Intention-to-treat analysis and accounting for missing data in orthopaedic randomized clinical trials.

TitleIntention-to-treat analysis and accounting for missing data in orthopaedic randomized clinical trials.
Publication TypeJournal Article
Year of Publication2009
AuthorsHerman A, Botser I B, Tenenbaum S, Chechick A
JournalThe Journal of bone and joint surgery. American volume
Volume91
Issue9
Pagination2137-43
Date Published2009 Sep
ISSN1535-1386
KeywordsBias (Epidemiology), Humans, Orthopedics, Publishing, Randomized Controlled Trials as Topic, Research Design
Abstract

BACKGROUND: The intention-to-treat principle implies that all patients who are randomized in a clinical trial should be analyzed according to their original allocation. This means that patients crossing over to another treatment group and patients lost to follow-up should be included in the analysis as a part of their original group. This principle is important for preserving the randomization scheme, which is the basis for correct inference in any randomized trial. In this study, we examined the use of the intention-to-treat principle in recently published orthopaedic clinical trials.

METHODS: We surveyed eight leading orthopaedic journals for randomized clinical trials published between January 2005 and August 2008. We determined whether the intention-to-treat principle was implemented and, if so, how it was used in each trial. Specifically, we ascertained which methods were used to account for missing data.

RESULTS: Our search yielded 274 randomized clinical trials, and the intention-to-treat principle was used in ninety-six (35%) of them. There were significant differences among the journals with regard to the use of the intention-to-treat principle. The relative number of trials in which the principle was used increased each year. The authors adhered to the strict definition of the intention-to-treat principle in forty-five of the ninety-six studies in which it was claimed that this principle had been used. In forty-four randomized trials, patients who had been lost to follow-up were excluded from the final analysis; this practice was most notable in studies of surgical interventions. The most popular method of adjusting for missing data was the "last observation carried forward" technique.

CONCLUSIONS: In most of the randomized clinical trials published in the orthopaedic literature, the investigators did not adhere to the stringent use of the intention-to-treat principle, with the most conspicuous problem being a lack of accounting for patients lost to follow-up. This omission might introduce bias to orthopaedic randomized clinical trials and their analysis.

DOI10.2106/JBJS.H.01481
Alternate JournalJ Bone Joint Surg Am
PubMed ID19723990