Meta‐analysis combining parallel and crossover trials using generalised estimating equation method

This is the authors' abstract. We don't add key points for this paper.

Clinical trials have different designs: In late stage drug development, the parallel trial design is the most frequent one; however, the crossover design is not rare; different techniques are used to analyse their results. Although both designs measure the same treatment effect, combining parallel and crossover trials in a meta-analysis is not straightforward. We present here a meta-analysis method based on generalised estimating equation (GEE) regression to combine aggregated results of crossover and parallel trials using a marginal estimation approach. This method is based on the fixed effects meta-analytic model; it allows combining average outcomes belonging to the exponential distributions obtained from trials of different designs and in particular from crossover trials with more than 2 periods and 2 treatments. By extending the methods proposed so far to combine the 2 trial designs, the GEE regression allows for adjusting for bias, such as a carry-over effect typical in crossover trials. In this paper, the GEE meta-analysis method is compared to the classical weighted average method with examples of published and simulated meta-analyses. Although the GEE can account for crossover specificities, it is limited by the availability of detailed trial information often encountered with reports of these trials.