Combining multiple outcome measures in a meta-analysis: an application

Authors

  • Lidia R. Arends,

    Corresponding author
    1. Department of Epidemiology & Biostatistics, Erasmus University Medical School, P.O. Box 1738, 3000 DR Rotterdam, The Netherlands
    • Institute of Epidemiology and Biostatistics, Erasmus University Medical School, P.O. Box 1738, 3000 DR Rotterdam, The Netherlands
    Search for more papers by this author
  • Zoltán Vokó,

    1. Department of Epidemiology & Biostatistics, Erasmus University Medical School, P.O. Box 1738, 3000 DR Rotterdam, The Netherlands
    2. School of Public Health, Medical and Health Science Center, University of Debrecen, Kassai út 26/b, 4028 Debrecen, Hungary
    Search for more papers by this author
  • Theo Stijnen

    1. Department of Epidemiology & Biostatistics, Erasmus University Medical School, P.O. Box 1738, 3000 DR Rotterdam, The Netherlands
    Search for more papers by this author

Abstract

In meta-analysis of clinical trials published in the medical literature it is customary to restrict oneself to standard univariate fixed or random effects models. If multiple endpoints are present, each endpoint is analysed separately. A few articles have been written in the statistical literature on multivariate methods for multiple outcome measures. However, these methods were not easy to apply in practice, because self-written programs had to be used, and the examples were only two-dimensional. In this paper we consider a meta-analysis on the effect on stroke-free survival of surgery compared to conservative treatment in patients with increased risk of stroke. Three summary measures per trial are available: short-term post-operative morbidity/mortality in the surgical group; long-term event rate in the surgical group, and the event rate in the conservative group. We analyse the three outcomes jointly with a general linear MIXED model, compare the results with the standard univariate approaches and discuss the many advantages of multivariate modelling. It turns out that the general linear MIXED model is a very convenient framework for multivariate meta-analysis. All analyses could be carried out in standard general linear MIXED model software. Copyright © 2003 John Wiley & Sons, Ltd.

Ancillary