Moderate to Severe Plaque Psoriasis With Scalp Involvement: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Moderate to Severe Plaque Psoriasis With Scalp Involvement (NCT00791765), a randomized phase 4 study. The primary outcome is Percentage Change From Baseline in Psoriasis Scalp Severity Index at Week 12.

2. Clinical Question

3. Trial Design

The registry describes a completed Phase 4 study with randomized allocation, quadruple masking, a parallel-group model, and placebo control. Its official title describes a randomized, double-blind, placebo-controlled study evaluating etanercept for scalp involvement in subjects with moderate to severe plaque psoriasis. The record lists psoriasis as the condition and Amgen as the sponsor. The study start is recorded as 2008-10 and primary completion as 2010-01.

Enrollment was 124. The two treatment sequences were placebo twice per week for the first 12 weeks followed by etanercept 50 mg twice per week, and etanercept 50 mg twice per week for the first 12 weeks followed by etanercept 50 mg once per week plus placebo once per week. The primary outcome is measured at Week 12, so its comparison reflects the first treatment period. Later outcomes include a Week 24 measure among participants who switched from placebo to etanercept, as well as patient satisfaction at Week 12.

The registry calls the masking quadruple and also describes the study as double-blind in the official title. It does not report the specific roles of people masked, the randomization method, allocation concealment details, or the factors, if any, used to stratify allocation. The protocol's original sample-size assumptions and detailed statistical analysis plan are not reported in the registry record. These missing details limit what can be concluded about design choices beyond the registered structure and the analyses posted.

The primary outcome summaries use available data from the intention-to-treat population and specify LOCF imputation. The arm-specific sample sizes for that outcome are 61 and 59. They should be read as the reported primary-outcome summary sizes, rather than assumed to describe every analysis or every point in follow-up.

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.

Weeks 1 to 12

Reasons for not completing this period:

Weeks 13 to 24

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intention-to-Treat population (all patients who were randomized to investigational product) with available data; last observation carried forward (LOCF) imputation was used.

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 From Baseline in Psoriasis Scalp Severity Index at Week 12, measured over Baseline and Week 12.

The primary endpoint is percentage change from baseline in the Psoriasis Scalp Severity Index (PSSI) at Week 12. The PSSI assesses the extent of scalp psoriasis involvement and physician-rated severity of erythema, infiltration, and desquamation. Its score ranges from 0 to 72, with 0 indicating no psoriasis and higher scores indicating more severe disease. The PSSI calculation excludes the face and neck.

A change-from-baseline endpoint describes how the measured condition differs from a participant's baseline assessment over the specified period. Expressing change as a percentage places the reported change relative to the baseline value. The registry reports the group results as means with standard errors. It does not provide an endpoint-specific threshold for deciding what size of change is clinically important, nor does it give a separate distribution of individual participant changes in the record.

PSSI is relevant to this study because the trial's stated purpose was to assess treatment of scalp involvement in people with moderate to severe plaque psoriasis. The Week 12 measure focuses on the scalp rather than the whole body or the face and neck. It is therefore a domain-specific endpoint, and its result should be interpreted as an assessment of scalp involvement and severity, not as a measure of every aspect of psoriasis or overall health.

7. Results Posted in the Registry

• Etanercept 50 mg BIW/Etanercept 50 mg QW: mean 86.80 versus 20.40 on control; difference 66.40 (95% CI 55.61 to 77.19), standardized effect d = 2.18; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Percentage of Participants With PSSI 75% Response at Week 12

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Etanercept 50 mg BIW/Etanercept 50 mg QW: 86.4% (51/59) versus 11.5% (7/61) on control; risk difference 75.0 percentage points (95% CI 63.1 to 86.8), risk ratio 7.53 (3.72–15.23); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Etanercept 50 mg BIW/Etanercept 50 mg QW than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes extend the assessment beyond the primary Week 12 mean percentage change. They include a binary PSSI response threshold at Week 12, change in PSSI at Week 24 among participants switching from placebo to etanercept at Week 12, and treatment satisfaction at Week 12. The posted binary response results show a marked separation between the randomized groups, and the registered comparison reports p < 0.001. This direction is broadly coherent with the primary result, while the threshold-based outcome and the continuous primary measure summarize different features of the data.

The remaining listed outcomes address later change after the placebo group switches treatment and patient satisfaction. Numeric results for those outcomes are not reported in the registry record analyzed. Their inclusion in the outcome list does not establish a particular result, and they cannot be used to infer persistence, switching effects, or satisfaction patterns without the posted estimates.

Secondary endpoints can add context, but they generally carry less weight than a prespecified primary endpoint when many outcomes are assessed. Multiple statistical tests create more opportunities for apparently notable findings by chance. The registry record does not report whether a multiplicity adjustment or a hierarchical testing procedure was used, so the degree of confirmatory control for secondary analyses is not known. Their p-values should be read as nominal unless an adjustment is documented.

The secondary results also differ in population and timing. A Week 24 outcome among participants who switched after Week 12 is not the same randomized comparison as the initial placebo-controlled period. In general, once both groups receive active treatment, later between-group contrasts may no longer isolate the original placebo-controlled question. The registry record's outcome descriptions support attention to these distinctions, but do not provide enough detail to characterize all later analyses.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Percentage of Participants With PSSI 75% Response at Week 12
• Percent Change From Baseline in PSSI at Week 24 in Participants Switching From Placebo to Etanercept at Week 12
• Patient Satisfaction With Treatment at Week 12

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: it is a percentage-change measure, and the registry reports a mean for each arm. For a continuous endpoint, a mean describes the average observed value within a group. It does not imply that every participant had a value near that average. The reported standard errors describe the precision of the estimated arm means, not the spread of individual participant outcomes. General statistical interpretation distinguishes a standard error from a standard deviation: the former concerns uncertainty in an estimated mean, while the latter describes variability among individual observations.

What does the unadjusted mean difference represent?

The recalculated contrast subtracts the placebo-first group mean from the etanercept-first group mean. It is a simple, unadjusted comparison based on the posted summary statistics. The resulting mean difference is 66.4 percentage points of the reported percent-change scale, and its 95% confidence interval is 55.61 to 77.19. The term unadjusted means the calculation does not apply a covariate adjustment or reproduce the sponsor's named test. The registry record does not report sufficient detail to characterize every feature of the sponsor's analysis.

A confidence interval describes a range of values compatible with the data and the statistical procedure under its assumptions. In repeated use of the same procedure, intervals constructed this way would cover the underlying quantity at the stated rate. For an individual trial, it is not a probability statement that the true value lies within the particular interval. The interval conveys uncertainty around the estimated difference; it does not describe the range of individual responses or determine clinical importance.

Why is the sponsor's test different?

The registry reports van Elteren's test for the primary comparison. In general, the van Elteren test is a stratified rank-based comparison related to the Wilcoxon-Mann-Whitney approach. Rank-based methods compare the ordering of observations rather than relying solely on arithmetic means, and the stratified form combines comparisons across strata. The registry record does not report the stratification variables or enough detail to reproduce the test from the summary statistics. For that reason, the reported test result and the unadjusted mean-based recalculation answer related but not identical statistical questions.

The reported primary p-value is p < 0.001. A p-value describes how incompatible the observed data, or more extreme data, would be with a specified null model under the test's assumptions. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical relevance of an effect. The registry's reported p-value belongs to the sponsor's named test. The recalculated p-value, p < 0.001, belongs to the separate unadjusted calculation.

How does the binary outcome differ?

The PSSI 75% response outcome is binary: a participant either meets the stated response threshold or does not. The registry reports the proportions and a Cochran-Mantel-Haenszel comparison. In general, the Cochran-Mantel-Haenszel method combines evidence across strata for an association between a group assignment and a binary outcome. The record does not specify the strata or provide enough details to reconstruct that registered test. The posted p-value is p < 0.001. A binary response can be easy to interpret against a threshold, but it does not retain all the gradations in a continuous outcome.

The recalculated risk difference for this outcome is based on the posted event counts and group sizes. As with the continuous endpoint, this simple recalculation is distinct from the registered test. Risk differences express an absolute contrast in proportions, whereas a rank-based test or a stratified binary test evaluates evidence using its own procedure. These methods should not be conflated merely because they address the same randomized groups.

Why can over-dispersion matter?

General: over-dispersion occurs when observed variability is greater than a statistical model assumes. For count or binary data, a model that assumes less variability than is actually present can produce uncertainty estimates that are too small and tests that appear more decisive than warranted. For a continuous outcome, a poor variance model can likewise distort standard errors and confidence intervals. The registry record does not state that over-dispersion was assessed or report a model-based correction, so this is a general consideration rather than a claim about this trial's analysis.

The primary outcome's population is described as intention-to-treat, including randomized patients with available data, with LOCF imputation. In general, LOCF substitutes a participant's last recorded value for a later missing value. It can preserve a defined analysis set, but it relies on an assumption about how the unobserved later value relates to the last observed value. LOCF may not reflect continued improvement, worsening, or fluctuation after the last observation. The record does not report missingness counts, reasons, timing, or sensitivity analyses, so the impact of LOCF cannot be determined from these details.

These distinctions matter for interpretation: the effect estimate, its uncertainty, the test used, and the data-handling assumptions are separate elements. The posted summaries permit an unadjusted descriptive contrast, while the registered inferential result is the sponsor's van Elteren test. The original detailed statistical plan is not reported in the registry record.

11. Confidence Intervals and Precision

The unadjusted mean difference for the primary outcome is 66.4, with a 95% confidence interval from 55.61 to 77.19. The interval gives a range of plausible values for the population mean difference under the assumptions of this recalculation. It is centered around the estimated contrast and quantifies uncertainty in that estimate. It does not indicate that individual participants' changes fall within this range, and it does not provide a clinical-importance threshold.

The lower endpoint of the interval is above zero, so the unadjusted interval is consistent with a positive mean difference on the reported scale. That direction describes the numerical contrast between the two arm means. It should not be extended to claims about all participants or outcomes. The registry's inferential test is separately reported as van Elteren's test with p < 0.001; the confidence interval is from the unadjusted re-calculation and is not the interval from that registered test.

Precision depends on both the estimated effect and the amount of uncertainty in the data. A narrower interval generally indicates a more precise estimate, while a wider interval leaves more uncertainty about the magnitude. The standard errors reported for the two arm means are 5.0 and 2.3. The record does not post a sponsor-derived confidence interval for the primary registered test, so the recalculated interval should be read in that context.

Even a relatively precise estimate does not resolve limitations related to missing data, endpoint interpretation, or the population studied. The primary outcome uses available data and LOCF imputation, and the registry does not report missing-data patterns or sensitivity analyses. Confidence intervals quantify sampling uncertainty under a specified analysis; they do not incorporate every possible source of bias or uncertainty in study conduct.

12. 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 figures are planning illustrations derived from the observed effect, not the trial's original design calculations. They are expressed as participants per arm, not as total events. The listed assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Each row considers detecting a stated fraction of the observed effect. The trial's own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design that would have an 80% probability of detecting the effect used in that row, if the planning assumptions and statistical model applied. The 90% power column gives the corresponding illustration for a 90% probability. These are design-planning concepts, not probabilities that the observed result is correct. This is not observed power.

The rows consider planning for 100%, 75%, and 50% of the observed effect. Because a smaller effect is harder to distinguish from random variation, the illustration requires more participants per arm as the assumed effect becomes smaller. The numbers depend on using the observed effect as a starting point, which means they are not an independent justification of the trial's actual enrollment. They do not account for unreported design features, missing data, multiplicity, or the sponsor's registered test unless those are incorporated in the stated planning assumptions.

The sample-size values should therefore be read as conditional illustrations of how enrollment needs can change with effect size and target power. They are not observed participant counts, and they do not demonstrate whether the completed study was adequately powered under its original plan. The original plan is not reported in the registry record.

13. How the Sample Size Is Derived

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

Formula

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

Worked calculation for this trial

1. Observed difference Δ = 66.400; pooled standard deviation σ = 30.477.
2. n = 2 × (1.96 + 0.842)² × 30.477² / 66.400² = 3.3, rounded up to 4 participants per arm for 80% power.

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

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- 66.4                      # observed difference in means
sigma <- 30.4767735958641                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

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

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(791765)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 4 (80% power), 5 (90% power)
 75% of observed effect: n per arm = 6 (80% power), 8 (90% power)
 50% of observed effect: n per arm = 14 (80% power), 18 (90% power)
power.t.test: 4.5 
Simulated power at n = 4 per arm: 0.729 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The registry's sponsor-reported primary analysis uses van Elteren's test for the two groups and reports p < 0.001. The unadjusted re-calculation instead uses the posted arm means and standard errors to estimate a mean difference of 66.4, with a 95% confidence interval from 55.61 to 77.19, and reports p < 0.001. The two p-values are not inconsistent: they arise from different statistical procedures and summaries.

A rank-based test evaluates the data differently from a comparison of arithmetic means. In addition, the registered test is described as van Elteren's test, while the re-calculation is explicitly unadjusted and based on summary statistics. The registry record does not report the strata used in the sponsor's test or enough individual-level information to reproduce it. The re-calculation is therefore a useful independent description of the size and uncertainty of the posted mean contrast, not a replacement for the registered analysis.

There is no discrepancy flag for this outcome. Where the sponsor's own analysis and a simple recalculation differ in method, the sponsor's analysis takes precedence as the registered inferential result. The recalculated estimate and interval should be identified as unadjusted and interpreted alongside, rather than in place of, the sponsor-reported test.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists four outcome measures and four analyses, including the primary endpoint and secondary outcomes. It does not report whether the statistical plan adjusted for testing multiple endpoints, multiple time points, or multiple comparisons. Without a stated procedure, the reported p-values for secondary outcomes should not be interpreted as if family-wise error or another multiplicity criterion had necessarily been controlled. A small p-value from an individual secondary analysis is evidence under that specific test, but testing more outcomes increases the chance of at least one apparently significant result under a global null.

The record identifies the primary population as the intention-to-treat population consisting of randomized patients with available data and says LOCF imputation was used. This is an important qualification: the analysis population is not described simply as every randomized participant with an observed Week 12 result. The amount of missing data, reasons for missingness, timing of last observations, and arm-specific missingness are not reported in the registry record.

LOCF carries forward the last recorded measurement for a participant with later missing data. In general, this approach assumes the carried-forward value is an adequate substitute for the unobserved value at the analysis time. That assumption may not match the course of an outcome, especially if it changes after the last observed visit. The registry record does not report sensitivity analyses using alternative missing-data methods, so the robustness of the result to the imputation choice cannot be assessed from the posted details.

The record also does not report the original statistical analysis plan, the timing of any interim analyses, or sample-size justification. It does not specify any multiplicity strategy, beyond naming the reported tests. These absences should not be filled by assumptions about common trial practice. They limit evaluation of whether all planned analyses are represented and how the inferential error rate was managed across outcomes.

16. 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 serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cholecystitis (1.7%), cholelithiasis (1.7%), metastatic malignant melanoma (1.7%), fall (1.6%), rib fracture (1.6%).

The registry reports serious adverse events affecting 1 participant among 62 at risk in the placebo-first group and 2 participants among 59 at risk in the etanercept-first group. These are counts of participants with serious adverse events, not a complete description of event duration, severity grading, relatedness, or timing. The registry record does not report deaths for these groups.

Other adverse events affected 25 participants among 62 at risk in the placebo-first group and 27 among 59 at risk in the etanercept-first group. These counts are distinct from the serious adverse event counts. The record lists cholecystitis, cholelithiasis, metastatic malignant melanoma, fall, and rib fracture among the top serious adverse event terms, with percentages as posted in the registry. It does not specify in this summary which arm each listed term occurred in, and the terms should not be assigned to a particular treatment group without that information.

Safety counts are descriptive. They do not by themselves establish whether an event was caused by a treatment, and small numbers can provide limited information about uncommon events. The treatment sequences also changed after Week 12, so timing matters when interpreting events across the full study. The registry record does not report enough detail to compare event rates by exposure period or make causal judgments.

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

The posted primary results show different Week 12 mean percentage-change values between the randomized groups: 20.4 for placebo twice per week during the initial period and 86.8 for etanercept 50 mg twice per week during that period. The unadjusted mean difference is 66.4, with a 95% confidence interval from 55.61 to 77.19. The sponsor-reported van Elteren test has p < 0.001. These statistics describe a strong separation in the posted primary outcome data under the stated analyses.

They do not, by themselves, establish the clinical importance of the difference. The registry record does not report a threshold for a clinically meaningful PSSI change. Nor do the summary results show how outcomes were distributed among individuals, whether the difference was similar across participant subgroups, or how it relates to outcomes not measured. A group mean and a p-value cannot answer all of those questions.

The finding concerns PSSI at Week 12 in participants with moderate to severe plaque psoriasis and scalp involvement, under the randomized comparison of the initial treatment period. It should not be generalized automatically to later periods, other psoriasis populations, other treatment schedules, or outcomes outside the scalp measure. After Week 12, the groups followed different treatment sequences from those used in the initial comparison, and the placebo-first group switched to etanercept.

The registry describes an intention-to-treat population with available data and LOCF imputation. Missing-data patterns and sensitivity analyses are not reported, so it is not possible to assess from this record how different missing-data assumptions might change the estimate. The primary registered inferential result and the unadjusted recalculation also use different methods and should retain their separate labels.

These results are statistical evidence about the measured endpoint in this trial, not medical advice and not a complete account of benefit, risk, or long-term outcomes. The record's adverse-event counts provide descriptive safety information, but do not establish causation. A full judgment about treatment decisions requires broader evidence and clinical context beyond these trial summaries.

18. Why This Trial Matters Statistically

This study illustrates why the estimand and measurement scale matter. Its primary endpoint is percentage change in a scalp-specific severity index, not a general measure of psoriasis across all body areas. Understanding what the PSSI includes and excludes helps keep the interpretation aligned with the question actually studied.

It also illustrates the distinction between a registered analysis and a summary-statistic recalculation. The sponsor reports a van Elteren test, while the simple recalculation reports a mean difference and confidence interval. Both provide relevant information, but they address the data through different procedures. Reporting the method alongside the result prevents a numerical estimate from being mistaken for a reproduction of the registered test.

The trial further shows why significance and precision are not the same as clinical importance. A small p-value indicates evidence against a specified null under the test assumptions; a confidence interval describes uncertainty in an effect estimate. Neither supplies a threshold for meaningful change. That threshold is not reported in the registry record.

Finally, the registry's use of LOCF, its available-data description, and the absence of posted missingness details demonstrate how analysis choices affect interpretation. Secondary outcomes, multiple testing, later treatment switching, and descriptive adverse-event counts each require their own context. A statistical reading that keeps these issues distinct gives a more accurate account than treating one significant result as a complete summary of the trial.

19. 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 outcome analysis is described as intention-to-treat among randomized patients with available data, with LOCF imputation. The registry record does not give the number of missing observations, their reasons, when they occurred, or the results of sensitivity analyses. Therefore, the effect of missing data and the imputation approach on the primary estimate cannot be evaluated from the posted details.

The registered primary test is van Elteren's test, but the registry record does not describe its strata or other implementation details. The recalculated mean difference and confidence interval are unadjusted summary-statistic calculations and should not be treated as a reconstruction of the registered test. The record also does not provide the original analysis plan or sample-size justification, so the intended handling of covariates, analysis populations, and other design assumptions is not known.

Multiplicity control is not reported. The registry lists several outcomes, but it does not state whether secondary testing was adjusted or sequenced. Consequently, secondary p-values should be treated cautiously, particularly when considered apart from the primary endpoint. Numeric secondary results are not available for every listed outcome in the record analyzed.

The study's treatment sequences change after Week 12. That makes the primary Week 12 comparison distinct from later comparisons, when the placebo-first group receives etanercept. Later outcomes cannot be interpreted as the same placebo-controlled contrast without additional analysis details. The registry record also does not report a clinical-importance threshold for PSSI, limiting interpretation of the practical size of the primary difference.

Safety information is presented as counts, with no deaths reported in the record and limited detail on event timing, relatedness, or arm attribution for the listed serious-event terms. These data do not support causal attribution or detailed comparisons of safety by exposure period. The record's population and outcomes are specific to moderate to severe plaque psoriasis with scalp involvement, limiting generalization beyond that setting.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Moderate to Severe Plaque Psoriasis With Scalp Involvement — NCT00791765.
• Registry record last updated 2014-07-23; status last verified 2014-07.
• Results first posted 2013-11-07.
• 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.

23. Record Summary

This completed Phase 4 randomized, quadruple-masked, parallel-group, placebo-controlled study evaluated etanercept for scalp involvement in moderate to severe plaque psoriasis. Enrollment was 124. The primary outcome was percentage change from baseline in PSSI at Week 12, with the registry describing an intention-to-treat population with available data and LOCF imputation.

The posted Week 12 means were 20.4 for placebo BIW followed by etanercept and 86.8 for etanercept 50 mg BIW followed by etanercept. The sponsor-reported van Elteren test gave p < 0.001. The unadjusted recalculated mean difference was 66.4, with a 95% confidence interval from 55.61 to 77.19. Secondary outcomes include PSSI response, later PSSI change after switching, and treatment satisfaction; multiplicity handling and several analysis details are not reported in the registry record.