Online Program Home
My Program

Abstract Details

Activity Number: 407 - Novel Methods for Causal Inference in Health Policy
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 2:00 PM to 3:50 PM
Sponsor: Health Policy Statistics Section
Abstract #304807 Presentation
Title: A Probabilistic Approach to Cost-Effectiveness Analysis with Censored Outcomes
Author(s): Nicholas Illenberger* and Andrew J. Spieker and Nandita Mitra
Companies: University of Pennsylvania and Vanderbilt University Medical Center and University of Pennsylvania
Keywords: cost-effectiveness; potential outcomes; censoring; inverse probability weighting; cancer

To make informed health policy decisions, we must consider both a treatment's effectiveness and its cost. We previously developed a novel probabilistic measure of cost-effectiveness using the potential outcomes framework. This approach elucidates the probability that a patient receiving one treatment will have a more cost-effective outcome than a patient receiving another treatment, at a particular willingness-to-pay value. Our cost-effectiveness determination (CED) curve serves as a graphical tool based on this parameter that overcomes limitations of currently used visual aids such as the acceptability curve. In this talk, we present an inverse-probability weighting approach to estimate the CED for censored survival outcomes. This approach accommodates modifications to account for confounding in observational databases, as well as regression approaches to allow for subgroup discovery. Through simulations, we show that the method has desirable finite-sample properties (e.g., low bias and proper coverage). As an illustration, we use data from a large observational cancer registry to determine the cost-effectiveness of adjuvant radiation therapy in endometrial cancer patients.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program