Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul-Aug;24(4):192-199.
doi: 10.1016/j.ipej.2024.06.003. Epub 2024 Jun 11.

Using artificial intelligence and deep learning to optimise the selection of adult congenital heart disease patients in S-ICD screening

Mohamed ElRefai  1 , Mohamed Abouelasaad  2 , Isobel Conibear  3 , Benedict M Wiles  4 , Anthony J Dunn  5 , Stefano Coniglio  6 , Alain B Zemkoho  7 , John Morgan  3 , Paul R Roberts  8
Affiliations

Using artificial intelligence and deep learning to optimise the selection of adult congenital heart disease patients in S-ICD screening

Mohamed ElRefai et al. Indian Pacing Electrophysiol J. 2024 Jul-Aug.

Abstract

Introduction: The risk of complications associated with transvenous ICDs make the subcutaneous implantable cardiac defibrillator (S-ICD) a valuable alternative in patients with adult congenital heart disease (ACHD). However, higher S-ICD ineligibility and higher inappropriate shock rates-mostly caused by T wave oversensing (TWO)- are observed in this population. We report a novel application of deep learning methods to screen patients for S-ICD eligibility over a longer period than conventional screening.

Methods: Adult patients with ACHD and a control group of normal subjects were fitted with a 24-h Holters to record their S-ICD vectors. Their T:R ratio was analysed utilising phase space reconstruction matrices and a deep learning-based model to provide an in-depth description of the T: R variation plot for each vector. T: R variation was compared statistically using t-test.

Results: 13 patients (age 37.4 ± 7.89 years, 61.5 % male, 6 ACHD and 7 control subjects) were enrolled. A significant difference was observed in the mean and median T: R values between the two groups (p < 0.001). There was also a significant difference in the standard deviation of T: R between both groups (p = 0.04).

Conclusions: T:R ratio, a main determinant for S-ICD eligibility, is significantly higher with more tendency to fluctuate in ACHD patients when compared to a population with normal hearts. We hypothesise that our novel model could be used to select S-ICD eligible patients by better characterisation of T:R ratio, reducing the risk of TWO and inappropriate shocks in the ACHD patient cohort.

Keywords: Adult congenital heart disease; Cardiac implantable devices; Deep learning; S-ICD.

PubMed Disclaimer

Conflict of interest statement

Declaration of competing interest x The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: -Dr. Mohamed ElRefai has received an unrestricted grant from Boston Scientific. -Dr. Benedict Wiles has received unrestricted research funding and consultancy payments from Boston Scientific. -Dr. Paul Roberts receives consultancy fees from Boston Scientific and Medtronic. -Professor John Morgan is a medical director at Boston Scientific. - None of the other authors of this study has conflict of interest to declare.

Figures

Fig. 1
Fig. 1
Showing the typical S-ICD vectors on the left and on the right, the Holter® surface ECG positions. 1 = 1 cm infero-lateral to the xiphisternum 2 = 14 cm superior to position 1 3 = 5th intercostal space, parasternal position 4 = 6th intercostal space left mid axillary line 6 = Adjacent to 2 7 = Adjacent to 4 Holter Channel A records between points 1 and 4 = surrogate of S-ICD primary vector Holter Channel B records between points 2 and 3 = surrogate of S-ICD alternate vector Holter Channel C records between points 6 and 7 = surrogate of S-ICD secondary vector 5 = 5th intercostal space right mid clavicular line = neutral electrode Image prior to annotation © Boston Scientific Corporation or its affiliates.
Fig. 2
Fig. 2
Mean, median, and SD of the T:R ratios measured in 24 h for the all the Leads/S-ICD vectors in ACHD and healthy volunteers with normal hearts groups.
Fig. 3
Fig. 3
Mean T:R ratios measured in 24 h classified according to the S-ICD vector.
Fig. 4
Fig. 4
Median T:R ratios measured in 24 h classified according to the S-ICD vector.
Fig. 5
Fig. 5
Standard deviation (SD) of the T:R ratios measured in 24 h classified according to the S-ICD vector.
See this image and copyright information in PMC

References

    1. Baumgartner H., de Backer J., Babu-Narayan S.v., et al. 2020 ESC Guidelines for the management of adult congenital heart disease. Eur Heart J. 2021;42(6):563–645. doi: 10.1093/eurheartj/ehaa554. - DOI - PubMed
    1. Koyak Z., Harris L., de Groot J.R., et al. Sudden cardiac death in adult congenital heart disease. Circulation. 2012;126(16):1944–1954. doi: 10.1161/CIRCULATIONAHA.112.104786. - DOI - PubMed
    1. Vehmeijer J.T., Brouwer T.F., Limpens J., et al. Implantable cardioverter-defibrillators in adults with congenital heart disease: a systematic review and meta-analysis. Eur Heart J. 2016;37(18):1439–1448. doi: 10.1093/eurheartj/ehv735. - DOI - PMC - PubMed
    1. Olde Nordkamp L.R.A., Warnaars J.L.F., Kooiman K.M., et al. Which patients are not suitable for a subcutaneous ICD: incidence and predictors of failed QRS-T-wave morphology screening. J Cardiovasc Electrophysiol. 2014;25(5):494–499. doi: 10.1111/JCE.12343. - DOI - PubMed
    1. Randles D.A., Hawkins N.M., Shaw M., Patwala A.Y., Pettit S.J., Wright D.J. How many patients fulfil the surface electrocardiogram criteria for subcutaneous implantable cardioverter-defibrillator implantation? Europace. 2014;16(7):1015–1021. doi: 10.1093/EUROPACE/EUT370. - DOI - PubMed

LinkOut - more resources