Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease
Acta Obstetricia et Gynecologica Scandinavica · 2023-11 · 102 (11) · 1511-1520
DOI: 10.1111/aogs.14623 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Obstetricia et Gynecologica Scandinavica, online erschienen am 10.08.2023. Verfasst von Ivar R de Vries und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics and Gynecology, Máxima Medical Center, Veldhoven, The Netherlands. Hauptthemen laut MEDLINE: Artificial Intelligence, Heart Defects, Congenital. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: ZonMw.
Abstract (Originalsprache)
Introduction
This study aims to investigate non‐invasive electrocardiography as a method for the detection of congenital heart disease (CHD) with the help of artificial intelligence. Material and methods An artificial neural network was trained for the identification of CHD using non‐invasively obtained fetal electrocardiograms. With the help of a Bayesian updating rule, multiple electrocardiographs were used to increase the algorithm's performance.
Results
Using 122 measurements containing 65 healthy and 57 CHD cases, the accuracy, sensitivity, and specificity were found to be 71%, 63%, and 77%, respectively. The sensitivity was however 75% and 69% for CHD cases requiring an intervention in the neonatal period and first year of life, respectively. Furthermore, a positive effect of measurement length on the detection performance was observed, reaching optimal performance when using 14 electrocardiography segments (37.5 min) or more. A small negative trend between gestational age and accuracy was found.
Conclusions
The proposed method combining recent advances in obtaining non‐invasive fetal electrocardiography with artificial intelligence for the automatic detection of CHD achieved a detection rate of 63% for all CHD and 75% for critical CHD. This feasibility study shows that detection rates of CHD might improve by using electrocardiography‐based screening complementary to the standard ultrasound‐based screening. More research is required to improve performance and determine the benefits to clinical practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Obstetrics and Gynecology, Máxima Medical Center, Veldhoven, The Netherlands.
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
- Department of Pediatric Cardiology, Emma Children's Hospital, Amsterdam University Medical Centers, Academic Medical Center, Amsterdam, The Netherlands.
- European Reference Network for rare, low prevalence and complex diseases of the heart - ERN GUARD-Heart (ERN GUARDHEART), Amsterdam, The Netherlands.
- Nemo Healthcare BV, Veldhoven, The Netherlands.
ORCID-Profile: Ivar R de Vries, Judith O E H van Laar, Marieke B van der Hout-van der Jagt, Sally-Ann B Clur, Rik Vullings
Förderung
- ZonMw
Zitieren
APA
de Vries, I. R., van Laar, J. O. E. H., van der Hout-van der Jagt, M. B., Clur, S. B., & Vullings, R. (2023). Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease. Acta Obstetricia et Gynecologica Scandinavica, 102(11), 1511-1520. https://doi.org/10.1111/aogs.14623
Vancouver
de Vries IR, van Laar JOEH, van der Hout-van der Jagt MB, Clur SB, Vullings R. Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease. Acta Obstetricia et Gynecologica Scandinavica. 2023;102(11):1511-1520. doi:10.1111/aogs.14623
BibTeX
@article{deVries2023,
author = {de Vries, Ivar R and van Laar, Judith O E H and van der Hout-van der Jagt, Marieke B and Clur, Sally-Ann B and Vullings, Rik},
title = {Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease},
journal = {Acta Obstetricia et Gynecologica Scandinavica},
year = {2023},
volume = {102},
number = {11},
pages = {1511--1520},
doi = {10.1111/aogs.14623}
}
EUVIMED