EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias

Maarten Z H Kolk, Samuel Ruipérez-Campillo, Cornelis P Allaart, Arthur A M Wilde, Reinoud E Knops, Sanjiv M Narayan, Fleur V Y Tjong, DEEP RISK investigators

Scientific Reports · 27.06.2024 · 14 (1)

DOI: 10.1038/s41598-024-65357-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Reports, online erschienen am 27.06.2024. Verfasst von Maarten Z H Kolk und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical and Experimental Cardiology, Heart Center, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, 1105 AZ,…. Hauptthemen laut MEDLINE: Cardiomyopathies, Electrocardiography, Magnetic Resonance Imaging, Arrhythmias, Cardiac. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, Dutch Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The efficacy of an implantable cardioverter-defibrillator (ICD) in patients with a non-ischaemic cardiomyopathy for primary prevention of sudden cardiac death is increasingly debated. We developed a multimodal deep learning model for arrhythmic risk prediction that integrated late gadolinium enhanced (LGE) cardiac magnetic resonance imaging (MRI), electrocardiography (ECG) and clinical data. Short-axis LGE-MRI scans and 12-lead ECGs were retrospectively collected from a cohort of 289 patients prior to ICD implantation, across two tertiary hospitals. A residual variational autoencoder was developed to extract physiological features from LGE-MRI and ECG, and used as inputs for a machine learning model (DEEP RISK) to predict malignant ventricular arrhythmia onset. In the validation cohort, the multimodal DEEP RISK model predicted malignant ventricular arrhythmias with an area under the receiver operating characteristic curve (AUROC) of 0.84 (95% confidence interval (CI) 0.71–0.96), a sensitivity of 0.98 (95% CI 0.75–1.00) and a specificity of 0.73 (95% CI 0.58–0.97). The models trained on individual modalities exhibited lower AUROC values compared to DEEP RISK [MRI branch: 0.80 (95% CI 0.65–0.94), ECG branch: 0.54 (95% CI 0.26–0.82), Clinical branch: 0.64 (95% CI 0.39–0.87)]. These results suggest that a multimodal model achieves high prognostic accuracy in predicting ventricular arrhythmias in a cohort of patients with non-ischaemic systolic heart failure, using data collected prior to ICD implantation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CardiomyopathiesElectrocardiographyMagnetic Resonance ImagingArrhythmias, CardiacDefibrillators, ImplantableHumansFemaleMaleMiddle AgedRetrospective StudiesAgedArtificial IntelligenceDeep LearningDeath, Sudden, CardiacRisk AssessmentRisk FactorsROC Curve

Autor:innen und Institutionen

  • Department of Clinical and Experimental Cardiology, Heart Center, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands.
  • Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, The Netherlands.
  • Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA.
  • Department of Computer Science (D-INFK), Swiss Federal Institute of Technology (ETH) Zurich, Gloriastrasse 35, Zurich, Switzerland.
  • Department of Cardiology, Amsterdam UMC, Location VU Medical Center, De Boelelaan 1118, Amsterdam, The Netherlands.
  • Department of Clinical and Experimental Cardiology, Heart Center, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands. f.v.tjong@amsterdamumc.nl.

Förderung

  • NHLBI NIH HHS
  • Dutch Research Council

Zitieren

APA

Kolk, M. Z. H., Ruipérez-Campillo, S., Allaart, C. P., Wilde, A. A. M., Knops, R. E., Narayan, S. M., Tjong, F. V. Y., & DEEP RISK investigators (2024). Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-65357-x

Vancouver

Kolk MZH, Ruipérez-Campillo S, Allaart CP, Wilde AAM, Knops RE, Narayan SM, et al. Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-65357-x

BibTeX
@article{Kolk2024,
  author = {Kolk, Maarten Z H and Ruipérez-Campillo, Samuel and Allaart, Cornelis P and Wilde, Arthur A M and Knops, Reinoud E and Narayan, Sanjiv M and Tjong, Fleur V Y and DEEP RISK investigators, DEEP RISK investigators},
  title = {Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias},
  journal = {Scientific Reports},
  year = {2024},
  volume = {14},
  number = {1},
  doi = {10.1038/s41598-024-65357-x}
}
Kostenlos starten →