Policy Optimization for Dynamic Heart Transplant Allocation

2025-12-13

AI Summary

Heart transplantation faces critical limitations due to donor scarcity and an allocation policy that fails to jointly optimize pre- and post-transplant mortality risks. Method: Leveraging real-world UNOS data, we developed a discrete-event dynamic simulation platform incorporating dynamic programming principles and potential-function modeling to evaluate allocation strategies. Contribution/Results: First, we introduce the “potential value” metric—novelly quantifying long-term survival utility per patient. Second, we propose a batch-based donor matching mechanism and systematically analyze how geographic distance and center-level refusal behavior impact equity and waitlist mortality. Comparative evaluation of myopic versus forward-looking policies shows our approach significantly increases average life-years gained over the 2018 OPTN policy. Small-batch processing further enhances matching efficiency. Crucially, geographic barriers and center refusals are identified as key structural drivers elevating waitlist mortality—highlighting actionable levers for policy reform.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Heart transplantation is a viable path for patients suffering from advanced heart failure, but this lifesaving option is severely limited due to donor shortage. Although the current allocation policy was recently revised in 2018, a major concern is that it does not adequately take into account pretransplant and post-transplant mortality. In this paper, we take an important step toward addressing these deficiencies. To begin with, we use historical data from UNOS to develop a new simulator that enables us to evaluate and compare the performance of different policies. We then leverage our simulator to demonstrate that the status quo policy is considerably inferior to the myopic policy that matches incoming donors to the patient who maximizes the number of years gained by the transplant. Moreover, we develop improved policies that account for the dynamic nature of the allocation process through the use of potentials -- a measure of a patient's utility in future allocations that we introduce. We also show that batching together even a handful of donors -- which is a viable option for a certain type of donors -- further enhances performance. Our simulator also allows us to evaluate the effect of critical, and often unexplored, factors in the allocation, such as geographic proximity and the tendency to reject offers by the transplant centers.

Problem

• Optimizes heart transplant allocation using dynamic policy potentials
• Addresses donor shortage by improving pre- and post-transplant mortality consideration
• Evaluates geographic proximity and offer rejection impacts via a new simulator

Innovation

• Developed a simulator using UNOS historical data
• Introduced potentials to account for dynamic allocation
• Evaluated batching donors and geographic factors