Estimating Respiratory Modulation in Atrial Fibrillation Using a Convolutional Neural Network
(2023) Computing in Cardiology- Abstract
- The quantification of autonomic nervous system (ANS) activity from ECG data may provide useful information for personalizing atrial fibrillation (AF) treatment, but is currently not possible. Since respiration is known to elicit an ANS response, the purpose of this study was to assess whether the respiratory modulation in AV nodal refractory period and conduction delay during AF can be estimated from ECG data. We trained a 1-dimensional convolutional neural network (1D-CNN) on synthetic data generated using a network model of the AV node to estimate the respiratory modulation in AV nodal conduction. The synthetic data replicates clinical ECG-derived data and contained 1-minute segments of RR series, respiration signals and atrial... (More)
- The quantification of autonomic nervous system (ANS) activity from ECG data may provide useful information for personalizing atrial fibrillation (AF) treatment, but is currently not possible. Since respiration is known to elicit an ANS response, the purpose of this study was to assess whether the respiratory modulation in AV nodal refractory period and conduction delay during AF can be estimated from ECG data. We trained a 1-dimensional convolutional neural network (1D-CNN) on synthetic data generated using a network model of the AV node to estimate the respiratory modulation in AV nodal conduction. The synthetic data replicates clinical ECG-derived data and contained 1-minute segments of RR series, respiration signals and atrial fibrillatory rates (AFR). Further, the synthetic data was generated using a total of 4 million unique parameter sets. We showed using synthetic data that the 1D-CNN can estimate the respiratory modulation from an RR series, respiration signal and AFR with a Pearson sample correlation of ρ = 0.855. The results of the present study suggest that the proposed method can be used to quantify respiratory-induced variations in ANS activity from ECG data. Further studies are needed to verify the estimates and to investigate the clinical value of the estimates. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/09aec079-861b-48cc-b93f-0dda8b92e38c
- author
- Plappert, Felix LU ; Wallman, Mikael ; Platonov, Pyotr LU and Sandberg, Frida LU
- organization
- publishing date
- 2023-09-11
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- atrial fibrillation, atrioventricular node, autonomic tone, respiratory modulation, convolutional neural network, deep breathing test, network model, ECG
- host publication
- 2023 Computing in Cardiology Conference (CinC)
- pages
- 4 pages
- conference name
- Computing in Cardiology
- conference location
- Atlanta, United States
- conference dates
- 2023-10-01 - 2023-10-04
- external identifiers
-
- scopus:85182320322
- DOI
- 10.22489/CinC.2023.066
- language
- English
- LU publication?
- yes
- id
- 09aec079-861b-48cc-b93f-0dda8b92e38c
- date added to LUP
- 2024-01-03 19:15:56
- date last changed
- 2024-02-16 15:13:32
@inproceedings{09aec079-861b-48cc-b93f-0dda8b92e38c, abstract = {{The quantification of autonomic nervous system (ANS) activity from ECG data may provide useful information for personalizing atrial fibrillation (AF) treatment, but is currently not possible. Since respiration is known to elicit an ANS response, the purpose of this study was to assess whether the respiratory modulation in AV nodal refractory period and conduction delay during AF can be estimated from ECG data. We trained a 1-dimensional convolutional neural network (1D-CNN) on synthetic data generated using a network model of the AV node to estimate the respiratory modulation in AV nodal conduction. The synthetic data replicates clinical ECG-derived data and contained 1-minute segments of RR series, respiration signals and atrial fibrillatory rates (AFR). Further, the synthetic data was generated using a total of 4 million unique parameter sets. We showed using synthetic data that the 1D-CNN can estimate the respiratory modulation from an RR series, respiration signal and AFR with a Pearson sample correlation of ρ = 0.855. The results of the present study suggest that the proposed method can be used to quantify respiratory-induced variations in ANS activity from ECG data. Further studies are needed to verify the estimates and to investigate the clinical value of the estimates.}}, author = {{Plappert, Felix and Wallman, Mikael and Platonov, Pyotr and Sandberg, Frida}}, booktitle = {{2023 Computing in Cardiology Conference (CinC)}}, keywords = {{atrial fibrillation; atrioventricular node; autonomic tone; respiratory modulation; convolutional neural network; deep breathing test; network model; ECG}}, language = {{eng}}, month = {{09}}, title = {{Estimating Respiratory Modulation in Atrial Fibrillation Using a Convolutional Neural Network}}, url = {{https://lup.lub.lu.se/search/files/167984830/CinC2023-066.pdf}}, doi = {{10.22489/CinC.2023.066}}, year = {{2023}}, }