An Ensemble Survival Model for Estimating Relative Residual Longevity Following Stroke: Application to Mortality Data in the Chronic Dialysis Population

• Activity Number: 333
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Milind Phadnis*+ and James B. Wetmore and Theresa I. Shireman and Edward F. Ellerbeck and Jonathan D. Mahnken
• Companies: University of Kansas Medical Center and Hennepin County Medical Center and University of Kansas Medical Center and University of Kansas Medical Center and University of Kansas Medical Center
• Keywords: additve hazards ; generalized gamma ; semi-Markov model ; relative times ; residual median life ; time-dependent covariates

Abstract

Time-dependent covariates can be modeled within the Cox regression framework and can result in non-proportional hazards for the risk factor of research interest. However, in many areas of health services research, interest centers on being able to estimate residual longevity after the occurrence of a particular event such as stroke. The survival trajectory of patients experiencing a stroke can be potentially influenced by stroke type (hemorrhagic or ischemic), time of the stroke (relative to time zero), time since the stroke occurred, or a combination of these factors. In such situations, researchers are more interested in estimating lifetime lost due to stroke rather than merely estimating the relative hazard due to stroke. To achieve this, we propose an ensemble approach using the generalized gamma (GG) distribution by means of a semi-Markov model with an additive hazards extension. Our modeling framework allows stroke as a covariate to affect all three parameters (location, scale, and shape) of the GG distribution. Using the concept of relative times (RT), we answer the research question by estimating residual life lost (RLL) due to stroke in the chronic dialysis population.