From the Eunice Kennedy Shriver National Institute of Child Health and Human Development, Bethesda, MD
The views and conclusions in this article are those of the author and should not be interpreted to represent the practice or policy of any Federal agency or the Department of Health and Human Services.
Author's disclosure of potential conflicts of interest is found at the end of this article.
Address reprint requests to Steven Hirschfeld, MD, PhD, Eunice Kennedy Shriver National Institute of Child Health and Human Development, 31 Center Drive, 2A03, MSC-2425, Bethesda, MD 20814; e-mail: hirschfs{at}mail.nih.gov
Overview: The outcomes of efficacy studies must be selected with care to either directly demonstrate clinical benefit or to indirectly imply clinical benefit by using an outcome that has predictive value for clinical benefit. The goal of studies intended to establish clinical benefit should be to refine data on an outcome that has already been assessed during the development of the intervention. Study size is determined using best estimates of the number of informative events. The use of non-overlapping confidence intervals can establish superior efficacy relative to any comparator and, depending on the context and effect size, could be established with a differential of approximately 25 events. The quality of execution of a study is another component that can support the overall credibility of inferred conclusions, and a formal mechanism to assess study quality is proposed.
