Design and interpretation of equivalence trials

Abstract

The efficacy of a new therapeutic agent would be established if its treatment effects prove to be at least equivalent to those observed from a standard-of-care regimen, which itself has a precisely determined and substantial level of efficacy. If a new agent not only demonstrates its equivalence with standard therapy but also offers advantages in terms of toxicity, ease of administration, or cost, the new agent may provide an important advance in clinical care. Because of the increasing importance of equivalence trials, the clinical trials that determine whether equivalence exists between new and standardofcare therapies, it is important to understand how such trials are designed and interpreted. In the Global Use of Strategies to Open Occluded Coronary Arteries (GUSTO) IIl trial, a new thrombolytic agent, reteplase (recombinant plasminogen activator), was administered in double-bolus infusion to patients with acute myocardial infarction (AMD. Reteplase did not provide additional survival benefit over alteplase (recombinant tissue plasminogen activator),’ administered in accelerated infusion. The primary endpoint, 30 day mortality, was not statistically significantly different between the two agents. Do these results mean that reteplase has now been shown to be equivalent to alteplase in treating patients with AMI? If so, reteplase might become the preferred treatment because it may offer more convenient administration than does alteplase. The superiority of a new therapy to the standardofcare regimen is traditionally established by ruling out its equality to the standard therapy. In turn, the equivalence of a new therapy with a standard regimen is established by analyses that allow investigators to rule out that there are clinically important differences favoring the standard regimen. While nonsignificant P values from tests of equality indicate that trial results have not conclusively established the superiority of an experimental regimen, these tests do not address the issue of the equivalence of that regimen with standard therapy. Confidence intervals should be used to address the issue of equivalence, and it is important that they be used properly when investigators draw conclusions about the equivalence of a new therapy to established therapy.