Estimating the Causal Effect of Solid Organ Transplantation Treatment Regimes on Survival

• Activity Number: 270
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 2:45 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Jeffrey Boatman* and David Vock
• Companies: and University of Minnesota
• Keywords: Causal Inference ; Dynamic Treatment Regimes ; Lung Transplantation

Abstract

Patients awaiting organ transplantation may confront a difficult decision if offered a low-quality organ: accept the organ or remain on the waiting list with the hope of receiving a better organ but with the possibility that they may die before another organ is offered. Previous methods to test treatment strategies from observational data do not account for situations where treatment is available randomly. A patient awaiting transplantation may have multiple opportunities to accept or decline a transplant, and organ availability varies probabilistically. Furthermore, treatment is not independent across subjects: if a patient receives an organ for transplantation then other patients cannot receive that organ. We propose an extension of inverse-of-probability-of-compliance weighted estimators to the situation where treatment is available stochastically to estimate the anticipated survival if a patient were to follow certain rules on whether to decline an offered organ. We discuss both the asymptotic properties of our estimators and the finite sample properties. We implement the method with data from the United Network for Organ Sharing national registry of lung transplantations.