Wanneer is er genoeg bewijs?; tussentijdse analyse van klinisch onderzoek

There are ethical and economic reasons to design and conduct medical research as efficiently as possible. Clinical trials often take a long time because of the number of patients that must be included and the follow-up time in the study. Many data already become available during that time. By making interim analyses of these data it is possible to decide whether a final conclusion can be made. This may save time and may lead to a reduction in the number of patients. The statistical methodology of interim analyses is more complex than a fixed sample analysis and must be planned carefully in advance. The most important methods are sequential analysis and group sequential analysis. Both methods are aimed at a low risk of a false-positive conclusion. In this article we explain the application of these methods as well as considerations in the design of a study and interpretation of the results.