Estimands & Missing Data Within Clinical Trials

How often is the planned statistical analysis approach changed in randomised controlled trials?

Project led by Brennan Kahan at Pragmatic Clinical Trials Unit at Queen Mary University of London

Imperial team: Suzie Cro, Nicholas Johnson

 

To avoid issues of selective reporting it is important that the planned analysis for a randomised controlled trial is pre-specified, and that any changes to the planned analysis are flagged. For full transparency, the pre-specified analysis approach should also be made publicly available, to allow comparison between the planned and actual analyses.

 

We are conducting a review of recently published trials to evaluate (i) how often a pre-specified analysis approach is publicly available (e.g. in a protocol or Statistical Analysis Plan); and (ii) how often the planned analysis approach was changed, and whether these changes were flagged.   

Statistical approaches used to adjust for the use of rescue medication in randomised controlled trials

Team: Anca Chis Ster, Victoria Cornelius, Suzie Cro

In chronic conditions, such as asthma and eczema, access to rescue medication is often allowed to aid recruitment and retention of participants in addition to ethical considerations. Allowing participants to have rescue medication, as well as the study drug treatment, may impact the treatment effect estimate. It can therefore be of value to obtain estimates of the treatment effect which adjust for the use of rescue medication. There are currently no existing best approaches to calculate these adjusted estimates. We are therefore conducting a systematic review to identify what statistical approaches are being used by trialists to describe and adjust for rescue medication use.

The protocol for this project is available here.

 

How should compliance be defined in smartphone app trials?

Team: Jack Elkes, Suzie Cro, Victoria Cornelius

The need to validate the use of smartphone apps and other digital technologies in healthcare is rapidly growing. A randomised controlled trial remains the gold standard approach and typically, an intention-to-treat analysis will be performed to determine if the intervention is beneficial.

However, the use of an app is known to decline substantially over time and an additional question of interest to answer is how effective the app in those is who use it (‘complie’).  Unlike drug and behavioural interventions, compliance with digital interventions is more complex to define. There are currently recommended approaches to define participant compliance for smartphone app use in a trial. This is needed when calculating the benefit of treatment receipt (using complier causal inference methods).

We are conducting research to identify the different ways patients access the app based on key metrics; duration in app, pages accessed, and time of day accessed. PCA will be used to identify clusters of the different user profiles, which in turn will help us to develop a strategy for defining compliance to an app.