A Placebo-Controlled Double-Blind Study on the Safety and Efficacy of Etanercept in Palmoplantar Pustulosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Placebo-Controlled Double-Blind Study on the Safety and Efficacy of Etanercept in Palmoplantar Pustulosis (NCT00353119), a randomized phase 3 study. The primary outcome is Percentage Change in Palmoplantar Pustulosis Severity Index (PPPASI) Before Crossover.

2. Clinical Question

The endpoint is a percentage change in a disease-severity score, rather than the score itself. The record describes the primary comparison as being made at 12 weeks, before the placebo group switched treatment. This timing matters: the primary result concerns the initial treatment period, not a comparison of the two groups after both had received etanercept. The registry does not report a confidence interval or a p-value for this result, and its endpoint description does not state the sign convention for percentage change. The means and standard deviations therefore describe the posted group summaries, but do not by themselves establish the size or precision of a treatment contrast.

3. Trial Design

This was a phase 3, randomized, quadruple-masked, placebo-controlled crossover study of etanercept in palmoplantar pustulosis. The registry reports that enrollment was 15 and that the study is completed. Innovaderm Research Inc. is listed as the sponsor. The recorded start was 2006-04, and primary completion was 2007-03.

The registry describes two treatment sequences. One group began with placebo for the first 12 weeks and then crossed over to etanercept 50 mg twice weekly for weeks 12 to 24. The other group received etanercept 50 mg subcutaneously twice weekly for 24 weeks. The primary endpoint is explicitly defined as a comparison before crossover, at 12 weeks. Consequently, that endpoint uses the initial period in which the treatment sequences differ; it is not a post-crossover comparison.

A crossover design means that a participant can receive more than one assigned treatment over successive periods. In general, this design can make within-participant comparisons possible, but interpreting such comparisons depends on how the study period, treatment sequence, and possible carryover effects are handled. The registry record does not report those details for the primary analysis. The posted primary results are presented as separate placebo and etanercept group summaries, with five participants in the placebo group and ten in the etanercept group.

The registry identifies the study as quadruple-masked but does not specify which roles were masked. The randomization method, allocation concealment procedures, crossover sequence methods, and any washout period are not reported in the registry record. The record also does not provide a detailed statistical analysis plan or explain the rationale for the enrollment target. These absences limit how fully the design and its safeguards can be evaluated from the registry information alone.

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.

First Intervention Day 0 to Week 12

Second Intervention Week 12 to Week 28

Analysis population for the primary outcome, as defined in the registry: The intent to treat (ITT) population is the same as the per protocol (PP) population. There was no imputation technique necessary.

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 Percentage Change in Palmoplantar Pustulosis Severity Index (PPPASI) Before Crossover, measured over 12 weeks.

The primary endpoint is the percentage change in the Palmoplantar Pustulosis Severity Index (PPPASI) at 12 weeks, before crossover. PPPASI is a composite score based on assessment of erythema, pustules, desquamation, and the affected area on the right and left palms and soles. The registry describes the component severity ratings and area ratings and gives the possible score range as 0, representing absence of disease, to 72, representing the most severe palmoplantar psoriasis possible.

A severity index combines several observed features into one measure. In general, this can provide a structured way to track disease status over time and compare groups using the same assessment framework. Reporting percentage change expresses the endpoint relative to a baseline measure, rather than simply reporting the follow-up score. However, the registry does not report the baseline group means or the formula used to calculate percentage change, and it does not state the sign convention. Readers therefore should not infer from the direction of the posted values alone whether a larger or smaller percentage change represents improvement.

The endpoint is used to compare disease-severity change during the initial 12-week treatment period. The posted mean percentage change was 30.1 in the placebo group and 7.1 in the etanercept group. These are group means, with standard deviations of 25.7 and 60.4, respectively. The registry does not report confidence intervals or a formal statistical test for this endpoint. The summaries describe the observed results, but do not quantify the uncertainty around the between-group contrast.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a percentage-change measure, summarized with a mean and standard deviation. A mean describes the average observed value in a group. A standard deviation describes how dispersed observations are around that average. These summaries are useful for a first description of the data, but do not by themselves answer how uncertain a comparison between groups is.

What does the mean tell us?

The reported mean percentage change was 30.1 for placebo and 7.1 for etanercept at 12 weeks before crossover. These are group-level averages. They do not imply that every participant had a value close to the mean, and they do not show the range of individual results. The standard deviations were 25.7 and 60.4, respectively. In general, greater dispersion makes an average less representative of each individual observation and can make a group contrast less precise.

The endpoint description identifies PPPASI as a severity index built from ratings of erythema, pustules, desquamation, and affected area on the palms and soles. The primary outcome is percentage change in that index, not the absolute score. The record does not report baseline means, the detailed percentage-change calculation, or the sign convention. Those omissions make it important to avoid interpreting the numerical direction as improvement or worsening based only on the posted means.

How should uncertainty be assessed?

In general, a confidence interval gives a range of values compatible with the data and the statistical method used, while indicating the uncertainty in an estimate. A p-value, when reported, addresses how compatible the observed data are with a specified null hypothesis under the chosen model. Neither is a measure of clinical importance by itself. The registry does not report a confidence interval or p-value for the primary comparison. It also does not report a model-based estimate of the between-group contrast. The means and standard deviations therefore permit descriptive reading, but not a registry-based assessment of inferential precision.

For continuous outcomes, the choice of statistical method can depend on the distribution of observations, the design, and whether the analysis compares groups or accounts for repeated measurements. In general, a crossover study may require attention to treatment sequence, period, and possible carryover. The primary result is defined as occurring before crossover, which avoids interpreting it as a post-crossover comparison, but the analysis method itself is not reported. The record does not say whether any adjustment or model was used.

What does a crossover design imply?

In general, a crossover design assigns treatment sequences so that participants can receive different treatments during different periods. Measurements from the same participant may be related, so analyses of all periods commonly need to account for that relationship. A pre-crossover comparison, as specified for this endpoint, is distinct from an analysis that uses observations from both periods. The registry describes the sequences and the 12-week timing, but does not provide further analysis details. No washout period or carryover assessment is reported in the registry record.

The study is described as randomized and quadruple-masked. In general, randomization is intended to reduce systematic differences between assigned groups, and masking is intended to limit the influence of knowledge of treatment assignment. The registry does not specify the randomization procedure, allocation concealment, or which roles were masked. These labels describe design features, but do not supply the operational details needed to assess their implementation.

How should the planning illustrations be read?

The posted planning illustrations are based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They use specified fractions of the observed effect to illustrate participants per arm for 80% and 90% power. These are planning illustrations, not results observed in the trial and not evidence of observed power. They do not establish that the original study was designed using those assumptions; the registry does not report the trial’s own sample-size justification.

In general, a planning calculation asks what sample size would be needed under stated assumptions to detect a target effect with a chosen error rate and power. Its output depends on the assumed effect, variability, allocation, test, and model. When the target effect is derived from a small study, that effect estimate may itself be imprecise. Planning illustrations based on the observed effect should therefore be treated as conditional examples, not as a validated estimate of the sample size needed for a future study.

The registry reports no analysis entries. It also does not report a prespecified model, adjustment variables, a test statistic, a standard error, a confidence interval, or handling of potential outliers. These are not details that can be reconstructed from the two means and standard deviations alone. The posted summaries are consequently best interpreted as descriptive statistics, with the inferential method and uncertainty not reported in the registry record.

10. Confidence Intervals for Each Arm

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

R code and output

arm <- c("Placebo", "Etanercept")
n   <- c(5, 10)
m   <- c(30.1, 7.1)
sp  <- c(25.7, 60.4)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Placebo  5  30.100  25.700  -1.811  62.011
CARM  Etanercept  10  7.100  60.400  -36.108  50.308

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and three secondary outcomes: number of adverse events, percentage change in PPPASI, and percentage change in PPPASI after crossover. It reports four outcome measures overall. The record does not report a multiplicity adjustment, a hierarchy among secondary outcomes, or a plan for controlling the chance of false-positive findings across multiple analyses. No formal analysis entries are reported. Without a stated testing strategy, the role of any secondary comparisons in confirmatory inference is not reported in the registry record.

The endpoint population description states that the intent-to-treat population was the same as the per-protocol population and that no imputation technique was necessary. This indicates that the registry described the two analysis populations as identical for the primary endpoint and did not use imputation. It does not provide the number of participants with endpoint data at each time point, a detailed accounting of missing observations, or a reason why imputation was unnecessary. Those details are not reported in the registry record.

In general, missing-data methods matter because conclusions can depend on whether missingness is related to outcomes or treatment assignment. An analysis that excludes missing observations can differ from one that imputes values or uses a model for incomplete repeated measurements. The registry’s statement about no imputation does not identify which specific approach generated the posted summary values. The handling of missing data beyond that statement is not reported.

The crossover design and multiple outcomes make the analysis plan particularly relevant to interpretation. The registry does not report how it handled period effects, treatment sequence, possible carryover, or multiplicity. It also does not report whether any secondary-outcome analyses were exploratory or confirmatory. These absences should not be filled in by assuming conventional methods; the record supports only the stated population and missing-data description.

12. Safety Results

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

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 reports no serious adverse events in either group: zero affected among five at risk in the placebo group, and zero affected among ten at risk in the etanercept group. These are counts for the recorded study groups, not estimates that establish the absence of serious risk. With small at-risk groups, zero observed events still leaves uncertainty about event rates beyond the participants and observation periods recorded.

For other adverse events, the registry reports five affected among five at risk in the placebo group and fifteen affected among fifteen at risk in the etanercept group. These are the registry’s counts and denominators; they should not be interpreted as a comparative rate without accounting for the study periods and exposure described. The etanercept group received treatment for 24 weeks, while the placebo sequence received placebo for the first 12 weeks and etanercept thereafter. The registry does not provide a detailed exposure-adjusted safety analysis.

Deaths are not reported in the registry record. The record does not list top serious adverse-event terms. It also does not provide event-level detail, timing, severity grades for other events, or a formal comparison of safety outcomes. The counts describe what was posted, but do not determine whether a treatment caused an event or how risks compare in a larger population.

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

The posted primary result is a descriptive comparison of mean percentage change in PPPASI at 12 weeks before crossover. The placebo mean was 30.1, with a standard deviation of 25.7, and the etanercept mean was 7.1, with a standard deviation of 60.4. The registry gives no confidence interval, p-value, or model-based estimate for the contrast. The result therefore communicates group summaries without a reported measure of inferential precision.

The primary endpoint description identifies PPPASI as a severity index, but the record does not specify the sign convention for percentage change. It also does not report baseline group means or individual-level results. Consequently, the numerical values should not be recast as a direction of benefit or harm. A clinical interpretation of the scale would require information about the calculation and context that is not reported in the registry record.

The trial’s crossover design means treatment sequences changed after the first 12 weeks for the group that began on placebo. The primary endpoint is specifically located before that crossover. It does not describe a comparison at the end of both sequences, and the posted means should not be treated as though both groups were compared after the same treatment exposure. The registry does not provide a separate analysis of the post-crossover endpoint in the results.

The safety counts record no serious adverse events in either group, alongside other adverse events in each at-risk group. Such counts are descriptive and do not establish that serious events cannot occur. Nor do they, without a reported exposure-adjusted analysis and fuller event information, establish a comparative safety profile. Deaths are not reported in the registry record.

These results do not establish whether etanercept is effective or ineffective. They show the means, variability, and safety counts entered in the registry for this small study, while important elements of statistical inference and endpoint interpretation are not reported. The findings should be read as a limited record of observed group summaries, not as medical advice or a definitive treatment conclusion.

14. Why This Trial Matters Statistically

This study is statistically informative because its design and endpoint require careful attention to timing. It is described as a randomized crossover trial, but the primary comparison is defined before crossover, at 12 weeks. That distinction separates the primary result from any comparison using later observations, when the placebo sequence had switched to etanercept. Clear timing is essential when interpreting results from studies in which participants change treatment over time.

The reported group sizes are small, and the standard deviations are large relative to the means, particularly for the etanercept group. In general, small samples make estimates more sensitive to individual observations and tend to leave greater uncertainty. The registry does not report confidence intervals or a formal test, so readers cannot use the posted primary summaries to judge that uncertainty through an inferential estimate.

The endpoint itself also illustrates why measurement definitions matter. PPPASI combines several signs and affected-area assessments into a severity score, while the primary result is expressed as percentage change. Without the sign convention and baseline summaries, the numerical result is not self-interpreting. Clear reporting of outcome calculation and direction would help readers understand what a reported change represents.

The record identifies the intent-to-treat and per-protocol populations as the same and says no imputation was necessary. It also lists secondary outcomes, but does not report a multiplicity plan or analysis entries. The combination of limited inferential detail and a crossover design makes the registry’s descriptive results important to distinguish from a complete statistical analysis. This is a useful example of how design labels, outcome summaries, and analysis reporting each contribute different pieces of evidence.

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 registry record leaves several trial-specific questions unanswered. It does not report the randomization procedure, allocation concealment, which roles were masked, or how the crossover sequence was implemented. Although the treatment sequences and the pre-crossover timing are described, a washout period and any assessment of carryover are not reported in the registry record.

For the primary outcome, the registry gives group means and standard deviations but no confidence interval, p-value, test statistic, or adjusted estimate. It does not report baseline PPPASI summaries, the sign convention for percentage change, or the detailed calculation used for the percentage-change result. The distribution of individual observations is also not reported. These omissions limit assessment of both the magnitude and precision of the comparison.

The analysis plan and sample-size justification are not reported in the registry record. The planning illustrations use the observed effect and stated assumptions, but they are not evidence of the original design rationale or observed power. The registry also does not report how period, sequence, or carryover considerations were handled analytically, or how multiplicity across outcomes was addressed.

The missing-data description is brief: the intent-to-treat and per-protocol populations are stated to be the same, and no imputation was necessary. The record does not provide a detailed flow of outcome availability or explain that statement. For safety, serious and other adverse-event counts are posted, but event-level details, exposure-adjusted comparisons, and death counts are not reported. These limitations do not invalidate the posted summaries; they define what can and cannot be concluded from the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Placebo-Controlled Double-Blind Study on the Safety and Efficacy of Etanercept in Palmoplantar Pustulosis — NCT00353119.
• Registry record last updated 2011-09-09; status last verified 2011-09.
• Results first posted 2010-12-21.
• 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.

19. Record Summary

The registry describes a completed phase 3 randomized, quadruple-masked, placebo-controlled crossover study of etanercept for palmoplantar pustulosis. Enrollment was 15. One sequence began with placebo for 12 weeks and then crossed over to etanercept; the other received etanercept for 24 weeks. The primary endpoint was mean percentage change in PPPASI at 12 weeks before crossover.

The posted primary means were 30.1 for placebo and 7.1 for etanercept, with standard deviations of 25.7 and 60.4. The registry does not report a confidence interval, p-value, or detailed inferential analysis. It states that the intent-to-treat and per-protocol populations were the same and that no imputation was necessary.

The registry reports no serious adverse events in either group and records other adverse events in each group. Deaths are not reported in the registry record. The analysis plan, multiplicity approach, and original sample-size justification are also not reported.