Informed Choice of Composite End Points in Cardiovascular Trials

Abstract

A composite end point is often used as the primary end point to assess the efficacy of a new treatment in randomized clinical trials. In cardiovascular trials, the often rare event of the relevant primary end point (individual or composite), such as cardiovascular death, myocardial infarction, or both, is combined with a more common secondary end point, such as target lesion revascularization, with the aim to increase the statistical power of the study. Gómez and Lagakos developed statistical methodology to be used at the design stage of a randomized clinical trial for deciding whether to expand a study-relevant primary end point to the composite of the relevant end point and a secondary end point. The method uses the asymptotic relative efficiency of the logrank test for comparing treatment groups based on the relevant end point versus the logrank test based on the composite end point. The method is used to assess, in the cardiovascular research area, the characteristics of the candidate individual end points that should govern the choice of using a composite end point as the primary end point in a clinical trial. A set of recommendations is provided based on the reported values of the frequencies of observing each candidate end point and on the magnitude of the effect of treatment as expressed by the hazard ratio, supported by cardiovascular randomized clinical trials published in 2008.

Traditional and new composite endpoints in heart failure clinical trials: facilitating comprehensive efficacy assessments and improving trial efficiency

“…Estimated treatment effects may be diluted if a substantial proportion of events are not influenced by the treatment . A greater number of events will increase statistical power only if those additional events are potentially modifiable by the intervention.…”

“…1 Estimated treatment effects may be diluted if a substantial proportion of events are not influenced by the treatment. 8 A greater number of events will increase statistical power only if those additional events are potentially modifiable by the intervention. The addition of outcomes that are not influenced by the treatment will reduce the measured treatment effect and the study power.…”

The Use of a Binary Composite Endpoint and Sample Size Requirement: Influence of Endpoints Overlap

“…Along with the probabilities of observing the event components and the magnitude of treatment effect on each component via the hazard ratio, Spearman's rank correlation between the times-to-each-component is needed (23). Describing the relationship between the overlap of components of a binary CE and the correlation between them in the context of the time-to-event analysis is beyond the scope of this manuscript and should be addressed in future work.…”

“…The method is built from the marginal laws of the times to each of these 2 outcomes and uses Spearman's rank correlation between these 2 times. Other papers discuss the relationship between asymptotic relative efficiency and needed sample sizes (22) and provide recommendations in cardiovascular studies (23).…”

Development and validation of a major adverse transplant event (MATE) score to predict late graft loss in pediatric heart transplantation

“…One established strategy to decrease sample size is to increase the event rate by using a composite end-point. 1,2 In adult cardiovascular trials, the major adverse cardiac event (MACE) score is perhaps the most widely used composite end-point, and includes mortality, non-fatal myocardial infarction (MI) and non-fatal stroke. A second strategy to decrease sample size is to use an ordinal rather than a binary endpoint.…”