Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset

TL;DR

This study benchmarks machine learning models using longitudinal UNOS data to predict waitlist mortality in heart transplantation, achieving high accuracy and revealing both known and novel risk factors.

Contribution

It introduces a comprehensive time-to-event modeling approach leveraging new longitudinal data, significantly improving mortality prediction accuracy.

Findings

Best model achieves C-Index of 0.94 and AUROC of 0.89

Key predictors include known risk factors and novel associations

Model outperforms previous approaches

Abstract

Decisions about managing patients on the heart transplant waitlist are currently made by committees of doctors who consider multiple factors, but the process remains largely ad-hoc. With the growing volume of longitudinal patient, donor, and organ data collected by the United Network for Organ Sharing (UNOS) since 2018, there is increasing interest in analytical approaches to support clinical decision-making at the time of organ availability. In this study, we benchmark machine learning models that leverage longitudinal waitlist history data for time-dependent, time-to-event modeling of waitlist mortality. We train on 23,807 patient records with 77 variables and evaluate both survival prediction and discrimination at a 1-year horizon. Our best model achieves a C-Index of 0.94 and AUROC of 0.89, significantly outperforming previous models. Key predictors align with known risk factors while also revealing novel associations. Our findings can support urgency assessment and policy refinement in heart transplant decision making.