Sleep modelled as a continuous and dynamic process predicts healthy ageing better than traditional sleep scoring.
Age
Gaussian mixture model
Machine learning
Polysomnography
Slow wave sleep
Spectral analysis
Journal
Sleep medicine
ISSN: 1878-5506
Titre abrégé: Sleep Med
Pays: Netherlands
ID NLM: 100898759
Informations de publication
Date de publication:
01 2021
01 2021
Historique:
received:
25
08
2020
revised:
24
11
2020
accepted:
27
11
2020
pubmed:
29
12
2020
medline:
22
6
2021
entrez:
28
12
2020
Statut:
ppublish
Résumé
In current clinical practice, sleep is manually scored in discrete stages of 30-s duration. We hypothesize that modelling sleep automatically as continuous and dynamic process predicts healthy ageing better than traditional scoring. Sleep electroencephalography of 15 young healthy subjects (aged ≤40 years) was used to train the modelling method. Each 3-s sleep mini-epoch was modelled as a probabilistic combination of wakefulness, light and deep sleep. For 79 healthy sleepers (aged 20-77 years), 15 sleep features were derived from manual traditional scoring (manual features), 7 from the automatic modelling (automatic features) and 24 from a combination of automatic modelling with traditional scoring (combined features). Age was predicted with seven multiple linear regression models with i) manual, ii) automatic, iii) combined, iv) manual + automatic, v) manual + combined, vi) automatic + combined, and vii) manual + automatic + combined sleep features. Using the same seven sleep feature groups, two support vector machine and one random forest classifiers were used to discriminate younger (aged <47 years) from older subjects with fivefold cross-validation. Adjusted coefficients of determination (adj-R The linear model and the classifiers using only manual features achieved the lowest values of adjusted coefficient of determination and classification validation accuracy (adj-R Continuous and dynamic sleep modelling captures healthy ageing better than traditional sleep scoring.
Sections du résumé
BACKGROUND
In current clinical practice, sleep is manually scored in discrete stages of 30-s duration. We hypothesize that modelling sleep automatically as continuous and dynamic process predicts healthy ageing better than traditional scoring.
METHODS
Sleep electroencephalography of 15 young healthy subjects (aged ≤40 years) was used to train the modelling method. Each 3-s sleep mini-epoch was modelled as a probabilistic combination of wakefulness, light and deep sleep. For 79 healthy sleepers (aged 20-77 years), 15 sleep features were derived from manual traditional scoring (manual features), 7 from the automatic modelling (automatic features) and 24 from a combination of automatic modelling with traditional scoring (combined features). Age was predicted with seven multiple linear regression models with i) manual, ii) automatic, iii) combined, iv) manual + automatic, v) manual + combined, vi) automatic + combined, and vii) manual + automatic + combined sleep features. Using the same seven sleep feature groups, two support vector machine and one random forest classifiers were used to discriminate younger (aged <47 years) from older subjects with fivefold cross-validation. Adjusted coefficients of determination (adj-R
RESULTS
The linear model and the classifiers using only manual features achieved the lowest values of adjusted coefficient of determination and classification validation accuracy (adj-R
CONCLUSIONS
Continuous and dynamic sleep modelling captures healthy ageing better than traditional sleep scoring.
Identifiants
pubmed: 33360558
pii: S1389-9457(20)30533-5
doi: 10.1016/j.sleep.2020.11.033
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
136-146Subventions
Organisme : Austrian Science Fund FWF
ID : KLI 236
Pays : Austria
Informations de copyright
Copyright © 2020 The Authors. Published by Elsevier B.V. All rights reserved.