Prediction of Outcomes After Heart Transplantation in Pediatric Patients Using National Registry Data: Evaluation of Machine Learning Approaches
Open Access
- 20 June 2023
- journal article
- research article
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 7, e45352
Abstract
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.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- Quality of life after organ transplantation in childrenCurrent Opinion in Organ Transplantation, 2013
- Creation of a Quantitative Recipient Risk Index for Mortality Prediction After Cardiac Transplantation (IMPACT)The Annals of Thoracic Surgery, 2011
- Change in Mortality Risk Over Time in Young Kidney Transplant RecipientsAmerican Journal of Transplantation, 2011
- RADIAL: A novel primary graft failure risk score in heart transplantationThe Journal of Heart and Lung Transplantation, 2011
- Adherence to medical recommendations in pediatric transplant recipients: Time for actionPediatric Transplantation, 2008
- Improving adherence to medications in pediatric liver transplant recipientsPediatric Transplantation, 2008
- Non‐adherence to post‐transplant care: Prevalence, risk factors and outcomes in adolescent liver transplant recipientsPediatric Transplantation, 2007
- Current issues in pediatric transplantationPediatric Transplantation, 2006
- Adolescent non‐adherence: Prevalence and consequences in liver transplant recipientsPediatric Transplantation, 2006
- SRTR Center-Specific Reporting Tools: Posttransplant OutcomesAmerican Journal of Transplantation, 2006