Efficacy of Alitretinoin Treatment in Patients With Pustular Form of Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy of Alitretinoin Treatment in Patients With Pustular Form of Psoriasis (NCT01245140), a randomized phase 2 study. The primary outcome is Change From Baseline in the Palmo-plantar Pustulosis Psoriasis Area and Severity Index (PPPASI) Score at the End of Treatment (EOT) (Week 24) or at the Last Assessment.

2. Clinical Question

3. Trial Design

The registry describes a phase 2, randomized, parallel-group trial with quadruple masking. The interventions were alitretinoin and matching placebo. The study is listed as completed, with enrollment of 33. Its recorded start date is 2011-04-26 and its primary completion date is 2014-03-12. The registry identifies Stiefel, a GSK Company, as the sponsor.

The primary outcome was change from baseline in the palmo-plantar pustulosis psoriasis area and severity index (PPPASI) score at the end of treatment (EOT), defined as Week 24, or at the last assessment. The stated primary population was treated participants with at least one efficacy result after receiving study medication. The primary-outcome analysis lists 9 participants in the matching-placebo group and 22 in the alitretinoin group.

Those analysis counts differ from the arm descriptions, which state that 10 patients were to receive placebo and 20 were to receive alitretinoin. The safety figures also use different group counts: 9 for matching placebo and 24 for alitretinoin. The reasons for these differing counts are not reported in the registry record. The listed enrollment of 33 should therefore not be treated as the denominator for every outcome.

The registry lists 25 outcome measures and 8 analyses. Among the secondary outcomes are pustule counts, modified psoriasis area severity index (mPASI) scores and responses, nail psoriasis severity index (NAPSI) scores, and adverse events. The record does not report the full protocol, allocation ratio, treatment duration beyond the primary outcome timeframe, or details of the masking procedures. Those design details are not reported in the registry 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.

Before assignment: The total study duration was 33 weeks, with a Screening Period of up to 4 weeks, followed by 24 weeks of treatment and a 5-week safety Follow-up Period. Participants who met eligibility criteria were randomized (2:1) to receive 30 milligrams (mg) alitretinoin or matching placebo, given orally as gelatin capsules, once daily (QD) for up to 24 weeks.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set : treated participants with \>=1 efficacy result after receiving study medication.

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 Change From Baseline in the Palmo-plantar Pustulosis Psoriasis Area and Severity Index (PPPASI) Score at the End of Treatment (EOT) (Week 24) or at the Last Assessment, measured over Baseline and EOT (Week 24) or the last assessment.

The primary endpoint is change from baseline in PPPASI score at EOT (Week 24) or at the last assessment. The PPPASI is a clinical severity score for palmo-plantar pustulosis. Investigators score erythema, total pustule count, and desquamation on a 5-point scale for each palm and sole. Scores are adjusted for the area involved, based on a 7-point scale, and for whether the site is a palm or sole. The four site-specific scores are added to produce a total from 0, meaning no PPP, to 72, meaning most severe PPP.

Change is defined as the EOT or last-assessment value minus the baseline value. Thus, a negative change represents a lower score at follow-up than at baseline. That direction describes the score’s arithmetic meaning; it does not alone establish why the score changed or whether the change is attributable to treatment.

A severity index brings several clinical features into one outcome, allowing the trial to compare group-level changes in disease severity rather than relying on a single feature such as pustule count. This is a general statistical reason to use a composite score. Interpretation also depends on how consistently the components are assessed and how meaningful a given score change is clinically. A threshold for a clinically important PPPASI change is not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous: it is a score measured on a scale, and the reported summary is a mean with standard deviation. For a continuous outcome, the mean describes the group’s average score change, while the standard deviation describes the spread of individual observations around that group mean. These answer different questions. A mean change can be near another group’s mean even when participant-level changes vary widely, as the reported standard deviations indicate.

What does the ANCOVA estimate represent?

The registry reports an analysis of covariance (ANCOVA) and labels its result a mean difference (net). In general, ANCOVA compares group outcomes while adjusting for one or more variables in a statistical model. Baseline outcome values are commonly relevant in trials of change, but the covariates actually included in this trial’s model are not reported in the registry record. It is therefore not possible to describe the specific adjustment or reproduce the sponsor’s model from the registry entry.

The ANCOVA estimate is the trial’s reported comparison between groups, not simply a restatement of the two descriptive means. Its value is 0.573, with a 95% confidence interval from -30.974 to 32.120. Since the interval crosses zero, the data do not identify a clearly positive or negative net difference at the stated confidence level. Its breadth signals imprecision. General statistical interpretation: a narrow interval would indicate greater precision than a broad interval, conditional on the model and assumptions.

How should the p-value be read?

The reported p-value is 0.971. In general, a p-value measures how unusual data at least as incompatible with the null hypothesis as those observed would be if that null hypothesis and the statistical model were correct. It is not the probability that the null hypothesis is true, the probability that the result arose by chance, or a measure of clinical importance. The p-value should be considered with the effect estimate, confidence interval, study size, outcome variability, and analysis assumptions.

Why does outcome variability matter?

The standard deviations are 45.9 for matching placebo and 32.8 for Alitretinoin 30 mg. Standard deviation is a measure of spread, not uncertainty in the mean itself. In general, greater outcome variability makes it harder to estimate a group mean or a between-group contrast precisely, particularly when group sizes are limited. The reported interval is broad, and the registry’s analysis groups are small. The record does not report a variance model or diagnostics that would clarify whether the model accounted for any unusual outcome distribution.

Over-dispersion is a general concern when observed variation exceeds what a statistical model assumes. If present and not accommodated, it can make standard errors too small and confidence intervals too narrow. The endpoint is a bounded score rather than a count model outcome, and the registry does not report an assessment of over-dispersion. It should not be assumed either that over-dispersion occurred or that it was evaluated.

What does randomization contribute?

Random allocation is intended, in general, to make groups comparable at the point of assignment with respect to both measured and unmeasured characteristics. It does not guarantee balance in a particular small trial, nor does it remove uncertainty from estimates. The allocation sequence method, concealment procedures, and realized baseline balance are not reported in the registry record. The word randomized describes the recorded design but does not supply those additional details.

Masking can, in general, reduce the influence of expectations on treatment delivery, assessment, or reporting. The registry records quadruple masking, but does not identify which participants, investigators, assessors, or other roles were masked, or how masking was maintained. No further inference about the masking process is warranted from the label alone.

What can a planning illustration tell readers?

Sample-size calculations are planning illustrations, not observed power. In general, such illustrations depend on assumptions about the effect to detect, variability, allocation, significance level, and statistical method. The stated planning assumptions for this trial’s illustration are a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the effect expressed as a fraction of the observed effect. Those assumptions describe the illustration, not necessarily the trial’s original design. The trial’s own sample-size justification is not reported in the registry record. Numerical planning results are not reported in the registry record.

Any planning estimate based on the observed effect is especially dependent on that estimate’s uncertainty. It should not be interpreted as evidence that the trial had a particular probability of detecting a true effect. The registry does not report the original target effect, a formal power calculation, or the rationale for the enrolled sample size.

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("Matching Placebo", "Alitretinoin 30 mg")
n   <- c(9, 22)
m   <- c(-44.6, -45.2)
sp  <- c(45.9, 32.8)
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  Matching Placebo  9  -44.600  45.900  -79.882  -9.318
CARM  Alitretinoin 30 mg  22  -45.200  32.800  -59.743  -30.657

11. Analyses Reported by the Sponsor

The registry’s reported primary comparison is the sponsor’s ANCOVA result: a net mean difference of 0.573, with a 95% confidence interval from -30.974 to 32.120 and p = 0.971. The registry also lists unadjusted arm summaries: means of -44.6 for matching placebo and -45.2 for Alitretinoin 30 mg, with standard deviations of 45.9 and 32.8. Those descriptive values are not a substitute for the reported ANCOVA estimate.

No discrepancy is flagged between the sponsor’s analysis and a recalculation in the registry record. A separate unadjusted recalculation is not reported in the registry record. Consequently, there is no alternative calculated estimate to set against the sponsor’s model-based result. The sponsor’s own analysis remains the reported inferential comparison.

The ANCOVA model’s covariates, assumptions, and handling of missing outcomes are not reported in the registry record. The estimate and interval can be described as posted, but cannot be independently reproduced from the information recorded. The confidence interval’s breadth should remain central to interpretation: the point estimate is not precise enough to rule out materially different values on the PPPASI scale.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists 25 outcome measures and 8 analyses, including secondary measures of pustule count, mPASI, NAPSI, and adverse events. Testing or estimating multiple outcomes creates a general multiplicity concern: when many statistical questions are considered, the chance of at least one apparently notable result can increase. The registry record does not report a multiplicity adjustment, a hierarchy of hypotheses, or which outcomes were designated confirmatory beyond identifying the primary endpoint. It is therefore not possible to determine how the secondary analyses were intended to contribute to confirmatory conclusions.

The primary population is described as treated participants with at least one efficacy result after receiving study medication. This definition identifies who could enter the analysis, but does not explain how participants without an efficacy result were handled, how many had missing measurements, or why measurements were absent. The endpoint permits use of the last assessment when EOT data are unavailable, but the imputation or analysis procedure for such cases is not reported in the registry record. Last assessment should not be assumed to be equivalent to a prespecified missing-data method.

Missing-data assumptions matter because observed outcomes may differ from outcomes that would have been recorded if assessments were complete. In general, analyses can produce different estimates depending on whether missingness is related to treatment, outcome severity, or other factors, and on the assumptions used to address it. The registry record does not report sensitivity analyses or enough detail to assess the robustness of the primary estimate to missing data.

The recorded enrollment is 33, while arm descriptions state 20 patients for alitretinoin and 10 for placebo. Primary efficacy counts are 22 and 9, and safety counts are 24 and 9. These denominators differ across the record. The reasons are not reported in the registry record, so they should not be reconciled by assumption. The analysis population, safety population, and enrollment count are distinct figures in the posted information.

13. 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: dizziness (4.2%).

The registry reports serious adverse events in 0 of 9 participants at risk in the matching-placebo group and 1 of 24 participants at risk in the Alitretinoin 30 mg group. For other adverse events, it reports 8 of 9 at risk in the placebo group and 16 of 24 at risk in the alitretinoin group. These counts are descriptive safety summaries; they are not the primary efficacy endpoint.

The record lists Dizziness as a top serious-event term at 4.2%. It does not report enough context in the available entry to connect that term to a particular group or explain its relationship to the serious-event count. Deaths are not reported in the registry record.

Serious adverse events and other adverse events are different categories, and the counts should not be combined. With these group sizes, the summaries provide limited information about uncommon events. In general, absence of a reported event in a small group does not establish that the event cannot occur, and a difference in counts alone does not establish a causal relationship to treatment. The registry entry does not report event-level narratives, exposure-adjusted rates, or a detailed account of severity and relatedness for each event.

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

The primary results show negative mean PPPASI changes in both analyzed groups and a sponsor-reported ANCOVA net mean difference of 0.573. The 95% confidence interval, from -30.974 to 32.120, spans zero and is broad. The p-value is 0.971. Together, these figures indicate that the posted analysis does not estimate a precise difference between groups. They do not establish that the groups are equivalent or that the true difference is zero.

The endpoint measures change in a clinical severity score, with lower values representing less severity on the score’s scale. A negative group mean change means that the average follow-up score was lower than the average baseline score. That within-group direction does not establish that the intervention caused the change: the placebo group also had a negative mean change, and the comparative question is addressed by the between-group analysis.

The confidence interval includes a range of possible net differences, including values in either direction. General statistical interpretation: uncertainty about an estimate is not evidence that every value in the interval is equally plausible, nor does the interval describe individual participant responses. Its width means that the posted data do not pin down the magnitude of the comparative effect with high precision.

The registry record does not provide a clinically important PPPASI threshold, detailed missing-data methods, the ANCOVA covariates, or the original sample-size justification. Without those details, the clinical importance of the estimated contrast and the robustness of the model cannot be fully assessed. The record also gives different participant counts across arm descriptions, efficacy analyses, and safety summaries, without explaining the differences.

Accordingly, the result should be read as a report of one trial’s posted primary analysis, not as a definitive answer about treatment effectiveness. It describes the analyzed groups, outcome, and model estimate, while leaving uncertainty about precision, analysis details, and the interpretation of secondary outcomes.

15. Why This Trial Matters Statistically

This trial is statistically informative because it illustrates why a comparison should be read through its estimate and uncertainty, rather than through a p-value alone. The reported ANCOVA estimate is 0.573, but its 95% confidence interval extends from -30.974 to 32.120. That interval is broad and spans zero. Readers can see both the model’s point estimate and the extent to which the data leave the size and direction of the net difference uncertain.

The study also shows why descriptive change within each group is not the same as a treatment comparison. The placebo and alitretinoin groups both have negative average PPPASI changes. The question of comparative difference is addressed by the reported net mean difference, not by treating change from baseline in either arm as proof of a treatment effect.

Its participant counts highlight the importance of identifying the analysis population for each outcome. Enrollment, planned arm descriptions, efficacy analysis counts, and safety denominators do not match exactly in the registry record. Without an explanation, readers cannot assume that every outcome used the same participants or that the differences have a particular cause.

Finally, the entry provides an opportunity to distinguish reported design labels from detailed methods. Randomization and quadruple masking are recorded, but the sequence, concealment, masking roles, model covariates, and missing-data procedures are not. Such details matter when assessing how a statistical estimate was produced and how robust it may be. These limitations do not erase the reported result; they define what can and cannot be concluded from the registry record.

16. 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 efficacy analysis includes 22 participants in the alitretinoin group and 9 in the placebo group, while the arm descriptions state 20 and 10, respectively. The safety denominators are 24 and 9. Enrollment is listed as 33. The registry does not explain these differences, which limits assessment of participant flow and the relationship between the assigned, treated, and analyzed populations.

The ANCOVA result is reported without the model covariates or enough specification to reproduce the analysis. The registry also does not report its missing-data method, the number of participants with missing endpoint data, or sensitivity analyses. Because the endpoint allows the last assessment as an alternative to EOT, details of how those observations were selected and analyzed would be relevant, but are not reported in the registry record.

The record does not report the trial’s original sample-size justification, a prespecified clinically important PPPASI difference, or a formal equivalence margin. The wide confidence interval therefore cannot be judged against a reported clinical threshold, and a nonsignificant result should not be interpreted as evidence of equivalence.

Although the record identifies the study as randomized and quadruple-masked, it does not report the allocation sequence or concealment procedures, who was masked, or how masking was maintained. It lists multiple outcome measures and analyses but does not report a multiplicity strategy or a hierarchy for interpreting the secondary outcomes. These omissions limit evaluation of potential bias, model assumptions, and the confirmatory status of secondary findings. They do not change the posted primary estimate, but they constrain how fully that estimate can be assessed.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Efficacy of Alitretinoin Treatment in Patients With Pustular Form of Psoriasis — NCT01245140.
• Registry record last updated 2017-12-21; status last verified 2017-11.
• Results first posted 2017-04-04.
• 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.

20. Record Summary

The registry describes a completed, randomized, parallel-group, quadruple-masked phase 2 study of oral alitretinoin versus matching placebo for palmo-plantar pustulosis. Enrollment is listed as 33. The primary endpoint was change from baseline in PPPASI score at EOT (Week 24) or at the last assessment, among treated participants with at least one efficacy result.

The primary analysis lists 9 participants in the placebo group and 22 in the Alitretinoin 30 mg group. Their mean changes were -44.6 and -45.2, respectively. The reported ANCOVA net mean difference was 0.573, with a 95% confidence interval from -30.974 to 32.120 and p = 0.971. The interval is broad and crosses zero, leaving substantial uncertainty about the comparative estimate.

The registry also reports adverse-event counts, but group denominators differ across efficacy and safety summaries. Reasons for the differing counts, model details, and missing-data procedures are not reported in the registry record.