Abstract
Accurate, consistent indexing of biomedical publications is important for retrieving and evaluating evidence, that in turn can affect clinical decisions, evidence syntheses and research directions. Adaptive trials are arguably among the most complex clinical trial designs, being defined as trials in which the allocation or intervention given to subjects is not fixed in advance, but can vary according to the responses or characteristics of the participants. In the course of preparing to tackle the automated indexing of adaptive clinical trial articles, we manually examined the PubMed articles bearing the Adaptive Clinical Trial publication type to date and identified a surprisingly high proportion of erroneous and questionable indexing decisions. If one agrees that each article should be indexed according to its own study design (rather than the study design of the larger trial that it is linked to), then 46.7% of the articles were mis-assigned. If we consider that articles which presented partial results (e.g., one arm of a multi-arm trial) might be broadly deserving of being indexed as adaptive trials, then the adjusted error rate would still be 24.2%. These errors are worth discussing in detail because they have more general lessons to teach us - not only for biomedical end-users who want to utilize indexing terms for efficient retrieval, but for indexers who need to annotate articles accurately and consistently.