Cardiorespiratory sleep stage detection using conditional random fields

Research output: Contribution to journalArticleAcademicpeer-review

9 Citations (Scopus)
171 Downloads (Pure)

Abstract

This paper explores the probabilistic properties of sleep stage sequences and transitions to improve the performance of sleep stage detection using cardiorespiratory features. A new classifier, based on conditional random fields, is used in different sleep stage detection tasks (N3, NREM, REM, and wake) in night-time recordings of electrocardiogram and respiratory inductance plethysmography of healthy subjects. Using a dataset of 342 polysomnographic recordings of healthy subjects, among which 135 with regular sleep architecture, it outperforms hidden Markov models and Bayesian linear discriminants in all tasks, achieving an average accuracy of 87.38% and kappa of 0.41 (87.27% and 0.49 for regular subjects) for N3 detection, 78.71% and 0.55 (80.34% and 0.56 for regular subjects) for NREM detection, 88.49% and 0.51 (87.35% and 0.57 for regular subjects) for REM, and 85.69% and 0.51 (90.42% and 0.52 for regular subjects) for wake. In comparison with the state of the art, and having been tested on a much larger dataset, the classifier was found to outperform most of the work reported in the literature for some of the tasks, in particular for subjects with regular sleep architecture. It achieves a comparable accuracy for N3, higher accuracy and kappa for REM, and higher accuracy and comparable kappa for NREM than the best performing classifiers described in the literature.

Original languageEnglish
Pages (from-to)956-966
Number of pages11
JournalIEEE Journal of Biomedical and Health Informatics
Volume21
Issue number4
DOIs
Publication statusPublished - 1 Jul 2017

Fingerprint

Sleep Stages
Healthy Volunteers
Sleep
Classifiers
Plethysmography
Linear Models
Electrocardiography
Hidden Markov models
Inductance
Datasets

Keywords

  • Cardiac
  • conditional random fields (CRFs)
  • respiratory
  • sleep staging

Cite this

@article{223cec5338b34013865ea6620a19b816,
title = "Cardiorespiratory sleep stage detection using conditional random fields",
abstract = "This paper explores the probabilistic properties of sleep stage sequences and transitions to improve the performance of sleep stage detection using cardiorespiratory features. A new classifier, based on conditional random fields, is used in different sleep stage detection tasks (N3, NREM, REM, and wake) in night-time recordings of electrocardiogram and respiratory inductance plethysmography of healthy subjects. Using a dataset of 342 polysomnographic recordings of healthy subjects, among which 135 with regular sleep architecture, it outperforms hidden Markov models and Bayesian linear discriminants in all tasks, achieving an average accuracy of 87.38{\%} and kappa of 0.41 (87.27{\%} and 0.49 for regular subjects) for N3 detection, 78.71{\%} and 0.55 (80.34{\%} and 0.56 for regular subjects) for NREM detection, 88.49{\%} and 0.51 (87.35{\%} and 0.57 for regular subjects) for REM, and 85.69{\%} and 0.51 (90.42{\%} and 0.52 for regular subjects) for wake. In comparison with the state of the art, and having been tested on a much larger dataset, the classifier was found to outperform most of the work reported in the literature for some of the tasks, in particular for subjects with regular sleep architecture. It achieves a comparable accuracy for N3, higher accuracy and kappa for REM, and higher accuracy and comparable kappa for NREM than the best performing classifiers described in the literature.",
keywords = "Cardiac, conditional random fields (CRFs), respiratory, sleep staging",
author = "P. Fonseca and {den Teuling}, N.G.P. and X. Long and R.M. Aarts",
year = "2017",
month = "7",
day = "1",
doi = "10.1109/JBHI.2016.2550104",
language = "English",
volume = "21",
pages = "956--966",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers",
number = "4",

}

Cardiorespiratory sleep stage detection using conditional random fields. / Fonseca, P.; den Teuling, N.G.P.; Long, X.; Aarts, R.M.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 21, No. 4, 01.07.2017, p. 956-966.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Cardiorespiratory sleep stage detection using conditional random fields

AU - Fonseca, P.

AU - den Teuling, N.G.P.

AU - Long, X.

AU - Aarts, R.M.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - This paper explores the probabilistic properties of sleep stage sequences and transitions to improve the performance of sleep stage detection using cardiorespiratory features. A new classifier, based on conditional random fields, is used in different sleep stage detection tasks (N3, NREM, REM, and wake) in night-time recordings of electrocardiogram and respiratory inductance plethysmography of healthy subjects. Using a dataset of 342 polysomnographic recordings of healthy subjects, among which 135 with regular sleep architecture, it outperforms hidden Markov models and Bayesian linear discriminants in all tasks, achieving an average accuracy of 87.38% and kappa of 0.41 (87.27% and 0.49 for regular subjects) for N3 detection, 78.71% and 0.55 (80.34% and 0.56 for regular subjects) for NREM detection, 88.49% and 0.51 (87.35% and 0.57 for regular subjects) for REM, and 85.69% and 0.51 (90.42% and 0.52 for regular subjects) for wake. In comparison with the state of the art, and having been tested on a much larger dataset, the classifier was found to outperform most of the work reported in the literature for some of the tasks, in particular for subjects with regular sleep architecture. It achieves a comparable accuracy for N3, higher accuracy and kappa for REM, and higher accuracy and comparable kappa for NREM than the best performing classifiers described in the literature.

AB - This paper explores the probabilistic properties of sleep stage sequences and transitions to improve the performance of sleep stage detection using cardiorespiratory features. A new classifier, based on conditional random fields, is used in different sleep stage detection tasks (N3, NREM, REM, and wake) in night-time recordings of electrocardiogram and respiratory inductance plethysmography of healthy subjects. Using a dataset of 342 polysomnographic recordings of healthy subjects, among which 135 with regular sleep architecture, it outperforms hidden Markov models and Bayesian linear discriminants in all tasks, achieving an average accuracy of 87.38% and kappa of 0.41 (87.27% and 0.49 for regular subjects) for N3 detection, 78.71% and 0.55 (80.34% and 0.56 for regular subjects) for NREM detection, 88.49% and 0.51 (87.35% and 0.57 for regular subjects) for REM, and 85.69% and 0.51 (90.42% and 0.52 for regular subjects) for wake. In comparison with the state of the art, and having been tested on a much larger dataset, the classifier was found to outperform most of the work reported in the literature for some of the tasks, in particular for subjects with regular sleep architecture. It achieves a comparable accuracy for N3, higher accuracy and kappa for REM, and higher accuracy and comparable kappa for NREM than the best performing classifiers described in the literature.

KW - Cardiac

KW - conditional random fields (CRFs)

KW - respiratory

KW - sleep staging

UR - http://www.scopus.com/inward/record.url?scp=85023607708&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2016.2550104

DO - 10.1109/JBHI.2016.2550104

M3 - Article

C2 - 27076473

AN - SCOPUS:85023607708

VL - 21

SP - 956

EP - 966

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 4

ER -