Machine learning‐based prediction of mortality after heart transplantation in adults with congenital heart disease: A UNOS database analysis

Abstract

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.

Noninvasive Advanced Cardiovascular Magnetic Resonance–Derived Fontan Hemodynamics Are Associated With Reduced Kidney Function But Not Albuminuria

“… 3 A multitude of studies have implicated kidney dysfunction as one of the most important risk factors for death in adults with congenital heart disease, increasing the risk of death by 2‐ to 3‐fold. 4 , 5 , 6 Similar findings have been confirmed within the subgroup of patients with Fontan circulation. 7 Despite widespread availability as key screening tools for chronic kidney disease (CKD), data regarding estimated glomerular filtration rate (eGFR) and urine albumin‐to‐creatinine ratio (ACR) in patients with Fontan circulation remain limited.…”

Using machine learning algorithms to identify chronic heart disease: National Health and Nutrition Examination Survey 2011–2018

“…23 A recent study showed that Catboost (a gradient-boosting algorithm) can predict the posttransplant mortality rate of adults with congenital heart disease, with an AUC value of 0.80. 24 In these four models, the performance of identifying highrisk populations for CHD was very similar. SVM has the best performance (AUC ¼ 0.898), whereas other models (logistic regression, AUC ¼ 0.895; random forest, AUC ¼ 0.894; XGBoost, AUC ¼ 0.891) can provide similar results.…”

“…Mohan et al constructed a mixed machine learning technique based on linear models and random forest to predict heart disease, with an accuracy of 88.7% 23 . A recent study showed that Catboost (a gradient-boosting algorithm) can predict the posttransplant mortality rate of adults with congenital heart disease, with an AUC value of 0.80 24 …”

The Role of Artificial Intelligence in Prediction, Risk Stratification, and Personalized Treatment Planning for Congenital Heart Diseases

“…Prediction models are central to healthcare research and practice. In cardiology, ML-based prediction models are gaining traction for forecasting outcomes and supporting clinical decisions [ 14 , 15 ]. For instance, these models have been employed to predict mortality following heart transplantation in adults with congenital heart disease, aiding physicians in personalized treatment strategies [ 15 ].…”

“…In cardiology, ML-based prediction models are gaining traction for forecasting outcomes and supporting clinical decisions [ 14 , 15 ]. For instance, these models have been employed to predict mortality following heart transplantation in adults with congenital heart disease, aiding physicians in personalized treatment strategies [ 15 ]. While AI holds immense potential in healthcare, including pediatric cardiology, there is still a need for further research to develop models that are interpretable, reliable, and applicable to a diverse range of complex CHD cases.…”