Estimation of the apnea-hypopnea index in a heterogeneous sleep-disordered population using optimised cardiovascular features

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

5 Downloads (Pure)

Uittreksel

Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder, which results in daytime symptoms, a reduced quality of life as well as long-term negative health consequences. OSA diagnosis and severity rating is typically based on the apnea-hypopnea index (AHI) retrieved from overnight poly(somno)graphy. However, polysomnography is costly, obtrusive and not suitable for long-term recordings. Here, we present a method for unobtrusive estimation of the AHI using ECG-based features to detect OSA-related events. Moreover, adding ECG-based sleep/wake scoring yields a fully automatic method for AHI-estimation. Importantly, our algorithm was developed and validated on a combination of clinical datasets, including datasets selectively including OSA-pathology but also a heterogeneous, “real-world” clinical sleep disordered population (262 participants in the validation set). The algorithm provides a good representation of the current gold standard AHI (0.72 correlation, estimation error of 0.56 ± 14.74 events/h), and can also be employed as a screening tool for a large range of OSA severities (ROC AUC ≥ 0.86, Cohen’s kappa ≥ 0.53 and precision ≥70%). The method compares favourably to other OSA monitoring strategies, showing the feasibility of cardiovascular-based surrogates for sleep monitoring to evolve into clinically usable tools.
Originele taal-2Engels
Artikelnummer17448
Aantal pagina's16
TijdschriftScientific Reports
Volume9
Nummer van het tijdschrift1
DOI's
StatusGepubliceerd - 1 dec 2019

Vingerafdruk

Obstructive Sleep Apnea
Apnea
Sleep
Polysomnography
Population
Electrocardiography
Quality of Life
Pathology
Health

Citeer dit

@article{e9168c5ac6c2499085c1c4fb6549311c,
title = "Estimation of the apnea-hypopnea index in a heterogeneous sleep-disordered population using optimised cardiovascular features",
abstract = "Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder, which results in daytime symptoms, a reduced quality of life as well as long-term negative health consequences. OSA diagnosis and severity rating is typically based on the apnea-hypopnea index (AHI) retrieved from overnight poly(somno)graphy. However, polysomnography is costly, obtrusive and not suitable for long-term recordings. Here, we present a method for unobtrusive estimation of the AHI using ECG-based features to detect OSA-related events. Moreover, adding ECG-based sleep/wake scoring yields a fully automatic method for AHI-estimation. Importantly, our algorithm was developed and validated on a combination of clinical datasets, including datasets selectively including OSA-pathology but also a heterogeneous, “real-world” clinical sleep disordered population (262 participants in the validation set). The algorithm provides a good representation of the current gold standard AHI (0.72 correlation, estimation error of 0.56 ± 14.74 events/h), and can also be employed as a screening tool for a large range of OSA severities (ROC AUC ≥ 0.86, Cohen’s kappa ≥ 0.53 and precision ≥70{\%}). The method compares favourably to other OSA monitoring strategies, showing the feasibility of cardiovascular-based surrogates for sleep monitoring to evolve into clinically usable tools.",
keywords = "ECG, Sleep Apnea, Obstructive, Machine learning, Sleep Disorders",
author = "Gabriele Papini and Pedro Fonseca and {van Gilst}, {Merel M.} and {van Dijk}, {J.P. (Hans)} and Pevernagie, {Dirk A.} and Bergmans, {Jan W.M.} and Rik Vullings and Sebastiaan Overeem",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-53403-y",
language = "English",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Estimation of the apnea-hypopnea index in a heterogeneous sleep-disordered population using optimised cardiovascular features

AU - Papini, Gabriele

AU - Fonseca, Pedro

AU - van Gilst, Merel M.

AU - van Dijk, J.P. (Hans)

AU - Pevernagie, Dirk A.

AU - Bergmans, Jan W.M.

AU - Vullings, Rik

AU - Overeem, Sebastiaan

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder, which results in daytime symptoms, a reduced quality of life as well as long-term negative health consequences. OSA diagnosis and severity rating is typically based on the apnea-hypopnea index (AHI) retrieved from overnight poly(somno)graphy. However, polysomnography is costly, obtrusive and not suitable for long-term recordings. Here, we present a method for unobtrusive estimation of the AHI using ECG-based features to detect OSA-related events. Moreover, adding ECG-based sleep/wake scoring yields a fully automatic method for AHI-estimation. Importantly, our algorithm was developed and validated on a combination of clinical datasets, including datasets selectively including OSA-pathology but also a heterogeneous, “real-world” clinical sleep disordered population (262 participants in the validation set). The algorithm provides a good representation of the current gold standard AHI (0.72 correlation, estimation error of 0.56 ± 14.74 events/h), and can also be employed as a screening tool for a large range of OSA severities (ROC AUC ≥ 0.86, Cohen’s kappa ≥ 0.53 and precision ≥70%). The method compares favourably to other OSA monitoring strategies, showing the feasibility of cardiovascular-based surrogates for sleep monitoring to evolve into clinically usable tools.

AB - Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder, which results in daytime symptoms, a reduced quality of life as well as long-term negative health consequences. OSA diagnosis and severity rating is typically based on the apnea-hypopnea index (AHI) retrieved from overnight poly(somno)graphy. However, polysomnography is costly, obtrusive and not suitable for long-term recordings. Here, we present a method for unobtrusive estimation of the AHI using ECG-based features to detect OSA-related events. Moreover, adding ECG-based sleep/wake scoring yields a fully automatic method for AHI-estimation. Importantly, our algorithm was developed and validated on a combination of clinical datasets, including datasets selectively including OSA-pathology but also a heterogeneous, “real-world” clinical sleep disordered population (262 participants in the validation set). The algorithm provides a good representation of the current gold standard AHI (0.72 correlation, estimation error of 0.56 ± 14.74 events/h), and can also be employed as a screening tool for a large range of OSA severities (ROC AUC ≥ 0.86, Cohen’s kappa ≥ 0.53 and precision ≥70%). The method compares favourably to other OSA monitoring strategies, showing the feasibility of cardiovascular-based surrogates for sleep monitoring to evolve into clinically usable tools.

KW - ECG

KW - Sleep Apnea, Obstructive

KW - Machine learning

KW - Sleep Disorders

UR - http://www.scopus.com/inward/record.url?scp=85075598051&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-53403-y

DO - 10.1038/s41598-019-53403-y

M3 - Article

C2 - 31772228

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 17448

ER -