Pediatric Electrocardiogram-Based Deep Learning to Predict Secundum Atrial Septal Defects
Pediatric Cardiology · 2025
DOI: 10.1007/s00246-024-03540-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pediatric Cardiology, 2025. Verfasst von Joshua Mayourian und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Boston Children's Hospital, 300 Longwood Avenue, Boston, MA, 02115, USA. Hauptthemen laut MEDLINE: Electrocardiography, Heart Septal Defects, Atrial, Deep Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NLM NIH HHS, Thrasher Early Career Award, Kostin Innovation Fund.
Abstract (Originalsprache)
Secundum atrial septal defect (ASD2) detection is often delayed, with the potential for late diagnosis complications. Recent work demonstrated artificial intelligence-enhanced ECG analysis shows promise to detect ASD2 in adults. However, its application to pediatric populations remains underexplored. In this study, we trained a convolutional neural network (AI-pECG) on paired ECG–echocardiograms (≤ 2 days apart) to detect ASD2 from patients ≤ 18 years old without major congenital heart disease. Model performance was evaluated on the first ECG–echocardiogram pair per patient for Boston Children’s Hospital internal testing and emergency department cohorts using area under the receiver operating (AUROC) and precision-recall (AUPRC) curves. The training cohort comprised of 92,377 ECG–echocardiogram pairs (46,261 patients; median age 8.2 years) with an ASD2 prevalence of 6.7%. Test groups included internal testing (12,631 patients; median age 7.4 years; 6.9% prevalence) and emergency department (2,830 patients; median age 7.5 years; 4.9% prevalence) cohorts. Model performance was higher in the internal test (AUROC 0.84, AUPRC 0.46) cohort than the emergency department cohort (AUROC 0.80, AUPRC 0.30). In both cohorts, AI-pECG outperformed ECG findings of incomplete right bundle branch block. Model explainability analyses suggest high-risk limb lead features include greater amplitude P waves (suggestive of right atrial enlargement) and V1 RSR’ (suggestive of RBBB). Our findings demonstrate the promise of AI-pECG to inexpensively screen and/or detect ASD2 in pediatric patients. Future multicenter validation and prospective trials to inform clinical decision making are warranted.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiology, Boston Children's Hospital, 300 Longwood Avenue, Boston, MA, 02115, USA.
- Department of Pediatrics, Harvard Medical School, Boston, MA, USA.
- Department of Cardiology, Boston Children's Hospital, 300 Longwood Avenue, Boston, MA, 02115, USA. john.triedman@cardio.chboston.org.
- Department of Pediatrics, Harvard Medical School, Boston, MA, USA. john.triedman@cardio.chboston.org.
Förderung
- NLM NIH HHS
- Thrasher Early Career Award
- Kostin Innovation Fund
- Electrophysiology Research Education Fund
- National Library of Medicine
Zitieren
APA
Mayourian, J., Geggel, R., La Cava, W. G., Ghelani, S. J., & Triedman, J. K. (2025). Pediatric Electrocardiogram-Based Deep Learning to Predict Secundum Atrial Septal Defects. Pediatric Cardiology. https://doi.org/10.1007/s00246-024-03540-7
Vancouver
Mayourian J, Geggel R, La Cava WG, Ghelani SJ, Triedman JK. Pediatric Electrocardiogram-Based Deep Learning to Predict Secundum Atrial Septal Defects. Pediatric Cardiology. 2025. doi:10.1007/s00246-024-03540-7
BibTeX
@article{Mayourian2025,
author = {Mayourian, Joshua and Geggel, Robert and La Cava, William G and Ghelani, Sunil J and Triedman, John K},
title = {Pediatric Electrocardiogram-Based Deep Learning to Predict Secundum Atrial Septal Defects},
journal = {Pediatric Cardiology},
year = {2025},
doi = {10.1007/s00246-024-03540-7}
}
EUVIMED