In CRTs, “intact social units, or clusters of individuals, rather than individuals themselves, are randomised” [6]. For example, hospitals, wards, or physicians can be randomised, as well as schools or geographical areas. Such a design is well adapted to assess organisational and behavioural interventions and health promotion programmes—interventions that are usually implemented at the level of health organisational units or geographical areas [9]. As well, randomisation of clusters rather than individuals could prevent contamination. As an example, to assess the impact of a screening programme, widespread publicity is needed to encourage participants to undergo screening. With individual randomisation, communication among participants would induce contamination, but with cluster randomisation, it may strengthen participant compliance.

Use of the CRT has greatly increased over the past 15 years [10] and has motivated the publication of an extension of the CONSORT Statement for this design [11] because of its particular methodological issues. The main issue is that observations from the same cluster are more similar than observations from two different clusters. This situation requires the use of both an inflated sample size and adapted statistical analysis to take into account this concern [6],[7]. Otherwise, for the recruitment process, we can distinguish two different designs: a whole CRT or a CRT with active recruitment. In the first design, once the person in charge of the cluster (the cluster guardian [12]) has agreed to participate, every individual belonging to the cluster is automatically recruited for the trial; in the second design, the guardian (or someone other than the guardian but depending on the guardian) must select and include participants for the trial. Also, Murray distinguishes between cohort designs, whereby a sample of participants is included, followed up, and assessed repeatedly (as is usually done in individually randomised trials), and repeated cross-sectional designs, whereby a distinct sample of participants is assessed at each assessment time [7]. Such a distinction makes sense only in whole CRTs. The design is always a cohort one when it involves active recruitment.

In individually randomised trials, randomisation and allocation concealment aim to prevent selection bias and allow for the comparability of groups at the beginning of the study. The aim of ITT analysis is to maintain this comparability during analysis. In CRTs, the situation is more complex because (i) the design entails a hierarchical structure (cluster and individual levels) and (ii) recruitment and follow-up processes differ from those in individually randomised trials.

First, the hierarchical structure of CRTs requires the consideration of both the cluster and individual levels. When Elbourne et al. [13] appealed for an extension of the CONSORT Statement to CRTs, they explicitly stated that authors must report whether “[the ITT] principle applies to clusters, individuals or both”. Campbell defined ITT analysis in CRTs as taking into account all participants, regardless of whether non-adherence to the protocol occurred at the individual or cluster level [14]. Indeed, in CRTs, participants lost to follow-up and protocol deviation can occur at the level of the cluster (cluster withdrawal or lost to follow-up, inactive cluster, merging of clusters) or the individual (participant withdrawal or lost to follow-up, or transfer from one cluster to another). Moreover, results of a CRT can be analysed by considering the individual or cluster as the statistical unit. Even in the latter case, a summary statistic is estimated from individual responses within each cluster. Therefore, the comparability of groups must be achieved at both the cluster (i.e., for randomised units) and individual levels.

Second, in a CRT, both recruitment and follow-up raise specific issues that may compromise the comparability of groups (Figures 1 and 2). The usual definition of an ITT analysis in CRTs is restrictive because it focuses only on follow-up issues. However, during the recruitment process, clusters may withdraw, or cluster guardians may not actively recruit participants; these situations lead to empty clusters, which should be taken into account to apply the ITT principle. Another important issue is differential recruitment between active clusters, which could be both quantitative (i.e., different number of participants recruited) and qualitative (i.e., participants with different characteristics recruited in both groups). As an example, in the UK BEAM trial, 71.4% of recruited participants were in the intervention group, even though the randomisation was 1∶1, and groups were not comparable on several clinically important criteria [15]. Eldridge et al. concluded that “about a quarter [of CRTs] were potentially biased because of procedures surrounding recruitment and identification of patients” [16], as previously acknowledged by Puffer et al. [8].

In CRTs, cluster withdrawal or loss to follow-up and participant withdrawal or loss to follow-up must be handled as is usually done in individually randomised trials, by use of ad hoc missing data methods [17],[18]. More specific to CRTs are participant switches from one cluster to another (e.g., patients who change physicians) and cluster merging (e.g., two medical practices that merge). These follow-up issues are not problematic per se and can be easily handled by keeping clusters as they were randomised. Thus, participants who switch from one cluster to another must be kept in their original cluster, and merged clusters must be split.

The major difference between individually randomised trials and CRTs in applying the ITT principle is that in the former, we know which participants were randomised and must be taken into account in the ITT analysis, whereas in CRTs, we know which clusters have been randomised but we frequently do not know exactly which participants within clusters should have been included in the trial. Whole CRTs and CRTs with active recruitment raise distinct issues, but for both, this dilemma is the real challenge of applying ITT analysis and preserving the comparability of groups.

The application of the ITT principle in analysis of data is much more complex in CRTs than in individually randomised trials because the principle must be applied at the level of both the cluster and the individual, and because of challenging issues surrounding the recruitment process in CRTs. These issues raise concerns regarding the internal validity of such trials.