Comparison Trial of OPA-15406 Ointment in Adult Patients With Atopic DermatitisSyndrome: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Comparison Trial of OPA-15406 Ointment in Adult Patients With Atopic DermatitisSyndrome (NCT03908970), a randomized phase 3 study. The primary outcome is Responder Rate of Investigator's Global Assesment(IGA) of Disease Severity.

2. Clinical Question

3. Trial Design

This was a randomized, multicenter, triple-masked, parallel-group, vehicle-controlled Phase 3 trial. The record lists 364 participants as the enrollment and reports two groups: 1% OPA-15406 ointment and placebo. Both were administered twice daily. The intended treatment period was 4 weeks, and the primary outcome was assessed at Week 4.

Random allocation is intended to make treatment groups comparable, on average, with respect to measured and unmeasured characteristics at the point of assignment. Masking can reduce the influence of treatment knowledge on participant experience, investigator assessment, and study conduct. The registry labels masking as triple but does not specify which roles were masked, or how masking was maintained.

The primary endpoint was the responder rate on the Investigator's Global Assessment (IGA). The record also lists change from baseline in Eczema Area and Severity Index (EASI) score and change from baseline in Verbal Rating Scale (VRS) for pruritus score as secondary outcomes. For the primary outcome, results are reported for 182 participants in each arm. The secondary outcome summaries report 166 participants in the active-treatment arm and 134 in the placebo arm. The record does not explain these analysis denominators or provide participant-flow details.

The trial is marked completed. The registry record does not report the planned sample-size justification, the randomization procedure, allocation concealment, the timing of any interim analyses, or a detailed statistical analysis plan. It also does not identify the analysis population used for each outcome. Those omissions limit how fully the design and analysis can be reconstructed from the 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.

Overall Study

Reasons for not completing this period:

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.

6. Primary Endpoint

The registry lists the primary outcome as Responder Rate of Investigator's Global Assesment(IGA) of Disease Severity, measured over At Week 4.

The primary endpoint is the responder rate for the Investigator's Global Assessment (IGA) of disease severity at Week 4. Investigators or subinvestigators assessed overall symptoms in the treatment area, including erythema, infiltration, papules, effusion, and scab formation. They scored severity from 0, clear, through 4, severe or very severe. A participant counted as a responder only if the Week 4 IGA score was 0 or 1 and the score had improved by at least 2 grades from baseline.

This endpoint combines an absolute status at follow-up with change from baseline. Requiring both a low Week 4 score and improvement means that a participant must meet the stated response criteria rather than simply show any movement on the scale. Reporting a responder rate expresses the result as the proportion meeting that definition, which can be easier to interpret than a mean score change when the question concerns how many participants crossed a specified threshold.

As a general statistical point, a responder endpoint depends on the particular cutoff used. Participants close to a threshold may be classified differently despite similar underlying severity, while differences in the full range of scores are not conveyed by a single rate. The registry record defines the threshold but does not report whether the endpoint definition was prespecified in a protocol or analysis plan. The posted record gives arm-specific responder estimates and confidence intervals; it does not report a direct between-arm estimate or test for this primary outcome.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation begins by distinguishing the outcome estimate from its uncertainty and from a formal comparison between randomized groups. The IGA outcome is reported as a percentage in each arm, with a 95% confidence interval for each percentage. Those intervals describe uncertainty in the arm-specific response estimates. The record does not report the corresponding comparative estimate, so the primary results do not provide a direct interval for the contrast that answers the superiority question.

What does a confidence interval communicate?

In general, a confidence interval is calculated from data using a method with a stated coverage property under its assumptions. It shows a range of values compatible with the observed data and method. A narrower interval indicates greater precision than a wider interval, all else being comparable. The interval does not account automatically for bias from missing data, outcome measurement, selective reporting, or deviations from the analysis plan. For this trial, the registry reports 95% confidence intervals around the primary arm-specific responder rates. It does not state the method used to calculate those intervals.

Separate intervals for each arm are not the same as an interval for a difference between arms. General statistical practice assesses a comparative question using a contrast estimate and its uncertainty, ideally using the prespecified analysis. The primary record contains no reported comparative test or between-arm interval. It is therefore important not to treat the separate confidence intervals as a substitute for an unreported comparison, or to calculate a new comparison from the arm-level values.

How should the secondary comparisons be read?

The EASI and VRS outcomes are continuous measures, and the posted results give mean changes from baseline with standard errors. A mean summarizes the average change in the analyzed group. A standard error describes the estimated precision of that mean; it is not the spread of individual participants' values. The secondary results also include recalculated, unadjusted mean differences and confidence intervals. These are simple unadjusted recalculations from the posted summary statistics, not reported sponsor analyses. They should be understood as descriptive comparisons, not as substitutes for the trial's own analysis.

As a general concept, a mean difference expresses the contrast between group averages on the outcome's original scale. Its confidence interval reflects uncertainty under the recalculation method. A p-value assesses how compatible the data are with a specified null hypothesis under a statistical model; it does not measure the probability that the null hypothesis is true, the size of an effect, or its practical importance. The unadjusted p-values posted for the secondary comparisons are each < 0.001. The registry record reports no analyses for these outcomes, so the recalculations should not be described as the trial's prespecified inferential results.

Why can over-dispersion matter?

In general, over-dispersion occurs when observed variability exceeds what a statistical model assumes. It can make standard errors too small and confidence intervals too narrow if the model does not account for the extra variability. That concern is most relevant when choosing a model for outcomes whose variation is constrained or otherwise differs from the model assumptions. The registry record does not provide enough detail about the primary endpoint's confidence-interval method to determine how variability was modeled. No claim about over-dispersion in this trial can therefore be made from the posted record.

What do the planning illustrations mean?

The sample-size illustrations are planning exercises based on fractions of the observed secondary effects, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. They are not the trial's design justification and are not observed power. In general, planning sample sizes ask how many participants per arm a future study might require under specified assumptions about effect size, variability, allocation, and testing. Such results change when those assumptions change. The registry record does not report the assumptions used to plan the actual trial, nor does it report an observed-power analysis. The illustrations should not be used to infer that the trial was designed around the observed effects.

Finally, reported analyses and analysis populations matter. A statistical result is interpretable only in relation to who was included, how missing outcomes were treated, and what comparison was prespecified. The registry record does not supply those details for the primary outcome or identify a formal analysis plan. In general, a preregistered analysis helps limit selective emphasis on results after they are known; without the relevant plan and analysis details, the degree of prespecification cannot be assessed from this record.

10. Multiplicity, Missing Data and Analysis Populations

The registry record identifies one primary endpoint and two secondary outcomes, but it does not report a statistical analysis plan or a multiplicity procedure. Multiplicity refers to the issue created when many hypotheses or outcomes are assessed: without an adjustment or a prespecified testing strategy, the chance of obtaining one or more apparently notable results can rise. General approaches include adjusting significance thresholds, controlling an error rate across a family of tests, or specifying a hierarchy in which outcomes are tested in order. No such approach is reported for this trial.

The primary IGA outcome is reported with arm-specific estimates and confidence intervals, but no comparative test or between-arm confidence interval is listed. The secondary outcomes have unadjusted recalculated comparisons, rather than reported trial analyses. Their p-values should therefore be read as unadjusted results and not as multiplicity-controlled evidence. The registry record does not say whether the secondary outcomes were exploratory, whether their analyses were prespecified, or whether any additional outcomes were assessed but not posted.

Missing-data handling is also not reported in the registry record. The primary endpoint lists 182 participants per arm, while the secondary outcome summaries list different denominators. The record does not explain why these denominators differ, whether participants lacked measurements, or how missing observations were handled. It does not state whether a participant without a Week 4 assessment was treated as a nonresponder, excluded, imputed, or handled by another method. These possibilities can affect interpretation and should not be assumed.

The registry record does not identify the analysis populations, such as whether results follow randomized assignment regardless of treatment received or use another defined population. It also does not provide participant-flow details, protocol deviations, or a missingness sensitivity analysis. These omissions prevent a full assessment of whether the reported results preserve the benefits of randomization or how robust the findings are to missing outcomes. They are limits of the available registry information, not evidence that any particular analysis or data problem occurred.

11. 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 non-serious adverse event terms

The registry lists zero serious adverse events in each arm and zero deaths in each arm. For other adverse events, it reports 7 affected participants in the 1% OPA-15406 arm and 22 in the placebo arm. Each group has 182 participants listed as at risk for these safety summaries. These are reported counts, not estimates of comparative risk or evidence about causation.

Serious adverse events and other adverse events are different reporting categories. A zero count for serious adverse events means none are recorded in this registry summary; it does not establish that an event could not occur or that the treatments have equivalent safety. Similarly, the counts for other adverse events do not show event type, severity, timing, duration, recurrence, or whether an investigator considered an event related to treatment. The registry record lists no top serious-event terms because no serious events are reported in the posted summary.

Safety interpretation is limited by the short 4-week treatment period and the information available in the record. The counts should be read as descriptive observations within this trial, not as a complete safety profile or a formal comparison. The registry record does not report a statistical test for adverse-event differences or detailed safety-analysis methods.

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

The posted primary results show different observed IGA responder rates between the two randomized arms at Week 4: 38.46% for 1% OPA-15406 and 12.64% for placebo. The registry defines a responder as having an IGA score of 0 or 1 and improving by at least 2 grades from baseline. The confidence intervals describe uncertainty around the two arm-specific estimates. The record does not report a direct between-arm estimate or test for the primary outcome, so the observed rates should not be recast as a formal comparative result that the registry does not provide.

The trial was designed to assess superiority, but a stated objective is not itself evidence that a prespecified statistical criterion was met. The registry reports no analysis results and does not provide the comparative primary analysis. The values can be described accurately as posted outcome estimates, while the strength of statistical evidence for the superiority question remains incompletely documented in this record.

These results do not establish what would happen beyond the reported 4-week treatment period, in populations other than adults with atopic dermatitis, or with different treatment schedules or formulations. The record does not report long-term follow-up. Nor can the summary determine whether the observed pattern is important to patients or clinicians; no threshold for clinical importance is reported.

The secondary outcomes show a similar broad direction in the group mean changes, but their comparisons are unadjusted recalculations and no sponsor analyses are reported. They do not resolve the missing comparative analysis for the primary outcome. Safety counts are also descriptive, and absence of recorded serious events during the study does not prove absence of risk.

In general, a randomized design strengthens a comparison by reducing confounding at assignment, but interpretation still depends on how outcomes were measured, who was analyzed, how missing observations were handled, and whether the reported analysis followed a prespecified plan. Several of those details are not reported in the registry record. The most defensible reading is therefore bounded: the posted estimates describe the Week 4 outcomes in this trial, while the record leaves important inferential and design details unavailable.

13. Why This Trial Matters Statistically

This trial illustrates why outcome estimates and comparative inference should be distinguished. The primary result is presented as a responder rate for each arm, accompanied by arm-specific confidence intervals. The research question, however, concerns a contrast between randomized groups. Without a reported between-arm estimate and its uncertainty, readers can describe the observed pattern but cannot rely on the registry record for a complete formal answer to the superiority question.

It also shows how endpoint definition shapes interpretation. The IGA responder outcome requires both a low severity score at Week 4 and improvement from baseline. That threshold-based definition conveys the proportion meeting a specific criterion, but not the full distribution of severity or the range of individual changes. The secondary continuous outcomes provide a different view of change, yet their unadjusted recalculations are not equivalent to reported confirmatory analyses.

The record makes the role of statistical planning visible as well. Planning illustrations based on observed secondary effects can demonstrate how assumed effect size affects hypothetical sample sizes, but they are not evidence of the trial's design justification or observed power. The actual sample-size rationale and statistical plan are not reported. This distinction matters because a post hoc planning exercise cannot establish that the completed trial was planned with the same assumptions.

Finally, the record highlights the importance of documenting analysis populations, missing-data rules, and multiplicity methods. Different denominators appear across outcomes, but reasons are not stated. Secondary comparisons are unadjusted, and no multiplicity strategy is reported. These are not merely technical details: they determine which questions a result can answer and how confidently it can be interpreted. Careful statistical reading keeps the claims aligned with the analyses that are actually recorded.

14. 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.

Several limitations are specific to the information and scope of this trial. The study enrolled adults with atopic dermatitis, so the registry record does not support conclusions about other populations. The intervention was 1% OPA-15406 ointment given twice daily and the comparator was placebo; no other concentration, schedule, or comparator is described. The posted primary assessment is at Week 4, and longer-term outcomes are not reported in the registry record.

The primary outcome is an investigator-assessed, threshold-based response. The record describes the IGA scale and response definition, but does not report additional information about assessor training, assessment reliability, or the method used to construct the confidence intervals. The registry calls the trial triple-masked but does not identify the masked roles or explain how masking was maintained.

The primary results are arm-specific rather than a reported comparative analysis. No primary between-arm estimate, confidence interval, or test is listed. The registry record also does not report the statistical analysis plan, sample-size justification, analysis populations, or handling of missing data. The secondary denominators differ from those for the primary endpoint, and the reasons are not stated. These gaps limit assessment of the analysis and prevent determining whether the recorded results follow a prespecified approach.

The secondary comparisons are unadjusted recalculations from summary statistics, and no multiplicity strategy is reported. Their results therefore have a different evidential status from a reported, prespecified analysis. Safety information is summarized as counts and does not include detailed event descriptions, timing, severity, or treatment attribution. These limitations concern what the registry record reports; they should not be interpreted as proof that the trial did not collect additional information.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Comparison Trial of OPA-15406 Ointment in Adult Patients With Atopic DermatitisSyndrome — NCT03908970.
• Registry record last updated 2021-01-25; status last verified 2021-01.
• Results first posted 2021-01-25.
• 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.

18. Record Summary

The record describes NCT03908970, a completed, randomized, multicenter, triple-masked, parallel-group, vehicle-controlled Phase 3 trial in adults with atopic dermatitis. It compared 1% OPA-15406 ointment with placebo, both given twice daily for 4 weeks. The primary outcome was the Week 4 IGA responder rate, defined by an IGA score of 0 or 1 and improvement of at least 2 grades from baseline.

The posted primary results report arm-specific responder estimates and 95% confidence intervals, but no direct comparative analysis. EASI and VRS change from baseline are listed as secondary outcomes; their posted comparisons are unadjusted recalculations, and the registry reports no analyses. Serious adverse events and deaths are listed as zero in each arm, with other adverse-event counts reported descriptively.

The registry record does not report the statistical analysis plan, sample-size justification, analysis populations, or missing-data methods. Those omissions limit the conclusions that can be drawn from the posted results.