Prediction of donor heart acceptance for transplant and its clinical implications – results from the Donor Heart Study

Abstract

AbstractBackgroundDespite a shortage of potential donors for heart transplant in the United States (US), most potential donor hearts are discarded. We evaluated predictors of donor heart acceptance in the US and applied modern analytic methods to improve prediction.MethodsWe included anationwide(2005 – 2020) cohort of potential heart donors in the US (n = 73,948) from the Scientific Registry of Transplant Recipients and a more recent (2015 – 2020) rigorously phenotyped cohort of potential donors from the Donor Heart Study (DHS; n = 4,130). We identified predictors of acceptance for heart transplant in both cohorts using multivariate logistic regression, incorporating time-interaction terms to characterize their varying effects over time. We fit models predicting acceptance for transplant in a 50% training subset of the DHS using multiple machine learning algorithms and compared their performance in the remaining 50% (test) subset.ResultsPredictors of donor heart acceptance were similar in thenationwideandDHScohorts. Among these, older age has become increasingly predictive of discard over time while other factors – including those related to drug use, infection, and mild cardiac diagnostic abnormalities - have become less influential. A random forest model (area under the curve 0.90, accuracy 0.82) outperformed other prediction algorithms in the test subset and was used as the basis of a novel web-based prediction tool.ConclusionsPredictors of donor heart acceptance for transplantation have changed significantly over the last two decades, likely reflecting evolving evidence regarding their impact on post-transplant outcomes. Real-time prediction of donor heart acceptance, using our web-based tool, may improve efficiency during donor management and heart allocation.Clinical PerspectivePredictors of donor heart acceptance for transplantation have changed significantly over the last two decades. Donor age has become increasingly influential while several other factors have become less so - likely reflecting the lack of evidence regarding their impact on post-transplant outcomes. Our web-based tool can enable real-time prediction of donor heart acceptance, and thereby improve efficiency during donor management and heart allocation.