Meta-analyses of chronic disease trials with competing causes of death may yield biased odds ratios

J Clin Epidemiol. 2008 Apr;61(4):365-72. doi: 10.1016/j.jclinepi.2007.05.009. Epub 2007 Oct 15.

Abstract

Objective: To study the odds ratio (OR) as measure of treatment effect in the context of mutually exclusive causes of death.

Study design and setting: As example we consider meta-analyses of randomized trials of implantable cardioverter defibrillator implantation (ICD). We compare the pooled OR to the pooled cause-specific hazard ratio (HR) for each of the mutually exclusive outcomes "sudden cardiac death" (SCD) and "death other than SCD."

Results: The pooled OR and cause-specific HR for the reduction of SCD are similar (0.43 and 0.44, respectively) for nine included trials. However, the OR erroneously presumes a potential trend toward an adverse effect of the ICD on "death other than arrhythmia" (OR 1.11 [0.84-1.45]), whereas such an effect is small with the cause-specific HR (HR 1.03 [0.79-1.32]). In general, it is shown that a spurious association of treatment with "other death" may be seen when a substantial number of death from the cause of interest is postponed.

Conclusion: The OR should be used with caution to study effects of treatment on mutually exclusive causes of death. Practically this concern applies primarily to meta-analysis where the use of the cause-specific HR, whenever available, is recommended.

MeSH terms

  • Bias
  • Cause of Death
  • Chronic Disease
  • Clinical Trials as Topic / statistics & numerical data*
  • Data Interpretation, Statistical*
  • Humans
  • Meta-Analysis as Topic*
  • Odds Ratio
  • Randomized Controlled Trials as Topic
  • Research Design
  • Treatment Outcome