Ruxolitinib in Seborrheic Dermatitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ruxolitinib in Seborrheic Dermatitis (NCT05787860), a non-randomized phase 2 study. The primary outcome is Number of Participants With Investigator Global Assessment of 0 or 1 at Week 4.

2. Clinical Question

The trial was designed to assess the efficacy of ruxolitinib in seborrheic dermatitis and to characterize molecular immune profiles at week 0 and week 4. Its clinical endpoint focuses on whether participants were assessed as clear or almost clear at the end of treatment. In the registry’s scale description, 0 means no signs of seborrheic dermatitis, while 1 means just perceptible erythema and just perceptible scaling.

These are related but distinct aims. The clinical endpoint records an investigator’s assessment of disease signs; the molecular objective concerns immune profiles. The registry describes comparison of the participants’ profiles with baseline profiles in healthy control subjects, but it does not report molecular results in the record.

The design can describe the observed status of participants receiving the cream if outcome data are reported, but without a randomized treatment comparator it cannot isolate a treatment effect from other explanations for change. In this record, even the primary endpoint count is not reported, so the observed Week 4 response and its uncertainty cannot be characterized.

3. Trial Design

This was a Phase 2, prospective interventional study listed as completed. It was open-label, nonrandomized, and used a single-group model for the treatment intervention. The registry lists an enrollment of 45; that is the recorded enrollment figure, not necessarily the number contributing to any particular outcome.

Participants with seborrheic dermatitis were to receive topical ruxolitinib 1.5% cream. The registry also lists age- and gender-matched healthy control subjects. Those subjects are described as a source of baseline profiles for comparison with molecular immune profiles from participants with seborrheic dermatitis. The record explicitly cautions that the arms are not a like-for-like control comparison. The healthy controls therefore should not be treated as a randomized or equivalent untreated group for estimating a clinical treatment effect.

The study’s primary outcome was the number of participants with an Investigator Global Assessment score of 0 or 1 at Week 4, at the end of treatment. The registry lists secondary outcomes involving change in Investigator Global Assessment, severity scores, scale, erythema, pruritus, and adverse events. It records nine outcome measures, but does not provide analysis results for the primary endpoint or the listed secondary outcomes.

The registry gives a start date of 2022-11-15, a primary completion date of 2024-01-26, and a completed status. Those dates describe the registry record’s study timeline; they do not supply outcome estimates. The record does not report a statistical analysis plan, a sample-size justification, interim analyses, or the rules used to handle missing outcome data. The stated enrollment should not be interpreted as the endpoint analysis denominator without participant-flow and outcome-specific counts.

Because allocation was nonrandomized and masking was absent, the design is susceptible to differences in assessment and to influences unrelated to treatment. Those design features matter when interpreting any reported response. In this record, the lack of a reported response count prevents direct assessment of the primary result in addition to those design limitations.

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: Data collected only for participants with SD

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 Number of Participants With Investigator Global Assessment of 0 or 1 at Week 4, measured over At end of Treatment, Week 4.

The primary endpoint is the number of participants with seborrheic dermatitis whose Investigator Global Assessment score was 0 or 1 at Week 4, the end of treatment. The assessment uses a scale from 0 to 4. A score of 0 is defined as clear, with no signs of seborrheic dermatitis; a score of 1 is almost clear, with just perceptible erythema and just perceptible scaling. The higher categories describe increasing severity, from mild through severe.

This endpoint is a binary classification for each participant: the score either falls in the 0-or-1 range or it does not. Counting participants who meet a prespecified clinical state can make an outcome easier to interpret than a change in a continuous score, because it expresses how many reached the defined state at the specified assessment time. That is a general statistical explanation of the endpoint type, not a claim about the results of this study.

The registry specifies that primary outcome data were collected only for participants with seborrheic dermatitis. The record does not report the number meeting the endpoint, the number assessed at Week 4, or an estimate of the proportion meeting it. Without those quantities, the clinical response cannot be described and the precision of an estimate cannot be evaluated. The endpoint definition alone does not show how participants fared.

The endpoint is also a Week 4 status rather than, as described, a comparison against a randomized control group. A single-group count can describe the observed outcome among assessed participants, but it does not by itself establish what would have happened without treatment. No causal treatment contrast is reported in this registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a count of participants who meet a binary criterion. Each assessed participant is classified according to whether the Investigator Global Assessment score at Week 4 is 0 or 1. The registry defines those categories as clear and almost clear, respectively. This is a general explanation of a binary endpoint: the individual outcome has two possible classifications for analysis, even though the underlying assessment scale has multiple ordered categories.

What a response count can tell us

A count is meaningful only alongside its denominator. The numerator would be the number meeting the 0-or-1 criterion, and the denominator would be the number of participants with an evaluable Week 4 assessment in the population specified for the endpoint. The registry says primary data were collected only for participants with seborrheic dermatitis, but it does not report either the response count or the Week 4 denominator. The enrollment of 45 does not establish the denominator for this analysis.

If both numbers were available, the fraction meeting the criterion could describe the observed response in the assessed population. A confidence interval could then convey uncertainty around that estimate. In general, confidence intervals are wider when information is less precise and narrower when it is more precise, though the actual interval depends on the data and method. No estimate or interval is reported for this endpoint, so none can be interpreted.

What the design does and does not estimate

A single-group study can report outcomes among participants receiving the intervention. In general, it does not provide the randomized counterfactual comparison needed to separate a treatment effect from other explanations for an outcome. This study is listed as nonrandomized, open-label, and single-group. The registry also lists healthy control subjects, but it describes them for molecular-profile comparisons and cautions that the arms are not a like-for-like control comparison. That distinction is important: a group included for biological characterization should not automatically be treated as a clinical treatment control.

Open-label assessment means that masking was not used. In general, knowledge of treatment assignment can influence reporting or clinical assessment, particularly when an outcome involves investigator judgment. This does not show that an assessment was biased in this study; it identifies a possible source of measurement uncertainty associated with the design.

Statistical plan and precision

The registry record does not report the statistical analysis plan, the planned inferential method for the primary endpoint, an interim-analysis plan, or a sample-size justification. It also does not report a primary-endpoint p-value, confidence interval, or model-based estimate. These omissions mean the analysis choices and the precision intended by the study cannot be reconstructed from the registry record.

The record’s sample-size assumptions describe planning illustrations rather than the trial’s own design. They specify a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect expressed as a stated fraction of the observed effect. These are not a description of the actual single-group, nonrandomized treatment design. Any participant counts generated under such assumptions are planning illustrations, not observed power, and cannot replace a reported endpoint analysis. No numerical planning results are reported in the record.

Over-dispersion is a general concern for some count outcomes when variation exceeds the assumptions of a simple model; accounting for it can affect standard errors and intervals. The primary endpoint in this study, however, is described as a count of participants meeting a binary threshold, not as a rate of repeated events. The registry does not report a model or dispersion parameter for this outcome, so there is no basis for attributing a particular method to the investigators.

Why missing outcome information matters

Missing outcome data can affect both the denominator and the interpretation of a response estimate. In general, the consequences depend on how many outcomes are missing and why they are missing. A complete-case estimate describes participants with observed assessments; other strategies may make different assumptions about missing participants. The registry does not report the number missing at Week 4 or the method, if any, used to handle missing assessments. Therefore, neither the extent nor the impact of missing primary endpoint data can be assessed.

Multiplicity is another general statistical issue when a study evaluates several outcomes or comparisons. Testing many hypotheses can increase the chance of at least one apparently notable result unless the analysis plan addresses that issue. The registry lists one primary outcome and several secondary outcome measures, but does not report a multiplicity strategy or analysis results. It is not possible to determine whether any adjustment was planned or applied.

Finally, statistical significance and clinical interpretation are not interchangeable. In general, a p-value addresses compatibility of data with a specified null model and depends on the analysis assumptions; it does not measure the size or importance of an effect. An effect estimate and its interval are needed to assess magnitude and precision. Here, no primary endpoint estimate or inferential result is reported, so those interpretations cannot be made.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Ruxolitinib Cream")
n      <- c(25)
events <- c(20)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Ruxolitinib Cream  25  20  80.0  59.3  93.2  60.9  91.1  60.6  91.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and nine outcome measures overall, including changes in Investigator Global Assessment, severity, scale, erythema, and pruritus, as well as adverse-event measures. Having multiple outcomes creates a general multiplicity question: when many outcomes are assessed, the chance of finding at least one apparently notable result may increase. The registry record does not report whether a multiplicity adjustment or a hierarchy among outcomes was planned. It also reports no analysis results with which to assess the issue empirically.

The record does not report how missing data were handled. It gives the enrollment figure but does not provide a participant flow, a Week 4 assessment denominator, the number with missing primary outcome data, or reasons for missingness. In general, missing outcomes can change the denominator and may affect an estimate if participants with missing data differ from those assessed. Without information about missingness or the analysis population, the impact cannot be determined.

The primary endpoint population is described as participants with seborrheic dermatitis, but the registry does not state how many of them were included in the analysis. The adverse-event populations are separately reported by group, but those figures do not establish the primary endpoint population or the number assessed for clinical response.

The record also does not report a statistical analysis plan, interim-analysis methods, or a sample-size justification. These omissions prevent reconstruction of the planned approach to outcome selection, missing assessments, or multiplicity. They do not establish that such procedures were absent from study conduct; they are not reported in the registry record.

12. 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.

For the Ruxolitinib Cream group, the registry reports 25 participants at risk for serious adverse events and 0 affected; it also reports 25 at risk for other adverse events and 0 affected. Deaths are reported as 0. For Healthy Control Subjects, 20 participants are reported at risk for serious adverse events and 0 affected, and 20 at risk for other adverse events and 0 affected. Deaths are reported as 0.

These are recorded counts, not evidence that the risk of an adverse event is zero. The registry does not provide event-level details, follow-up completeness, or a safety comparison suitable for estimating a treatment effect. The group sizes differ and the study was nonrandomized; the registry cautions that the arms are not a like-for-like control comparison. Consequently, the counts should be read descriptively, not as evidence that one group had safer outcomes than another.

The registry lists secondary outcomes for adverse-event frequency, duration, and severity, but does not report those results in the record. A count of zero affected participants in the posted group fields does not supply information about event duration or severity beyond the recorded count, nor does it establish how events were solicited or monitored. The safety figures describe what the registry reports for these groups and should not be extended to populations or circumstances not described in the record.

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

The registry record establishes the study question, intervention, design, endpoint definition, and recorded safety counts. It does not provide the primary endpoint result. Therefore, it cannot show how many participants with seborrheic dermatitis achieved an Investigator Global Assessment score of 0 or 1 at Week 4, or how precise any response estimate would be. A completed status does not substitute for a reported outcome.

The absence of a reported response is not evidence that no participants responded, just as the study’s stated purpose is not evidence that a response occurred. Without the endpoint count and denominator, the clinical result remains unquantified in this registry record. The record also gives no reported estimate or uncertainty interval for changes in the secondary clinical outcomes.

Even if a single-group response count were available, its interpretation would remain descriptive. The open-label, nonrandomized, single-group design does not include a randomized clinical comparison capable of separating treatment-associated outcomes from other possible influences. Healthy control subjects are listed for molecular-profile comparisons, and the registry cautions against treating the arms as a like-for-like control comparison.

The record does not report molecular results, a statistical analysis plan, handling of missing data, or a multiplicity strategy. Those gaps limit interpretation of both the planned biological characterization and the listed outcome measures. They do not establish that the study failed to collect such data or that no analyses were performed; those details are not reported in the registry record.

Statistically, the central distinction is between a question that has been defined and a result that has been reported. The Week 4 threshold is well specified, but the outcome count needed to describe observed response is unavailable. The posted information therefore supports understanding what investigators intended to measure, not a quantitative judgment about efficacy or a claim that ruxolitinib does or does not work.

14. Why This Trial Matters Statistically

This study illustrates why endpoint definitions and outcome reporting are both necessary for statistical interpretation. The registry defines a clinically interpretable threshold: an Investigator Global Assessment score of 0 or 1 at Week 4. But without the number meeting that threshold and the number assessed, the endpoint cannot be summarized as an observed response frequency, and its precision cannot be evaluated.

It also illustrates the importance of distinguishing a treatment group from a control group. Healthy control subjects can be useful for the study’s stated molecular-profile objective, but they do not create a randomized clinical comparison. The registry explicitly cautions that the arms are not like-for-like controls. Treating them as equivalent groups for estimating a treatment effect would overstate what the design supports.

Several statistical questions remain unanswered in the registry record: the primary analysis denominator, missing-data handling, multiplicity strategy, and analysis plan. These matters affect how results should be interpreted and reproduced. Their absence from the record should be distinguished from evidence about what was done in the study.

The safety fields also show why event counts require context. The registry reports zero affected participants in the listed groups, but those counts alone do not establish comparative risk, completeness of follow-up, or event characteristics. Overall, this trial is statistically informative as an example of the gap between a stated research objective and a reported result: a clearly defined outcome is not enough unless the observed data and their uncertainty are also available.

15. 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 limitation for interpreting this study from the registry record is that the primary endpoint result is not reported. There is no Week 4 count meeting the 0-or-1 criterion, no corresponding analysis denominator, and no uncertainty estimate. The enrollment figure of 45 cannot be substituted for the number assessed for this endpoint.

The study design is also limited for causal interpretation. It is nonrandomized, open-label, and listed as a single-group model for the treatment intervention. The healthy control subjects are described for molecular-profile comparisons, not as a randomized clinical comparator; the registry cautions that the arms are not a like-for-like comparison. These features prevent a straightforward treatment-versus-control interpretation.

The registry does not report participant flow, reasons for missing assessments, or the method used to handle missing data. It does not report the statistical analysis plan, a sample-size justification, interim analyses, or a multiplicity approach. These omissions limit assessment of analysis choices, endpoint completeness, and the relationship between the listed outcomes and any inferential claims.

The secondary outcomes are named but their results are not reported in the registry record. Molecular-profile findings are also not reported. The safety fields provide group counts, but do not describe event-level details, monitoring procedures, or the completeness of follow-up. These limitations concern the information available in the registry record and do not establish that the study collected no additional data or that no further analyses were performed.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Ruxolitinib in Seborrheic Dermatitis — NCT05787860.
• Registry record last updated 2025-05-06; status last verified 2025-05.
• Results first posted 2025-05-06.
• 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.

19. Record Summary

NCT05787860, titled “Ruxolitinib in Seborrheic Dermatitis,” is a completed Phase 2, prospective interventional study sponsored by Icahn School of Medicine at Mount Sinai. The registry lists enrollment of 45, nonrandomized allocation, no masking, and a single-group model. Participants with seborrheic dermatitis received topical ruxolitinib 1.5% cream; healthy control subjects were included for molecular-profile comparisons.

The primary endpoint was the number of participants with seborrheic dermatitis whose Investigator Global Assessment score was 0 or 1 at Week 4. The registry record does not report that result, an analysis denominator, or an uncertainty estimate. It lists nine outcome measures and provides adverse-event group counts, including zero affected participants for the reported serious and other adverse-event fields and zero deaths in each group.

The study started on 2022-11-15, reached primary completion on 2024-01-26, and is listed as completed. The record does not report the statistical analysis plan, missing-data handling, multiplicity approach, or sample-size justification.