Study Evaluating Efficacy and Safety of PF-04965842 in Subjects Aged 12 Years And Older With Moderate to Severe Atopic Dermatitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study Evaluating Efficacy and Safety of PF-04965842 in Subjects Aged 12 Years And Older With Moderate to Severe Atopic Dermatitis (NCT03575871), a randomized phase 3 study. The primary outcome is Percentage of Participants Achieving Investigator's Global Assessment (IGA) Response of Clear (0) or Almost Clear (1) and Greater Than or Equal to (>=) 2 Points Improvement From Baseline at Week 12.

2. Clinical Question

3. Trial Design

The registry record describes a phase 3, randomized, double-blind, placebo-controlled, parallel-group, multicenter study of PF-04965842 monotherapy. The masking designation is quadruple. The study evaluated two oral once-daily dosage strengths, 100 mg and 200 mg, against placebo in people aged 12 years and older with moderate to severe atopic dermatitis. The brief summary specifies a minimum body weight of 40 kg and describes 12 weeks of study participation for the efficacy and safety evaluation.

Enrollment was 391. The record lists 155 participants analyzed in each PF-04965842 group and 77 in the placebo group for the primary outcome. These are outcome-specific analyzed counts; the record defines the full analysis set as randomized participants who received at least one dose, while noting that the number analyzed for this endpoint represents participants evaluable for it. The safety counts use different group denominators, so they should be read separately from the primary outcome counts.

The registry status is completed. The listed start date is 2018-06-29, and the primary completion date is 2019-08-13. Eligible participants had an option to enter a long-term extension study after completing 12 weeks of treatment; the results presented for the primary endpoint concern the week 12 assessment. The record lists 19 outcome measures and 122 analyses, with 17 secondary outcomes posted. The listed secondary measures include itch ratings, symptom scores, EASI responses, and additional IGA outcomes at specified study visits.

The record does not report the trial’s original sample-size justification, its planned statistical analysis details beyond the posted analyses, or whether interim analyses were planned or conducted. The sample-size planning illustration accompanying the results is based on the observed effect and is not a description of the trial’s original design assumptions.

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: This study was conducted from 29-June-2018 to 13-Aug-2019 at 106 sites in 13 countries.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full analysis set included all randomized participants who received at least 1 dose of study medication. Here, "Overall Number of Participants Analyzed" signifies participants evaluable for this outcome measure.

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: The full analysis set (FAS) included all randomized participants who received at least 1 dose of study medication.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Achieving Investigator's Global Assessment (IGA) Response of Clear (0) or Almost Clear (1) and Greater Than or Equal to (>=) 2 Points Improvement From Baseline at Week 12, measured over Baseline, Week 12.

The primary endpoint is the percentage of participants who, at week 12, had an IGA response of clear or almost clear and at least a 2-point improvement from baseline. It combines an absolute assessment of disease status at the visit with a change requirement. Meeting only one part of the definition is not enough for the endpoint.

The IGA is a 5-point scale, with higher scores indicating greater severity. A score of 0 means clear, with no inflammatory signs of atopic dermatitis; a score of 1 means almost clear, with specified residual findings. Scores of 2, 3, and 4 describe mild, moderate, and severe atopic dermatitis, respectively. The endpoint therefore uses a clinician’s assessment of severity alongside improvement from each participant’s baseline rating. Assessments excluded the soles, palms, and scalp.

A threshold-based response can be easier to interpret as the share of participants who met a stated clinical criterion than as an average score change. However, it also reduces a range of scores and changes to a yes-or-no outcome: participants just short of the criteria and participants with little improvement both count as not meeting the endpoint. The posted primary results do not describe the full distribution of IGA scores or changes. The registry record lists 95% confidence intervals for the group comparisons, which convey uncertainty around the estimated differences in response percentages.

7. Results Posted in the Registry

• PF-04965842 100 mg: 28.4% (44/155) versus 9.1% (7/77) on control; risk difference 19.3 percentage points (95% CI 9.7 to 28.9), risk ratio 3.12 (1.48–6.61); unadjusted two-proportion z-test p = <0.001.
• PF-04965842 200 mg: 38.1% (59/155) versus 9.1% (7/77) on control; risk difference 29.0 percentage points (95% CI 19.0 to 39.0), risk ratio 4.19 (2.01–8.73); unadjusted two-proportion z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

What does a response percentage represent?

The primary endpoint is binary at the participant level: each evaluable participant either met the combined IGA criteria at week 12 or did not. A group percentage expresses the share meeting those criteria. It does not preserve how far a participant’s score changed beyond the threshold, and it does not show the distribution of scores among people who did not meet the response definition. The registry also reports the analyzed counts, which let readers see the number of endpoint responders and the denominator used for each group.

How should the risk difference be understood?

The sponsor reports a difference in percentage between each PF-04965842 group and placebo. This is an absolute comparison of response percentages, expressed in percentage points. For the 100 mg comparison, the reported estimate is 19.3; for 200 mg, it is 28.7. A positive difference means the reported response percentage was higher in the PF-04965842 group than in placebo for this endpoint. The comparison is specific to the outcome definition, time point, and analyzed population.

The registry also includes recalculated unadjusted comparisons based on the posted summary counts. Such recalculations use the group-level event counts and denominators without the sponsor’s stated Cochran-Mantel-Haenszel procedure. They can serve as a basic check on the direction and approximate size of a contrast, but they do not reproduce an analysis that uses a different method. In particular, they do not incorporate information that is not present in the posted summary counts.

What does the sponsor’s method do?

The reported method is Cochran-Mantel-Haenszel, and the reported measure is a difference in percentage. This is a method for comparing categorical outcomes across groups, with a framework that can account for stratification when strata are part of the analysis. The registry record does not report the strata or further details of the sponsor’s implementation, so those details should not be inferred. The method label alone does not establish which covariates or adjustment factors were used.

The sponsor reports a 95% confidence interval and a p-value for each comparison. A confidence interval gives a range of values compatible with the data and the analysis procedure, subject to its assumptions. A p-value measures how incompatible the observed data are with a specified null hypothesis under the analysis model; it is not the probability that the null hypothesis is true, nor a measure of the size or clinical importance of a difference. The sponsor labels the comparisons as superiority analyses. The record does not report further details of the testing hierarchy or multiplicity control.

Why are several effect measures possible?

For a binary outcome, an absolute difference, a risk ratio, and an odds ratio describe different aspects of the same group data. The sponsor’s displayed result is a difference in percentage, which is naturally read as an absolute contrast. A ratio instead compares relative quantities, and its interpretation depends on whether it is a risk ratio or an odds ratio. These measures are not interchangeable. The primary interpretation should follow the endpoint and measure that the sponsor reported, rather than selecting whichever measure appears largest.

The registry also posts recalculated ratio measures, but the sponsor’s reported comparison is the Cochran-Mantel-Haenszel difference in percentage. The recalculated measures are simple, unadjusted calculations from summary statistics and should not be described as adjusted sponsor estimates. No additional covariate-adjusted estimate is reported in the registry record.

Why does the analysis population matter?

The primary endpoint description says that the full analysis set included all randomized participants who received at least one dose of study medication. It further clarifies that the number analyzed for this outcome means participants evaluable for the measure. These definitions matter because the denominator for an outcome may depend on its evaluability and need not match enrollment or a safety denominator. The registry record does not report the reasons participants were not evaluable or a detailed account of missing-outcome handling. It would therefore be inappropriate to assume a particular imputation rule or to treat the outcome denominator as though every enrolled participant contributed to the endpoint.

In general, missing outcome data can affect a response percentage if the likelihood of having an observed assessment differs between groups or relates to outcome status. Statistical approaches to missing data make assumptions, and those assumptions can affect estimates. The available record does not state which specific method, if any, was used for missing week 12 IGA assessments. This uncertainty is distinct from the confidence interval, which quantifies sampling uncertainty under the analysis used but does not automatically account for unreported missing-data assumptions.

Why can binary outcomes vary more than a simple model expects?

General statistical explanation: a binomial model treats each participant’s response as a binary event and uses a specified response probability to describe variation in the count. Over-dispersion means the observed variation is greater than that model expects. It can arise in some settings when participants’ outcomes are more heterogeneous or dependent than the simple model assumes. If over-dispersion is present but not addressed, standard errors and confidence intervals from a simple model may be too narrow. The registry record does not report an over-dispersion assessment or a method for handling it, and the posted endpoint results alone do not establish that over-dispersion occurred.

10. Confidence Intervals and Precision

The sponsor’s 95% confidence interval for the 100 mg comparison extends from 9.6 to 29.0 percentage points; for the 200 mg comparison it extends from 18.6 to 38.8 percentage points. Both ranges are entirely above zero, consistent with the sponsor’s reported superiority tests. The intervals also show that the exact size of either difference remains uncertain: the estimate is not a precise, fixed value known without error.

In general, a confidence interval describes values compatible with the observed data under the statistical method and its assumptions. It is not a range containing 95% of individual participant outcomes, and it is not a guarantee that the true value lies within that particular interval. The interval’s width reflects statistical uncertainty, including the amount of information available and the variability represented by the model. It does not, on its own, account for every possible source of bias, such as unreported missing-data assumptions or limitations in study conduct.

The group response percentages are estimates from the participants analyzed for this endpoint. The primary outcome counts were 44 of 155 in the 100 mg group, 59 of 155 in the 200 mg group, and 7 of 77 in placebo. The intervals for the comparisons are not intervals for each group percentage; they describe the difference between groups under the reported analysis. Their interpretation should therefore remain tied to the sponsor’s contrast and the week 12 response definition.

The confidence intervals do not describe the range of effects across future trials, and their overlap or non-overlap should not substitute for the reported comparison tests. The registry record does not report further information about the assumptions used to construct these intervals beyond the named comparison method and confidence level.

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 sample-size planning figures are participants per arm for 80% power and participants per arm for 90% power. They are not total events. The planning illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It uses the observed effect or a stated fraction of that effect as the effect to detect. The trial’s original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of rejecting the null hypothesis if the assumed effect is the true effect, under the planning assumptions. The 90% power column describes the corresponding illustration for a 90% chance. These are prospective planning quantities, not a measure of the probability that the trial’s result is correct.

The estimates are shown for planning at the observed effect and for planning at 75% or 50% of the observed effect. Smaller effects need more participants to detect under the same planning framework, which is why the estimates rise as the assumed fraction of the observed effect falls. For example, the 100 mg comparison has estimates of 64 and 84 participants per arm when planning for the observed effect, and 201 and 269 when planning for 50% of it. For the 200 mg comparison, the corresponding figures are 33 and 43 for the observed effect, and 102 and 135 for 50% of it.

These figures are planning illustrations based on an effect observed in this trial, not observed power. They should not be read as evidence that the trial had a particular probability of detecting its result after the outcome was observed. The reported enrollment and endpoint analyzed counts describe the study; the planning figures answer a different, hypothetical design question.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.091; treatment proportion p₁ = 0.284; average p̄ = 0.187.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5519 = 1.0816.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5347 = 0.4500.
4. n = (1.0816 + 0.4500)² / (0.1930)² = 63.0, rounded up to 64 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
p0 <- 0.0909090909090909                          # control proportion
p1 <- 0.283870967741935                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3575871)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 64 (80% power), 84 (90% power)
 75% of observed effect: n per arm = 102 (80% power), 135 (90% power)
 50% of observed effect: n per arm = 201 (80% power), 269 (90% power)
power.prop.test: 63 
Simulated power at n = 64 per arm: 0.817 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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. Analyses Reported by the Sponsor

The sponsor’s own primary comparisons use the Cochran-Mantel-Haenszel method and report differences in percentage. For 100 mg versus placebo, the sponsor reports 19.3 with a 95% confidence interval from 9.6 to 29.0 and p < 0.001. For 200 mg versus placebo, the reported difference is 28.7 with a 95% confidence interval from 18.6 to 38.8 and p < 0.001. These are the trial’s reported analyses and should be the main reference for the sponsor’s findings.

The recalculated comparisons use only posted group-level counts and denominators and are unadjusted. They do not reproduce the sponsor’s named method. A difference between an unadjusted recalculation and the reported result can arise because the procedures and available information differ; the recalculation should not be treated as a correction to the sponsor’s estimate. The posted record does not describe enough detail to reconstruct every aspect of the sponsor’s analysis.

For this record, the recalculations do not trigger a discrepancy flag. That does not make them interchangeable with the reported analysis. The distinction is methodological: the sponsor’s result is the appropriate figure to cite as the reported trial comparison, while the unadjusted recalculation is a separate check using summary statistics. Neither should be used to imply that all analytical uncertainty or design limitations have been resolved.

14. Multiplicity, Missing Data and Analysis Populations

The registry record lists 19 outcome measures, 122 analyses, and 17 posted secondary outcomes. The primary endpoint is one of several efficacy outcomes, and the posted secondary measures include repeated assessments over different visits as well as distinct itch, symptom, EASI, and IGA outcomes. Testing multiple outcomes or time points raises the general issue of multiplicity: when many hypotheses are tested, the chance of at least one apparently notable result can increase unless the testing strategy accounts for that family of tests.

The record reports the primary comparisons as superiority analyses and gives p-values, but it does not report a multiplicity adjustment or a testing hierarchy. It is therefore not possible to determine from the registry record whether the reported p-values were adjusted for other outcomes, doses, or time points, or how any such adjustment was performed. The reported p-values should be interpreted as attached to the stated comparisons, not as proof that every possible testing issue has been addressed.

The primary outcome population is described as the full analysis set, defined as randomized participants who received at least one dose of study medication. The record also says the number analyzed for this measure means participants evaluable for the outcome. This makes the analyzed denominator explicit, but it does not explain any difference between the randomized and evaluable populations, or identify reasons for missing assessments.

The registry record does not report the method used to handle missing week 12 IGA outcomes, whether missingness was imputed, or whether sensitivity analyses tested alternative assumptions. In general, missing-data methods can affect a binary response estimate if participants without an observed assessment differ in outcome status from those assessed. The available record does not allow those assumptions or their influence to be evaluated. Nor does it report an interim-analysis plan or whether interim efficacy testing occurred. These are limitations of what can be concluded about the analysis plan, not evidence that a particular unreported procedure was used.

15. 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: eczema herpeticum (1.3%), staphylococcal skin infection (1.3%), anaphylactic shock (0.6%), femoral neck fracture (0.6%), sudden death (0.6%).

The safety figures report serious adverse events, other adverse events, and deaths by group. For serious adverse events, the record lists 5 participants affected among 158 at risk in the 100 mg group, 2 among 155 in the 200 mg group, and 1 among 78 in placebo. For other adverse events, it lists 56 among 158, 52 among 155, and 22 among 78, respectively. The recorded deaths were 1 in the 100 mg group and 0 in each of the other groups.

These are descriptive counts with their stated safety denominators. They are not the primary efficacy denominators, and the groups should not be compared by simply treating the counts as if the denominators were identical. The registry also lists serious adverse event terms with reported percentages, including eczema herpeticum and staphylococcal skin infection at 1.3% each, and anaphylactic shock, femoral neck fracture, sudden death, and herpangina at 0.6% each. These terms and percentages are reported entries, not a complete account of severity, timing, causality, or clinical context.

The record does not establish from these counts alone whether an event was caused by study medication. Small event counts also leave substantial uncertainty about how frequently such events might occur outside the observed groups. The safety figures should be read descriptively alongside the trial’s separate efficacy results, not as a standalone causal comparison or a complete safety profile.

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

The posted results describe week 12 IGA response percentages in the analyzed groups and the sponsor’s estimated differences from placebo. The endpoint required both a clear or almost clear IGA rating and at least a 2-point improvement from baseline. The sponsor reported a positive difference in percentage for each PF-04965842 strength compared with placebo, with 95% confidence intervals above zero and the stated p-values. This is evidence about the specified endpoint under the analyses reported in the registry record.

The result does not mean that every participant receiving PF-04965842 met the response definition. The reported percentages show that response was not universal in either intervention group, and some participants in placebo also met the endpoint. Nor does the result describe how much each participant improved, the full range of IGA scores, or changes in itch and other symptoms. Those questions concern different summaries or outcomes.

The endpoint is a threshold-based clinician assessment at a particular visit. It does not by itself establish longer-term outcomes, effects on every area of the body, or the durability of a response after the reported assessment. The brief summary notes an option to enter a long-term extension, but the primary results concern week 12. The registry record does not establish that the week 12 findings apply to populations or settings beyond those studied.

The reported statistical comparisons also do not settle questions about the clinical importance of a difference, individual benefit, or harms. Confidence intervals quantify uncertainty under the analysis method; they do not remove possible limitations from missing data, multiplicity, or other aspects not reported in the registry. The separate safety counts are descriptive and cannot establish causation on their own. A careful reading keeps the statistical finding, the outcome’s meaning, and the limits of the record distinct.

17. Why This Trial Matters Statistically

This trial illustrates how a clinical study can report a response percentage and an absolute comparison while still requiring attention to the endpoint definition and analysis method. The primary outcome is not simply a lower IGA score: it combines a week 12 category of clear or almost clear with a minimum change from baseline. That conjunction determines who counts as a responder and makes the clinical meaning of the threshold central to interpretation.

It also demonstrates why the sponsor’s analysis and a simple recalculation should be distinguished. The registry reports Cochran-Mantel-Haenszel comparisons, while recalculation from summary counts is unadjusted. Those approaches answer related but not necessarily identical analytical questions. Reporting both without conflating them supports transparency about what follows directly from counts and what comes from the sponsor’s analysis.

The confidence intervals are important alongside the point estimates and p-values. They communicate that the estimated group differences have uncertainty, and they help readers consider a range of values compatible with the reported analysis. At the same time, intervals do not resolve missing-data or multiplicity questions that the record does not answer.

Finally, the record offers a useful example of keeping efficacy and safety descriptions separate. The primary endpoint is a binary efficacy measure; adverse event counts use their own denominators and are descriptive. Reading each according to its purpose avoids treating a positive statistical comparison as a complete account of outcomes or safety. The study’s multiple listed measures and analyses also make clear why a narrowly defined primary comparison should not be generalized to every secondary result.

18. 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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The registry record does not report the original sample-size justification or the trial’s initial design assumptions. The planning illustration is based on the observed effect and therefore cannot explain the trial’s original enrollment target. It also does not report the planned handling of multiplicity, a testing hierarchy, or whether interim analyses were planned or conducted. These omissions limit assessment of how the primary endpoint fit within the complete prespecified analysis plan.

The record defines the full analysis set and clarifies that the primary outcome denominator comprises evaluable participants, but it does not explain why some participants may not have been evaluable or how missing week 12 assessments were handled. Without that information, the possible effect of missing outcome data cannot be assessed from the posted results. The registry also does not provide details sufficient to reproduce the sponsor’s Cochran-Mantel-Haenszel analysis, such as any stratification factors.

The primary outcome is a threshold response at week 12. It does not show the distribution of scores, the degree of change among responders or nonresponders, or how outcomes evolved outside the listed assessments. The record includes other measures, but the primary results alone cannot answer those separate questions. The summary indicates a possible long-term extension option, while the primary endpoint reported is at week 12; longer-term conclusions are not established by this endpoint.

Safety counts are descriptive, and the registry record does not provide enough information in these figures to establish event causality or a complete account of timing and clinical context. The serious event and death counts should not be treated as definitive comparative estimates of risk. These limitations qualify interpretation of the posted record without implying that unreported procedures or outcomes took any particular form.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Study Evaluating Efficacy and Safety of PF-04965842 in Subjects Aged 12 Years And Older With Moderate to Severe Atopic Dermatitis — NCT03575871.
• Registry record last updated 2020-04-21; status last verified 2020-04.
• Results first posted 2020-04-21.
• 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.

22. Record Summary

NCT03575871 is a completed phase 3 randomized, double-blind, placebo-controlled, parallel-group, multicenter study of PF-04965842 monotherapy for moderate to severe atopic dermatitis. It enrolled 391 participants aged 12 years and older; the brief summary specifies a minimum weight of 40 kg and a 12-week evaluation of oral once-daily 100 mg and 200 mg doses against placebo.

The primary endpoint was the percentage achieving a clear or almost clear IGA rating and at least a 2-point improvement from baseline at week 12. The sponsor reported differences in percentage versus placebo of 19.3 for 100 mg and 28.7 for 200 mg, using Cochran-Mantel-Haenszel analyses. The registry also posts safety counts and multiple secondary outcomes. Original sample-size assumptions, detailed missing-data methods, and multiplicity procedures are not reported in the registry record.