Article Text

Download PDFPDF
How should clinicians interpret results reflecting the effect of an intervention on composite end points?
  1. Jørgen Hilden, MD
  1. University of Copenhagen, Department of Biostatistics
 Copenhagen, Denmark

    Statistics from

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Evidence-Based Medicine recently published a thoughtful commentary by Montori et al,1 addressing the above question, prompted by the Australian Carbohydrate Intolerance Study in Pregnant Women (ACHOIS),2 which was abstracted in the same issue.3 The ACHOIS investigators compared a screen-and-treat programme for gestational diabetes with routine pregnancy care and used as their main end point a composite of 4 outcomes: shoulder dystocia, Duchenne-Erb palsy, fracture, and death—a natural choice given that a main purpose of gestational glycaemic control is to prevent the baby from being born too big. The topic is important and several points are worth noting.

    Montori et al listed 3 questions to help decide the appropriateness of a composite outcome:

    (a) Are the component …

    View Full Text