JMIR Publications

ABSTRACT

Background:

Missing cases present a challenge to our ability to evaluate the effects of web-based psychotherapy trials. Because they are often lost to follow up, less is known about the characteristics of missing cases or their likely clinical outcomes, or the likely effect of the treatment being trialled.

Objective:

To explore the characteristics of cases missing, their likely treatment outcomes, and the ability of different statistical models to approximate missing post-treatment data.

Methods:

A sample of internet-delivered cognitive behavioural therapy participants in routine care (n=6701) was used to identify predictors of dropping out of treatment, and predictors that moderated clinical outcomes, such as psychological distress, anxiety and depressive symptoms. These variables were then incorporated into statistical models that approximated replacement outcomes for missing cases, with the results compared through sensitivity and cross-validation analyses.

Results:

Lower treatment completion and higher symptom scores at pre-treatment were identified as the dominant predictors of missing cases, as well as the rate of symptom change. Statistical replacement methods that overlooked these features underestimated missing case outcomes by as much as 40%.

Conclusions:

The treatment outcomes of the cases that were missing at follow up were distinct from the remaining observed sample. Overlooking the features of missing cases is likely to result in an inaccurate estimate of the effect of treatment.