The Fragility of Statistically Significant Randomized Controlled Trials in Plastic Surgery
Bibliographic record
Abstract
BACKGROUND: The fragility index has been proposed as a metric to evaluate the robustness of statistically significant findings in randomized controlled trials. It measures the number of events that a trial result relies on to maintain statistical significance. This study examines the robustness of statistically significant results from randomized controlled trials in the plastic surgery literature. METHODS: A systematic literature search of the 15 highest impact plastic surgery journals was conducted to identify randomized controlled trials published between 2000 and 2017 that reported a statistically significant dichotomous outcome (p < 0.05). The fragility index of each study was calculated using Fisher's exact test. Multiple linear regression was used to determine trial characteristics associated with the fragility index. RESULTS: The 90 eligible randomized controlled trials had a median sample size of 73.5 patients (25th to 75th percentile, 50 to 115) and a median of 20 events (25th to 75th percentile, 11 to 33.5) for the chosen outcome. The median fragility index was 1 (25th to 75th percentile, 0 to 4), indicating that statistical significance would be lost in half of the randomized controlled trials if a single patient had a change in event status. The fragility index was 0 in 24 of 90 (27 percent) randomized controlled trials, meaning the outcome immediately lost statistical significance on recalculation of the p value using Fisher's exact test. CONCLUSIONS: The results of randomized controlled trials in plastic surgery demonstrate substantial fragility, as statistically significant results were found to hinge on a small number of events. The fragility index offers an intuitive and simple metric to complement the p value and determine the confidence in the results of randomized controlled trials.
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 | 0.688 | 0.971 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.167 | 0.046 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".