A Study to Evaluate the Effect of ACT-774312 in Subjects With Bilateral Nasal Polyposis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Effect of ACT-774312 in Subjects With Bilateral Nasal Polyposis (NCT03688555), a randomized phase 2 study. The primary outcome is Change From Baseline to Week 12 in Nasal Polyp Score as Measured by Nasal Endoscopy (Assessed Centrally).

2. Clinical Question

3. Trial Design

This was a randomized, placebo-controlled, parallel-group Phase 2 study of ACT-774312 in participants with bilateral nasal polyposis. The official title describes a 12-week treatment study and calls it double-blind; the registry record lists triple masking. The identities of the roles included in the masking description are not reported in the registry record. The study status is completed, and the registry lists enrollment of 10 participants.

Participants assigned to ACT-774312 received 400 mg twice daily for 12 weeks, with or without food, as well as mometasone furoate nasal spray. The placebo group received placebo twice daily over the same period and also used mometasone furoate nasal spray. Thus, the registry describes a comparison of ACT-774312 plus nasal spray with placebo plus nasal spray, rather than a comparison with no background nasal spray.

The primary outcome was change from baseline to Week 12 in nasal polyp score measured by nasal endoscopy and assessed centrally. The primary analysis population was the per-protocol set, defined in the record as randomized participants who completed treatment up to Week 12 without protocol deviations that may affect evaluation of the primary endpoints. The posted arm counts for this analysis were 5 for ACT-774312 and 2 for placebo. Those counts are distinct from the adverse-event risk sets, which were 7 and 3, respectively.

The registry lists 11 outcome measures and 10 posted secondary outcomes. These include imaging-based measures of sinus opacification and sinus volumes, a smell identification test, a symptom visual analog scale, and a physician global assessment. The statistical plan beyond the named primary analysis method, including any planned interim analyses or sample-size justification, is not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: At screening, patients were on a stable regimen of intranasal corticosteroids (INCS) for at least 8 weeks. If a participant was using an INCS product different from mometasone furoate nasal spray prior to the screening visit, the investigator had to switch to mometasone furoate nasal spray at screening (Visit 1). Only once a participant was eligible for randomization was data collected.

Run-in Period

Treatment Period

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Per-protocol set. This analysis set includes all randomized participants who completed the treatment up to Week 12 without protocol deviations that may affect the evaluation of the primary endpoints.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Population: This analysis set included all randomized participants who received at least one dose of the study treatment. Participants were evaluated according to the actual study treatment they received.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline to Week 12 in Nasal Polyp Score as Measured by Nasal Endoscopy (Assessed Centrally), measured over Pre-dose (Baseline on Day 1) and Week 12.

The primary endpoint was change from baseline to Week 12 in total nasal polyp score, assessed from nasal endoscopy recordings by independent reviewers who were blinded to treatment. Each nostril received a score from 0 to 4 according to polyp size and obstruction. The total is the sum of the right and left nostril scores and ranges from 0 to 8. Higher scores indicate greater disease severity.

The endpoint is intended to represent change in the endoscopic appearance of nasal polyps over the treatment period. Using central review by independent readers can help make scoring more consistent across participants, while blinding reviewers to treatment can reduce the chance that knowledge of allocation influences their ratings. These features do not remove all measurement uncertainty, and the registry does not report measures of reader agreement.

The baseline was the Day 1 value before dosing. Change was defined as the post-baseline visit value minus the baseline value. The registry specifically states that a negative change indicates worsening. That direction statement should be retained when interpreting the reported changes rather than replaced with an assumed convention. The endpoint is a score-based measure; the registry does not report a threshold for a clinically important change.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a numerical score, and the registry summarizes its change using least-squares means. The sponsor’s primary comparison is described as a mixed model for repeated measurements. These methods address the structure of repeated observations over time and produce a model-based estimate of change and of the contrast between groups. The registry does not report the full model specification, so the precise assumptions and adjustments used cannot be reconstructed from the record.

What is a least-squares mean?

In general, a least-squares mean is a model-based group estimate. It can differ from a simple arithmetic mean because it is calculated within the fitted statistical model and may reflect the model’s treatment of repeated measurements and other included terms. The registry reports least-squares mean changes for each arm and a least-squares means difference for the comparison. It does not describe all model terms or the adjustments, if any, used to form these estimates.

What does a standard error describe?

In general, a standard error describes the estimated uncertainty of an estimate across repeated samples under the statistical model. It is not the same as the spread of individual participant scores. The reported standard errors are 0.161 for the ACT-774312 least-squares mean and 0.253 for the placebo least-squares mean. They indicate estimation uncertainty for those arm estimates, but with only 5 and 2 participants in the primary analysis, the results remain dependent on a very small set of observations.

How should the confidence interval be read?

The sponsor-reported 95% confidence interval for the least-squares means difference ranges from -0.06 to 1.59. In general, a confidence interval expresses the uncertainty around an estimated effect under the assumptions of the analysis. Its inclusion of zero means that the posted interval does not exclude a zero contrast. The interval also extends into positive values. The registry’s estimate and interval should be interpreted alongside the stated score direction: the registry says that negative change indicates worsening. The record does not define a threshold for a clinically important contrast, so the interval cannot be classified as clinically important or unimportant from the registry information alone.

What does the p-value add?

The reported p-value is = 0.062. In general, a p-value describes how compatible the observed data are with a specified null model, under the assumptions of the analysis. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The result should be read together with the estimated contrast and its confidence interval, rather than as a binary verdict. The registry does not report whether the comparison was adjusted for multiple testing.

Why do repeated measurements matter?

A mixed model for repeated measurements can use observations collected at multiple visits while accounting for the fact that measurements from the same participant are related. In general, this can be preferable to treating every visit as independent. The registry says that data up to Week 12 were included in the analyses, and identifies Day 1 as baseline. It does not report the visit schedule used in the model, the covariance structure, the handling of incomplete repeated measurements, or sensitivity analyses. Those details matter because model estimates can depend on how correlation and missing observations are handled.

What can be said about re-calculation?

The arm summaries do not support a posted independent two-arm re-calculation for this continuous endpoint; the record indicates that values were missing or not estimable for that comparison. The available analysis is therefore the sponsor-reported model-based contrast, not a second independently recalculated contrast. A simple re-calculation from group summaries would also not necessarily reproduce a repeated-measures model estimate, since the latter can use information across visits and model assumptions not contained in the arm summaries.

How should planning illustrations be understood?

In general, sample-size illustrations based on an observed effect describe hypothetical planning under stated assumptions. They are not observed power and are not a retrospective probability that the trial detected an effect. The registry describes planning assumptions using a two-sided significance level of 0.05, equal allocation, a normal approximation, and effects expressed as fractions of the observed effect. The trial’s own sample-size justification is not reported in the registry record. The planning assumptions should therefore not be mistaken for evidence that the study was designed around a particular target or that its observed result has a particular probability of being replicated.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("ACT-774312", "Placebo")
n   <- c(5, 2)
m   <- c(-0.23, -0.99)
sp  <- c(0.161, 0.253)
sd  <- sp * sqrt(n)      # standard errors converted to SDs
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  ACT-774312  5  -0.230  0.360  -0.677  0.217
CARM  Placebo  2  -0.990  0.358  -4.205  2.225

11. Analyses Reported by the Sponsor

The sponsor-reported primary comparison is a mixed model for repeated measurements. It gives a least-squares means difference of 0.76, with a 95% confidence interval from -0.06 to 1.59 and a p-value of = 0.062. The group summaries report least-squares mean changes of -0.23 for ACT-774312 and -0.99 for placebo, with standard errors of 0.161 and 0.253, respectively.

An independent two-arm re-calculation is not available for this continuous endpoint because the record identifies values as missing or not estimable for that comparison. It would therefore be misleading to present a separately calculated contrast as though it were a reproducible check on the sponsor’s model. The model-based result is the posted comparative analysis. The registry does not provide the complete model specification or enough information to reconstruct the repeated-measures analysis from the group summaries alone.

The record does not flag a discrepancy between a sponsor analysis and a re-calculation. That does not make the result more definitive: the confidence interval includes zero, and the primary analysis involved 5 and 2 participants in the two arms. The sponsor’s estimate should be read as the reported model-based comparison, with its uncertainty and analysis-population limitations, rather than as an independently confirmed calculation.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists 11 outcome measures and 10 posted secondary outcomes, in addition to the primary outcome. The secondary outcomes cover several kinds of assessment, including sinus imaging, smell identification, symptoms, and physician assessment. When many outcomes are evaluated, the chance of observing an apparently notable result somewhere among them can increase. Statistical approaches such as prespecifying a testing hierarchy or adjusting for multiple comparisons can address that issue, but whether such procedures were planned or used is not reported in the registry record.

The primary analysis population was the per-protocol set. The registry defines it as randomized participants who completed treatment up to Week 12 without protocol deviations that may affect evaluation of the primary endpoints. The primary arm counts were 5 and 2. The record does not report an intention-to-treat primary analysis or a comparison of results across alternative analysis populations.

The registry states that data up to Week 12 were included in the analyses, but the detailed handling of missing observations is not reported in the registry record. The named mixed model for repeated measurements does not by itself establish which assumptions about missing data were used, how much data were missing, or whether sensitivity analyses were performed. Those details are important for understanding how incomplete follow-up could affect a model-based result.

The protocol deviations that led to exclusion from the per-protocol set, the number of participants with missing endpoint data, and the reasons for any missing data are not reported in the registry record. Interim analyses and the full statistical analysis plan are also not reported in the registry record. Without these details, readers cannot fully assess selection into the analysis set, the management of missing outcomes, or the planned approach to multiple outcomes.

13. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent non-serious adverse event terms

The serious adverse event risk sets were 7 participants for ACT-774312 and 3 for placebo. No serious adverse events were reported in either group, and the recorded number of deaths was 0 in both groups. These are event counts in the stated risk sets, not evidence that the risk of a serious event is absent.

Other adverse events were reported for 5 of the 7 ACT-774312 participants and 3 of the 3 placebo participants. The registry does not provide further detail in the serious-event summary about the nature, severity, timing, or relatedness of these other events. No serious adverse-event terms are listed in the record.

Safety counts should be read separately from the primary efficacy analysis. The adverse-event risk sets differ from the primary per-protocol counts of 5 and 2. The registry summary does not provide enough information to compare event rates reliably or to assess how the groups might differ in a larger population. These figures describe the events recorded in this study, not a general safety conclusion.

14. What the Result Does, and Does Not, Mean

The posted results describe a small randomized comparison of ACT-774312 plus mometasone furoate nasal spray against placebo plus mometasone furoate nasal spray. The primary outcome was centrally assessed change in nasal polyp score through Week 12. The sponsor-reported model estimated a least-squares means difference of 0.76, with a 95% confidence interval from -0.06 to 1.59 and a p-value of = 0.062.

The interval includes zero, so the estimate is not precise enough to rule out a zero contrast under the reported analysis. The interval also includes positive values. The registry states that a negative change in the endpoint indicates worsening; readers should use that stated convention rather than assume a direction based on other scoring systems. The record does not provide a threshold for a clinically meaningful score change, so statistical uncertainty cannot be translated into a conclusion about clinical importance.

The primary analysis involved 5 participants in the ACT-774312 group and 2 in the placebo group. Estimates from such small groups can be strongly influenced by the particular participants included. The analysis was per protocol, and the registry does not report an intention-to-treat result or detailed missing-data sensitivity analyses. These features limit how far the posted estimate can be generalized.

The result does not establish that ACT-774312 works or does not work. It does not demonstrate equivalence, and it does not show that the groups are the same. It is an estimate with substantial uncertainty from a specific analysis population and model. The adverse-event counts likewise describe only the participants in the reported risk sets and cannot settle broader safety questions.

15. Why This Trial Matters Statistically

This trial illustrates why a numerical contrast should be read with its uncertainty, analysis population, and endpoint definition rather than in isolation. The primary comparison is a model-based difference in a score that ranges from 0 to 8, and the registry explicitly states that negative change indicates worsening. Preserving that sign convention is essential to avoid reversing the intended interpretation.

It also shows the distinction between a planned or model-based analysis and a simple check based on arm summaries. The sponsor used a mixed model for repeated measurements, while the available summaries do not permit an independent two-arm re-calculation for the continuous endpoint. Without the full model specification and participant-level data, the model-based contrast cannot be independently reconstructed from the posted arm estimates alone.

The very small primary analysis set highlights the importance of precision. A confidence interval that includes zero leaves uncertainty about the direction and size of the comparative effect. A p-value by itself cannot resolve that uncertainty, and the record does not report a clinical-importance threshold.

Finally, the registry lists multiple outcomes but does not report a multiplicity procedure. It also does not describe the missing-data methods or the trial’s own sample-size justification. These omissions do not invalidate the posted analysis, but they constrain what readers can infer from it. The study is a useful example of how registry results should be interpreted in the context of design, endpoint direction, analysis choices, and reporting completeness.

16. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The primary analysis included 5 participants assigned to ACT-774312 and 2 assigned to placebo, even though the registry reports 10 participants enrolled overall. The small primary analysis set limits precision and makes the estimates sensitive to the observations included. The registry defines the primary set as per protocol, so it represents participants meeting completion and protocol-deviation criteria rather than all randomized participants.

The reported model is identified as a mixed model for repeated measurements, but the full specification is not reported in the registry record. Details such as model terms, covariance structure, and the handling of incomplete repeated measurements are not reported in the registry record. The extent and reasons for missing endpoint data, and sensitivity analyses for missingness, are not reported in the registry record.

The record lists multiple outcome measures, but the statistical approach to multiplicity is not reported in the registry record. A threshold for a clinically important change in nasal polyp score is also not reported in the registry record. The available information therefore does not establish how the observed contrast relates to a clinically meaningful difference or how the primary result fits into a broader testing strategy.

The registry describes the study as completed, but the posted primary analysis is restricted to the per-protocol set. The record does not provide a separate intention-to-treat analysis or enough detail to evaluate the effects of exclusions. The sample-size justification and the planned interim-analysis approach are not reported in the registry record. These limitations restrict independent assessment and generalization beyond this small study.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: A Study to Evaluate the Effect of ACT-774312 in Subjects With Bilateral Nasal Polyposis — NCT03688555.
• Registry record last updated 2022-04-11; status last verified 2022-03.
• Results first posted 2022-02-01.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

20. Record Summary

NCT03688555 is a completed randomized, parallel-group Phase 2 study of ACT-774312 in participants with bilateral nasal polyposis. The registry reports enrollment of 10 participants. ACT-774312, given at 400 mg twice daily for 12 weeks with mometasone furoate nasal spray, was compared with placebo plus the same nasal spray.

The primary endpoint was change from baseline to Week 12 in centrally assessed nasal polyp score. The per-protocol analysis included 5 participants in the ACT-774312 group and 2 in the placebo group. The sponsor-reported mixed model estimated a least-squares means difference of 0.76, with a 95% confidence interval from -0.06 to 1.59 and a p-value of = 0.062. The registry states that negative change indicates worsening.

The small analysis set, the confidence interval that includes zero, and limited reporting of model and missing-data details constrain interpretation. Serious adverse events and deaths were reported as 0 in both safety risk sets.