A comparison of probabilistic classifiers for sleep stage classification

Research output: Contribution to journalArticleAcademicpeer-review

9 Citations (Scopus)
52 Downloads (Pure)

Abstract

Objective: To compare conditional random fields (CRF), hidden Markov models (HMMs) and Bayesian linear discriminants (LDs) for cardiorespiratory sleep stage classification on a five-class sleep staging task (wake/N1/N2/N3/REM), to explore the benefits of incorporating time information in the classification and to evaluate the feasibility of sleep staging on obstructive sleep apnea (OSA) patients. Approach: The classifiers with and without time information were evaluated with 10-fold cross-validation on five-, four- (wake/N1 + N2/N3/REM) and three-class (wake/NREM/REM) classification tasks using a data set comprising 443 night-time polysomnography (PSG) recordings of 231 participants (180 healthy participants, 100 of which had a 'regular' sleep architecture, and 51 participants previously diagnosed with OSA). Main results: CRF with time information (CRFt) outperforms all other classifiers on all tasks, achieving a median accuracy and Cohen's κ for all participants of 62.8% and 0.44 for five classes, 68.8% and 0.47 for four classes, and 77.6% and 0.55 for three classes. An advantage was found in training classifiers, specifically for 'regular' and 'OSA' participants, achieving an improvement in classification performance for these groups. For 'regular' participants, CRFt achieved a median accuracy and Cohen's κ of 67.0% and 0.51, 70.8% and 0.53 and 81.3% and 0.62 for five-, four- and three-classes respectively, and for 'OSA' patients, of 59.9% and 0.40, 69.7% and 0.45, and 75.8% and 0.51 for five-, four- and three-classes respectively. Significance: The results suggest that CRFt is not only better at learning and predicting more complex and irregular sleep architectures, but that it also performs reasonably well in five-class classification - the standard for sleep scoring used in clinical PSG. Additionally, and albeit with a decrease in performance when compared with healthy participants, sleep stage classification in OSA patients using cardiorespiratory features and CRFt seems feasible with reasonable accuracy.

Original languageEnglish
Article number055001
Number of pages15
JournalPhysiological Measurement
Volume39
Issue number5
DOIs
Publication statusPublished - 15 May 2018

Fingerprint

Sleep Stages
Obstructive Sleep Apnea
Classifiers
Sleep
Polysomnography
Healthy Volunteers
Linear Models
Learning
Hidden Markov models

Keywords

  • cardiac
  • conditional random fields
  • respiratory
  • sleep staging

Cite this

@article{00c58621c3f74c76a9b9f0f029205b32,
title = "A comparison of probabilistic classifiers for sleep stage classification",
abstract = "Objective: To compare conditional random fields (CRF), hidden Markov models (HMMs) and Bayesian linear discriminants (LDs) for cardiorespiratory sleep stage classification on a five-class sleep staging task (wake/N1/N2/N3/REM), to explore the benefits of incorporating time information in the classification and to evaluate the feasibility of sleep staging on obstructive sleep apnea (OSA) patients. Approach: The classifiers with and without time information were evaluated with 10-fold cross-validation on five-, four- (wake/N1 + N2/N3/REM) and three-class (wake/NREM/REM) classification tasks using a data set comprising 443 night-time polysomnography (PSG) recordings of 231 participants (180 healthy participants, 100 of which had a 'regular' sleep architecture, and 51 participants previously diagnosed with OSA). Main results: CRF with time information (CRFt) outperforms all other classifiers on all tasks, achieving a median accuracy and Cohen's κ for all participants of 62.8{\%} and 0.44 for five classes, 68.8{\%} and 0.47 for four classes, and 77.6{\%} and 0.55 for three classes. An advantage was found in training classifiers, specifically for 'regular' and 'OSA' participants, achieving an improvement in classification performance for these groups. For 'regular' participants, CRFt achieved a median accuracy and Cohen's κ of 67.0{\%} and 0.51, 70.8{\%} and 0.53 and 81.3{\%} and 0.62 for five-, four- and three-classes respectively, and for 'OSA' patients, of 59.9{\%} and 0.40, 69.7{\%} and 0.45, and 75.8{\%} and 0.51 for five-, four- and three-classes respectively. Significance: The results suggest that CRFt is not only better at learning and predicting more complex and irregular sleep architectures, but that it also performs reasonably well in five-class classification - the standard for sleep scoring used in clinical PSG. Additionally, and albeit with a decrease in performance when compared with healthy participants, sleep stage classification in OSA patients using cardiorespiratory features and CRFt seems feasible with reasonable accuracy.",
keywords = "cardiac, conditional random fields, respiratory, sleep staging",
author = "Pedro Fonseca and {Den Teuling}, Niek and Xi Long and Aarts, {Ronald M.}",
year = "2018",
month = "5",
day = "15",
doi = "10.1088/1361-6579/aabbc2",
language = "English",
volume = "39",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "Institute of Physics",
number = "5",

}

A comparison of probabilistic classifiers for sleep stage classification. / Fonseca, Pedro; Den Teuling, Niek; Long, Xi; Aarts, Ronald M.

In: Physiological Measurement, Vol. 39, No. 5, 055001, 15.05.2018.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A comparison of probabilistic classifiers for sleep stage classification

AU - Fonseca, Pedro

AU - Den Teuling, Niek

AU - Long, Xi

AU - Aarts, Ronald M.

PY - 2018/5/15

Y1 - 2018/5/15

N2 - Objective: To compare conditional random fields (CRF), hidden Markov models (HMMs) and Bayesian linear discriminants (LDs) for cardiorespiratory sleep stage classification on a five-class sleep staging task (wake/N1/N2/N3/REM), to explore the benefits of incorporating time information in the classification and to evaluate the feasibility of sleep staging on obstructive sleep apnea (OSA) patients. Approach: The classifiers with and without time information were evaluated with 10-fold cross-validation on five-, four- (wake/N1 + N2/N3/REM) and three-class (wake/NREM/REM) classification tasks using a data set comprising 443 night-time polysomnography (PSG) recordings of 231 participants (180 healthy participants, 100 of which had a 'regular' sleep architecture, and 51 participants previously diagnosed with OSA). Main results: CRF with time information (CRFt) outperforms all other classifiers on all tasks, achieving a median accuracy and Cohen's κ for all participants of 62.8% and 0.44 for five classes, 68.8% and 0.47 for four classes, and 77.6% and 0.55 for three classes. An advantage was found in training classifiers, specifically for 'regular' and 'OSA' participants, achieving an improvement in classification performance for these groups. For 'regular' participants, CRFt achieved a median accuracy and Cohen's κ of 67.0% and 0.51, 70.8% and 0.53 and 81.3% and 0.62 for five-, four- and three-classes respectively, and for 'OSA' patients, of 59.9% and 0.40, 69.7% and 0.45, and 75.8% and 0.51 for five-, four- and three-classes respectively. Significance: The results suggest that CRFt is not only better at learning and predicting more complex and irregular sleep architectures, but that it also performs reasonably well in five-class classification - the standard for sleep scoring used in clinical PSG. Additionally, and albeit with a decrease in performance when compared with healthy participants, sleep stage classification in OSA patients using cardiorespiratory features and CRFt seems feasible with reasonable accuracy.

AB - Objective: To compare conditional random fields (CRF), hidden Markov models (HMMs) and Bayesian linear discriminants (LDs) for cardiorespiratory sleep stage classification on a five-class sleep staging task (wake/N1/N2/N3/REM), to explore the benefits of incorporating time information in the classification and to evaluate the feasibility of sleep staging on obstructive sleep apnea (OSA) patients. Approach: The classifiers with and without time information were evaluated with 10-fold cross-validation on five-, four- (wake/N1 + N2/N3/REM) and three-class (wake/NREM/REM) classification tasks using a data set comprising 443 night-time polysomnography (PSG) recordings of 231 participants (180 healthy participants, 100 of which had a 'regular' sleep architecture, and 51 participants previously diagnosed with OSA). Main results: CRF with time information (CRFt) outperforms all other classifiers on all tasks, achieving a median accuracy and Cohen's κ for all participants of 62.8% and 0.44 for five classes, 68.8% and 0.47 for four classes, and 77.6% and 0.55 for three classes. An advantage was found in training classifiers, specifically for 'regular' and 'OSA' participants, achieving an improvement in classification performance for these groups. For 'regular' participants, CRFt achieved a median accuracy and Cohen's κ of 67.0% and 0.51, 70.8% and 0.53 and 81.3% and 0.62 for five-, four- and three-classes respectively, and for 'OSA' patients, of 59.9% and 0.40, 69.7% and 0.45, and 75.8% and 0.51 for five-, four- and three-classes respectively. Significance: The results suggest that CRFt is not only better at learning and predicting more complex and irregular sleep architectures, but that it also performs reasonably well in five-class classification - the standard for sleep scoring used in clinical PSG. Additionally, and albeit with a decrease in performance when compared with healthy participants, sleep stage classification in OSA patients using cardiorespiratory features and CRFt seems feasible with reasonable accuracy.

KW - cardiac

KW - conditional random fields

KW - respiratory

KW - sleep staging

UR - http://www.scopus.com/inward/record.url?scp=85049020064&partnerID=8YFLogxK

U2 - 10.1088/1361-6579/aabbc2

DO - 10.1088/1361-6579/aabbc2

M3 - Article

C2 - 29620019

AN - SCOPUS:85049020064

VL - 39

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 5

M1 - 055001

ER -