Related Experiment Video
Updated: Jul 26, 2025
Author Spotlight: Enhancing Graft Viability Assessment Through Quantitative Metrics and Innovative Reservoir Systems
Published on: August 2, 2024
Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of
Michael O Killian1, Shubo Tian2, Aiwen Xing2
1College of Social Work, Florida State University, Tallahassee, FL, United States.
Insights
Machine learning models accurately predict rejection and mortality in pediatric heart transplant recipients. Random Forest and AdaBoost showed the best performance, identifying key risk factors for improved post-transplant care.
Area of Science:
- Cardiovascular Medicine
- Biomedical Informatics
- Pediatric Transplantation
Background:
- Accurate prediction of posttransplant health outcomes is crucial for pediatric heart transplant recipients.
- Risk stratification and high-quality care depend on reliable outcome prediction.
Purpose of the Study:
- To evaluate machine learning (ML) models for predicting rejection and mortality in pediatric heart transplant recipients.
- To assess the utility of ML in identifying risk factors for posttransplant outcomes.
Main Methods:
- Utilized United Network for Organ Sharing data (1987-2019) for pediatric heart transplant recipients.
- Evaluated seven ML models (e.g., Random Forest, AdaBoost) and a deep learning model.
- Employed 10-fold cross-validation and SHAP values to assess model performance and variable importance.
Main Results:
- Random Forest (RF) and Adaptive Boosting (AdaBoost) demonstrated superior performance in predicting outcomes.
- RF excelled in predicting mortality and rejection at 1 and 3 years.
- AdaBoost showed the best performance for predicting 5-year rejection.
Conclusions:
- ML models effectively model posttransplant outcomes using registry data.
- ML can uncover unique risk factors and their complex associations with outcomes.
- These findings highlight the potential of ML to enhance pediatric heart transplant care and decision-making.
Background:
The prediction of posttransplant health outcomes for pediatric heart transplantation is critical for risk stratification and high-quality posttransplant care.
Objective:
The purpose of this study was to examine the use of machine learning (ML) models to predict rejection and mortality for pediatric heart transplant recipients.
Methods:
Various ML models were used to predict rejection and mortality at 1, 3, and 5 years after transplantation in pediatric heart transplant recipients using United Network for Organ Sharing data from 1987 to 2019. The variables used for predicting posttransplant outcomes included donor and recipient as well as medical and social factors. We evaluated 7 ML models-extreme gradient boosting (XGBoost), logistic regression, support vector machine, random forest (RF), stochastic gradient descent, multilayer perceptron, and adaptive boosting (AdaBoost)-as well as a deep learning model with 2 hidden layers with 100 neurons and a rectified linear unit (ReLU) activation function followed by batch normalization for each and a classification head with a softmax activation function. We used 10-fold cross-validation to evaluate model performance. Shapley additive explanations (SHAP) values were calculated to estimate the importance of each variable for prediction.
Results:
RF and AdaBoost models were the best-performing algorithms for different prediction windows across outcomes. RF outperformed other ML algorithms in predicting 5 of the 6 outcomes (area under the receiver operating characteristic curve [AUROC] 0.664 and 0.706 for 1-year and 3-year rejection, respectively, and AUROC 0.697, 0.758, and 0.763 for 1-year, 3-year, and 5-year mortality, respectively). AdaBoost achieved the best performance for prediction of 5-year rejection (AUROC 0.705).
Conclusions:
This study demonstrates the comparative utility of ML approaches for modeling posttransplant health outcomes using registry data. ML approaches can identify unique risk factors and their complex relationship with outcomes, thereby identifying patients considered to be at risk and informing the transplant community about the potential of these innovative approaches to improve pediatric care after heart transplantation. Future studies are required to translate the information derived from prediction models to optimize counseling, clinical care, and decision-making within pediatric organ transplant centers.
More Related Videos
10:56Transplantation of Pulmonary Valve Using a Mouse Model of Heterotopic Heart Transplantation
Published on: July 23, 2014
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
