Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

During the course of the COVID-19 pandemic the impetus to find potentially effective treatments as quickly as possible has driven an increased interest in adaptive designs and platform trials.  Several high profile trials, such as PRINCIPLE, RECOVER, and RECAMP-CAP are exemplars of platform trials conducted during this pandemic.  The advantage of the platform design is that it increases efficiency over traditional parallel randomised designs by using the same setup to compare multiple potential interventions, with the capacity to add additional interventions in the future (Berry, Connor and Lewise, 2015). In particular, PRINCIPLE is the largest platform trial in the world with focus on evaluation of treatment in primary.  This trial employs response adaptive randomisation in order to prioritise randomisation to interventions that appear promising, in order to be able to declare superiority of such treatments as soon as possible. This trade-off means interventions that appear less promising are assigned a lower randomisation probability and so may take longer to declare futility. Despite these advantages the risk in a platform trial is that there may be a tendency to underestimate the treatment effect when the trial is stopped early for futility or overestimate when it is stopped early for superiority. 

Issues of missing data in randomised clinical trials has been well documented and many methodological researches have been carried out over the past 30 years.  However, little is known on the impact of missing data and its role in decision making process when conducting interim analysis in platform trials.  The aim of this project is to address these issues.

If interested, please contact Ly-Mee Yu ly-mee.yu@phc.ox.ac.uk