Related Experiment Video
Updated: Aug 23, 2025
Author Spotlight: Enhancing Graft Viability Assessment Through Quantitative Metrics and Innovative Reservoir Systems
Published on: August 2, 2024
Machine learning-based prediction of mortality after heart transplantation in adults with congenital heart disease: A
Polydoros N Kampaktsis1, Athanasios Siouras2, Ilias P Doulamis3
1Division of Cardiology, Columbia University Irving Medical Center, New York, New York, USA.
Insights
Machine learning accurately predicts mortality after heart transplantation in adults with congenital heart disease. This tool aids in personalized risk assessment for better patient outcomes.
Area of Science:
- Cardiology
- Medical Informatics
- Transplantation Science
Background:
- Machine learning (ML) is increasingly utilized in cardiology for outcome prediction and clinical decision support.
- Adults with congenital heart disease (ACHD) undergoing heart transplantation (HT) represent a unique population with specific post-transplant risks.
- Developing accurate predictive models for mortality in this cohort is crucial for improving patient management.
Purpose of the Study:
- To develop and validate a machine learning model for predicting mortality in adults with congenital heart disease following heart transplantation.
- To identify key predictors of mortality in this specific patient population.
- To enable individualized mortality risk assessment.
Main Methods:
- Utilized the United Network for Organ Sharing (UNOS) database (2000-2020) for adult patients with ACHD undergoing isolated HT.
- Split the cohort into derivation (70%) and validation (30%) datasets to train and test a CatBoost ML model.
- Employed SHapley Additive exPlanations (SHAP) for feature selection and explainability analysis, assessing recipient, donor, procedural, and post-transplant factors.
Main Results:
- The study included 1033 recipients; 19.9% experienced mortality within 1 year post-HT.
- A 1-year ML model achieved an Area Under the Curve (AUC) of 0.80 and 75.2% predictive accuracy; a 3-year model had an AUC of 0.69 and 74.2% accuracy.
- SHAP analysis identified post-HT hemodialysis, estimated glomerular filtration rate, age, and ischemic time as significant predictors of 1-year mortality.
Conclusions:
- Machine learning models demonstrate satisfactory predictive accuracy for mortality after heart transplantation in ACHD patients.
- The developed ML model facilitates individualized mortality risk assessment, aiding clinical decision-making.
- These findings highlight the potential of ML to enhance care for ACHD patients post-heart transplant.
Background:
Machine learning (ML) is increasingly being applied in Cardiology to predict outcomes and assist in clinical decision-making. We sought to develop and validate an ML model for the prediction of mortality after heart transplantation (HT) in adults with congenital heart disease (ACHD).
Methods:
The United Network for Organ Sharing (UNOS) database was queried from 2000 to 2020 for ACHD patients who underwent isolated HT. The study cohort was randomly split into derivation (70%) and validation (30%) datasets that were used to train and test a CatBoost ML model. Feature selection was performed using SHapley Additive exPlanations (SHAP). Recipient, donor, procedural, and post-transplant characteristics were tested for their ability to predict mortality. We additionally used SHAP for explainability analysis, as well as individualized mortality risk assessment.
Results:
The study cohort included 1033 recipients (median age 34 years, 61% male). At 1 year after HT, there were 205 deaths (19.9%). Out of a total of 49 variables, 10 were selected as highly predictive of 1-year mortality and were used to train the ML model. Area under the curve (AUC) and predictive accuracy for the 1-year ML model were .80 and 75.2%, respectively, and .69 and 74.2% for the 3-year model, respectively. Based on SHAP analysis, hemodialysis of the recipient post-HT had overall the strongest relative impact on 1-year mortality after HΤ, followed by recipient-estimated glomerular filtration rate, age and ischemic time.
Conclusions:
ML models showed satisfactory predictive accuracy of mortality after HT in ACHD and allowed for individualized mortality risk assessment.
