Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
To gauge the relative efficacy of treatments, authors of review articles and commentary might attempt to compare results across clinical trials, but failure to recognize inherent differences across studies or apply proper statistical principles could yield flawed conclusions. Several approaches can mitigate the risks in these cross-trial comparisons.