Assessing Life Extension from Medical Interventions

• Activity Number: 32
• Type: Contributed
• Date/Time: Sunday, July 29, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Jerry Cheng*+ and Kezhen Liu and Javier Cabrera and John Kostis
• Companies: Robert Wood Johnson Medical School and Rutgers University and Rutgers University and Robert Wood Johnson Medical School
• Keywords: Survival analysis ; Bootstrap method ; Kaplan-meier estimator ; Cox regression ; Life extension ; Area under survival curve

Abstract

Comparing outcomes and assessing performance of several types of treatments is an important task in clinical trials as well as in observational studies. Among various measurements in assessing life extension, the gain in life expectancy is one of the performance measures of interest. In this presentation, we propose a framework for estimating life extension by calculating the area between estimated survival curves given by the treatment and placebo or for two comparative treatments. We estimate the survival curves first via non-parametric Kalplan-Meier estimator to reflect the observed survival curves. We then use semi-parametric Cox model and obtain the survival curves contributed only by the two treatment types. In order to assess the variability of our estimate, we propose a new Bootstrap method for obtaining bootstrap confidence intervals for this quantity. We also propose the corr