Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

Modified intention-to-treat analysis did not bias trial results

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Thresholds for clinical importance were established to improve interpretation of the EORTC QLQ-C30 in clinical practice and research

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Overall bias and sample sizes were unchanged in ICU trials over time: a meta-epidemiological study

    Research output: Contribution to journalReviewResearchpeer-review

  3. Transparent and systematic reporting of meta-epidemiological studies

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Apparently conclusive meta-analyses on interventions in critical care may be inconclusive - a meta-epidemiological study

    Research output: Contribution to journalReviewResearchpeer-review

View graph of relations

OBJECTIVE: To investigate whether analysis of the modified intention-to-treat (mITT) population with post-randomisation exclusion of patients from analysis is associated with biased estimates of treatment effect compared to the conservative intention-to-treat (ITT) population.

STUDY DESIGN AND SETTING: Placebo-controlled, blinded randomised trials on biological or targeted interventions for rheumatoid arthritis were identified through a systematic search. Two authors independently extracted data. A random-effects meta-analysis was used to combine odds ratios as an expression of treatment effect and stratify according to the different analysis populations.

RESULTS: Seventy-two randomised trials were included and analysed (23,842 patients). Thirty trials analysed the ITT population, 37 analysed an mITT population, and 5 trials had an unclear analysis population. The treatment effect of active intervention compared to control, when based on mITT, was comparable to ITT (odds ratio 3.76 [95% confidence interval 3.09 to 4.57], and 3.47 [2.77 to 4.34]; comparison P=0.60).

CONCLUSION: We found no difference in the treatment effect between randomised trials using ITT and mITT analyses populations. This suggests that the mITT approach in rheumatoid arthritis trials investigating biological or targeted interventions does not introduce bias compared to ITT.

Original languageEnglish
JournalJournal of Clinical Epidemiology
Volume72
Pages (from-to)66-74
ISSN0895-4356
DOIs
Publication statusPublished - 2016

ID: 45783263