Balancing Efficiency and Fairness in Dynamic Kidney Exchange

The preferred treatment for kidney failure is a transplant; however, demand for donor kidneys far outstrips supply. Kidney exchange, an innovation where willing but incompatible donor-patient pairs can exchange organs—via cycles and altruist-initiated chains— provides a life-saving alternative to long waiting lists for deceased-donor organs. Typically, fielded exchanges act myopically, considering only the current pool of pairs when planning the cycles and chains. Yet kidney exchange is inherently dynamic, with participants arriving and departing. Also, many planned exchange transplants do not go to surgery due to various failures. Thus, it is important to consider the future when matching. Motivated by our experience running the computational side of the US nationwide kidney exchange, we present FUTUREMATCH, a framework for learning to match in a general dynamic model. We validate FUTUREMATCH on the real nationwide exchange data. Not only does dynamic matching result in more expected transplants than myopic matching, but also even dynamic matching under economically inefficient objectives that enforce equity can result in statistically significant increases in social welfare over efficient myopic matching.