EUVIMEDEUVIMED entdecken
Crossref

Electrocardiogram-Based Deep Learning to Predict Mortality in Repaired Tetralogy of Fallot

Joshua Mayourian, Juul P A van Boxtel, Lynn A Sleeper, Vedang Diwanji, Alon Geva, Edward T O'Leary, John K Triedman, Sunil J Ghelani, Rachel M Wald, Anne Marie Valente, Tal Geva

JACC: Clinical Electrophysiology · 2024-12 · 10 (12) · 2600-2612

DOI: 10.1016/j.jacep.2024.07.015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JACC: Clinical Electrophysiology, 2024-12. Verfasst von Joshua Mayourian und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachus…. Hauptthemen laut MEDLINE: Tetralogy of Fallot, Deep Learning, Electrocardiography. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: NHLBI NIH HHS, Thrasher Research Fund, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Artificial intelligence-enhanced electrocardiogram (AI-ECG) analysis shows promise to predict mortality in adults with acquired cardiovascular diseases. However, its application to the growing repaired tetralogy of Fallot (rTOF) population remains unexplored. OBJECTIVES: This study aimed to develop and externally validate an AI-ECG model to predict 5-year mortality in rTOF. METHODS: A convolutional neural network was trained on electrocardiograms (ECGs) obtained at Boston Children's Hospital and tested on Boston (internal testing) and Toronto (external validation) INDICATOR (International Multicenter TOF Registry) cohorts to predict 5-year mortality. Model performance was evaluated on single ECGs per patient using area under the receiver operating (AUROC) and precision recall (AUPRC) curves. RESULTS: The internal testing and external validation cohorts comprised of 1,054 patients (13,077 ECGs at median age 17.8 [Q1-Q3: 7.9-30.5] years; 54% male; 6.1% mortality) and 335 patients (5,014 ECGs at median age 38.3 [Q1-Q3: 29.1-48.7] years; 57% male; 8.4% mortality), respectively. Model performance was similar during internal testing (AUROC 0.83, AUPRC 0.18) and external validation (AUROC 0.81, AUPRC 0.21). AI-ECG performed similarly to the biventricular global function index (an imaging biomarker) and outperformed QRS duration. AI-ECG 5-year mortality prediction, but not QRS duration, was a significant independent predictor when added into a Cox regression model with biventricular global function index to predict shorter time-to-death on internal and external cohorts. Saliency mapping identified QRS fragmentation, wide and low amplitude QRS complexes, and flattened T waves as high-risk features. CONCLUSIONS: This externally validated AI-ECG model may complement imaging biomarkers to improve risk stratification in patients with rTOF.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tetralogy of FallotDeep LearningElectrocardiographyHumansMaleFemaleAdultYoung AdultAdolescentChildMiddle Aged

Stichwörter der Autor:innen

Artificial intelligencecardiovascular magnetic resonancecongenital heart diseaseelectrocardiogramtetralogy of Fallot

Autor:innen und Institutionen

  • Department of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA.
  • Department of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA; Department of Biomedical Engineering, Eindhoven University…
  • Department of Anesthesiology, Critical Care, and Pain Medicine, and Computational Health Informatics Program, Boston Children's Hospital, Boston, Massachusetts, USA; Department of Anesthesia, Harvard Medical School, Bos…
  • Division of Cardiology, University of Toronto, Peter Munk Cardiac Centre, Toronto, Ontario, Canada.
  • Department of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA. Electronic address: tal.geva@cardio.chboston.org.

Förderung

  • NHLBI NIH HHS
  • Thrasher Research Fund
  • National Institutes of Health

Zitieren

APA

Mayourian, J., van Boxtel, J. P. A., Sleeper, L. A., Diwanji, V., Geva, A., O'Leary, E. T., Triedman, J. K., Ghelani, S. J., Wald, R. M., Valente, A. M., & Geva, T. (2024). Electrocardiogram-Based Deep Learning to Predict Mortality in Repaired Tetralogy of Fallot. JACC: Clinical Electrophysiology, 10(12), 2600-2612. https://doi.org/10.1016/j.jacep.2024.07.015

Vancouver

Mayourian J, van Boxtel JPA, Sleeper LA, Diwanji V, Geva A, O'Leary ET, et al. Electrocardiogram-Based Deep Learning to Predict Mortality in Repaired Tetralogy of Fallot. JACC: Clinical Electrophysiology. 2024;10(12):2600-2612. doi:10.1016/j.jacep.2024.07.015

BibTeX
@article{Mayourian2024,
  author = {Mayourian, Joshua and van Boxtel, Juul P A and Sleeper, Lynn A and Diwanji, Vedang and Geva, Alon and O'Leary, Edward T and Triedman, John K and Ghelani, Sunil J and Wald, Rachel M and Valente, Anne Marie and Geva, Tal},
  title = {Electrocardiogram-Based Deep Learning to Predict Mortality in Repaired Tetralogy of Fallot},
  journal = {JACC: Clinical Electrophysiology},
  year = {2024},
  volume = {10},
  number = {12},
  pages = {2600--2612},
  doi = {10.1016/j.jacep.2024.07.015}
}
Kostenlos starten →