Accounting for treatment by center interaction in sample size determinations and the use of surrogate outcomes in the pessary for the prevention of preterm birth trial: a simulation study
Bibliographic record
Abstract
BACKGROUND: The Pessary for the Prevention of Preterm Birth Study (PS3) is an international, multicenter, randomized clinical trial designed to examine the effectiveness of the Arabin pessary in preventing preterm birth in pregnant women with a short cervix. During the design of the study two methodological issues regarding power and sample size were raised. Since treatment in the Standard Arm will vary between centers, it is anticipated that so too will the probability of preterm birth in that arm. This will likely result in a treatment by center interaction, and the issue of how this will affect the sample size requirements was raised. The sample size requirements to examine the effect of the pessary on the baby's clinical outcome was prohibitively high, so the second issue is how best to examine the effect on clinical outcome. The approaches taken to address these issues are presented. RESULTS: Simulation and sensitivity analysis were used to address the sample size issue. The probability of preterm birth in the Standard Arm was assumed to vary between centers following a Beta distribution with a mean of 0.3 and a coefficient of variation of 0.3. To address the second issue a Bayesian decision model is proposed that combines the information regarding the between-treatment difference in the probability of preterm birth from PS3 with the data from the Multiple Courses of Antenatal Corticosteroids for Preterm Birth Study that relate preterm birth and perinatal mortality/morbidity. The approach provides a between-treatment comparison with respect to the probability of a bad clinical outcome. The performance of the approach was assessed using simulation and sensitivity analysis. Accounting for a possible treatment by center interaction increased the sample size from 540 to 700 patients per arm for the base case. The sample size requirements increase with the coefficient of variation and decrease with the number of centers. Under the same assumptions used for determining the sample size requirements, the simulated mean probability that pessary reduces the risk of perinatal mortality/morbidity is 0.98. The simulated mean decreased with coefficient of variation and increased with the number of clinical sites. CONCLUSION: Employing simulation and sensitivity analysis is a useful approach for determining sample size requirements while accounting for the additional uncertainty due to a treatment by center interaction. Using a surrogate outcome in conjunction with a Bayesian decision model is an efficient way to compare important clinical outcomes in a randomized clinical trial in situations where the direct approach requires a prohibitively high sample size.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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; a candidate call from one teacher head, not a consensus.
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".