Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Cardiopulmonary exercise testing-derived circulatory power predicts major adverse cardiac events in adults with repaired tetralogy of Fallot.

Annals of pediatric cardiology·2026

Same author

Advances and unmet needs in pharmacologic therapy for pediatric heart failure: Insights from the 2025 International Society for Heart and Lung Transplantation Guidelines.

Annals of pediatric cardiology·2026

Same author

Heart Transplant Outcomes in Chemotherapy-Induced vs. Non-Ischemic-Dilated Cardiomyopathy: Pediatric and Adult Recipients in the Ventricular Assist Device Era.

Reviews in cardiovascular medicine·2026

Same author

Corrigendum to 'Cardiac Catheterization and Interventions in Pediatric Patients on ECMO: Analysis of the IMPACT Registry' [Journal of the Society for Cardiovascular Angiography & Interventions; Volume 4, Issue 3 (2025): 102570].

Journal of the Society for Cardiovascular Angiography & Interventions·2026

Same author

A 10-year single-centre report on Fontan attrition and non-Fontan candidacy.

Cardiology in the young·2026

Same author

Pediatric Myocarditis: Challenges in Diagnosis and Treatment.

Paediatric drugs·2026

Same journal

Achieving Equity in Generative Artificial Intelligence in Cardiovascular Medicine.

JACC. Advances·2026

Same journal

Real-World Experience With a Novel Intravascular Hertz Contact Lithotripsy Balloon in Severely Calcified Coronary Lesions.

JACC. Advances·2026

Same journal

Trends in Cardiac Arrest Mortality Among Young Adults in the United States, 1999 to 2024.

JACC. Advances·2026

Same journal

Pulmonary Hypertension in Adults With a Systemic Right Ventricle (Biventricular Circulation).

JACC. Advances·2026

Same journal

Cholesterol Perceptions and Preferences Among Young Adults: A Survey of U.S. Adults Aged 30 to 39 Years.

JACC. Advances·2026

Same journal

Radiomics for the Detection and Prediction of Cancer Therapy-Related Cardiotoxicity.

JACC. Advances·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

Author Spotlight: Enhancing Graft Viability Assessment Through Quantitative Metrics and Innovative Reservoir Systems

Author Spotlight: Enhancing Graft Viability Assessment Through Quantitative Metrics and Innovative Reservoir Systems

Published on: August 2, 2024

Predicting 1-Year Mortality After Pediatric Heart Transplantation Using Machine Learning: A Systematic Review and

Bibhuti B Das¹, Shriprasad R Deshpande², Swati Choudhry³

¹Department of Pediatric Cardiology, Methodist Children's Hospital, San Antonio, Texas, USA.

|December 13, 2025

Summary

This summary is machine-generated.

Machine learning models significantly improve prediction of 1-year mortality after pediatric heart transplant (HT). These advanced models capture evolving risk factors, enhancing accuracy and equity in transplant decisions.

Keywords:

1-year mortality machine learning meta-analysis pediatric heart transplantation risk prediction

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents

A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents

Published on: September 21, 2021

Related Experiment Videos

Last Updated: Jan 8, 2026

Author Spotlight: Enhancing Graft Viability Assessment Through Quantitative Metrics and Innovative Reservoir Systems

Author Spotlight: Enhancing Graft Viability Assessment Through Quantitative Metrics and Innovative Reservoir Systems

Published on: August 2, 2024

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents

A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents

Published on: September 21, 2021

Area of Science:

Pediatric cardiology and transplant medicine.
Biomedical informatics and machine learning applications.
Health services research and organ allocation.

Background:

Accurate prediction of post-heart transplant (HT) mortality is crucial for pediatric donor selection, perioperative care, and equitable organ allocation.
Traditional risk models struggle with nonlinear and dynamic patterns in pediatric HT outcomes.
Machine learning (ML) offers potential for improved predictive precision across different time periods.

Purpose of the Study:

To systematically evaluate ML-based models for predicting 1-year mortality after pediatric HT.
To synthesize the pooled diagnostic performance of these ML models.
To identify temporal shifts in major risk predictors influencing pediatric HT survival.

Main Methods:

Systematic literature search of PubMed, Scopus, and Embase up to December 2024.
Inclusion of five studies (n=33,286) utilizing various ML methods (e.g., ensemble algorithms, SHAP-driven models).
Random-effects meta-analysis for performance pooling, bias assessment using established tools, and era-stratified survival analyses.

Main Results:

Pooled ML models achieved an AUC of 0.86, sensitivity of 90%, and specificity of 91%.
Significant heterogeneity was observed (I²=72%-88%), attributed to variations in feature selection and validation.
Temporal analysis revealed a shift in key predictors from ischemic time/pulmonary vascular resistance to ECMO/VAD dependence, donor-recipient mismatch, and socioeconomic factors.

Conclusions:

ML-based models demonstrate superior performance compared to traditional methods in predicting pediatric HT mortality.
These models effectively capture evolving risk profiles, supporting their integration into clinical practice.
Enhanced accuracy and equity in pediatric HT decision-making can be achieved through the adoption of ML risk stratification.