A Study of the Safety and Efficacy of Ustekinumab in Patients With Psoriatic Arthritis With and Without Prior Exposure to Anti-TNF Agents: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of the Safety and Efficacy of Ustekinumab in Patients With Psoriatic Arthritis With and Without Prior Exposure to Anti-TNF Agents (NCT01077362), a randomized phase 3 study. The primary outcome is Percentage of Participants With American College of Rheumatology (ACR) 20 Response at Week 24..

2. Clinical Question

3. Trial Design

This was a Phase 3, multicenter, randomized, double-blind, placebo-controlled, parallel-group trial. The registry lists quadruple masking. Enrollment was 312. The study began in 2010-03, reached primary completion in 2012-03, and is listed as completed. Details of the randomization sequence, allocation concealment, and the operational meaning of the masking categories are not reported in the registry record.

Three treatment groups were described: placebo, ustekinumab 45 mg, and ustekinumab 90 mg, administered by subcutaneous injection. The placebo schedule included injections at Weeks 0, 4, 16, and 20, followed by crossover to ustekinumab 45 mg beginning at Week 24. The ustekinumab groups began active treatment at Weeks 0 and 4 and continued on the described schedule. The arm descriptions also refer to early escape and differing subsequent doses. The complete details of those schedules are not reported in the registry record.

The main comparison reported for the primary endpoint is at Week 24, before the placebo crossover described in the registry. The efficacy population included all participants randomly assigned to a treatment group, whether or not they received their assigned treatment. For early escape, observations at or before Week 16 were carried forward through Week 24. Further details about handling other missing observations, adherence, and protocol deviations are not reported in the registry record.

The record lists 6 outcome measures and 18 analyses. It identifies the primary endpoint as the percentage achieving ACR 20 response at Week 24. Secondary outcomes include HAQ-DI change, PASI 75 response, ACR 50 and ACR 70 responses, and change in a combined radiographic score. The original design assumptions, including any sample-size justification and interim-analysis plan, 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All participants randomly assigned to a treatment group were included in the efficacy analysis regardless of whether they received the assigned treatment. For early escape, data at or prior to Week 16 were carried forward through Week 24.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With American College of Rheumatology (ACR) 20 Response at Week 24., measured over Week 24.

The primary endpoint is the percentage of participants achieving an ACR 20 response at Week 24. The response definition combines joint counts with assessments of pain, disease activity, physical function, and C-reactive protein. It requires at least 20 percent improvement from baseline in swollen and tender joint counts, together with at least 20 percent improvement in 3 of the 5 additional assessments.

This is a binary outcome: each participant either meets the response definition or does not. Reporting the percentage makes the endpoint interpretable as the proportion of participants who reached a prespecified threshold of improvement across several disease-related measures. It is not a measure of the average change in every component, nor does it describe how far beyond the threshold a responder improved.

Composite response definitions are used in clinical research to summarize multiple aspects of disease activity in a single outcome. Their interpretation depends on the exact criteria: a participant can qualify through the required pattern of component improvements without every component improving by the same amount. The registry record describes the endpoint definition and analysis population, but does not report component-level results that would show which assessments most often contributed to response.

The analysis included all randomly assigned participants regardless of whether they received assigned treatment. For early escape, data collected at or before Week 16 were carried forward through Week 24. The record does not report further details of missing-data handling or any sensitivity analyses for this endpoint.

7. Results Posted in the Registry

• Ustekinumab 45 mg: 43.7% (45/103) versus 20.2% (21/104) on control; risk difference 23.5 percentage points (95% CI 11.2 to 35.8), risk ratio 2.16 (1.39–3.36); unadjusted two-proportion z-test p = <0.001.
• Ustekinumab 90 mg: 43.8% (46/105) versus 20.2% (21/104) on control; risk difference 23.6 percentage points (95% CI 11.4 to 35.8), risk ratio 2.17 (1.40–3.37); 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.

Change From Baseline to Week 24 in the Disability Index Score as Measured With the "Disability Index of the Health Assessment Questionnaire" (HAQ-DI)

• 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 deviations.
• Result:
  • Ustekinumab 45 mg: mean -0.21 versus -0.03 on control; difference -0.18 (95% CI -0.30 to -0.06), standardized effect d = -0.43; z-test p = 0.002.
  • Ustekinumab 90 mg: mean -0.22 versus -0.03 on control; difference -0.19 (95% CI -0.30 to -0.08), standardized effect d = -0.46; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Ustekinumab 45 mg 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 Ustekinumab 90 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants (With >= 3% Baseline Body Surface Area (BSA) Psoriatic Involvement) Who Achieved a Psoriasis Area and Severity Index 75 (PASI 75) Response 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:
  • Ustekinumab 45 mg: 51.2% (41/80) versus 5.0% (4/80) on control; risk difference 46.2 percentage points (95% CI 34.3 to 58.2), risk ratio 10.25 (3.85–27.28); unadjusted two-proportion z-test p = <0.001.
  • Ustekinumab 90 mg: 55.6% (45/81) versus 5.0% (4/80) on control; risk difference 50.6 percentage points (95% CI 38.7 to 62.4), risk ratio 11.11 (4.19–29.45); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Ustekinumab 45 mg 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 Ustekinumab 90 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants With American College of Rheumatology (ACR) 50 Response 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:
  • Ustekinumab 45 mg: 17.5% (18/103) versus 6.7% (7/104) on control; risk difference 10.7 percentage points (95% CI 2.0 to 19.5), risk ratio 2.60 (1.13–5.95); unadjusted two-proportion z-test p = 0.018.
  • Ustekinumab 90 mg: 22.9% (24/105) versus 6.7% (7/104) on control; risk difference 16.1 percentage points (95% CI 6.8 to 25.5), risk ratio 3.40 (1.53–7.54); unadjusted two-proportion z-test p = 0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Ustekinumab 45 mg 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 Ustekinumab 90 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover several related but distinct aspects of psoriatic arthritis: physical function measured by HAQ-DI, skin response measured by PASI 75 in participants meeting the stated baseline skin-involvement criterion, higher-threshold joint responses measured by ACR 50 and ACR 70, and radiographic change. In the posted Week 24 results, the direction of the comparisons generally aligns with the primary result: the ustekinumab groups show more favorable response proportions on the binary response measures, while the HAQ-DI group summaries show more negative mean changes than placebo. The radiographic outcome is listed, but its posted results are not part of the secondary summaries analyzed.

This broad pattern can be viewed as supportive context for the primary endpoint, not as an independent confirmation of every aspect of the primary finding. The outcomes differ in definition, scale, eligible population, and sample size. In particular, the PASI 75 analysis applies to participants with at least 3% baseline body surface area involvement, rather than the full efficacy population. Findings from that subgroup do not automatically generalize to participants outside its eligibility definition.

Several outcomes and comparisons were examined. Unless a multiplicity strategy is specified, repeated testing increases the chance that at least one nominally notable result may occur even if there is no true effect for some outcomes. The registry record does not report a multiplicity adjustment or a hierarchy governing secondary endpoint testing. The unadjusted secondary p-values therefore carry less inferential weight than a prespecified primary comparison would carry, and should be read as exploratory or supportive rather than definitive evidence for each outcome.

The secondary results can help assess whether the primary response pattern is accompanied by changes in other domains, but the registry summaries do not provide enough detail to establish consistency at the participant level or the clinical importance of each change. The secondary outcomes do not replace the primary endpoint, and they do not resolve limitations related to missing data, multiplicity, or follow-up after placebo crossover.

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

• Change From Baseline to Week 24 in the Disability Index Score as Measured With the "Disability Index of the Health Assessment Questionnaire" (HAQ-DI)
• Percentage of Participants (With >= 3% Baseline Body Surface Area (BSA) Psoriatic Involvement) Who Achieved a Psoriasis Area and Severity Index 75 (PASI 75) Response at Week 24
• Percentage of Participants With American College of Rheumatology (ACR) 50 Response at Week 24
• Change From Baseline to Week 24 in Total Modified Van Der Heijde-Sharp (vdH-S) Score for the Combined Radiographic Data From Studies CNTO1275PSA3001 and CNTO1275PSA3002
• Percentage of Participants With American College of Rheumatology (ACR) 70 Response at Week 24

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is binary because it classifies each participant as either meeting the ACR 20 response criteria or not meeting them. A natural summary is the proportion responding in each randomized group. Comparing proportions preserves the endpoint's original meaning: the share of participants who crossed the defined response threshold. It does not treat the response as a continuously measured score.

What does a risk difference describe?

A risk difference is the difference between the response proportions in two groups, expressed on the proportion scale. A positive estimate in these comparisons indicates a higher observed response proportion in the ustekinumab group than in placebo. For the 45 mg comparison the estimate is 0.235; for the 90 mg comparison it is 0.236. These are unadjusted re-calculations from posted summary statistics. They do not account for covariates or additional design features unless those are explicitly included in the reported analysis.

The posted percentages are rounded summaries, while the re-calculation uses the response counts and group sizes listed in the record. Small discrepancies between rounded percentages and estimates calculated from counts can arise from rounding. The record does not flag a discrepancy between the re-calculations and the sponsor's reported analyses.

What does a confidence interval add?

A confidence interval describes uncertainty around an estimated contrast under the assumptions of the method used. It gives a range of effect values reasonably compatible with the observed data and method; it is not a guarantee that the true effect lies in that particular interval. The primary risk-difference intervals run from 0.112 to 0.358 for 45 mg versus placebo and from 0.114 to 0.358 for 90 mg versus placebo. Both intervals are above zero, consistent with the positive observed contrasts. The intervals overlap substantially, but overlap is not a formal test of whether the doses differ.

How should the p-values be read?

The unadjusted p-values for the primary comparisons are <0.001. A p-value describes how unusual data at least as inconsistent with a null comparison would be under that null and the test assumptions. It is not the probability that the null hypothesis is true, the probability that the result arose by chance, or a measure of the size or importance of an effect. The record reports sponsor p-values from re-randomization tests. The simple risk-difference calculations are a separate, unadjusted summary and should not be confused with those sponsor tests.

Re-randomization tests assess the observed contrast against contrasts that could arise under the random assignment mechanism, subject to the test's implementation. The registry names this method but does not report enough detail to reconstruct its exact statistic, randomization scheme, or any adjustment procedure. It also does not report whether the primary analysis was prespecified in a statistical analysis plan.

Why does the analysis population matter?

The record states that all randomly assigned participants were included in the efficacy analysis regardless of whether they received assigned treatment. This approach retains the randomized group assignment for the stated efficacy analysis. It can preserve the benefits of randomization, but interpretation also depends on the handling of outcomes that are not observed. For early escape, observations at or before Week 16 were carried forward through Week 24. The record does not give a complete account of other missing-data rules or sensitivity analyses, so the robustness of the findings to alternative assumptions cannot be assessed from this information.

The study also included a placebo crossover after Week 24. That matters when interpreting later follow-up: after crossover, later comparisons would not have the same simple placebo-versus-active-treatment meaning as the Week 24 contrast. The primary endpoint's Week 24 timing precedes the described crossover and is therefore the clearest randomized placebo comparison in the posted primary results.

Statistical methods are tools for quantifying uncertainty and organizing comparisons, not substitutes for the endpoint definition or trial conduct. The estimate, interval, p-value, analysis population, and missing-data approach answer related but different questions. The registry record does not report the full statistical analysis plan, multiplicity strategy, or rationale for the specific analysis choices.

11. Confidence Intervals and Precision

The primary risk-difference confidence intervals quantify uncertainty in each ustekinumab-versus-placebo contrast. For 45 mg, the estimate is 0.235 and the interval extends from 0.112 to 0.358. For 90 mg, the estimate is 0.236 and the interval extends from 0.114 to 0.358. Both intervals are on the positive side of zero, while their width shows that the data are compatible with a range of possible effect magnitudes rather than one exact contrast.

Confidence intervals are useful because a point estimate alone can give a misleading impression of certainty. The interval reflects sampling uncertainty under the calculation's assumptions; it does not encompass every source of uncertainty, such as possible bias from missing data, outcome measurement, or analysis choices. The registry record does not report enough information to evaluate all such sources.

The intervals for the two dose comparisons are similar and overlap. This supports caution about interpreting their point estimates as evidence that one dose has a larger effect than the other. A direct randomized comparison between dose groups, with its own estimate and uncertainty, is not reported in the registry record.

The sponsor-reported p-values are from re-randomization tests, whereas these confidence intervals accompany simple unadjusted re-calculations from posted summary statistics. The registry does not report sponsor confidence intervals for the primary comparisons. Accordingly, the intervals are helpful for understanding the scale and precision of the posted contrasts, but they should not be presented as a replacement for the sponsor's full analysis.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size figures are planning illustrations derived from the observed effect, not the original trial's design calculations. For the binary primary endpoint, the values are participants per arm. The stated 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. The original trial's sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the estimated participants per arm under these assumptions for an 80% chance of detecting the chosen effect if that effect were the true one and the assumptions held. The 90% power column uses a higher target chance of detection, and therefore generally calls for more participants. These are prospective planning quantities: they do not describe the probability that the completed trial's finding is correct, and they are not observed power.

For the primary comparison with ustekinumab 45 mg, planning for 100% of the observed effect gives 61 participants per arm for 80% power and 81 for 90% power. Planning for 75% of the observed effect gives 103 and 138 participants per arm; planning for 50% gives 218 and 292. For 90 mg, the corresponding entries are 61 and 80 for the full observed effect, 102 and 136 for 75%, and 216 and 289 for 50%.

The general pattern is that smaller effects are harder to distinguish from random variation, so more participants are needed to target the same power. The observed effect is used as the starting point for these illustrations, but future studies may reasonably plan around a smaller effect. These figures depend on the listed assumptions and should not be read as a recommendation or as evidence about what the trial originally planned.

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 = 0.202; treatment proportion p₁ = 0.437; average p̄ = 0.319.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6594 = 1.2923.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6381 = 0.5370.
4. n = (1.2923 + 0.5370)² / (0.2350)² = 60.6, rounded up to 61 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 <- 0.201923076923077                          # control proportion
p1 <- 0.436893203883495                          # 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(1077362)
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 = 61 (80% power), 81 (90% power)
 75% of observed effect: n per arm = 103 (80% power), 138 (90% power)
 50% of observed effect: n per arm = 218 (80% power), 292 (90% power)
power.prop.test: 60.6 
Simulated power at n = 61 per arm: 0.803 (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 using re-randomization tests for the primary comparisons. The reported p-values are <0.001 for placebo versus ustekinumab 45 mg and <0.001 for placebo versus ustekinumab 90 mg. The registry also reports a placebo-versus-combined-ustekinumab analysis with p <0.001.

The re-calculated risk differences use posted response counts and group sizes to produce simple, unadjusted comparisons. Their reported unadjusted p-values are also <0.001 for both dose comparisons. The estimates and intervals offer an interpretable summary of the magnitude and uncertainty of the contrasts, while the re-randomization tests are the sponsor's reported inferential method.

The record does not provide the full analysis specification needed to reproduce the re-randomization tests or determine whether they included adjustments not captured by the simple calculations. It also does not report a sponsor confidence interval for the primary contrasts. The registry does not identify a discrepancy between the recalculations and the sponsor results. They should therefore be read as complementary summaries, not as competing analyses or as evidence that one method supersedes the other.

15. Multiplicity, Missing Data and Analysis Populations

The record lists a primary endpoint, multiple secondary outcomes, and 18 analyses. It reports p-values for primary and some secondary comparisons, but a multiplicity adjustment, testing hierarchy, or family-wise error strategy is not reported in the registry record. When several outcomes or comparisons are examined, unadjusted p-values do not account for the chance of obtaining at least one apparently notable result through repeated testing. This is why the primary endpoint should be distinguished from the secondary results, and why unadjusted secondary findings warrant more cautious interpretation.

The primary efficacy population is described as all participants randomly assigned to a treatment group, regardless of whether they received assigned treatment. For early escape, observations at or before Week 16 were carried forward through Week 24. The record does not report how other missing primary endpoint observations were handled, the extent of missingness, or sensitivity analyses under alternative assumptions. It therefore is not possible from the registry record to assess whether the result changes under different missing-data approaches.

The crossover design also affects interpretation across time. Participants assigned to placebo were scheduled to switch to ustekinumab at Week 24. The Week 24 primary contrast precedes that described crossover, but later comparisons would need to account for the changed treatment exposure. The registry record does not provide enough detail to evaluate a later randomized comparison against continuing placebo.

The original statistical analysis plan, trial-specific sample-size justification, interim-analysis plan, and detailed prespecification of secondary analyses are not reported in the registry record. These omissions limit assessment of how closely the posted analyses follow the intended plan, whether analyses were selected after reviewing data, and how uncertainty across outcomes was managed. The record's stated efficacy population and early-escape rule are informative, but do not answer those broader questions.

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: myocardial infarction (2.0%), umbilical hernia (1.2%), breast cancer (1.2%), acute myocardial infarction (1.0%), gastric ulcer haemorrhage (1.0%).

The serious adverse event summaries are presented for different treatment periods and group labels, including the controlled period, Weeks 16-24, and Weeks 16-60. During the controlled period, the record reports 5 participants with serious adverse events in the placebo group, 0 in the ustekinumab 45 mg group, and 1 in the ustekinumab 90 mg group. Later period summaries report 0 for placebo during Weeks 16-24, and 2, 6, and 6 for the placebo-to-ustekinumab 45 mg, ustekinumab 45 mg, and ustekinumab 90 mg groups during Weeks 16-60, respectively.

These are counts within the stated periods and groups, not direct estimates of comparative risk adjusted for exposure time. The periods differ, and the placebo crossover means treatment exposure changes for some participants. The registry also lists serious adverse event terms and their reported percentages, including myocardial infarction at 2.0%, umbilical hernia at 1.2%, and breast cancer at 1.2%. Death counts are not reported in the registry record. These summaries alone do not establish causation or permit a complete benefit-risk assessment.

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

The posted primary results show that a greater percentage of participants assigned to either ustekinumab dose met the ACR 20 response definition at Week 24 than participants assigned to placebo. The risk-difference estimates and their confidence intervals describe the size and uncertainty of those observed group contrasts. The sponsor's reported re-randomization tests also give p-values of <0.001 for each dose-versus-placebo comparison.

These results do not show that every participant improved, that every ACR component changed in the same way, or that the observed group difference will be identical in other populations. ACR 20 is a threshold-based composite, and the record does not report component-level results that would explain the contributions to response. The comparisons also do not establish whether 45 mg and 90 mg differ from each other; a direct dose comparison is not reported.

The findings are limited to the studied population and the specified analysis at Week 24, including the stated rule for early escape. They do not by themselves describe longer-term outcomes, effects after placebo crossover, or the balance of benefits and harms across all relevant outcomes. Secondary findings cover additional domains, but their multiplicity status and analysis hierarchy are not reported in the registry record.

Statistical evidence of a group contrast is not the same as proof of clinical importance for every patient. The record does not provide a threshold for a clinically important difference in the risk difference or enough detail to evaluate all potential sources of bias and uncertainty. The results should therefore be understood as estimates from a randomized trial, interpreted alongside the endpoint definition, precision, missing-data limitations, and safety summaries. They are not individualized medical advice.

18. Why This Trial Matters Statistically

This trial is statistically informative because it uses randomized placebo comparisons for a prespecified Week 24 response endpoint and reports results for two ustekinumab dose groups. Random assignment supports a structured comparison of groups, while placebo provides a reference for the observed response proportions during the controlled period. The record also identifies the efficacy population and describes a specific early-escape data rule, both of which are important for interpreting the analysis.

The primary endpoint translates a complex clinical construct into a defined binary outcome. That makes response proportions and risk differences comparatively straightforward to communicate, but it also discards detail about the size and pattern of individual changes. Reporting both group percentages and uncertainty intervals helps distinguish the observed magnitude from the uncertainty surrounding it.

The two dose-versus-placebo estimates are close in the posted primary summaries. That similarity is useful context, but it is not a formal equivalence or noninferiority finding and does not establish that the doses are interchangeable. A direct comparison, with a prespecified question and appropriate uncertainty estimate, is not reported in the registry record.

The record also illustrates why a positive primary result is not the end of statistical interpretation. Missing-data rules, the multiplicity of secondary analyses, the crossover schedule, and the duration of follow-up all affect what can be concluded. Separating the primary randomized comparison from later and secondary summaries prevents over-reading individual p-values and helps keep the inference tied to the question the trial directly addresses.

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 trial-specific details needed for a fuller assessment are not reported in the registry record. These include eligibility criteria beyond the broad description of active psoriatic arthritis, the number of participants with prior anti-TNF exposure, and outcome results stratified by prior exposure. The title establishes that patients with and without prior biologic anti-TNF treatment were included, but does not establish whether treatment effects were similar across those subgroups.

The registry's arm descriptions include early escape and crossover, but the complete treatment schedules are not available in the record text. The placebo group was scheduled to cross over at Week 24, limiting the interpretation of later placebo comparisons. The early-escape rule carried observations forward, but other missing-data procedures, the amount of missingness, and sensitivity analyses are not reported.

The record does not report the trial's original sample-size justification, statistical analysis plan, multiplicity strategy, interim-analysis plan, or a direct comparison between the two ustekinumab doses. It lists combined radiographic data from two studies as an outcome, but the radiographic result itself is not included in the analyzed summaries. These gaps restrict evaluation of prespecification and the complete pattern of efficacy evidence.

Safety summaries are divided across different periods and treatment exposure groups. The record does not provide exposure-adjusted event rates in the registry record described, and the group definitions change after crossover. The listed serious adverse event counts and terms therefore should not be treated as a definitive comparative safety analysis. Death counts are not reported in the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study of the Safety and Efficacy of Ustekinumab in Patients With Psoriatic Arthritis With and Without Prior Exposure to Anti-TNF Agents — NCT01077362.
• Registry record last updated 2014-02-27; status last verified 2014-01.
• Results first posted 2014-02-27.
• 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 Phase 3, randomized, quadruple-masked, parallel-group, placebo-controlled trial of subcutaneous ustekinumab in patients with active psoriatic arthritis, including those with and without prior biologic anti-TNF exposure. Enrollment was 312. The primary endpoint was ACR 20 response at Week 24.

At Week 24, response was reported for 20.2% of the placebo group, 43.7% of the ustekinumab 45 mg group, and 43.8% of the ustekinumab 90 mg group. The unadjusted risk-difference estimates versus placebo were 0.235 and 0.236, respectively, with both sponsor-reported p-values <0.001. The result describes the randomized comparisons at the stated time point; missing-data, multiplicity, dose-to-dose, and later crossover interpretations remain limited by details not reported in the registry record.