A computationally efficient algorithm for wearable sleep staging in clinical populations.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
06 06 2023
06 06 2023
Historique:
received:
31
01
2023
accepted:
03
06
2023
medline:
8
6
2023
pubmed:
7
6
2023
entrez:
6
6
2023
Statut:
epublish
Résumé
This study describes a computationally efficient algorithm for 4-class sleep staging based on cardiac activity and body movements. Using an accelerometer to calculate gross body movements and a reflective photoplethysmographic (PPG) sensor to determine interbeat intervals and a corresponding instantaneous heart rate signal, a neural network was trained to classify between wake, combined N1 and N2, N3 and REM sleep in epochs of 30 s. The classifier was validated on a hold-out set by comparing the output against manually scored sleep stages based on polysomnography (PSG). In addition, the execution time was compared with that of a previously developed heart rate variability (HRV) feature-based sleep staging algorithm. With a median epoch-per-epoch κ of 0.638 and accuracy of 77.8% the algorithm achieved an equivalent performance when compared to the previously developed HRV-based approach, but with a 50-times faster execution time. This shows how a neural network, without leveraging any a priori knowledge of the domain, can automatically "discover" a suitable mapping between cardiac activity and body movements, and sleep stages, even in patients with different sleep pathologies. In addition to the high performance, the reduced complexity of the algorithm makes practical implementation feasible, opening up new avenues in sleep diagnostics.
Identifiants
pubmed: 37280297
doi: 10.1038/s41598-023-36444-2
pii: 10.1038/s41598-023-36444-2
pmc: PMC10244431
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
9182Informations de copyright
© 2023. The Author(s).
Références
BMC Sports Sci Med Rehabil. 2018 May 31;10:10
pubmed: 29881626
Front Physiol. 2013 Oct 16;4:294
pubmed: 24137133
Dev Psychol. 2020 Apr;56(4):783-794
pubmed: 31999180
Sleep. 2015 Oct 01;38(10):1555-66
pubmed: 25902809
Physiol Meas. 2019 Feb 26;40(2):025006
pubmed: 30699397
Sleep. 2020 Sep 14;43(9):
pubmed: 32249911
IEEE Eng Med Biol Mag. 2001 May-Jun;20(3):51-7
pubmed: 11446210
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571
Sleep Med Rev. 2012 Feb;16(1):47-66
pubmed: 21658979
Med Sci Sports Exerc. 2019 Jul;51(7):1538-1557
pubmed: 30789439
NPJ Digit Med. 2021 Sep 15;4(1):135
pubmed: 34526643
IEEE Trans Pattern Anal Mach Intell. 2020 Feb;42(2):318-327
pubmed: 30040631
BMC Res Notes. 2020 Nov 10;13(1):513
pubmed: 33168051
J Gen Intern Med. 2011 Feb;26(2):192-6
pubmed: 20857339
Bioengineering (Basel). 2023 Jan 12;10(1):
pubmed: 36671681
J Clin Sleep Med. 2013 Jan 15;9(1):81-7
pubmed: 23319910
Physiol Meas. 2018 Aug 08;39(8):084001
pubmed: 29995641
Springerplus. 2014 Jul 25;3:376
pubmed: 26034664
J Appl Physiol. 1976 Nov;41(5 Pt. 1):734-8
pubmed: 993161
J Sleep Res. 2022 Aug;31(4):e13541
pubmed: 34927296
Sci Rep. 2019 Oct 2;9(1):14149
pubmed: 31578345
Nat Sci Sleep. 2021 Jun 28;13:885-897
pubmed: 34234595
BMJ Open. 2019 Nov 25;9(11):e030996
pubmed: 31772091
Sleep. 2017 Jul 1;40(7):
pubmed: 28838130
J Clin Sleep Med. 2021 Jul 1;17(7):1343-1354
pubmed: 33660612