Bayesian model averaging in meta-analysis: vitamin E supplementation and mortality

Abstract

Context: The strength and relevance of a meta-analysis depends on the validity of the statistical methods used. Of special importance is appropriately assessing different sources of variability. Many studies including meta-analyses have evaluated the efficacy and safety of vitamin E and have yielded varying results. Illuminating and resolving these disparities requires addressing study variability and model uncertainty.

Objective: To describe Bayesian meta-analysis methods for combining data from clinical trials, using recent studies that analyzed the relationship between vitamin E dose and all-cause mortality.

Data sources: Studies used in a previously published meta-analysis appended by studies identified by a search of MEDLINE from August 2004 to December 2005 using the MeSH terms vitamin e and alpha tocopherol.

Inclusion criteria: men and nonpregnant women; use of vitamin E alone or in combination with other vitamins or minerals; random allocation of participants to either vitamin E or a placebo or other control group; intervention and follow-up duration greater than 1 year; 10 or more deaths.

Data extraction: Independent data extraction by one author was reviewed and confirmed by a second author. Corresponding authors of the original publications were contacted when questions arose.

Data synthesis: Data collection included the number of patients and deaths, percent men, use of other vitamins or minerals, mean age, and length of follow-up. We combined study results using Bayesian hierarchical model averaging. Analyses used Markov chain Monte Carlo computational techniques.

Conclusions: Vitamin E intake is unlikely to affect mortality regardless of dose. The Bayesian meta-analyses presented here are ideal for incorporating disparate sources of variability, including trial effect and model uncertainty.