EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning for Prediction of Adverse Cardiovascular Events in Adults With Repaired Tetralogy of Fallot Using Clinical and Cardiovascular Magnetic Resonance Imaging Variables

Ayako Ishikita iD, Chris McIntosh iD, Kate Hanneman iD, Myunghyun M Lee, Tiffany Liang, Gauri R Karur, S Lucy Roche iD, Edward Hickey, Tal Geva iD, David J Barron iD, Rachel M Wald iD

Circulation: Cardiovascular Imaging · 2023-06 · 16 (6)

DOI: 10.1161/circimaging.122.015205 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Circulation: Cardiovascular Imaging, 2023-06. Verfasst von Ayako Ishikita und 10 weiteren Autor:innen. Beteiligte Einrichtung: Division of Cardiology, Peter Munk Cardiac Centre, University Health Network, University of Toronto, ON, Canada (A.I., C.M., T.L., S.L.R., R.M.W.). Hauptthemen laut MEDLINE: Tetralogy of Fallot, Ventricular Dysfunction, Right. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Existing models for prediction of major adverse cardiovascular events (MACE) after repair of tetralogy of Fallot have been limited by modest predictive capacity and limited applicability to routine clinical practice. We hypothesized that an artificial intelligence model using an array of parameters would enhance 5-year MACE prediction in adults with repaired tetralogy of Fallot.

Methods

A machine learning algorithm was applied to 2 nonoverlapping, institutional databases of adults with repaired tetralogy of Fallot: (1) for model development, a prospectively constructed clinical and cardiovascular magnetic resonance registry; (2) for model validation, a retrospective database comprised of variables extracted from the electronic health record. The MACE composite outcome included mortality, resuscitated sudden death, sustained ventricular tachycardia and heart failure. Analysis was restricted to individuals with MACE or followed ≥5 years. A random forest model was trained using machine learning (n=57 variables). Repeated random sub-sampling validation was sequentially applied to the development dataset followed by application to the validation dataset.

Results

We identified 804 individuals (n=312 for development and n=492 for validation). Model prediction (area under the curve [95% CI]) for MACE in the validation dataset was strong (0.82 [0.74–0.89]) with superior performance to a conventional Cox multivariable model (0.63 [0.51–0.75]; P =0.003). Model performance did not change significantly with input restricted to the 10 strongest features (decreasing order of strength: right ventricular end-systolic volume indexed, right ventricular ejection fraction, age at cardiovascular magnetic resonance imaging, age at repair, absolute ventilatory anaerobic threshold, right ventricular end-diastolic volume indexed, ventilatory anaerobic threshold % predicted, peak aerobic capacity, left ventricular ejection fraction, and pulmonary regurgitation fraction; 0.81 [0.72–0.89]; P =0.232). Removing exercise parameters resulted in inferior model performance (0.75 [0.65–0.84]; P =0.002).

Conclusions

In this single-center study, a machine learning-based prediction model comprised of readily available clinical and cardiovascular magnetic resonance imaging variables performed well in an independent validation cohort. Further study will determine the value of this model for risk stratification in adults with repared tetralogy of Fallot.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tetralogy of FallotVentricular Dysfunction, RightHumansAdultStroke VolumeRetrospective StudiesArtificial IntelligenceVentricular Function, LeftVentricular Function, RightMagnetic Resonance ImagingHeart VentriclesMachine Learning

Stichwörter der Autor:innen

heart defects, congenitalmachine learningmagnetic resonance imagingprognosistetralogy of Fallot

Autor:innen und Institutionen

  • Division of Cardiology, Peter Munk Cardiac Centre, University Health Network, University of Toronto, ON, Canada (A.I., C.M., T.L., S.L.R., R.M.W.).
  • Department of Medical Biophysics (C.M.), University of Toronto, ON, Canada.
  • Department of Medical Imaging, University Health Network (C.M., K.H., G.R.K., R.M.W.), University of Toronto, ON, Canada.
  • Department of Cardiovascular Surgery, Hospital for Sick Children (M.M.L., D.J.B.), University of Toronto, ON, Canada.
  • Department of Surgery, Division of Congenital Heart Surgery, Texas Children's Hospital, Houston (E.H.).
  • Department of Cardiology, Children's Hospital Boston and Department of Pediatrics, Harvard Medical School, Boston, MA (T.G.).

ORCID-Profile: Ayako Ishikita, Chris McIntosh, Kate Hanneman, S Lucy Roche, Tal Geva, David J Barron, Rachel M Wald

Zitieren

APA

Ishikita, A., McIntosh, C., Hanneman, K., Lee, M. M., Liang, T., Karur, G. R., Roche, S. L., Hickey, E., Geva, T., Barron, D. J., & Wald, R. M. (2023). Machine Learning for Prediction of Adverse Cardiovascular Events in Adults With Repaired Tetralogy of Fallot Using Clinical and Cardiovascular Magnetic Resonance Imaging Variables. Circulation: Cardiovascular Imaging, 16(6). https://doi.org/10.1161/circimaging.122.015205

Vancouver

Ishikita A, McIntosh C, Hanneman K, Lee MM, Liang T, Karur GR, et al. Machine Learning for Prediction of Adverse Cardiovascular Events in Adults With Repaired Tetralogy of Fallot Using Clinical and Cardiovascular Magnetic Resonance Imaging Variables. Circulation: Cardiovascular Imaging. 2023;16(6). doi:10.1161/circimaging.122.015205

BibTeX
@article{Ishikita2023,
  author = {Ishikita, Ayako and McIntosh, Chris and Hanneman, Kate and Lee, Myunghyun M and Liang, Tiffany and Karur, Gauri R and Roche, S Lucy and Hickey, Edward and Geva, Tal and Barron, David J and Wald, Rachel M},
  title = {Machine Learning for Prediction of Adverse Cardiovascular Events in Adults With Repaired Tetralogy of Fallot Using Clinical and Cardiovascular Magnetic Resonance Imaging Variables},
  journal = {Circulation: Cardiovascular Imaging},
  year = {2023},
  volume = {16},
  number = {6},
  doi = {10.1161/circimaging.122.015205}
}
Kostenlos starten →