Safety, Efficacy and Pharmacokinetics of Rifaximin in Patients With Moderate-to-severe Papulopustular Rosacea: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety, Efficacy and Pharmacokinetics of Rifaximin in Patients With Moderate-to-severe Papulopustular Rosacea (NCT05150587), a randomized phase 2 study. The primary outcome is Co-primary Endpoint: Change From Baseline in Number of Rosacea Inflammatory Lesions.

2. Clinical Question

In practical statistical terms, the lesion-count question is whether the mean change during treatment differs between each rifaximin regimen and placebo. The posted group means are changes from baseline, so a negative value represents a decrease in the count relative to baseline. The comparison estimates then express the difference between each active group’s mean change and the placebo group’s mean change. The confidence intervals help show how uncertain those estimated contrasts are; they should be read alongside the point estimates rather than as proof of a particular effect.

The registry describes a success rule requiring both co-primary efficacy endpoints to be satisfied in an active group. It also notes that the two endpoints need not be satisfied in the same participant. Because the IGA result is not reported, the posted lesion-count result alone does not establish whether that stated success rule was met. The statistical interpretation is therefore limited to the endpoint result and safety counts available in the registry record.

3. Trial Design

This was a Phase IIa, multicenter, randomized, double-blind, parallel-group, placebo-controlled clinical trial of rifaximin delayed-release in patients with moderate-to-severe papulopustular rosacea. The listed study status is completed. The recorded start date is 2021-10-05, and the primary completion date is 2022-10-20. Alfasigma S.p.A. is listed as the sponsor.

The three reported groups were Rifaximin 250 mg TID, Rifaximin 500 mg TID, and placebo. The registry records enrollment of 216. For the primary lesion-count outcome, the group summaries list 65 participants in the 250 mg group, 76 in the 500 mg group, and 63 in the placebo group. These outcome-summary counts should be distinguished from the safety counts: the safety summaries list 70, 80, and 66 participants at risk, respectively. The registry record does not explain the difference between the outcome and safety counts.

The trial had two stated objectives: to explore safety and efficacy for the two rifaximin regimens compared with placebo, and to assess pharmacokinetics in a subgroup. The posted efficacy result concerns change in inflammatory lesion count at 30 days. The registry describes the primary efficacy population as the Full Analysis Set. The record also describes a second co-primary efficacy endpoint based on IGA score, but its result is not reported in the registry record.

Randomization and double masking are recorded, but further details about sequence generation, allocation concealment, who was masked, or the allocation ratio are not reported in the registry record. The trial’s original sample-size justification and its planned statistical methods are not reported in the registry record. The planning figures associated with the observed contrasts are separate illustrations and should not be interpreted as the trial’s original design rationale.

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.

Overall Study

Analysis population for the primary outcome, as defined in the registry: The primary efficacy outcomes measures are reported on the Full Analysis Set

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: Baseline analysis is based on the Full Analysis Set

6. Primary Endpoint

The registry lists the primary outcome as Co-primary Endpoint: Change From Baseline in Number of Rosacea Inflammatory Lesions, measured over 30 days.

The posted primary measure is the mean change from baseline in the number of rosacea inflammatory lesions, defined in the registry description as papules, pustules, or plaques. The unit is lesions, and the recorded timeframe is 30 days. The group results report a mean and standard deviation for each treatment group. The primary efficacy population is identified as the Full Analysis Set.

Change from baseline expresses how the lesion count at the end of treatment differs from the participant’s baseline count. A negative group mean therefore represents an average decrease from baseline; it does not mean every participant’s count decreased. Group averages also do not describe the range of individual responses. The standard deviation describes the spread of individual changes around the group mean, rather than the precision of the mean itself.

The registry calls this a co-primary endpoint and states that study success in an active group requires both co-primary efficacy endpoints to be satisfied. The other co-primary endpoint is treatment success, defined as an IGA score of 0 or 1 at the end of treatment. The IGA scale is described from 0, clear, through 4, severe. The lesion-count result is available, but the IGA success result is not reported in the registry record.

Using both a continuous change measure and a categorical success measure can address different aspects of outcome: the change measure retains the scale of lesion-count change, while the IGA definition classifies participants by a specified end-of-treatment status. The posted record does not provide enough information to assess the second measure’s result or how the two endpoints jointly contributed to the study’s success assessment.

7. Results Posted in the Registry

• Rifaximin 250 mg TID: mean -10.00 versus -9.20 on control; difference -0.80 (95% CI -4.23 to 2.63), standardized effect d = -0.08; z-test p = 0.647.
• Rifaximin 500 mg TID: mean -6.70 versus -9.20 on control; difference 2.50 (95% CI -1.71 to 6.71), standardized effect d = 0.19; z-test p = 0.245.

8. Statistical Interpretation

9. Statistical Methods Explained

What does a mean change represent?

The primary outcome is continuous: it records a numerical change in inflammatory lesion count from baseline. The reported mean is the average participant-level change within a group. A negative mean indicates an average decrease from baseline, while the standard deviation describes how dispersed individual changes are around that average. The mean and standard deviation answer different questions: the mean describes the group’s average change, and the standard deviation describes variability among participants.

The group means were -10.0 for Rifaximin 250 mg TID, -6.7 for Rifaximin 500 mg TID, and -9.2 for placebo. The corresponding standard deviations were 9.24, 14.78, and 10.49. These summaries do not show the distribution of individual observations, and they do not establish that every participant moved in the direction of the group mean.

How should the mean differences be read?

The active-versus-placebo mean difference is calculated as the active group’s mean change minus the placebo group’s mean change. For Rifaximin 250 mg TID, the recalculated difference is -0.8. For Rifaximin 500 mg TID, it is 2.5. A negative contrast means the active group’s average change is more negative than the placebo group’s; a positive contrast means it is less negative. This interpretation concerns the sign and scale of the change measure, not a judgment about clinical importance.

The posted recalculations use the observed group summaries and are unadjusted. The standardized effect estimates are -0.081 for Rifaximin 250 mg TID and 0.192 for Rifaximin 500 mg TID. A standardized effect expresses a group contrast relative to a measure of variability, making the scale unitless. It can help compare contrasts measured on different scales, but it does not replace interpretation of the original lesion-count scale. The registry record does not report a sponsor analysis of these contrasts, and it lists no analyses.

What does a confidence interval add?

A confidence interval gives a range of values compatible with the estimate under the method used to construct it. In general, it reflects sampling uncertainty: a narrower interval indicates a more precise estimate, while a wider interval indicates less precision. It is not a range containing a fixed proportion of individual participants’ changes, and it is not a guarantee that the true contrast lies inside the interval.

The 95% confidence interval for the 250 mg contrast is -4.229 to 2.629. For the 500 mg contrast it is -1.713 to 6.713. Both intervals include zero. As a result, the estimates do not rule out a zero mean difference under these unadjusted calculations, and they also include values in both directions. The width of an interval should be considered along with the point estimate and the outcome’s clinical context; the registry record does not report a threshold for a clinically important lesion-count difference.

How should the p-values be understood?

The unadjusted recalculated p-values are 0.647 for the 250 mg contrast and 0.245 for the 500 mg contrast. In general, a p-value measures how unusual data at least as inconsistent with a specified null model would be if that model were true. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of an effect.

Each p-value is an unadjusted result for one active-versus-placebo contrast. The posted record does not identify a multiplicity adjustment or provide adjusted p-values. Because the trial describes two active regimens and co-primary endpoints, the individual unadjusted p-values should not be treated as a complete test of the registry’s overall success rule. The result for the IGA endpoint is not reported in the registry record.

Why does variability matter?

In general, more variable outcomes make it harder to estimate group means and differences precisely. The standard deviation is one description of that variability. The 500 mg group’s reported standard deviation is 14.78, compared with 9.24 for the 250 mg group and 10.49 for placebo. This pattern helps explain why the uncertainty of a contrast depends not only on its point estimate, but also on the variability and number of observations contributing to it.

Over-dispersion is a general concern when count outcomes vary more than a proposed statistical model expects. When that occurs, a model that assumes less variability may report uncertainty that is too small. The registry record does not report a count model, a dispersion assessment, or an adjusted model for this endpoint. The posted means and standard deviations support the unadjusted summary-based comparisons, but they do not show which model the trial investigators used or whether over-dispersion was assessed.

What can and cannot be inferred from these calculations?

The comparisons are recalculated from posted summary statistics, using the group means, standard deviations, and sample sizes. They are not a substitute for a prespecified trial analysis, and the registry record does not report the original analysis plan or model specification. The discrepancy indicator is false, so no disagreement with a sponsor analysis is flagged. The recalculated estimates are best read as descriptive, unadjusted comparisons of the posted group summaries.

General statistical interpretation also depends on design and data handling. Randomization can support a fair comparison when implemented as planned, but details such as allocation concealment and the handling of missing observations are not reported in the registry record. The record identifies the Full Analysis Set for primary efficacy results, but does not define its membership or describe how incomplete endpoint data were handled. Consequently, the calculations should not be taken as evidence about those unreported procedures.

10. Confidence Intervals and Precision

Precision concerns how tightly the data estimate the active-versus-placebo mean difference. The point estimates are -0.8 for Rifaximin 250 mg TID and 2.5 for Rifaximin 500 mg TID, but each estimate is accompanied by substantial uncertainty. The 95% confidence interval is -4.229 to 2.629 for the 250 mg comparison and -1.713 to 6.713 for the 500 mg comparison.

Both intervals include zero and extend to values on either side of it. Thus, the unadjusted results are compatible with no mean difference and with differences in either direction. The intervals do not establish which direction is most plausible with certainty, nor do they show that every value within the interval is equally likely. A confidence interval is an uncertainty range for the estimated group contrast under its calculation method, not a range of individual participant outcomes.

The standard deviations show meaningful spread in participant changes within each group: 9.24 for Rifaximin 250 mg TID, 14.78 for Rifaximin 500 mg TID, and 10.49 for placebo. The reported outcome sample sizes are 65, 76, and 63, respectively. Precision depends on the amount of variability as well as the amount of information available. The registry record does not report an endpoint-specific clinical importance threshold, so the intervals cannot be classified as excluding or including a clinically important difference.

These are unadjusted confidence intervals recalculated from posted summary statistics. The registry record lists no analyses and does not report a planned confidence-interval method. The intervals should therefore be interpreted as descriptive recalculations rather than as a reproduction of a documented sponsor analysis. They also address only the lesion-count contrast, not the unreported IGA endpoint.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures describe participants per arm, not total participants across the trial. The 80% power column represents an illustrative design intended to have an 80% chance of detecting the specified effect if that effect were the true one and the stated assumptions held. The 90% power column represents a higher chance of detecting that effect under the same assumptions. Power is a property of a proposed design for a particular effect size and analysis; it is not a measure of what happened in this completed trial.

The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The rows labeled 100%, 75%, and 50% of the observed effect therefore represent planning for the full observed contrast or a smaller fraction of it. As the target effect becomes smaller, more participants are needed to detect it with the same planned power, all else held constant.

The figures are calculated separately for each active-versus-placebo contrast, using the observed contrast as the starting point. They are planning illustrations based on those observed effects, not the original trial’s design assumptions. The original sample-size justification is not reported in the registry record. The displayed calculations are not observed power; they should not be used to describe the probability that the completed trial detected an effect or to explain its result.

In general, planning estimates depend on assumptions about the outcome variability, allocation, significance level, and effect to be detected. Changing any of these can change the required sample size. These calculations use equal allocation between two arms for each contrast, even though the listed outcome group counts are not equal across the three trial groups. They do not supply a planning calculation for the combined three-group trial or for the IGA co-primary endpoint.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.800; pooled standard deviation σ = 9.875.
2. n = 2 × (1.96 + 0.842)² × 9.875² / -0.800² = 2,391.8, rounded up to 2,392 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -0.800000000000001                      # observed difference in means
sigma <- 9.8748729547785                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(5150587)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 2,392 (80% power), 3,202 (90% power)
 75% of observed effect: n per arm = 4,253 (80% power), 5,693 (90% power)
 50% of observed effect: n per arm = 9,568 (80% power), 12,808 (90% power)
power.t.test: 2392.7 
Simulated power at n = 2,392 per arm: 0.804 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Multiplicity, Missing Data and Analysis Populations

The registry describes two active regimens, each compared with placebo, and identifies two co-primary efficacy endpoints. Its stated success rule is that an active group succeeds only if both co-primary endpoints are satisfied. The record notes that the endpoint criteria need not be met by the same participant. This rule makes the joint endpoint interpretation important: a lesion-count result alone cannot establish the full stated success criterion.

The posted result includes the lesion-count outcome, but the IGA treatment-success result is not reported in the registry record. The record lists two outcome measures but no analyses. It does not report a multiplicity-control procedure, adjusted p-values, a testing hierarchy, or how the two dose comparisons were handled together. Therefore the unadjusted recalculated p-values should not be interpreted as multiplicity-adjusted evidence for an overall trial conclusion.

The record identifies the Full Analysis Set for primary efficacy outcomes, but does not define the set, give a detailed analysis population definition, or describe whether participants were analyzed according to randomized assignment. The methods for handling missing baseline or end-of-treatment measurements are not reported in the registry record. Missing-data assumptions and sensitivity analyses are also not reported in the registry record. These omissions limit assessment of whether incomplete outcome data could affect the estimates.

The original statistical analysis plan, the trial’s original sample-size justification, and whether interim analyses were planned or conducted are not reported in the registry record. No conclusions about these procedures should be inferred from the completed status or from the posted summary statistics. The recalculated estimates are unadjusted comparisons based on group-level summaries; they do not fill in the unreported analysis plan or missing-data procedures.

14. 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 2% reporting threshold.

Most frequent non-serious adverse event terms

The serious adverse event summaries report 0 affected participants in each group: among 70 at risk in the Rifaximin 250 mg TID group, among 80 at risk in the Rifaximin 500 mg TID group, and among 66 at risk in the placebo group. The deaths column reports 0 for each group. These are participant counts, not rates or estimates of comparative risk.

The registry also lists 8 participants with other adverse events in the 250 mg group, 17 in the 500 mg group, and 12 in the placebo group. These counts should be kept distinct from the serious adverse event counts. The safety population counts differ from the outcome-summary counts; the registry record does not explain that difference.

Zero reported serious adverse events in these summaries means none were recorded among the listed participants at risk in the registry result. It does not establish that no event could occur, nor does it by itself establish a comparative safety profile. The registry record does not provide event terms for serious events, because none are listed, and does not report further detail about the safety observation period or event ascertainment.

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

The posted lesion-count summaries show a mean decrease from baseline in all three groups at 30 days. The unadjusted active-versus-placebo estimates are -0.8 for Rifaximin 250 mg TID and 2.5 for Rifaximin 500 mg TID. Their confidence intervals include zero and span values in both directions. These results indicate uncertainty about the size and direction of the mean contrasts; they do not establish a precise difference between either active regimen and placebo.

The findings do not answer every question set out in the registry. The IGA success endpoint is part of the co-primary efficacy definition, but its result is not reported in the registry record. Since the stated success rule requires both endpoints to be satisfied in an active group, the lesion-count results alone cannot determine whether that rule was met. Pharmacokinetic results for the subgroup are also not reported in the registry record.

The safety summaries report no serious adverse events and no deaths in the listed groups, alongside counts for other adverse events. These are descriptive counts. They should not be taken as proof that an intervention is free of risk or as a basis for individual treatment decisions. The registry record does not report enough detail to assess event timing, severity beyond the serious/other distinction, or comparative safety using adjusted analyses.

Overall, the registry record supports a limited statistical reading: the posted group averages and unadjusted recalculations describe observed lesion-count changes and uncertainty in the contrasts. The record does not report the original analysis plan, missing-data methods, or a multiplicity strategy. Those omissions, together with the unreported co-primary IGA result, constrain what can be concluded from the posted results. No treatment recommendation follows from these statistical summaries.

16. Why This Trial Matters Statistically

This trial is statistically informative because it makes the distinction between a group’s change from baseline and the randomized comparison with placebo visible. All three group means are negative, but the comparison of interest is not whether each group changed from baseline in isolation. It is the difference between the active group’s mean change and the placebo group’s mean change. The recalculated contrasts are much closer to zero than the individual group changes, emphasizing why a within-group change alone cannot answer a comparative question.

The example also illustrates why uncertainty matters. Each active-versus-placebo confidence interval includes zero and extends in both directions. Reporting only the point estimates would conceal that uncertainty. The range of plausible contrasts is relevant to interpretation, especially when the registry record does not state a threshold for clinical importance.

The co-primary structure is another important statistical feature. The registry defines success using both lesion-count change and IGA treatment success, but the posted efficacy result is available for lesion count only. An incomplete set of co-primary results cannot support a complete assessment of the stated success rule. Likewise, the existence of two active comparisons makes multiplicity relevant, yet no adjustment strategy is reported.

Finally, the sample-size illustrations demonstrate how planning depends on the effect size to be detected: smaller target effects require larger planned groups under otherwise similar assumptions. Because those calculations use observed contrasts, they are not evidence of the trial’s original design rationale or its achieved power. Keeping design planning, observed estimates, and uncertainty separate is essential when reading a registry result.

17. 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 posted efficacy information is limited to the 30-day mean change in inflammatory lesion count. Although the registry describes IGA success as a second co-primary endpoint, that result is not reported in the registry record. The pharmacokinetic objective is also described, but its results are not reported in the registry record. These gaps prevent a complete account of all stated study objectives.

The reported lesion-count comparisons are unadjusted recalculations from group-level summary statistics. The registry record lists no analyses and does not report the original statistical analysis plan, the model used by investigators, or any multiplicity adjustment. The recalculations therefore cannot verify the trial’s planned inferential procedure.

The Full Analysis Set is named, but its definition is not reported in the registry record. The outcome group counts are 65, 76, and 63, while the safety counts at risk are 70, 80, and 66; the reason for these different counts is not reported in the registry record. Missing-data handling, sensitivity analyses, and the reasons for any differences in analysis populations are not reported in the registry record.

Further design details, including the randomization procedure, allocation ratio, allocation concealment, and masking roles, are not reported in the registry record. The original sample-size justification and interim-analysis plans are also not reported in the registry record. Finally, the posted summary does not state a clinically important difference for lesion count or provide enough detail to assess the clinical relevance of the confidence-interval ranges. These limitations call for a bounded interpretation of the summaries rather than claims that go beyond the recorded outcomes and methods.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Safety, Efficacy and Pharmacokinetics of Rifaximin in Patients With Moderate-to-severe Papulopustular Rosacea — NCT05150587.
• Registry record last updated 2024-04-24; status last verified 2023-05.
• Results first posted 2024-04-24.
• 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.

21. Record Summary

NCT05150587 is a completed Phase IIa, multicenter, randomized, double-blind, parallel-group, placebo-controlled trial sponsored by Alfasigma S.p.A. It enrolled 216 participants with moderate-to-severe papulopustular rosacea and compared Rifaximin 250 mg TID and Rifaximin 500 mg TID with placebo.

The posted primary efficacy result is mean change from baseline in inflammatory lesion count at 30 days. The recalculated unadjusted mean differences versus placebo are -0.8 for the 250 mg regimen and 2.5 for the 500 mg regimen; both confidence intervals include zero. The IGA co-primary endpoint result and pharmacokinetic results are not reported in the registry record.

The safety summaries list 0 serious adverse events and 0 deaths in each group. The registry record does not report the original statistical analysis plan, multiplicity approach, missing-data methods, or original sample-size justification.