Abstract

Clinical disease registries offer a rich collection of valuable patient information but also pose challenges that require special care and attention in statistical analyses. The goal of this paper is to propose a statistical framework that allows for estimating the effect of surgical insertion of a percutaneous endogastrostomy (PEG) tube for patients living with amyotrophic lateral sclerosis (ALS) using data from a clinical registry. Although all ALS patients are informed about PEG, only some patients agree to the procedure which, leads to the potential for selection bias. Assessing the effect of PEG is further complicated by the aggressively fatal disease, such that time to death competes directly with both the opportunity to receive PEG and clinical outcome measurements. Our proposed methodology handles the “censoring by death” phenomenon through principal stratification and selection bias for PEG treatment through generalized propensity scores. We develop a fully Bayesian modeling approach to estimate the survivor average causal effect (SACE) of PEG on BMI, a surrogate outcome measure of nutrition and quality of life. The use of propensity score methods within the principal stratification framework demonstrates a significant and positive effect of PEG treatment, particularly when time of treatment is included in the treatment definition.

Highlights

  • Zhang et al.[5] further outlines specific parametric approaches for identification of survivor average causal effect (SACE) in the analysis of truncation by death using principal stratification[5]

  • Of particular interest in this data is the effect of a surgical insertion of a percutaneous endoscopic gastrostomy (PEG), a palliative procedure that provides enteral nutrition, on the outcome BMI, a proxy measure of adiposity associated with nutritional status and mortality

  • SACE of PEG Treatment is estimated in 16 model scenarios; in addition to the two definitions of treatment, models are considered for various levels of propensity score inclusion and with or without the assumption of monotonicity

Read more

Summary

Introduction

Zhang et al.[5] further outlines specific parametric approaches for identification of survivor average causal effect (SACE) in the analysis of truncation by death using principal stratification[5]. When selection bias or confounding may be present, either as residual confounding in a randomized clinical trial or due to observational data, Shwartz et al.[6] show that the resulting principal effect estimate is likely to be biased[6] This result indicates that in the absence of randomization or when the randomization scheme results in poor balance among treatment groups, there is a need to incorporate methods for alleviating selection bias and confounding within a principal stratification framework. We propose a framework that allows for the causal effect of treatment in the ALS registry data by combining principal stratification with adjustment of covariates using generalized propensity score. For those individuals who receive PEG prior to 1 year post-baseline, treatment is recorded as both the time from PEG surgery until 1 year post baseline, TZ, as well as a binary indicator of PEG surgery within the first year post-baseline, Z

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call