Learning Potentials for Dynamic Matching and Application to Heart Transplantation
This addresses a critical life-threatening issue for patients awaiting heart transplants by improving allocation efficiency, though it builds on existing concepts from kidney exchange, making it incremental in method but with strong domain-specific impact.
The paper tackles the problem of inefficient heart transplant allocation due to dynamic organ arrivals and waitlist composition by proposing a novel non-myopic policy optimization framework using learned potentials, demonstrating significant outperformance over prior approaches including the current US policy in optimizing population-level outcomes with real historical data.
Each year, thousands of patients in need of heart transplants face life-threatening wait times due to organ scarcity. While allocation policies aim to maximize population-level outcomes, current approaches often fail to account for the dynamic arrival of organs and the composition of waitlisted candidates, thereby hampering efficiency. The United States is transitioning from rigid, rule-based allocation to more flexible data-driven models. In this paper, we propose a novel framework for non-myopic policy optimization in general online matching relying on potentials, a concept originally introduced for kidney exchange. We develop scalable and accurate ways of learning potentials that are higher-dimensional and more expressive than prior approaches. Our approach is a form of self-supervised imitation learning: the potentials are trained to mimic an omniscient algorithm that has perfect foresight. We focus on the application of heart transplant allocation and demonstrate, using real historical data, that our policies significantly outperform prior approaches -- including the current US status quo policy and the proposed continuous distribution framework -- in optimizing for population-level outcomes. Our analysis and methods come at a pivotal moment in US policy, as the current heart transplant allocation system is under review. We propose a scalable and theoretically grounded path toward more effective organ allocation.