Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset
arXiv:2507.07339v2 Announce Type: replace-cross 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
The increasing volume of longitudinal patient, donor, and organ data collected by UNOS since 2018 is now enabling more sophisticated machine learning applications for clinical decision-making.
This development indicates a growing capability for AI to augment critical human decisions in high-stakes medical contexts, potentially improving outcomes and efficiency in organ allocation.
The reliance on ad-hoc committee decisions for heart transplant waitlist management begins to shift towards data-driven, machine learning-supported protocols, introducing more objective and potentially more effective patient prioritization.
- · Machine learning researchers
- · Patients on transplant waitlists
- · Healthcare AI developers
- · Organ transplant centers
- · Traditional ad-hoc medical decision-making committees
- · Inefficient organ allocation systems
Machine learning models will become increasingly integrated into clinical decision support systems for organ transplantation.
This success could accelerate the adoption of AI in other complex medical decision-making scenarios, leading to broader healthcare transformation.
Ethical frameworks and regulatory guidelines for AI in critical medical applications will need to rapidly evolve to ensure fairness and accountability.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG