Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals

Marco Mamprin; Jo M. Zelis; Pim A.L. Tonino; Svitlana Zinger; Peter H.N. De With

doi:10.1145/3535694.3535708

Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals

Marco Mamprin, Jo M. Zelis, Pim A.L. Tonino, Svitlana Zinger, Peter H.N. De With

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

4 Downloads (Pure)

Abstract

This research aims to investigate the feasibility in predicting, at several stages of the transcatheter aortic valve implantation (TAVI) procedure, the risk to develop cardiac conduction defects (CCD) requiring a permanent pacemaker installation. Adopting deep-learning techniques specifically designed for time series signals, 2197 electrocardiograms for 631 TAVI patients have been analyzed. The most important leads for the perioperative stages have been identified. The experimental results have shown that more information is available during- and in the post-procedure stages. The highest AUC results have been obtained on the following leads and stages: 0.635 (lead V1) at pre-procedure stage, 0.711 (lead III) at during-procedure stage and 0.721 (lead aVF) at post-procedure stage. Overall, the highest AUC result has been obtained for the post-procedure stage reaching an AUC of 0.740 for the lead V1. This study confirms that it is possible to identify and stratify even further, the risk for patients that will develop CCD after TAVI, by using the information available in the ECG data immediately following the procedure.

Original language	English
Title of host publication	ICBET '22
Subtitle of host publication	Proceedings of the 12th International Conference on Biomedical Engineering and Technology
Publisher	Association for Computing Machinery, Inc
Pages	75-83
Number of pages	9
ISBN (Electronic)	978-1-4503-9577-9
DOIs	https://doi.org/10.1145/3535694.3535708
Publication status	Published - 11 Jul 2022
Event	12th International Conference on Biomedical Engineering and Technology, ICBET 2022 - Virtual, Online, Japan Duration: 20 Apr 2022 → 23 Apr 2022

Conference

Conference	12th International Conference on Biomedical Engineering and Technology, ICBET 2022
Country/Territory	Japan
City	Virtual, Online
Period	20/04/22 → 23/04/22

Keywords

cardiac conduction defects
ECG
LSTM
pacemaker implantation
RNN
TAVI

Access to Document

10.1145/3535694.3535708

pdfFinal published version, 1.99 MBLicence: CC BY

Cite this

Mamprin, M., Zelis, J. M., Tonino, P. A. L., Zinger, S., & De With, P. H. N. (2022). Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals. In ICBET '22: Proceedings of the 12th International Conference on Biomedical Engineering and Technology (pp. 75-83). Association for Computing Machinery, Inc. https://doi.org/10.1145/3535694.3535708

Mamprin, Marco ; Zelis, Jo M. ; Tonino, Pim A.L. et al. / Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure : A deep-learning approach on ECG signals. ICBET '22: Proceedings of the 12th International Conference on Biomedical Engineering and Technology. Association for Computing Machinery, Inc, 2022. pp. 75-83

@inproceedings{fe6c833f82394861be7e285fc4a058bd,

title = "Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals",

abstract = "This research aims to investigate the feasibility in predicting, at several stages of the transcatheter aortic valve implantation (TAVI) procedure, the risk to develop cardiac conduction defects (CCD) requiring a permanent pacemaker installation. Adopting deep-learning techniques specifically designed for time series signals, 2197 electrocardiograms for 631 TAVI patients have been analyzed. The most important leads for the perioperative stages have been identified. The experimental results have shown that more information is available during- and in the post-procedure stages. The highest AUC results have been obtained on the following leads and stages: 0.635 (lead V1) at pre-procedure stage, 0.711 (lead III) at during-procedure stage and 0.721 (lead aVF) at post-procedure stage. Overall, the highest AUC result has been obtained for the post-procedure stage reaching an AUC of 0.740 for the lead V1. This study confirms that it is possible to identify and stratify even further, the risk for patients that will develop CCD after TAVI, by using the information available in the ECG data immediately following the procedure.",

keywords = "cardiac conduction defects, ECG, LSTM, pacemaker implantation, RNN, TAVI",

author = "Marco Mamprin and Zelis, {Jo M.} and Tonino, {Pim A.L.} and Svitlana Zinger and {De With}, {Peter H.N.}",

year = "2022",

month = jul,

day = "11",

doi = "10.1145/3535694.3535708",

language = "English",

pages = "75--83",

booktitle = "ICBET '22",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

note = "12th International Conference on Biomedical Engineering and Technology, ICBET 2022 ; Conference date: 20-04-2022 Through 23-04-2022",

}

Mamprin, M, Zelis, JM, Tonino, PAL , Zinger, S & De With, PHN 2022, Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals. in ICBET '22: Proceedings of the 12th International Conference on Biomedical Engineering and Technology. Association for Computing Machinery, Inc, pp. 75-83, 12th International Conference on Biomedical Engineering and Technology, ICBET 2022, Virtual, Online, Japan, 20/04/22. https://doi.org/10.1145/3535694.3535708

Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals. / Mamprin, Marco; Zelis, Jo M.; Tonino, Pim A.L. et al.
ICBET '22: Proceedings of the 12th International Conference on Biomedical Engineering and Technology. Association for Computing Machinery, Inc, 2022. p. 75-83.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure

T2 - 12th International Conference on Biomedical Engineering and Technology, ICBET 2022

AU - Mamprin, Marco

AU - Zelis, Jo M.

AU - Tonino, Pim A.L.

AU - Zinger, Svitlana

AU - De With, Peter H.N.

PY - 2022/7/11

Y1 - 2022/7/11

N2 - This research aims to investigate the feasibility in predicting, at several stages of the transcatheter aortic valve implantation (TAVI) procedure, the risk to develop cardiac conduction defects (CCD) requiring a permanent pacemaker installation. Adopting deep-learning techniques specifically designed for time series signals, 2197 electrocardiograms for 631 TAVI patients have been analyzed. The most important leads for the perioperative stages have been identified. The experimental results have shown that more information is available during- and in the post-procedure stages. The highest AUC results have been obtained on the following leads and stages: 0.635 (lead V1) at pre-procedure stage, 0.711 (lead III) at during-procedure stage and 0.721 (lead aVF) at post-procedure stage. Overall, the highest AUC result has been obtained for the post-procedure stage reaching an AUC of 0.740 for the lead V1. This study confirms that it is possible to identify and stratify even further, the risk for patients that will develop CCD after TAVI, by using the information available in the ECG data immediately following the procedure.

AB - This research aims to investigate the feasibility in predicting, at several stages of the transcatheter aortic valve implantation (TAVI) procedure, the risk to develop cardiac conduction defects (CCD) requiring a permanent pacemaker installation. Adopting deep-learning techniques specifically designed for time series signals, 2197 electrocardiograms for 631 TAVI patients have been analyzed. The most important leads for the perioperative stages have been identified. The experimental results have shown that more information is available during- and in the post-procedure stages. The highest AUC results have been obtained on the following leads and stages: 0.635 (lead V1) at pre-procedure stage, 0.711 (lead III) at during-procedure stage and 0.721 (lead aVF) at post-procedure stage. Overall, the highest AUC result has been obtained for the post-procedure stage reaching an AUC of 0.740 for the lead V1. This study confirms that it is possible to identify and stratify even further, the risk for patients that will develop CCD after TAVI, by using the information available in the ECG data immediately following the procedure.

KW - cardiac conduction defects

KW - ECG

KW - LSTM

KW - pacemaker implantation

KW - RNN

KW - TAVI

UR - http://www.scopus.com/inward/record.url?scp=85134585836&partnerID=8YFLogxK

U2 - 10.1145/3535694.3535708

DO - 10.1145/3535694.3535708

M3 - Conference contribution

AN - SCOPUS:85134585836

SP - 75

EP - 83

BT - ICBET '22

PB - Association for Computing Machinery, Inc

Y2 - 20 April 2022 through 23 April 2022

ER -

Mamprin M, Zelis JM, Tonino PAL , Zinger S , De With PHN. Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals. In ICBET '22: Proceedings of the 12th International Conference on Biomedical Engineering and Technology. Association for Computing Machinery, Inc. 2022. p. 75-83 doi: 10.1145/3535694.3535708

Identification of patients at risk of cardiac conduction diseases requiring a permanent pacemaker following TAVI procedure: A deep-learning approach on ECG signals

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this