Learning Potentials for Dynamic Matching and Application to Heart Transplantation

TL;DR

This paper introduces a scalable, data-driven framework using learned potentials for dynamic matching, significantly improving heart transplant allocation efficiency over existing policies by leveraging real data and a novel non-myopic approach.

Contribution

It develops a scalable, expressive method for learning potentials in online matching, tailored for heart transplants, outperforming current US policies with a novel self-supervised imitation learning approach.

Findings

Our policies outperform the US status quo in population outcomes.

The learned potentials are more expressive and scalable than previous methods.

Real data demonstrates significant improvements in allocation efficiency.

Abstract

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.