Improving sleep/wake classification with recurrence quantification analysis features

Jérôme Rolink, P.M. ferreira dos santos da Fonseca, X. Long, Steffen Leonhardt

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

In this work the method of Recurrence Quantification Analysis (RQA), often used for the analysis of complex dynamic systems, is employed to extract novel features for sleep/wake classification only using cardio-respiratory signals like electrocardiogram (ECG), heart rate (HR) and respiratory effort (RE). A polysomnography data set consisting of 313 full-night recordings is used to evaluate the features. The sleep/wake classification is performed with a classifier based on Linear Discriminant Analysis (LDA) and it is validated in a Leave One Subject Out cross-validation (LOSOCV) scheme. More than 1300 features are extracted from five different cardio-respiratory modalities (ECG, RE, HR, and combinations of ECG + RE and RE + HR). Each modality is processed to obtain 13 basic RQA features, five post-processed versions and, furthermore, three normalizations are applied, leading to a total count of 975 RQA features. From literature, 126 known cardio-respiratory and actigraphy features, normalized with the same procedures thus resulting in 378 distinct features, are used for performance comparison. A feature selection method based on the Mahalanobis distance and the inter-feature correlation is used to determine the most relevant features of both sets, resulting in a set of 158 from the existing features (set A) and 232 from the RQA based features (set B). The pooled Cohen’s kappa coefficient for set A and set B is 0.586 and 0.522, respectively. The combination of both feature sets (set C) improves the kappa value to 0.625.

In addition, ROC and PR curves with their corresponding Area Under Curve (AUC) values are computed. It is also shown that derived sleep statistics (sleep efficiency, sleep onset, total sleep time, etc.) deviate less with respect to the ground truth annotations using the additional RQA features compared to the use of literature-based features only.

Besides the overall performance, the data set is split into six different but almost equally sized age and sex groups to allow unbiased comparisons among each other. It is shown, that the classification performance decreases with increasing age but is almost independent from sex. Hence, for future work it is suggested to implement the RQA features and also to focus on the improvement of features especially for elderly persons.
LanguageEnglish
Pages78-86
JournalBiomedical Signal Processing and Control
Volume49
DOIs
StatePublished - Mar 2019

Fingerprint

Sleep
Recurrence
Electrocardiography
Heart Rate
Actigraphy
Polysomnography
Discriminant Analysis
Discriminant analysis
Systems Analysis
ROC Curve
Area Under Curve
Feature extraction
Dynamical systems
Classifiers
Age Groups
Statistics
Datasets

Keywords

  • Recurrence quantification analysis
  • Feature extraction
  • Sleep/wake classification

Cite this

@article{6607c8538f2b4b3e8343cd8e98d12fea,
title = "Improving sleep/wake classification with recurrence quantification analysis features",
abstract = "In this work the method of Recurrence Quantification Analysis (RQA), often used for the analysis of complex dynamic systems, is employed to extract novel features for sleep/wake classification only using cardio-respiratory signals like electrocardiogram (ECG), heart rate (HR) and respiratory effort (RE). A polysomnography data set consisting of 313 full-night recordings is used to evaluate the features. The sleep/wake classification is performed with a classifier based on Linear Discriminant Analysis (LDA) and it is validated in a Leave One Subject Out cross-validation (LOSOCV) scheme. More than 1300 features are extracted from five different cardio-respiratory modalities (ECG, RE, HR, and combinations of ECG + RE and RE + HR). Each modality is processed to obtain 13 basic RQA features, five post-processed versions and, furthermore, three normalizations are applied, leading to a total count of 975 RQA features. From literature, 126 known cardio-respiratory and actigraphy features, normalized with the same procedures thus resulting in 378 distinct features, are used for performance comparison. A feature selection method based on the Mahalanobis distance and the inter-feature correlation is used to determine the most relevant features of both sets, resulting in a set of 158 from the existing features (set A) and 232 from the RQA based features (set B). The pooled Cohen’s kappa coefficient for set A and set B is 0.586 and 0.522, respectively. The combination of both feature sets (set C) improves the kappa value to 0.625.In addition, ROC and PR curves with their corresponding Area Under Curve (AUC) values are computed. It is also shown that derived sleep statistics (sleep efficiency, sleep onset, total sleep time, etc.) deviate less with respect to the ground truth annotations using the additional RQA features compared to the use of literature-based features only.Besides the overall performance, the data set is split into six different but almost equally sized age and sex groups to allow unbiased comparisons among each other. It is shown, that the classification performance decreases with increasing age but is almost independent from sex. Hence, for future work it is suggested to implement the RQA features and also to focus on the improvement of features especially for elderly persons.",
keywords = "Recurrence quantification analysis, Feature extraction, Sleep/wake classification",
author = "J{\'e}r{\^o}me Rolink and {da Fonseca}, {P.M. ferreira dos santos} and X. Long and Steffen Leonhardt",
year = "2019",
month = "3",
doi = "10.1016/j.bspc.2018.11.005",
language = "English",
volume = "49",
pages = "78--86",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier",

}

Improving sleep/wake classification with recurrence quantification analysis features. / Rolink, Jérôme; da Fonseca, P.M. ferreira dos santos; Long, X.; Leonhardt, Steffen.

In: Biomedical Signal Processing and Control, Vol. 49, 03.2019, p. 78-86.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Improving sleep/wake classification with recurrence quantification analysis features

AU - Rolink,Jérôme

AU - da Fonseca,P.M. ferreira dos santos

AU - Long,X.

AU - Leonhardt,Steffen

PY - 2019/3

Y1 - 2019/3

N2 - In this work the method of Recurrence Quantification Analysis (RQA), often used for the analysis of complex dynamic systems, is employed to extract novel features for sleep/wake classification only using cardio-respiratory signals like electrocardiogram (ECG), heart rate (HR) and respiratory effort (RE). A polysomnography data set consisting of 313 full-night recordings is used to evaluate the features. The sleep/wake classification is performed with a classifier based on Linear Discriminant Analysis (LDA) and it is validated in a Leave One Subject Out cross-validation (LOSOCV) scheme. More than 1300 features are extracted from five different cardio-respiratory modalities (ECG, RE, HR, and combinations of ECG + RE and RE + HR). Each modality is processed to obtain 13 basic RQA features, five post-processed versions and, furthermore, three normalizations are applied, leading to a total count of 975 RQA features. From literature, 126 known cardio-respiratory and actigraphy features, normalized with the same procedures thus resulting in 378 distinct features, are used for performance comparison. A feature selection method based on the Mahalanobis distance and the inter-feature correlation is used to determine the most relevant features of both sets, resulting in a set of 158 from the existing features (set A) and 232 from the RQA based features (set B). The pooled Cohen’s kappa coefficient for set A and set B is 0.586 and 0.522, respectively. The combination of both feature sets (set C) improves the kappa value to 0.625.In addition, ROC and PR curves with their corresponding Area Under Curve (AUC) values are computed. It is also shown that derived sleep statistics (sleep efficiency, sleep onset, total sleep time, etc.) deviate less with respect to the ground truth annotations using the additional RQA features compared to the use of literature-based features only.Besides the overall performance, the data set is split into six different but almost equally sized age and sex groups to allow unbiased comparisons among each other. It is shown, that the classification performance decreases with increasing age but is almost independent from sex. Hence, for future work it is suggested to implement the RQA features and also to focus on the improvement of features especially for elderly persons.

AB - In this work the method of Recurrence Quantification Analysis (RQA), often used for the analysis of complex dynamic systems, is employed to extract novel features for sleep/wake classification only using cardio-respiratory signals like electrocardiogram (ECG), heart rate (HR) and respiratory effort (RE). A polysomnography data set consisting of 313 full-night recordings is used to evaluate the features. The sleep/wake classification is performed with a classifier based on Linear Discriminant Analysis (LDA) and it is validated in a Leave One Subject Out cross-validation (LOSOCV) scheme. More than 1300 features are extracted from five different cardio-respiratory modalities (ECG, RE, HR, and combinations of ECG + RE and RE + HR). Each modality is processed to obtain 13 basic RQA features, five post-processed versions and, furthermore, three normalizations are applied, leading to a total count of 975 RQA features. From literature, 126 known cardio-respiratory and actigraphy features, normalized with the same procedures thus resulting in 378 distinct features, are used for performance comparison. A feature selection method based on the Mahalanobis distance and the inter-feature correlation is used to determine the most relevant features of both sets, resulting in a set of 158 from the existing features (set A) and 232 from the RQA based features (set B). The pooled Cohen’s kappa coefficient for set A and set B is 0.586 and 0.522, respectively. The combination of both feature sets (set C) improves the kappa value to 0.625.In addition, ROC and PR curves with their corresponding Area Under Curve (AUC) values are computed. It is also shown that derived sleep statistics (sleep efficiency, sleep onset, total sleep time, etc.) deviate less with respect to the ground truth annotations using the additional RQA features compared to the use of literature-based features only.Besides the overall performance, the data set is split into six different but almost equally sized age and sex groups to allow unbiased comparisons among each other. It is shown, that the classification performance decreases with increasing age but is almost independent from sex. Hence, for future work it is suggested to implement the RQA features and also to focus on the improvement of features especially for elderly persons.

KW - Recurrence quantification analysis

KW - Feature extraction

KW - Sleep/wake classification

U2 - 10.1016/j.bspc.2018.11.005

DO - 10.1016/j.bspc.2018.11.005

M3 - Article

VL - 49

SP - 78

EP - 86

JO - Biomedical Signal Processing and Control

T2 - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

ER -