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

2025-07-09

AI Summary

Current risk prediction for mortality among heart transplant candidates lacks dynamic, data-driven support. Method: Leveraging a longitudinal cohort from UNOS (2018–present; 23,807 patients, 77 variables), this study systematically benchmarks multiple time-to-event models and develops a high-accuracy, dynamic survival prediction framework by integrating survival analysis with machine learning techniques tailored to longitudinal clinical data. Performance is rigorously evaluated using the concordance index (C-index = 0.94) and area under the ROC curve (AUROC = 0.89) for one-year mortality prediction. Contribution/Results: The proposed model significantly outperforms existing approaches, uncovers novel risk-associated factors, and identifies clinically interpretable predictors highly consistent with domain knowledge. It delivers an explainable, deployable, data-driven decision-support framework to optimize transplant allocation priority.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Predicting heart transplant waitlist mortality using longitudinal data
• Benchmarking machine learning models for survival prediction
• Improving clinical decision-making with analytical approaches

Innovation

• Leveraging longitudinal UNOS data for modeling
• Time-to-event machine learning for mortality prediction
• Achieving high accuracy with C-Index 0.94