

Assisting Clinicians with Their Diagnosis

Mostafa Shahin, Beena Ahmed, Sana Tmar Ben Hamida, Fathima Lamana Mulaffer, Martin Glos, Thomas Penzel

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Effective sleep analysis is hampered by the lack of automated tools catering to disordered sleep patterns and cumbersome monitoring hardware. In this paper, we apply deep learning on a set of 57 EEG features extracted from a maximum of two EEG channels to accurately differentiate between patients with insomnia or controls with no sleep complaints. We investigated two different approaches to achieve this. The first approach used EEG data from the whole sleep recording irrespective of the sleep stage (stage-independent classification), while the second used only EEG data from insomnia-impacted specific sleep stages (stage-dependent classification). We trained and tested our system using both healthy and disordered sleep collected from 41 controls and 42 primary insomnia patients. When compared with manual assessments, an NREM + REM based classifier had an overall discrimination accuracy of 92% and 86% between two groups using both two and one EEG channels, respectively. These results demonstrate that deep learning can be used to assist in the diagnosis of sleep disorders such as insomnia.

Original languageEnglish
Article number7811237
Pages (from-to)1546-1553
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume21
Issue number6
DOIs
Publication statusPublished - 1 Nov 2017

Fingerprint

Sleep Initiation and Maintenance Disorders
Electroencephalography
Sleep
Learning
Sleep Stages
Deep learning
Classifiers
Hardware
Monitoring

Keywords

  • Automatic sleep stage scoring
  • deep learning
  • electroencephalogram (EEG)
  • insomnia
  • sleep analysis

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Deep Learning and Insomnia : Assisting Clinicians with Their Diagnosis. / Shahin, Mostafa; Ahmed, Beena; Hamida, Sana Tmar Ben; Mulaffer, Fathima Lamana; Glos, Martin; Penzel, Thomas.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 21, No. 6, 7811237, 01.11.2017, p. 1546-1553.

Research output: Contribution to journalArticle

Shahin, Mostafa ; Ahmed, Beena ; Hamida, Sana Tmar Ben ; Mulaffer, Fathima Lamana ; Glos, Martin ; Penzel, Thomas. / Deep Learning and Insomnia : Assisting Clinicians with Their Diagnosis. In: IEEE Journal of Biomedical and Health Informatics. 2017 ; Vol. 21, No. 6. pp. 1546-1553.
@article{02b8173c94e24662820857d43559fa63,
title = "Deep Learning and Insomnia: Assisting Clinicians with Their Diagnosis",
abstract = "Effective sleep analysis is hampered by the lack of automated tools catering to disordered sleep patterns and cumbersome monitoring hardware. In this paper, we apply deep learning on a set of 57 EEG features extracted from a maximum of two EEG channels to accurately differentiate between patients with insomnia or controls with no sleep complaints. We investigated two different approaches to achieve this. The first approach used EEG data from the whole sleep recording irrespective of the sleep stage (stage-independent classification), while the second used only EEG data from insomnia-impacted specific sleep stages (stage-dependent classification). We trained and tested our system using both healthy and disordered sleep collected from 41 controls and 42 primary insomnia patients. When compared with manual assessments, an NREM + REM based classifier had an overall discrimination accuracy of 92{\%} and 86{\%} between two groups using both two and one EEG channels, respectively. These results demonstrate that deep learning can be used to assist in the diagnosis of sleep disorders such as insomnia.",
keywords = "Automatic sleep stage scoring, deep learning, electroencephalogram (EEG), insomnia, sleep analysis",
author = "Mostafa Shahin and Beena Ahmed and Hamida, {Sana Tmar Ben} and Mulaffer, {Fathima Lamana} and Martin Glos and Thomas Penzel",
year = "2017",
month = "11",
day = "1",
doi = "10.1109/JBHI.2017.2650199",
language = "English",
volume = "21",
pages = "1546--1553",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Deep Learning and Insomnia

T2 - Assisting Clinicians with Their Diagnosis

AU - Shahin, Mostafa

AU - Ahmed, Beena

AU - Hamida, Sana Tmar Ben

AU - Mulaffer, Fathima Lamana

AU - Glos, Martin

AU - Penzel, Thomas

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Effective sleep analysis is hampered by the lack of automated tools catering to disordered sleep patterns and cumbersome monitoring hardware. In this paper, we apply deep learning on a set of 57 EEG features extracted from a maximum of two EEG channels to accurately differentiate between patients with insomnia or controls with no sleep complaints. We investigated two different approaches to achieve this. The first approach used EEG data from the whole sleep recording irrespective of the sleep stage (stage-independent classification), while the second used only EEG data from insomnia-impacted specific sleep stages (stage-dependent classification). We trained and tested our system using both healthy and disordered sleep collected from 41 controls and 42 primary insomnia patients. When compared with manual assessments, an NREM + REM based classifier had an overall discrimination accuracy of 92% and 86% between two groups using both two and one EEG channels, respectively. These results demonstrate that deep learning can be used to assist in the diagnosis of sleep disorders such as insomnia.

AB - Effective sleep analysis is hampered by the lack of automated tools catering to disordered sleep patterns and cumbersome monitoring hardware. In this paper, we apply deep learning on a set of 57 EEG features extracted from a maximum of two EEG channels to accurately differentiate between patients with insomnia or controls with no sleep complaints. We investigated two different approaches to achieve this. The first approach used EEG data from the whole sleep recording irrespective of the sleep stage (stage-independent classification), while the second used only EEG data from insomnia-impacted specific sleep stages (stage-dependent classification). We trained and tested our system using both healthy and disordered sleep collected from 41 controls and 42 primary insomnia patients. When compared with manual assessments, an NREM + REM based classifier had an overall discrimination accuracy of 92% and 86% between two groups using both two and one EEG channels, respectively. These results demonstrate that deep learning can be used to assist in the diagnosis of sleep disorders such as insomnia.

KW - Automatic sleep stage scoring

KW - deep learning

KW - electroencephalogram (EEG)

KW - insomnia

KW - sleep analysis

UR - http://www.scopus.com/inward/record.url?scp=85035787462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035787462&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2017.2650199

DO - 10.1109/JBHI.2017.2650199

M3 - Article

VL - 21

SP - 1546

EP - 1553

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 6

M1 - 7811237

ER -