Intention-to-treat analysis may be more conservative than per protocol analysis in antibiotic non-inferiority trials: a systematic review
Bibliographic record
Abstract
BACKGROUND: In non-inferiority trials, there is a concern that intention-to-treat (ITT) analysis, by including participants who did not receive the planned interventions, may bias towards making the treatment and control arms look similar and lead to mistaken claims of non-inferiority. In contrast, per protocol (PP) analysis is viewed as less likely to make this mistake and therefore preferable in non-inferiority trials. In a systematic review of antibiotic non-inferiority trials, we compared ITT and PP analyses to determine which analysis was more conservative. METHODS: In a secondary analysis of a systematic review, we included non-inferiority trials that compared different antibiotic regimens, used absolute risk reduction (ARR) as the main outcome and reported both ITT and PP analyses. All estimates and confidence intervals (CIs) were oriented so that a negative ARR favored the control arm, and a positive ARR favored the treatment arm. We compared ITT to PP analyses results. The more conservative analysis between ITT and PP analyses was defined as the one having a more negative lower CI limit. RESULTS: The analysis included 164 comparisons from 154 studies. In terms of the ARR, ITT analysis yielded the more conservative point estimate and lower CI limit in 83 (50.6%) and 92 (56.1%) comparisons respectively. The lower CI limits in ITT analysis favored the control arm more than in PP analysis (median of - 7.5% vs. -6.9%, p = 0.0402). CIs were slightly wider in ITT analyses than in PP analyses (median of 13.3% vs. 12.4%, p < 0.0001). The median success rate was 89% (interquartile range IQR 82 to 93%) in the PP population and 44% (IQR 23 to 60%) in the patients who were included in the ITT population but excluded from the PP population (p < 0.0001). CONCLUSIONS: Contrary to common belief, ITT analysis was more conservative than PP analysis in the majority of antibiotic non-inferiority trials. The lower treatment success rate in the ITT analysis led to a larger variance and wider CI, resulting in a more conservative lower CI limit. ITT analysis should be mandatory and considered as either the primary or co-primary analysis for non-inferiority trials. TRIAL REGISTRATION: PROSPERO registration number CRD42020165040 .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.887 | 0.959 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.121 | 0.037 |
| Bibliometrics | 0.016 | 0.072 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.010 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.044 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".