Efficacy and Safety Study of Two Doses of Apremilast (CC-10004) In Japanese Patients With Moderate-To-Severe Plaque-Type Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety Study of Two Doses of Apremilast (CC-10004) In Japanese Patients With Moderate-To-Severe Plaque-Type Psoriasis (NCT01988103), a randomized phase 2 study. The primary outcome is Percentage of Participants Who Achieved a 75% Improvement (Response) From Baseline in the Psoriasis Area and Severity Index (PASI-75) at Week 16.

2. Clinical Question

3. Trial Design

The registry describes a Phase 2B, multicenter, randomized, double-blind, placebo-controlled study with a parallel-group model and quadruple masking. The stated purpose was to assess the clinical effectiveness and safety of two orally administered apremilast doses compared with placebo in Japanese patients with moderate-to-severe plaque-type psoriasis. The registry lists an enrollment of 254 and records the study as completed. The recorded start date is 2013-07-09, and the primary completion date is 2014-11-20.

The three groups received apremilast 20 mg BID, apremilast 30 mg BID, or placebo BID. The placebo arm description specifies 16 weeks of placebo followed by blinded re-randomization to apremilast 20 mg or 30 mg BID for 52 weeks. The safety record includes both Weeks 0-16 groups and longer-duration apremilast groups through Weeks 0-68. Those later groups reflect the registry’s treatment descriptions and should not be read as a continuing placebo comparison.

The main efficacy comparison is at Week 16. The registry defines the primary analysis population as randomized participants who received at least one dose of investigational product, analyzed according to randomized group. Missing primary endpoint values were handled with LOCF. The original sample-size justification, planned statistical model details beyond the analyses reported, allocation ratio, interim-analysis plans, and planned multiplicity strategy are not reported in the registry record. The trial’s completion status does not resolve those missing design details.

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: Treatment assignments were stratified according to whether the participants had a psoriatic arthritis (PsA) diagnosis by Classification Criteria for Psoriatic Arthritis (CASPAR) criteria (yes/no) at screening, whether they participated in the sparse pharmacokinetic (PK) sampling, and whether they had participated in the intensive PK sampling.

Placebo-Controlled Phase Week 0-16

Reasons for not completing this period:

Active Treatment Phase (Weeks 16-68)

Reasons for not completing this period:

Observational Follow-up Phase

Analysis population for the primary outcome, as defined in the registry: mITT consisted of all participants who were randomized and received at least one dose of IP. Participants were included in the treatment group in which they were randomized. Missing values were imputed using the Last observation carried forward (LOCF) method.

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.

Population: Modified Intent-to-treat Population = (mITT) population consisted of all participants who were randomized and received at least one dose of investigational product (IP). Participants were included in the treatment group in which they were randomized.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Who Achieved a 75% Improvement (Response) From Baseline in the Psoriasis Area and Severity Index (PASI-75) at Week 16, measured over Baseline to Week 16.

The primary endpoint is the percentage of participants who achieved PASI-75 at Week 16: at least a 75% reduction from baseline in PASI score. PASI combines lesion redness (erythema), thickness, scaling, and the extent of affected skin across the head, trunk, upper limbs, and lower limbs. Its score ranges from 0 to 72, with higher scores indicating greater disease severity. The registry states that the score was set to missing if a severity score or affected-area assessment was missing.

A response threshold converts a continuous severity measure into a clear event: a participant either meets the specified reduction criterion or does not. The resulting percentage is readily interpretable as the share meeting that threshold, although it does not describe the full distribution of PASI changes or how far above or below the threshold individual participants were. The chosen endpoint therefore captures a substantial improvement criterion, rather than every possible change in disease severity.

In general, a prespecified clinical endpoint helps focus a trial’s main comparison and reduces the risk that the principal conclusion is selected after results are known. Whether this endpoint was designated in advance in the original protocol, and the rationale for selecting this particular threshold, are not reported in the registry record. The posted definition and analysis population should guide interpretation of the reported percentages.

7. Results Posted in the Registry

• Apremilast 20mg: 23.5% (20/85) versus 7.1% (6/84) on control; risk difference 16.4 percentage points (95% CI 5.8 to 27.0), risk ratio 3.29 (1.39–7.79); unadjusted two-proportion z-test p = 0.003.
• Apremilast 30mg: 28.2% (24/85) versus 7.1% (6/84) on control; risk difference 21.1 percentage points (95% CI 10.1 to 32.1), risk ratio 3.95 (1.70–9.18); unadjusted two-proportion 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 Who Achieved a Static Physician's Global Assessment (sPGA) Score of Clear (0) or Almost Clear (1) With at Least 2 Point Reduction From Baseline to Week 16

• 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:
  • Apremilast 20mg: 23.9% (17/71) versus 8.8% (6/68) on control; risk difference 15.1 percentage points (95% CI 3.1 to 27.1), risk ratio 2.71 (1.14–6.47); unadjusted two-proportion z-test p = 0.016.
  • Apremilast 30mg: 29.6% (21/71) versus 8.8% (6/68) on control; risk difference 20.8 percentage points (95% CI 8.2 to 33.3), risk ratio 3.35 (1.44–7.80); unadjusted two-proportion z-test p = 0.002.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Apremilast 20mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Apremilast 30mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent Change From Baseline in the Psoriasis Affected Body Surface Area (BSA) at Week 16

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Apremilast 20mg: mean -21.60 versus 7.50 on control; difference -29.10 (95% CI -44.46 to -13.74), standardized effect d = -0.57; z-test p = <0.001.
  • Apremilast 30mg: mean -30.50 versus 7.50 on control; difference -38.00 (95% CI -53.34 to -22.66), standardized effect d = -0.75; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Apremilast 20mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Apremilast 30mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent Change From Baseline in the Psoriasis Area and Severity Index (PASI) Score

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Apremilast 20mg: mean -33.10 versus -3.70 on control; difference -29.40 (95% CI -44.73 to -14.07), standardized effect d = -0.58; z-test p = <0.001.
  • Apremilast 30mg: mean -43.10 versus -3.70 on control; difference -39.40 (95% CI -54.71 to -24.09), standardized effect d = -0.78; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Apremilast 20mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Apremilast 30mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists a range of secondary measures, including skin assessment, affected body surface area, PASI change, itch, quality of life, physical and mental health summaries, and an arthritis response criterion. The posted numerical results available for several secondary measures include sPGA response, body surface area change, and PASI change. Across those measures, the group summaries generally follow a pattern in which the apremilast groups differ from placebo in a direction consistent with improvement. This broad pattern is supportive context for the primary PASI-75 result, but it is not a substitute for the primary endpoint and does not establish that every secondary outcome had the same result.

Secondary outcomes can illuminate different dimensions of disease and patient experience. A threshold response, an average change, a symptom scale, and a quality-of-life measure answer different questions and should not be treated as interchangeable. Nor should consistency across outcomes be taken to mean that all were independently confirmed: outcomes may be related, may be measured in different analysis populations, and may have different statistical properties.

Many outcomes and comparisons create a multiplicity concern. In general, the more hypotheses examined, the greater the chance that some results will appear statistically persuasive by chance if no adjustment or prespecified hierarchy is used. The registry does not report a multiplicity adjustment or complete testing hierarchy. Consequently, unadjusted secondary p-values carry less weight than the designated primary result and should be interpreted as exploratory or supportive rather than as a set of definitive independent findings. The original analysis plan and the full results for every listed secondary measure are not reported in the registry record.

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

• Percentage of Participants Who Achieved a Static Physician's Global Assessment (sPGA) Score of Clear (0) or Almost Clear (1) With at Least 2 Point Reduction From Baseline to Week 16
• Percent Change From Baseline in the Psoriasis Affected Body Surface Area (BSA) at Week 16
• Percent Change From Baseline in the Psoriasis Area and Severity Index (PASI) Score
• Percentage of Participants Who Achieved a 50% Improvement From Baseline (Response) Reduction in the PASI-50 at Week 16
• Change From Baseline in Pruritus Visual Analogue Scale 100-mm (VAS) at Week 16
• Change From Baseline in the Dermatology Life Quality Index (DLQI) Total Score at Week 16
• Change From Baseline in Mental Component Summary (MCS) Score of the Medical Outcome Study Short Form 36-item (SF-36) Health Survey Version 2.0 at Week 16
• Number of Participants Who Achieved an American College of Rheumatology Criteria (ACR) 20% Improvement (ACR 20)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is binary at the participant level: PASI-75 response is either achieved or not achieved by Week 16. The arm summaries are percentages, and the main contrasts compare each apremilast dose with placebo. In general, an absolute risk difference is the response proportion in one group minus the response proportion in the comparator group. It keeps the contrast on the percentage-point scale, which can be easier to interpret than a relative measure. The sponsor’s reported differences are 16.4 percentage points for 20 mg versus placebo and 21.1 percentage points for 30 mg versus placebo.

How should the binary comparison be read?

The registry reports chi-squared analyses for the primary binary comparisons. A chi-squared test evaluates whether the observed distribution of responders and nonresponders is compatible with equal response proportions under its null hypothesis. The registry reports p = 0.003 for the 20 mg comparison and p < 0.001 for the 30 mg comparison. These tests do not measure the size or practical importance of a difference; the reported differences and confidence intervals supply complementary information.

The posted recalculation is an unadjusted comparison based on arm-level response counts and denominators. It is not the sponsor’s full analysis. The record flags a discrepancy between the recalculation and sponsor analyses, so the sponsor’s own analysis takes precedence. The registry’s reported chi-squared method and results should therefore be used when describing the sponsor’s inference. The registry does not report enough detail to determine the source of the discrepancy or to reproduce every aspect of the sponsor’s analysis.

What does a confidence interval add?

A confidence interval expresses uncertainty around an estimated contrast. In general, a narrower interval indicates greater precision under the statistical model, while a wider interval leaves a broader range of plausible values. The primary sponsor-reported 95% intervals run from 5.8 to 27.0 percentage points for 20 mg and from 10.1 to 32.1 percentage points for 30 mg. Both intervals lie above zero, consistent with the reported direction of the differences. The intervals still allow a range of effect sizes, so the point estimates should not be mistaken for exact or certain effects.

How are the continuous secondary measures analyzed?

The registry reports least-squares means and standard errors for percent change in body surface area and PASI score. It reports ANCOVA comparisons for these outcomes. In general, analysis of covariance (ANCOVA) compares groups while accounting for covariates specified in the model; the particular covariates and full model specifications are not reported in the registry record. The sponsor reports mean differences with 95% confidence intervals and p-values. Negative percent changes indicate reductions from baseline in the measure as defined, but interpretation of an adjusted comparison depends on the model and analysis population.

The independent recalculations for these continuous measures are approximate and unadjusted, using posted summary statistics. The spread information is reported as standard errors, and the recalculation uses an approximate pooled standard deviation. It is not a substitute for the sponsor’s ANCOVA. The sponsor-reported comparisons for body surface area and PASI should be read as the registry’s own inferential results; they are not interchangeable with a simple calculation from group summaries.

What do analysis population and missing-data handling imply?

The primary mITT population includes participants who were randomized and received at least one dose of investigational product. Participants remain assigned to the group in which they were randomized for analysis. The registry says missing primary endpoint values were imputed using LOCF, meaning the last observed value was carried forward to fill a later missing assessment. This is an analysis convention, not an observed Week 16 measurement. In general, imputation can affect estimates and uncertainty, particularly when missingness is related to outcomes. The amount and reasons for missing primary data, and sensitivity analyses using alternative missing-data assumptions, are not reported in the registry record.

The registry identifies a primary endpoint and several secondary outcomes but does not report the complete protocol or statistical analysis plan. Details such as covariate choices, model diagnostics, handling of all analysis deviations, and multiplicity control are not reported in the registry record. Those absences limit independent assessment of the full analysis, even though the main endpoint definition and sponsor-reported comparisons are available.

11. Confidence Intervals and Precision

The sponsor-reported 95% confidence interval for the 20 mg versus placebo primary comparison is 5.8 to 27.0 percentage points. For 30 mg versus placebo, it is 10.1 to 32.1 percentage points. Each interval excludes zero, but both cover a range of possible contrasts rather than identifying one exact effect. Their widths make clear that the observed estimates are not precise to a single value.

In general, a confidence interval is a measure of statistical uncertainty under the analysis assumptions; it is not a range that is guaranteed to contain the true effect, nor does it show the probability that any particular value is correct. The endpoints of the interval depend on the data and statistical method. The registry reports 95% intervals from the sponsor’s chi-squared analyses. Because the record flags a discrepancy with the simple recalculations, the sponsor’s intervals are the appropriate ones to use when reporting the sponsor analysis.

The primary arm percentages are based on the stated mITT approach and missing-value imputation. Precision in the reported contrast does not remove uncertainty about the consequences of LOCF, the original design assumptions, or the extent to which the results would generalize beyond the trial population. The registry does not report alternative missing-data analyses or a full statistical analysis plan. Those limitations are distinct from the width of the confidence intervals: an interval describes uncertainty within an analysis, whereas incomplete reporting limits assessment of the analysis choices themselves.

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 illustrations are planning calculations derived from the observed effect, not the trial’s original design assumptions. For these binary and continuous comparisons, the listed values are participants per arm, not total participants and not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. Time-to-event illustrations, if present, would instead report total events, but the comparisons discussed for these outcomes are not time-to-event calculations.

The 80% power column gives the illustrated participants per arm for a design with an 80% chance of detecting the selected effect under the stated assumptions, if that effect were the true one and the model assumptions held. The 90% power column gives the corresponding planning figure for a 90% chance. These are design-planning quantities, not probabilities that the trial result is correct or that a treatment will be beneficial.

Rows describing 100%, 75%, and 50% of the observed effect show how the planning estimate changes when the target effect is reduced. Smaller effects generally require more participants to distinguish them from random variation at the same significance level and power target. The original trial’s sample-size justification, planned effect size, power target, and related design assumptions are not reported in the registry record. These illustrations are not observed power: they are hypothetical planning calculations based on the observed effect, and they should not be used to infer the probability that the completed trial detected a real effect.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.071; treatment proportion p₁ = 0.235; average p̄ = 0.153.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5096 = 0.9988.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4962 = 0.4176.
4. n = (0.9988 + 0.4176)² / (0.1639)² = 74.7, rounded up to 75 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
p0 <- 0.0714285714285714                          # control proportion
p1 <- 0.235294117647059                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1988103)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 75 (80% power), 100 (90% power)
 75% of observed effect: n per arm = 119 (80% power), 159 (90% power)
 50% of observed effect: n per arm = 233 (80% power), 311 (90% power)
power.prop.test: 74.7 
Simulated power at n = 75 per arm: 0.820 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 reports sponsor analyses for the primary endpoint using chi-squared comparisons. For apremilast 20 mg versus placebo, the reported difference is 16.4 percentage points, with a 95% confidence interval from 5.8 to 27.0 and p = 0.003. For apremilast 30 mg versus placebo, the reported difference is 21.1 percentage points, with a 95% confidence interval from 10.1 to 32.1 and p < 0.001.

The separate recalculations are simple, unadjusted checks using posted summary statistics. The registry record flags a discrepancy between those calculations and the sponsor’s analyses. Accordingly, the sponsor’s own analysis takes precedence. The recalculations should not be presented as if they reproduce the sponsor’s method or replace the sponsor-reported confidence intervals and p-values. The registry does not report the reason for the discrepancy or enough detail to reconcile every analytic difference.

For the continuous secondary measures, the registry reports ANCOVA results, while the independent recalculations are approximate and unadjusted. The sponsor’s ANCOVA results are the relevant posted analyses for those outcomes. In general, a calculation from summary statistics may not match an adjusted model because the model can incorporate covariates and other details not recoverable from group-level summaries. The covariates and complete model specifications are not reported in the registry record, so no more specific explanation of any difference is warranted.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies PASI-75 at Week 16 as the primary endpoint and lists numerous secondary outcomes. It reports sponsor p-values for the primary comparisons and for some secondary comparisons, but the multiplicity strategy is not reported in the registry record. It is therefore not possible from the registry record to determine whether the sponsor controlled the overall false-positive risk across the dose comparisons and the many secondary outcomes, used a prespecified testing sequence, or treated secondary analyses as exploratory.

In general, testing multiple hypotheses without adjustment increases the chance that at least one result will appear statistically significant by chance. Adjustments and hierarchical testing can address that issue, but they may change the interpretation of individual p-values. The unadjusted recalculations are descriptive statistical checks and should not be mistaken for a prespecified multiplicity-controlled analysis. The sponsor-reported primary comparisons remain the main registry analyses, while secondary results require more caution when no adjustment strategy is documented.

The primary endpoint description specifies an mITT analysis population: randomized participants who received at least one dose of investigational product, analyzed in their randomized groups. Missing values were imputed using LOCF. The registry does not report the number or pattern of missing primary endpoint observations, the reasons for missingness, or sensitivity analyses under alternative assumptions. It also does not report a complete account of analysis populations for every secondary outcome, protocol deviations, or how missing values were handled for all secondary measures.

LOCF carries the last observed value forward to a later missing assessment. In general, this assumes that the carried value is a suitable stand-in for the unobserved outcome, which may not hold in every circumstance. The direction and magnitude of any resulting influence cannot be determined without further information. The original protocol, complete statistical analysis plan, interim-analysis details, and original sample-size justification are not reported in the registry record. These reporting gaps limit evaluation of prespecification and robustness; they do not, on their own, show that the reported analyses are invalid.

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: cholelithiasis (1.7%), coronary artery stenosis (1.2%), arthritis bacterial (1.2%), cerebral haemorrhage (1.2%), periodontitis (0.8%).

The registry reports serious adverse event counts by treatment period. For Weeks 0-16, the counts are 0 in the placebo group, 4 in the apremilast 20 mg BID group, and 0 in the apremilast 30 mg BID group. For the Weeks 0-68 apremilast groups, the counts are 11 for 20 mg BID and 2 for 30 mg BID. These are counts of participants with serious adverse events as reported, not estimates of comparative risk adjusted for exposure or follow-up.

The early-period groups and the longer-period groups differ in treatment duration and group composition. The registry describes participants assigned to placebo as being re-randomized after 16 weeks to apremilast, so the Weeks 0-68 apremilast summaries should not be read as a direct placebo-controlled comparison. The record does not report deaths in the listed groups; death counts are not reported in the registry record.

In general, safety counts need context about event definitions, exposure time, follow-up, and whether participants can experience more than one event. The registry lists serious-event terms with reported percentages, including cholelithiasis, coronary artery stenosis, arthritis bacterial, cerebral haemorrhage, periodontitis, and increased intraocular pressure. The available summary does not establish comparative causation, and the counts alone do not determine the overall safety profile.

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

The posted primary result describes the proportion meeting a defined PASI response threshold at Week 16 in this randomized study. The sponsor-reported comparisons show higher response percentages in the two apremilast groups than in the placebo group, with reported confidence intervals above zero. This is a statistical description of the trial’s results under the registry-reported analysis; it is not a conclusion that a particular treatment is appropriate for an individual or that the same result will occur in other settings.

The endpoint captures participants who achieved at least a 75% reduction in PASI score. It does not show the distribution of all score changes, the experience of participants who did not reach the threshold, or the effect on every symptom or aspect of daily life. Secondary measures may add context, but the registry does not report complete results for every outcome listed. The primary result also concerns Week 16, not the full longer-term course.

Statistical significance and clinical importance are different questions. A p-value addresses compatibility with a null hypothesis under a statistical model; it does not quantify how meaningful a difference is to patients. The registry record does not report a threshold for clinically important between-group differences. Confidence intervals communicate uncertainty about the estimates, while missing-data assumptions and incomplete reporting of the analysis plan add further interpretive limits.

The study enrolled Japanese patients with moderate-to-severe plaque-type psoriasis. Generalization to people outside that population, other clinical settings, or different treatment durations is not established by these results alone. The safety counts are descriptive and arise from groups with different follow-up periods; they should not be used to infer a causal safety comparison. The record is a source of trial information, not individualized medical guidance.

18. Why This Trial Matters Statistically

This trial is statistically informative because it compares two active dose groups with placebo using a clearly defined response threshold and reports sponsor estimates with confidence intervals. The primary endpoint is understandable as a proportion achieving a specified reduction in PASI score, while the confidence intervals make uncertainty around the group contrasts visible. Looking at both dose comparisons also shows why effect estimates and uncertainty matter alongside p-values.

The record also illustrates the distinction between sponsor analyses and simple recalculation from posted group summaries. A recalculation can be useful as an independent check, but it may not reproduce an analysis using the sponsor’s methods. Because this record flags a discrepancy, the sponsor’s analysis takes precedence. For continuous secondary outcomes, reported ANCOVA analyses and approximate unadjusted calculations are also not equivalent. The distinction is important for readers who might otherwise treat every number derived from a summary as a replication of the original analysis.

The study offers a setting for considering analysis populations, imputation, multiple outcomes, and follow-up. The primary analysis uses an mITT definition and LOCF for missing values, while the registry does not report missingness details, alternative analyses, or a complete multiplicity plan. Secondary results can provide coherence across measures, but without a stated testing strategy their evidential strength is more limited.

Finally, safety summaries spanning different treatment periods show why counts require exposure and design context. A count in a longer follow-up group cannot be directly compared with a count from the initial placebo-controlled period as if follow-up were identical. These features make the study useful for statistical interpretation while also making transparent reporting essential.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several limitations specific to this record affect interpretation. The primary endpoint uses LOCF for missing values, but the number and pattern of missing assessments, reasons for missingness, and sensitivity analyses are not reported in the registry record. The extent to which this imputation choice influences the primary estimate therefore cannot be assessed from the record alone.

The registry reports sponsor analyses and separate unadjusted recalculations, and it flags a discrepancy. The sponsor analysis takes precedence, but the record does not explain the discrepancy or provide enough detail to independently reconstruct the complete sponsor analysis. The full statistical analysis plan, covariate specifications for ANCOVA, and original sample-size justification are not reported. Multiplicity handling across dose comparisons and secondary outcomes is also not reported.

The safety summaries use different treatment periods. Placebo follow-up is described through Week 16, with subsequent blinded re-randomization to apremilast, while longer-period safety groups are reported through Weeks 0-68. These summaries are not a uniform-duration head-to-head comparison. The record provides serious-event counts, but the listed summary does not provide enough information to characterize event timing, repeated events, or exposure-adjusted rates.

The primary endpoint is measured at Week 16 and applies to the defined mITT group. It does not alone describe longer-term efficacy, all listed secondary outcomes, or experience outside the studied Japanese population with moderate-to-severe plaque-type psoriasis. The registry record also does not report all details needed to assess every protocol or analysis decision. These are limits of the available record and should be kept distinct from the results that are reported.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Efficacy and Safety Study of Two Doses of Apremilast (CC-10004) In Japanese Patients With Moderate-To-Severe Plaque-Type Psoriasis — NCT01988103.
• Registry record last updated 2020-05-07; status last verified 2020-04.
• Results first posted 2020-03-20.
• 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

NCT01988103 is recorded as a completed Phase 2B, randomized, double-blind, placebo-controlled, parallel-group study with quadruple masking. It evaluated apremilast 20 mg BID and 30 mg BID against placebo in Japanese patients with moderate-to-severe plaque-type psoriasis. The registry lists enrollment of 254, a start date of 2013-07-09, and primary completion on 2014-11-20.

The primary endpoint was PASI-75 response at Week 16. The posted percentages were 7.1 for placebo, 23.5 for apremilast 20 mg, and 28.2 for apremilast 30 mg. Sponsor-reported comparisons were 16.4 and 21.1 percentage points, respectively, with reported 95% confidence intervals and p-values. Because the record flags a discrepancy with simple recalculations, the sponsor’s analyses take precedence.

The mITT population and LOCF handling are described, but missing-data sensitivity analyses, the original sample-size rationale, multiplicity strategy, and complete analysis plan are not reported in the registry record. Safety counts span different follow-up periods and should be interpreted descriptively.