Rethinking composite end points in clinical trials: insights from patients and trialists

Abstract

Background: Many clinical trials use composite end points to reduce sample size, but the relative importance of each individual end point within the composite may differ between patients and researchers.

Methods and results: We asked 785 cardiovascular patients and 164 clinical trial authors to assign 25 "spending weights" across 5 common adverse events comprising composite end points in cardiovascular trials: death, myocardial infarction, stroke, coronary revascularization, and hospitalization for angina. We then calculated end point ratios for each participant's ratings of each nonfatal end point relative to death. Whereas patients assigned an average weight of 5 to death, equal or greater weight was assigned to myocardial infarction (mean ratio, 1.12) and stroke (ratio, 1.08). In contrast, clinical trialists were much more concerned about death (average weight, 8) than myocardial infarction (ratio, 0.63) or stroke (ratio, 0.53). Both patients and trialists considered revascularization (ratio, 0.48 and 0.20, respectively) and hospitalization (ratio, 0.28 and 0.13, respectively) as substantially less severe than death. Differences between patient and trialist end point weights persisted after adjustment for demographic and clinical characteristics (P<0.001 for all comparisons).

Conclusions: Patients and clinical trialists did not weigh individual components of a composite end point equally. Whereas trialists are most concerned about avoiding death, patients place equal or greater importance on reducing myocardial infarction or stroke. Both groups considered revascularization and hospitalization as substantially less severe. These findings suggest that equal weights in a composite clinical end point do not accurately reflect the preferences of either patients or trialists.

Keywords: cardiovascular diseases; clinical trial; end point determination; patient preference; patient-centered care; statistics.

Figure 1. Survey for Weighing Clinical Endpoints

The order of individual endpoints was varied at random to help minimize bias when assigning endpoint weights.

Figure 2. Adjusted Endpoint Weights According to Patient Age, Race, and Annual Income

Shaded bars indicate mean absolute weights (after rescaling data so that weights sum to 100), adjusted for all available demographic and clinical characteristics.