SAFETY EVALUATION AND CONFIDENCE-INTERVALS WHEN THE NUMBER OF OBSERVED EVENTS IS SMALL OR ZERO

A common objective in many clinical studies is to determine the safety of a diagnostic test or therapeutic intervention. In these evaluation s, serious adverse effects are either rare or not encountered. In this setting, the estimation of the confidence interval (CI) far the unkno wn proportion of adverse events has special importance. When no advers e events are encountered, commonly used approximate methods for calcul ating Cls cannot be applied, and such information is not commonly repo rted. Furthermore, when only a few adverse events are encountered, the approximate methods for calculation of CIs can be applied, but are ne ither appropriate nor accurate. In both situations, CIs should be comp uted with the use of the exact binomial distribution. We discuss the n eed for such estimation and provide correct methods and rules of thumb for quick computations of accurate approximations of the 95% and 99.9 % Cls when the observed number of adverse events Is zero.