Efficacy and Safety Study of Apremilast (CC-10004) in Subjects With Moderate-to-Severe Plaque-Type Psoriasis (Core Study): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety Study of Apremilast (CC-10004) in Subjects With Moderate-to-Severe Plaque-Type Psoriasis (Core Study) (NCT00773734), a randomized phase 2 study. The primary outcome is Core Study: Percentage of Participants Who Achieved a 75% Improvement (Response) in Psoriasis Area and Severity Index (PASI) at Week 16.

2. Clinical Question

The endpoint is a responder measure: each participant either met the PASI-75 threshold or did not. Comparing the percentage of responders gives a direct summary of how often the specified improvement threshold was reached in each randomized group. It does not describe the size of improvement among participants who fell short of the threshold, nor does it capture every aspect of psoriasis or treatment experience. The registry record also lists PASI response thresholds and assessment times as secondary outcomes, giving additional views of response that should be interpreted in light of their secondary status and the multiple analyses conducted.

3. Trial Design

The registry record identifies this as a phase 2B, multicenter, randomized, double-blind, placebo-controlled, dose-ranging, parallel-group study. It lists enrollment of 352 and a completed status. The recorded start date is 2008-09-01, and the primary completion date is 2009-08-01. The sponsor is Amgen.

During the 16-week placebo-controlled phase, participants were randomized to placebo or one of three twice-daily apremilast dose groups: 10 mg, 20 mg, or 30 mg. The apremilast regimens followed dose titration, according to the arm descriptions. The primary Week 16 comparison uses the randomized placebo group as the comparator. The record describes a subsequent 8-week active-treatment phase, in which the initial apremilast groups continued their assigned doses and participants initially assigned to placebo were re-randomized to apremilast 20 mg or 30 mg.

Randomization and masking are stated in the registry record, but the details of sequence generation, allocation concealment, and which roles were included in quadruple masking are not reported in the registry record. The record describes the primary analysis population as all randomized participants and says that last observation carried forward was used to impute missing values for that endpoint. Further detail about adherence, protocol deviations, and the handling of missing data for the secondary outcomes is not reported in the registry record. The original design’s sample-size justification and statistical planning assumptions are also 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: Time gaps between the end of one study phase and start of the next phase precluded the continuation of some of the participants in the study.

Core: Placebo Controlled Phase Week 0-16

Reasons for not completing this period:

Core: Active Treatment Phase Week 16-24

Reasons for not completing this period:

Extension: Active Treatment Week 24-52

Reasons for not completing this period:

LTE Period: Week 52 to 6 Years

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The intent-to-treat (ITT) population = all randomized participants. Last observation carried forward (LOCF) method was used for imputing missing values

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: The intent-to-treat (ITT) population consisted of all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Core Study: Percentage of Participants Who Achieved a 75% Improvement (Response) in Psoriasis Area and Severity Index (PASI) at Week 16, measured over Week 0 and Week 16.

The primary endpoint is the percentage of participants who achieved a PASI-75 response at Week 16: at least a 75% reduction from baseline in PASI score. The PASI combines lesion characteristics—erythema, thickness, and scaling—with the extent of affected skin across the head, trunk, upper limbs, and lower limbs. The score ranges from 0 to 72, with higher scores indicating greater disease severity.

A responder threshold makes the result interpretable as the proportion of participants reaching a prespecified degree of improvement. It is useful for comparing the frequency of that response across randomized groups, but it reduces a continuous severity score to a yes-or-no classification. Participants with different degrees of improvement can therefore be counted alike if both meet the threshold, while improvements that do not reach the threshold are not counted as responses. PASI-75 does not, by itself, describe other clinical outcomes or the full distribution of PASI changes.

The registry record defines the primary analysis population as all randomized participants and states that missing values were imputed using last observation carried forward. The endpoint is described as measured from Week 0 to Week 16. The posted primary arm percentages are 5.7 for placebo, 11.2 for apremilast 10 mg, 28.7 for apremilast 20 mg, and 40.9 for apremilast 30 mg.

7. Results Posted in the Registry

• Apremilast 10mg BID: 11.2% (10/89) versus 5.7% (5/88) on control; risk difference 5.6 percentage points (95% CI -2.6 to 13.7), risk ratio 1.98 (0.70–5.55); unadjusted two-proportion z-test p = 0.185.
• Apremilast 20mg BID: 28.7% (25/87) versus 5.7% (5/88) on control; risk difference 23.1 percentage points (95% CI 12.4 to 33.7), risk ratio 5.06 (2.03–12.61); unadjusted two-proportion z-test p = <0.001.
• Apremilast 30 mg BID: 40.9% (36/88) versus 5.7% (5/88) on control; risk difference 35.2 percentage points (95% CI 23.9 to 46.6), risk ratio 7.20 (2.96–17.49); 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.

Core Study: Percentage of Participants Who Achieved a 75% Improvement (Response) in PASI Score at Week 24

• 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 BID: 26.4% (23/87) versus 18.0% (16/89) on control; risk difference 8.5 percentage points (95% CI -3.8 to 20.7), risk ratio 1.47 (0.84–2.59); unadjusted two-proportion z-test p = 0.177.
  • Apremilast 30 mg BID: 39.8% (35/88) versus 18.0% (16/89) on control; risk difference 21.8 percentage points (95% CI 8.8 to 34.8), risk ratio 2.21 (1.32–3.69); unadjusted two-proportion z-test p = 0.001.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Apremilast 20mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Apremilast 30 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Core Study: Percentage of Participants Who Achieved a 50% Improvement (Response) in PASI Score at 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 10mg BID: 38.2% (34/89) versus 25.0% (22/88) on control; risk difference 13.2 percentage points (95% CI -0.4 to 26.8), risk ratio 1.53 (0.98–2.39); unadjusted two-proportion z-test p = 0.059.
  • Apremilast 20mg BID: 47.1% (41/87) versus 25.0% (22/88) on control; risk difference 22.1 percentage points (95% CI 8.3 to 36.0), risk ratio 1.89 (1.23–2.88); unadjusted two-proportion z-test p = 0.002.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Apremilast 10mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Apremilast 20mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Core Study: Percentage of Participants Who Achieved a 50% Improvement (Response) in the PASI Score at Week 24

• 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 10mg BID: 38.2% (34/89) versus 61.8% (21/34) on control; risk difference -23.6 percentage points (95% CI -42.8 to -4.4), risk ratio 0.62 (0.43–0.90); unadjusted two-proportion z-test p = 0.019.
  • Apremilast 20mg: 49.4% (43/87) versus 61.8% (21/34) on control; risk difference -12.3 percentage points (95% CI -31.8 to 7.1), risk ratio 0.80 (0.57–1.12); unadjusted two-proportion z-test p = 0.222.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically lower for Apremilast 10mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Apremilast 20mg and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes extend the primary question in two broad ways: they use other PASI response thresholds, and they assess responses at Week 16 or Week 24. The posted Week 16 PASI-50 arm percentages show a pattern across the dose groups that is broadly aligned with the primary endpoint’s dose-ordered response pattern. Week 24 outcomes add information about response after the placebo-controlled phase, but they do not provide a continuing placebo comparison because initial placebo participants entered active treatment.

The secondary results are useful for considering whether the primary pattern is seen under different response definitions and assessment times. They are not independent replications of the primary endpoint: they involve the same trial, overlapping participants, related outcome measures, and multiple testing. A result that appears consistent across related PASI thresholds can add descriptive context, but it does not erase the uncertainty or limitations attached to the primary comparison.

The registry lists many outcomes and analyses, but the multiplicity handling for the secondary analyses is not reported in the registry record. When many outcomes are examined, some nominally notable findings may arise by chance even if no corresponding effect exists. Unadjusted p-values do not account for that broader set of tests. For this reason, secondary findings generally carry less confirmatory weight than a clearly prespecified primary endpoint analyzed under a reported plan.

Interpretation also depends on the treatment history at the assessment. Week 24 percentages for participants who began on placebo reflect subsequent apremilast treatment after re-randomization, whereas the initial apremilast groups continued active treatment. The Week 24 results therefore describe outcomes under those treatment sequences, not an ongoing placebo-controlled contrast. The registry does not report a sponsor analysis for every posted secondary comparison, so not all secondary results have the same inferential detail as the primary outcome.

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

• Core Study: Percentage of Participants Who Achieved a 75% Improvement (Response) in PASI Score at Week 24
• Core Study: Percentage of Participants Who Achieved a 50% Improvement (Response) in PASI Score at Week 16
• Core Study: Percentage of Participants Who Achieved a 50% Improvement (Response) in the PASI Score at Week 24
• Core Study: Percentage of Participants Who Achieved a 90% Improvement (Response) From Baseline in the PASI Score at Week 16
• Core Study: Percentage of Participants Who Achieved a 90% Improvement (Response) in the PASI Score at Week 24
• Core Study: Percentage of Participants Who Achieved a 100% Improvement (Response) in the PASI Score at Week 16
• Core Study: Percentage of Participants Who Achieved a 100% Improvement (Response) in the PASI Score at Week 24
• Core Study: Time to Achieve a PASI-100 Response During the Placebo Controlled Phase

9. Statistical Interpretation

10. Statistical Methods Explained

What does a responder percentage represent?

The primary outcome is binary at the participant level: a participant either reached PASI-75 at Week 16 or did not. An arm’s response percentage describes the proportion classified as responders under the registry’s analysis. The endpoint therefore emphasizes whether a threshold was reached, rather than the average change in PASI or the distribution of changes. It is possible for the same response percentage to arise from different patterns of underlying score change.

What is a risk difference?

A risk difference subtracts the event proportion in one group from the event proportion in another. For these comparisons, the event is a PASI-75 response and the groups are an apremilast dose and placebo. A positive risk difference indicates a higher observed response proportion in the apremilast group; a negative value would indicate a lower proportion. The sponsor’s reported Week 16 risk differences are 5.6 for 10 mg, 23.1 for 20 mg, and 35.2 for 30 mg. The registry reports those values on the percentage-point scale. The comparison is a difference in group response proportions, not a measure of the change within each participant.

How should a confidence interval be read?

A confidence interval gives a range of estimates compatible with the observed data and the statistical procedure used, under its assumptions. A narrower interval indicates greater precision than a wider interval for the same type of estimate. An interval crossing zero for a risk difference includes values representing no group difference; an interval wholly above zero is consistent with a positive difference under that interval procedure. The interval does not account automatically for every potential source of bias, missing-data uncertainty, or multiplicity.

What does the p-value tell the reader?

A p-value describes how unusual data at least as incompatible with a null hypothesis would be if that null hypothesis and the test assumptions held. It is not the probability that the null hypothesis is true, and it does not measure the size or importance of a difference. The registry’s reported primary analyses use chi-squared tests. The record does not report a multiplicity adjustment for the three dose comparisons, so the individual p-values should not be treated as if they necessarily control the error rate across the full set of comparisons.

What is different about the re-calculation?

The recalculated comparisons are simple, unadjusted analyses from posted summary statistics. They are not a substitute for the sponsor’s trial analysis, which takes precedence when the record flags a discrepancy. The re-calculated p-values are 0.185 for 10 mg and < 0.001 for each of 20 mg and 30 mg. Their purpose is to provide a transparent check of the summary data, not to reconstruct unreported elements of the original analysis plan. Details such as any stratification, covariate adjustment, or other protocol-specified procedures are not reported in the registry record.

How does last observation carried forward affect interpretation?

For the primary endpoint, the registry says that missing values were imputed by carrying the last observed value forward. This assigns a participant’s last recorded observation to the later assessment when the Week 16 value is missing. It can retain participants in an analysis, but it relies on an assumption about how a participant’s outcome would have behaved after the last observation. The method does not eliminate uncertainty from missing data. The number and reasons for missing Week 16 observations, and sensitivity analyses using alternative assumptions, are not reported in the registry record.

General statistical context: binary responder outcomes are not continuous measurements, so concerns such as over-dispersion in count outcomes do not apply in the same way. Nonetheless, interpretation still depends on the endpoint definition, analysis population, missing-data approach, and statistical test. Randomization supports comparisons between assigned groups, but it does not resolve limitations in reporting or make secondary and exploratory comparisons equivalent to the prespecified primary question.

11. Confidence Intervals and Precision

The sponsor-reported 95% confidence intervals for the primary risk differences are -2.6 to 13.7 for apremilast 10 mg versus placebo, 12.4 to 33.7 for apremilast 20 mg versus placebo, and 23.9 to 46.6 for apremilast 30 mg versus placebo. The first interval includes zero, so the range is compatible with no difference as well as with differences in either direction. The other two reported intervals lie above zero. These intervals describe uncertainty in the risk-difference estimates under the sponsor’s analysis.

Precision should be considered separately from the size of the estimate. An estimate can be large but still uncertain, and a confidence interval is not a guarantee that the true value lies inside it. These intervals also do not capture all uncertainty about study conduct, outcome measurement, missing values, or the multiplicity of analyses. The interval width reflects the data and the method used for the particular comparison, rather than a universal measure of study quality.

The primary arm percentages are posted without arm-level confidence intervals in the record. Reported confidence intervals are available for the risk differences. The primary comparison group sizes range from 87.0 to 89.0, as listed by arm. These arm sizes provide context for why estimates may remain uncertain, but precision should be judged from the intervals themselves rather than inferred from group size alone.

At Week 24, some secondary arm percentages are accompanied by 95% confidence intervals, but those outcomes have a different treatment context: participants initially assigned to placebo were re-randomized to active treatment. Their intervals should not be interpreted as placebo-controlled estimates at that time. More broadly, precision in a single comparison does not remove the need to account for the fact that many outcomes and analyses were posted.

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 planning figures are illustrative estimates of the number of participants per arm, not total events. They use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is set as the stated fraction of the observed effect. The registry record’s original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column describes the estimated participants per arm under which a study would have an 80% chance of detecting the specified effect using those planning assumptions, if that effect and assumptions held. The 90% power column describes the corresponding planning target for a 90% chance. These are design-planning quantities, not guarantees that a study will detect an effect, and they do not indicate the probability that the treatment effect is real.

Rows based on 100% of the observed effect use the effect estimate from the trial’s posted comparison as the planning target. Rows for 75% and 50% of the observed effect illustrate planning for smaller effects. Smaller effects need more participants to distinguish them from no difference at the same nominal significance level and power target. The required numbers can change substantially when the assumed effect changes, especially when the observed effect is used as the starting point.

For example, the planning figures for the 20 mg versus placebo primary comparison are 41 participants per arm for 80% power and 55 participants per arm for 90% power when planning for 100% of the observed effect. For 50% of that observed effect, the corresponding figures are 119 and 159 participants per arm. These estimates are recalculated planning illustrations, not the trial’s original design calculations. They are not observed power: they do not report the probability that this completed trial had of detecting an effect after the results were known.

The planning calculations use equal allocation between two groups, even though the trial includes multiple randomized arms. They should therefore be read as pairwise planning illustrations, not as a reconstruction of the full dose-ranging trial design. The calculations also do not incorporate any unreported adjustments, changes in enrollment, or anticipated loss to follow-up.

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 = 0.057; treatment proportion p₁ = 0.112; average p̄ = 0.085.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.3935 = 0.7713.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.3916 = 0.3296.
4. n = (0.7713 + 0.3296)² / (0.0555)² = 392.9, rounded up to 393 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 <- 0.0568181818181818                          # control proportion
p1 <- 0.112359550561798                          # 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(773734)
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 = 393 (80% power), 526 (90% power)
 75% of observed effect: n per arm = 647 (80% power), 866 (90% power)
 50% of observed effect: n per arm = 1,337 (80% power), 1,789 (90% power)
power.prop.test: 392.9 
Simulated power at n = 393 per arm: 0.804 (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 of each Week 16 apremilast dose versus placebo using chi-squared tests and risk differences. Those analyses are the appropriate reference for the trial’s own reported results. The record flags a discrepancy between the sponsor results and simple recalculations from the posted summary statistics; accordingly, the sponsor’s own analysis takes precedence.

For the primary endpoint, the sponsor reports risk differences of 5.6, 23.1, and 35.2 for the 10 mg, 20 mg, and 30 mg comparisons, respectively. The corresponding reported p-values are 0.185, < 0.001, and < 0.001. The recalculated unadjusted p-values are 0.185, < 0.001, and < 0.001. The close broad pattern does not mean that the calculations are identical: their methods and precision differ, and the registry’s sponsor-reported results should be used when describing the trial’s analysis.

The recalculation is a limited check based on the posted group summaries. It cannot reproduce any unreported features of the sponsor’s analysis, and it is not evidence that the original statistical plan used the same approach. The registry record does not report enough detail to resolve the discrepancy or to establish its cause. It is therefore important not to present recalculated estimates as though they were the sponsor’s results.

15. Multiplicity, Missing Data and Analysis Populations

The trial includes three primary dose-versus-placebo comparisons, multiple secondary PASI response thresholds and assessment times, and a much broader set of posted outcome measures and analyses. When many statistical comparisons are made, the chance of at least one apparently notable result can rise. Methods such as adjusting significance thresholds or using a hierarchical testing plan can address multiplicity, but the registry record does not report whether such a plan was used for the primary comparisons or secondary outcomes. The reported p-values should therefore be read as the values for their individual tests, not assumed to control error across all analyses.

The primary endpoint specifies the intent-to-treat population as all randomized participants and says missing values were handled using last observation carried forward. The record does not report the number of missing values at the primary assessment, reasons for missingness, or sensitivity analyses that test alternative missing-data assumptions. It also does not report whether the same analysis population and imputation procedure were applied to each secondary endpoint. Missing-data methods can affect estimated response percentages, particularly when the probability of missingness is related to outcome or treatment experience.

The registry record identifies a randomized, double-blind study and states quadruple masking, but details about the implementation of randomization and masking are not reported in the registry record. The exact prespecified statistical analysis plan, including any stratification, covariate adjustments, interim analyses, and multiplicity strategy, is not reported in the registry record. These details should not be inferred from the trial design label or the methods attached to the reported analysis.

The record lists 117 outcome measures and 27 analyses. Those counts indicate a broad reporting set, but they do not establish that every listed measure was tested in the same way or that every analysis was planned in advance. A clear interpretation distinguishes the primary endpoint from secondary analyses and descriptive results, and avoids treating all nominal findings as equally confirmatory.

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: pregnancy (2.3%), prostate cancer (1.6%), cellulitis (1.1%), nephrolithiasis (1.1%), psoriasis (1.1%).

The registry reports serious adverse event counts and other adverse event counts for the placebo-controlled period and for longer apremilast exposure periods. During Weeks 0–16, serious adverse events were reported for 2 participants in the placebo group, 0 in the 10 mg group, 3 in the 20 mg group, and 4 in the 30 mg group. Other adverse events were reported for 35, 42, 45, and 55 participants in those respective groups. These are counts in the registry record; they do not establish that an event was caused by treatment.

The record also lists serious and other adverse events for apremilast exposure periods labeled Years 0–6. Those periods are not directly comparable with the Week 0–16 groups because exposure duration and group composition differ. The registry lists serious-event terms including Pregnancy at 2.3%, Prostate cancer at 1.6%, Cellulitis at 1.1%, Nephrolithiasis at 1.1%, Psoriasis at 1.1%, and Myocardial infarction at 1.1%. The denominators and further details for these term percentages are not reported in the registry record. Death counts are not reported in the registry record.

These summaries do not provide enough information to compare safety risks fully. Event timing, severity beyond the serious-event classification, discontinuations, exposure-adjusted rates, and causal assessments are not reported in the registry record. The counts describe what was posted, not a complete safety evaluation.

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

The primary result describes the percentage of randomized participants in each group who met a specified PASI improvement threshold at Week 16, under the registry’s intent-to-treat and last-observation-carried-forward approach. The posted percentages and sponsor-reported risk differences show higher observed PASI-75 response proportions in the 20 mg and 30 mg groups than in the placebo group, while the 10 mg comparison has a confidence interval that includes zero. This is a statistical description of the trial record, not medical advice or a recommendation.

The result does not establish that every participant assigned to an apremilast dose experienced improvement, or that participants who did not meet PASI-75 had no improvement. It does not describe the full range of individual PASI changes, long-term outcomes for every randomized group, or all aspects of treatment experience. A group percentage is not a prediction for a particular person.

The trial was randomized and placebo-controlled during the primary assessment period, which supports interpretation of the Week 16 group contrasts. However, the registry record does not report all details of the original statistical plan, multiplicity handling, or missing-data sensitivity analyses. The discrepancy flag also means that the sponsor’s own analysis should be given precedence over simple recalculations.

Week 24 results concern a different treatment sequence because participants initially assigned to placebo were re-randomized to active treatment. They should not be interpreted as evidence from a continuing placebo comparison. Safety counts are descriptive and do not establish causation or quantify comparative risk fully. Taken together, the record supports a bounded reading of the posted efficacy and safety summaries, rather than a conclusion beyond the measured endpoints, analysis methods, and follow-up described in the registry.

18. Why This Trial Matters Statistically

This trial illustrates how an endpoint definition shapes the statistical question. PASI-75 turns a severity score into a responder classification, making group comparisons easy to communicate while discarding information about the amount of change below or beyond the threshold. Reading the response percentages alongside the risk differences and confidence intervals helps distinguish observed proportions from estimated between-group contrasts and their uncertainty.

The dose-ranging design also makes it important to separate descriptive dose patterns from formal evidence. The posted Week 16 percentages rise across the listed doses, but each dose-versus-placebo analysis is a separate comparison, and the registry does not report a multiplicity plan. A visually ordered pattern is not by itself a formal test of dose-response or proof that the differences between doses are statistically distinguishable.

The record provides an instructive example of why sponsor analyses and simple recalculations should be labeled separately. The recalculated comparisons are useful checks based on summary data, but the registry flags a discrepancy, so the sponsor’s analysis takes precedence. Similarly, planning figures based on observed effects can illustrate how assumptions affect required sample sizes, but they are not the original design justification and are not observed power.

Finally, the Week 24 treatment transition shows why assessment time and comparator history matter. Once the initial placebo group moves to active treatment, later percentages no longer represent the same placebo-controlled contrast as the primary Week 16 endpoint. Statistical interpretation depends not only on a number, but also on who was analyzed, what was measured, when it was measured, and what comparisons the design supports.

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 are specific to the registry record and the way these results are reported. The primary endpoint uses last observation carried forward for missing values, but the number and reasons for missing assessments and sensitivity analyses are not reported in the registry record. This leaves uncertainty about how alternative assumptions for missing outcomes might affect the response percentages and group comparisons.

The registry lists multiple doses, secondary PASI thresholds, assessment times, and a large set of outcomes and analyses. The approach to multiplicity is not reported in the registry record. As a result, individual secondary p-values, where available, should not automatically be treated as confirmatory. The record also does not report the original sample-size justification, the full prespecified analysis plan, or whether interim analyses were conducted.

The primary endpoint is a thresholded measure, so it does not convey the full distribution of PASI change. Primary arm-level confidence intervals are not posted in the record, although sponsor-reported confidence intervals are available for the risk differences. The discrepancy flag between the sponsor results and recalculations cannot be resolved from the reported information, and the sponsor’s analysis takes precedence.

Interpretation of Week 24 outcomes is constrained by the move from placebo to active treatment for participants initially assigned to placebo. Those results therefore reflect different treatment sequences rather than an uninterrupted placebo-controlled comparison. For safety, the record posts counts over periods with different exposure durations and lists event terms without all denominators and timing details. These summaries cannot establish causality or provide a complete comparison of adverse-event risk. Further detail on adherence, protocol deviations, and the implementation of masking and randomization is not reported in the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Efficacy and Safety Study of Apremilast (CC-10004) in Subjects With Moderate-to-Severe Plaque-Type Psoriasis (Core Study) — NCT00773734.
• Registry record last updated 2020-05-07; status last verified 2020-04.
• Results first posted 2014-11-13.
• 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

The registry record describes a completed, randomized, double-blind, placebo-controlled, parallel-group phase 2B dose-ranging study of apremilast in moderate-to-severe plaque-type psoriasis. Enrollment was 352. The primary endpoint was the percentage achieving PASI-75 at Week 16, analyzed in the intent-to-treat population with last observation carried forward for missing values.

Posted response percentages were 5.7 for placebo, 11.2 for apremilast 10 mg, 28.7 for 20 mg, and 40.9 for 30 mg. The sponsor reported risk differences versus placebo of 5.6, 23.1, and 35.2, respectively, with 95% confidence intervals and chi-squared tests. Because the record flags a discrepancy with recalculations, the sponsor’s own analysis takes precedence. The record does not report the original design assumptions or multiplicity approach. Week 24 results follow a treatment transition, and adverse-event summaries are descriptive, with important details not reported in the registry record.