The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing

Jiali Xie; Pedro Fonseca; Johannes P van Dijk; Xi Long; Sebastiaan Overeem

doi:10.3390/diagnostics13132146

The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing

Jiali Xie (Corresponding author), Pedro Fonseca, Johannes P van Dijk, Xi Long (Corresponding author), Sebastiaan Overeem

Onderzoeksoutput: Bijdrage aan tijdschrift › Tijdschriftartikel › Academic › peer review

4 Citaten (Scopus)

40 Downloads (Pure)

Samenvatting

BACKGROUND: Sleep apnea is a prevalent sleep-disordered breathing (SDB) condition that affects a large population worldwide. Research has demonstrated the potential of using electrocardiographic (ECG) signals (heart rate and ECG-derived respiration, EDR) to detect SDB. However, EDR may be a suboptimal replacement for respiration signals.

METHODS: We evaluated a previously described ECG-based deep learning algorithm in an independent dataset including 198 patients and compared performance for SDB event detection using thoracic respiratory effort versus EDR. We also evaluated the algorithm in terms of apnea-hypopnea index (AHI) estimation performance, and SDB severity classification based on the estimated AHI.

RESULTS: Using respiratory effort instead of EDR, we achieved an improved performance in SDB event detection (F1 score = 0.708), AHI estimation (Spearman's correlation = 0.922), and SDB severity classification (Cohen's kappa of 0.62 was obtained based on AHI).

CONCLUSION: Respiratory effort is superior to EDR to assess SDB. Using respiratory effort and ECG, the previously described algorithm achieves good performance in a new dataset from an independent laboratory confirming its adequacy for this task.

Originele taal-2	Engels
Artikelnummer	2146
Aantal pagina's	15
Tijdschrift	Diagnostics
Volume	13
Nummer van het tijdschrift	13
DOI's	https://doi.org/10.3390/diagnostics13132146
Status	Gepubliceerd - 1 jul. 2023

Financiering

Parts of this study were supported by the Open Technology Program from STW/NWO (OSA+ project no. 14619), OPZuid (Bedsense, 2015) and an Impulse grant in the Eindhoven MedTech Innovation Center (e/MTIC) cooperation.

Financiers	Financiernummer
Nederlandse Organisatie voor Wetenschappelijk Onderzoek	14619
STW

Toegang tot document

10.3390/diagnostics13132146

pdfDefinitieve gepubliceerde versie, 1,93 MBLicentie: CC BY

Andere bestanden en links

Link naar publicatie in Scopus

Sleep Medicine
van Gilst, M. M. (Content manager) & van der Hout-van der Jagt, M. B. (Content manager)
Impact: Research Topic/Theme (at group level)

Citeer dit

@article{facd1c88068d4cd89e9bbd1f59d375f8,

title = "The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing",

abstract = "BACKGROUND: Sleep apnea is a prevalent sleep-disordered breathing (SDB) condition that affects a large population worldwide. Research has demonstrated the potential of using electrocardiographic (ECG) signals (heart rate and ECG-derived respiration, EDR) to detect SDB. However, EDR may be a suboptimal replacement for respiration signals.METHODS: We evaluated a previously described ECG-based deep learning algorithm in an independent dataset including 198 patients and compared performance for SDB event detection using thoracic respiratory effort versus EDR. We also evaluated the algorithm in terms of apnea-hypopnea index (AHI) estimation performance, and SDB severity classification based on the estimated AHI.RESULTS: Using respiratory effort instead of EDR, we achieved an improved performance in SDB event detection (F1 score = 0.708), AHI estimation (Spearman's correlation = 0.922), and SDB severity classification (Cohen's kappa of 0.62 was obtained based on AHI).CONCLUSION: Respiratory effort is superior to EDR to assess SDB. Using respiratory effort and ECG, the previously described algorithm achieves good performance in a new dataset from an independent laboratory confirming its adequacy for this task.",

keywords = "apnea, ECG-derived respiration, electrocardiogram, recurrent neural network, respiratory effort, sleep-disordered breathing",

author = "Jiali Xie and Pedro Fonseca and {van Dijk}, {Johannes P} and Xi Long and Sebastiaan Overeem",

year = "2023",

month = jul,

day = "1",

doi = "10.3390/diagnostics13132146",

language = "English",

volume = "13",

journal = "Diagnostics",

issn = "2075-4418",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "13",

}

TY - JOUR

T1 - The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing

AU - Xie, Jiali

AU - Fonseca, Pedro

AU - van Dijk, Johannes P

AU - Long, Xi

AU - Overeem, Sebastiaan

PY - 2023/7/1

Y1 - 2023/7/1

N2 - BACKGROUND: Sleep apnea is a prevalent sleep-disordered breathing (SDB) condition that affects a large population worldwide. Research has demonstrated the potential of using electrocardiographic (ECG) signals (heart rate and ECG-derived respiration, EDR) to detect SDB. However, EDR may be a suboptimal replacement for respiration signals.METHODS: We evaluated a previously described ECG-based deep learning algorithm in an independent dataset including 198 patients and compared performance for SDB event detection using thoracic respiratory effort versus EDR. We also evaluated the algorithm in terms of apnea-hypopnea index (AHI) estimation performance, and SDB severity classification based on the estimated AHI.RESULTS: Using respiratory effort instead of EDR, we achieved an improved performance in SDB event detection (F1 score = 0.708), AHI estimation (Spearman's correlation = 0.922), and SDB severity classification (Cohen's kappa of 0.62 was obtained based on AHI).CONCLUSION: Respiratory effort is superior to EDR to assess SDB. Using respiratory effort and ECG, the previously described algorithm achieves good performance in a new dataset from an independent laboratory confirming its adequacy for this task.

AB - BACKGROUND: Sleep apnea is a prevalent sleep-disordered breathing (SDB) condition that affects a large population worldwide. Research has demonstrated the potential of using electrocardiographic (ECG) signals (heart rate and ECG-derived respiration, EDR) to detect SDB. However, EDR may be a suboptimal replacement for respiration signals.METHODS: We evaluated a previously described ECG-based deep learning algorithm in an independent dataset including 198 patients and compared performance for SDB event detection using thoracic respiratory effort versus EDR. We also evaluated the algorithm in terms of apnea-hypopnea index (AHI) estimation performance, and SDB severity classification based on the estimated AHI.RESULTS: Using respiratory effort instead of EDR, we achieved an improved performance in SDB event detection (F1 score = 0.708), AHI estimation (Spearman's correlation = 0.922), and SDB severity classification (Cohen's kappa of 0.62 was obtained based on AHI).CONCLUSION: Respiratory effort is superior to EDR to assess SDB. Using respiratory effort and ECG, the previously described algorithm achieves good performance in a new dataset from an independent laboratory confirming its adequacy for this task.

KW - apnea

KW - ECG-derived respiration

KW - electrocardiogram

KW - recurrent neural network

KW - respiratory effort

KW - sleep-disordered breathing

UR - http://www.scopus.com/inward/record.url?scp=85164727924&partnerID=8YFLogxK

U2 - 10.3390/diagnostics13132146

DO - 10.3390/diagnostics13132146

M3 - Article

C2 - 37443540

SN - 2075-4418

VL - 13

JO - Diagnostics

JF - Diagnostics

IS - 13

M1 - 2146

ER -

The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing

Samenvatting

Financiering

Toegang tot document

Andere bestanden en links

Vingerafdruk

Impact

Sleep Medicine

Citeer dit