EUVIMEDEUVIMED entdecken
Crossref

Risk Stratification for Graft Failure After Pediatric Heart Transplantation Using Random Survival Forests

Omar Altamimi iD, Ali Ahmad iD, Reem Badran iD, Yasmeen Sleihat iD, Ali Altamimi iD, Iyad Al-Ammouri iD

Pediatric Transplantation · 2026

DOI: 10.1111/petr.70346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Transplantation, 2026. Verfasst von Omar Altamimi und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, The University of Jordan, Amman, Jordan. Hauptthemen laut MEDLINE: Heart Transplantation, Graft Rejection. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Prediction in pediatric heart transplantation is challenging due to clinical heterogeneity. This presents the dilemma of modeling non‐linear relationships and complex variable structures. It may be overcome by survival‐based machine learning techniques designed to accommodate time to event outcomes, contrary to traditional approaches.

Methods

In this study, we developed and evaluated a Random Survival Forest model to predict graft failure among pediatric heart transplant recipients using United Network for Organ Sharing registry data (post‐July 2016). The primary outcome was graft failure.

Results

Data was divided randomly into training ( n = 3121) and testing ( n = 1041) sets in a 75:25 ratio, and the scikit‐survival implementation of the Random Survival Forest algorithm was chosen for this analysis. On the held‐out test set, the final model achieved a Harrell's C‐index of 0.60, and recorded 1‐ and 2‐year Time‐dependent Area Under the Curve (AUC) of 0.636 and 0.630 respectively; the 1‐ and 2‐year brier scores were 0.078 and 0.097 respectively. Risk stratification analysis showed that the model‐derived risk separated pediatric patients into low‐ and high‐risk groups, with significant divergence in Kaplan–Meier survival curves (log‐rank p = 0.003) and 1‐year estimated survival of 92.8% and 88.1%. Clinical utility of the model was further evaluated using decision curve analysis at 1‐year post transplant, the model suggested greater net benefit.

Conclusions

These results suggest that, even in the absence of high discrimination, machine learning approaches like Random Survival Forests can uncover clinically relevant patterns and may support future development of a framework for risk‐adapted monitoring in pediatric heart transplantation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Heart TransplantationGraft RejectionHumansRandom ForestRisk AssessmentChildFemaleChild, PreschoolMaleInfantMachine LearningPredictive Learning ModelsRegistriesAdolescentPrediction AlgorithmsRisk Factors

Stichwörter der Autor:innen

UNOS registrydecision curve analysismachine learningpediatric heart transplantationrandom survival forestrisk stratification

Autor:innen und Institutionen

  • School of Medicine, The University of Jordan, Amman, Jordan.
  • Division of Cardiology, Department of Pediatrics, The University of Jordan, Amman, Jordan.

ORCID-Profile: Omar Altamimi, Ali Ahmad, Reem Badran, Yasmeen Sleihat, Ali Altamimi, Iyad Al-Ammouri

Zitieren

APA

Altamimi, O., Ahmad, A., Badran, R., Sleihat, Y., Altamimi, A., & Al-Ammouri, I. (2026). Risk Stratification for Graft Failure After Pediatric Heart Transplantation Using Random Survival Forests. Pediatric Transplantation. https://doi.org/10.1111/petr.70346

Vancouver

Altamimi O, Ahmad A, Badran R, Sleihat Y, Altamimi A, Al-Ammouri I. Risk Stratification for Graft Failure After Pediatric Heart Transplantation Using Random Survival Forests. Pediatric Transplantation. 2026. doi:10.1111/petr.70346

BibTeX
@article{Altamimi2026,
  author = {Altamimi, Omar and Ahmad, Ali and Badran, Reem and Sleihat, Yasmeen and Altamimi, Ali and Al-Ammouri, Iyad},
  title = {Risk Stratification for Graft Failure After Pediatric Heart Transplantation Using Random Survival Forests},
  journal = {Pediatric Transplantation},
  year = {2026},
  doi = {10.1111/petr.70346}
}
Kostenlos starten →