Missing outcomes in randomized trials: addressing the dilemma

A LTHOUGH RANDOMIZED TRIALS HAVE BEEN CON­ ducted for several decades now, some aspects of their analysis remain contentious. Two such is­ sues are what to do about trial participants who do not adhere to the protocol (for example, if they do not re­ ceive the intended treatment) and how to deal with those for whom outcome assessments are missing (for example, because they are lost to follow­up). Both of these issues are relevant to the adoption of so­called " in­ tention to treat " (ITT) analysis – a topic that, not sur­ prisingly, also causes debate. ITT analysis is widely recommended as the preferred approach to analyzing the outcomes of randomized tri­ als. In an ITT analysis, all randomized patients are in­ cluded in the analysis in their assigned groups regardless of all considerations, including whether they in fact received the designated intervention. ITT analys­ is should therefore compare outcomes in groups that correspond exactly to the randomization scheme. Any deviation from that principle may introduce bias. An immediate problem is that some data are missing from almost all randomized trials. 3 Clearly, just a few missing outcomes will not be a concern, but one review found that, in about half of randomized controlled trials (RCTs), outcomes are missing for more than 10% of par­ ticipants. 4 A major concern is that being lost to follow­ up could be related to a patient's response to the treat­ ment; indeed, we should assume that this will be so. That concern can be compounded if the reasons for, or frequency of, dropout differs between the treatment groups. No analysis option is ideal here; there is, in effect, a choice between omitting participants without final out­ come data or estimating (imputing) the missing out­ come data. What should researchers do? A " complete case " (or " available case ") analysis simply omits those for whom data are incomplete. This commonly used ap­ proach loses power, and bias may well be introduced, given that the incompleteness of data will not be ran­ dom. Further, excluding some patients is not compat­ ible with the ITT principle. Imputation of the missing data allows the analysis to conform to ITT analysis but requires strong assumptions that may be hard to justi­ fy. 5,6 However, some concerns about " making up the data " are misplaced. 7 Methods for the imputation of missing values have been …