Combining composite endpoints: counterintuitive or a mathematical impossibility?

摘要: To the Editor: In their excellent article, DeMets and Califf1 discuss composite endpoints. I would appreciate further thoughts. When use of a treatment “X” reduces endpoint death, non-fatal myocardial infarction, softer such as revascularization or hospitalization rates, we are led to illusion that all 3 endpoints reduced. Often only most frequent, ie, softest is Because an increase in mortality be detected by safety monitoring, isn’t inclusion death when study underpowered show decrease simply misleading? Aside from perhaps calculation event-free survival uses time metric, combination events different …