EUVIMEDEUVIMED entdecken
Crossref

Development of a patient-specific Fontan failure risk calculator using machine learning—a step toward personalized medicine

Supreet P Marathe, Kim S Betts, Alyssia Venna, Michael Daley, Ajay J Iyengar, Rachael Cordina, David Celermajer, David Andrews, Terry Robertson, Matt Liava'a, Julian Ayer, Yves d'Udekem und 3 weitere

The Journal of Thoracic and Cardiovascular Surgery · 2026-06 · 171 (6) · 1289-1298.e1

DOI: 10.1016/j.jtcvs.2025.12.032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Thoracic and Cardiovascular Surgery, 2026-06. Verfasst von Supreet P Marathe und 14 weiteren Autor:innen. Beteiligte Einrichtung: Queensland Children's Hospital, Brisbane, Australia; The University of Queensland, Brisbane, Australia; Queensland University of Technology, Brisbane…. Hauptthemen laut MEDLINE: Fontan Procedure, Machine Learning, Precision Medicine, Heart Defects, Congenital. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 20 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: The Fontan operation is the final step in staged palliation for patients with single-ventricle physiology. It has extended their life expectancy and improved their quality of life. However, long-term complications and Fontan failure remain lifelong concerns. We aimed to use machine learning to develop a patient-specific preoperative Fontan failure risk calculator. METHODS: Patient data were obtained from the Australia and New Zealand Fontan Registry (ANZFR). The primary composite end point was Fontan failure, defined as any of death, transplant, Fontan takedown or conversion, protein-losing enteropathy, plastic bronchitis, or New York Heart Association class III/IV. To construct the risk calculator, we first used Cox regression with regularization to predict Fontan failure from 54 preoperative predictors in the ANZFR database. A regularization machine learning tool was used to automate variable selection among many predictors. We then manually added clinically relevant predictors. Six predictors (age, ventricular morphology, primary diagnosis, total anomalous pulmonary venous drainage, Fontan type, and moderate or greater atrioventricular valve regurgitation) were ultimately used in a subsequent multivariable Cox regression (without regularization) to ensure the final risk prediction model was simple and easy to interpret. RESULTS: Data from 1888 patients over 48 years (1975-2023) were available. The ANZFR collects perioperative and follow-up variables about each patient. After excluding patients with Fontan procedures with an atriopulmonary connection (n = 290) and missing predictors or outcome data (n = 125), data from 1473 patients were used to construct the calculator. Median age at Fontan was 4.5 years (interquartile range, 3.7, 5.6 years). Median follow-up was 11.0 years (interquartile range, 5.3, 17.8 years). Freedom from Fontan failure for the overall cohort at 10, 20, and 30 years was 92% (confidence interval [CI], 90%-93%), 83% (CI, 80%-86%), and 72% (CI, 65%-78%), respectively. External validation in an independent cohort demonstrated acceptable model performance. The risk prediction model was then implemented in a Desktop application using the Shiny library in R and used to develop the preoperative Fontan failure calculator on the basis of the 6 predictors. CONCLUSIONS: Machine learning can be applied to "big data" from a binational Fontan Registry to develop a preoperative, patient-specific Fontan failure risk calculator. The model will continue to learn and improve as more data is added. This is a step toward personalized medicine enabling patient-specific pre-operative counselling and realistic expectations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Fontan ProcedureMachine LearningPrecision MedicineHeart Defects, CongenitalHumansRisk AssessmentFemaleRegistriesRisk FactorsMaleTreatment FailurePredictive Learning ModelsChildChild, PreschoolNew ZealandPredictive Value of TestsAustraliaPrediction Algorithms

Stichwörter der Autor:innen

Fontan failuremachine learningrisk predictionsurgical outcomes

Autor:innen und Institutionen

  • Queensland Children's Hospital, Brisbane, Australia; The University of Queensland, Brisbane, Australia; Queensland University of Technology, Brisbane, Australia. Electronic address: s.marathe@uq.edu.au.
  • Curtin University, Perth, Australia.
  • Children's National Hospital, Washington, DC.
  • University of Melbourne, Melbourne, Australia; Murdoch Children's Research Institute, Melbourne, Australia.
  • Starship Children's Hospital, Auckland, New Zealand; Auckland University, Auckland, New Zealand.
  • Royal Prince Alfred Hospital, Sydney, Australia.

Zitieren

APA

Marathe, S. P., Betts, K. S., Venna, A., Daley, M., Iyengar, A. J., Cordina, R., Celermajer, D., Andrews, D., Robertson, T., Liava'a, M., Ayer, J., d'Udekem, Y., Konstantinov, I. E., Venugopal, P., & Alphonso, N. (2026). Development of a patient-specific Fontan failure risk calculator using machine learning—a step toward personalized medicine. The Journal of Thoracic and Cardiovascular Surgery, 171(6), 1289-1298.e1. https://doi.org/10.1016/j.jtcvs.2025.12.032

Vancouver

Marathe SP, Betts KS, Venna A, Daley M, Iyengar AJ, Cordina R, et al. Development of a patient-specific Fontan failure risk calculator using machine learning—a step toward personalized medicine. The Journal of Thoracic and Cardiovascular Surgery. 2026;171(6):1289-1298.e1. doi:10.1016/j.jtcvs.2025.12.032

BibTeX
@article{Marathe2026,
  author = {Marathe, Supreet P and Betts, Kim S and Venna, Alyssia and Daley, Michael and Iyengar, Ajay J and Cordina, Rachael and Celermajer, David and Andrews, David and Robertson, Terry and Liava'a, Matt and Ayer, Julian and d'Udekem, Yves and Konstantinov, Igor E and Venugopal, Prem and Alphonso, Nelson},
  title = {Development of a patient-specific Fontan failure risk calculator using machine learning—a step toward personalized medicine},
  journal = {The Journal of Thoracic and Cardiovascular Surgery},
  year = {2026},
  volume = {171},
  number = {6},
  pages = {1289--1298.e1},
  doi = {10.1016/j.jtcvs.2025.12.032}
}
Kostenlos starten →