A Study to Compare the Efficacy and Safety of CT-P43 to Stelara in Patients With Plaque Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Compare the Efficacy and Safety of CT-P43 to Stelara in Patients With Plaque Psoriasis (NCT04673786), a randomized phase 3 study. The primary outcome is The Mean Percent Improvement From Baseline in PASI Score at Week 12.

2. Clinical Question

The central comparison is between the two randomized groups during the initial treatment period. The registry record reports a mean percent improvement in PASI score of 77.93 for CT-P43 and 75.89 for EU-Stelara. The sponsor’s registered analysis is an ANCOVA comparison reported as a treatment difference with a 90% confidence interval and classified as an equivalence analysis. The registry record does not state an equivalence margin, so the estimate and interval can be described, but the criterion used to determine equivalence cannot be independently assessed from this record alone.

The later treatment schedule asks a different question from the Week 12 primary comparison. After Week 16, participants initially assigned to Stelara were randomized to continue Stelara or transition to CT-P43. Outcomes through Week 52 therefore include maintenance and switch groups, rather than a simple continuation of the original two-group comparison. The Week 12 endpoint is the principal result for the initial randomized comparison; later summaries should be read in light of the treatment changes and the different follow-up period.

3. Trial Design

This was a randomized, active-controlled, double-blind, Phase 3, parallel-group study sponsored by Celltrion. The registry record lists quadruple masking and an enrollment of 509. The study is marked completed. The recorded start date is 2021-01-11, and the primary completion date is 2021-08-04. These dates describe the registry record and do not establish the timing of any publication or later analysis.

The two biological interventions were CT-P43 and Stelara. Participants were initially randomized on Day 1 (Week 0). The CT-P43 arm description says that participants initially assigned to CT-P43 continued treatment through Week 40. The Stelara arm description says that, before dosing at Week 16, the initially assigned Stelara group was randomized again in a 1:1 ratio either to continue Stelara or transition to CT-P43; participants then continued treatment through Week 40. Thus, the initial allocation supports the Week 12 comparison, whereas later summaries distinguish maintenance and switch pathways.

The primary outcome is the mean percent improvement from baseline in PASI score at Week 12, reported for the Modified ITT Set. The registry record lists additional outcomes involving PASI scores and response categories at Week 12, PASI improvement and Dermatology Life Quality Index through Week 52, and clear or almost-clear sPGA status at Week 12. Outcomes do not all use the same scale or analysis form: some are continuous measurements and others are counts of participants meeting a response definition.

The registry record does not report the randomization sequence method, allocation concealment procedures, the operational details of masking, or the original sample-size justification. It also does not report the detailed protocol schedule beyond the arm descriptions and outcome timeframes recorded. The trial’s own complete statistical analysis plan is not reported in the registry record. Those omissions limit what can be established about design decisions and analysis procedures from the registry entry alone.

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.

Treatment Period I (Weeks 0 to 16)

Reasons for not completing this period:

Treatment Period II (Weeks 16 to 52)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Modified ITT Set

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 The Mean Percent Improvement From Baseline in PASI Score at Week 12, measured over From baseline to Week 12.

The primary endpoint is the mean percent improvement from baseline in the Psoriasis Area and Severity Index (PASI) score at Week 12. PASI combines information about psoriasis area and severity; the registry description states that its score ranges from 0 (no psoriasis) to 72 (severe psoriasis). The endpoint expresses change relative to each participant’s baseline score as a percentage improvement, then summarizes that outcome as a group mean.

A percent-improvement outcome is useful for comparing the amount of change relative to baseline rather than only comparing scores at follow-up. A larger improvement value represents a greater average reduction from baseline on this measure. The registered endpoint uses a least-squares mean, a model-based group estimate, and lists standard error as its dispersion measure. The primary population is the Modified ITT Set.

In general, an endpoint needs both a defined measurement and a defined assessment time. Week 12 makes the primary comparison a specific early follow-up contrast, before the Week 16 re-randomization of the initially assigned Stelara group. It is therefore not the same estimand as a comparison of the later maintenance and switch groups through Week 52. The record does not state the full calculation rules for the percent improvement, how missing Week 12 measurements were handled, or details of the Modified ITT Set beyond its label; these are not reported in the registry record.

7. Results Posted in the Registry

• EU-Stelara: mean 75.89 versus 77.93 on control; difference -2.04 (95% CI -6.90 to 2.82), standardized effect d = -0.07; z-test p = 0.411.

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.

The PASI Scores at Week 12

• 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:
  • EU-Stelara: mean 3.44 versus 2.98 on control; difference 0.46 (95% CI -0.23 to 1.15), standardized effect d = 0.12; z-test p = 0.188.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EU-Stelara and the control. The interval gives the range of effects that remain compatible with the data.

The Mean Percent Improvement From Baseline in PASI Score Through Week 52

• 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:
  • EU-Stelara Maintenance: mean 93.39 versus 93.79 on control; difference -0.40 (95% CI -3.44 to 2.64), standardized effect d = -0.03; z-test p = 0.797.
  • Switched to CT-P43: mean 91.58 versus 93.79 on control; difference -2.21 (95% CI -4.99 to 0.57), standardized effect d = -0.18; z-test p = 0.119.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EU-Stelara Maintenance and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Switched to CT-P43 and the control. The interval gives the range of effects that remain compatible with the data.

The Number of Patients With sPGA Score of Clear (0) or Almost Clear (1) at Week 12

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • EU-Stelara: 79.4% (201/253) versus 85.5% (219/256) on control; risk difference -6.1 percentage points (95% CI -12.7 to 0.5), risk ratio 0.93 (0.86–1.01); unadjusted two-proportion z-test p = 0.070.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EU-Stelara and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes cover several related but distinct aspects of psoriasis status: PASI scores, percent improvement, response categories, clear or almost-clear sPGA status, and quality of life. The posted summaries generally describe favorable average PASI improvement over the assessed periods, but each outcome has its own scale, time point, analysis population, and treatment grouping. Their results therefore add context rather than forming one combined measure of benefit.

The Week 12 secondary measures concern the initial randomized treatment groups and provide a different view of response from the primary mean percent-improvement endpoint. The summaries through Week 52 include the later maintenance and switch pathways. They cannot be interpreted as a direct extension of the original randomized contrast without accounting for the Week 16 re-randomization and the subsequent treatment histories. The registry record does not report a detailed estimand for those later comparisons.

These secondary results should be read alongside, not in place of, the primary endpoint and sponsor-reported analysis. The registry record does not report a multiplicity adjustment or a prespecified hierarchy for secondary hypotheses. In general, when many outcomes or comparisons are examined, an unadjusted finding is more likely to arise by chance, and a nominal p-value can overstate the strength of evidence if treated as confirmatory. This is why unadjusted secondary results carry less weight than a prespecified primary analysis with a documented plan.

The registry record also does not report a complete set of inferential analyses for all secondary outcomes. The summary-based recalculations are not adjusted for covariates, repeated measurements, or multiplicity. They should be understood as descriptive comparisons of posted aggregate results, not definitive tests of every secondary question. Further details on missing data, analysis populations, and the sponsor’s secondary models are not reported in the registry record.

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

• The PASI Scores at Week 12
• The Mean Percent Improvement From Baseline in PASI Score Through Week 52
• The Number of Patients Achieving PASI 50, PASI 75, PASI 90, and PASI 100 Responses at Week 12
• The Number of Patients With sPGA Score of Clear (0) or Almost Clear (1) at Week 12
• The Change From Baseline in Dermatology Life Quality Index (DLQI) Through Week 52

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: each participant contributes a percent improvement in PASI score, and the group result is a mean. The registry identifies the reported parameter as a least-squares mean and its dispersion as standard error. A least-squares mean is a model-based estimate; it is not necessarily identical to a raw arithmetic mean when the analysis adjusts for other variables. The registry does not list the covariates used for the primary ANCOVA, or the detailed model specification, so those features are not reported in the registry record.

What does the unadjusted recalculation represent?

The recalculation compares the posted group summaries without the sponsor’s ANCOVA adjustment. It is a simple unadjusted comparison, not a replacement for the registered analysis. For the primary endpoint, the estimate is -2.04 for EU-Stelara relative to CT-P43, with a 95% confidence interval from -6.905 to 2.825 and p=0.411. The calculation uses the recorded group estimates and an approximate pooled standard deviation; the approximation is flagged in the statistical summary. This distinction matters because standard errors, model adjustment, and the direction in which a contrast is written can lead to different-looking estimates or intervals.

Why is the primary analysis different?

The registry lists ANCOVA for the sponsor-reported primary analysis. In general, analysis of covariance compares groups while adjusting for specified covariates, often including a baseline measure. Adjustment may improve precision when the model and covariates are appropriate, but the exact adjustment cannot be reconstructed from the registry entry because the covariates and model details are not reported in the registry record. The reported treatment difference is 2.05 with a 90% confidence interval from -0.23 to 4.32. Since the sponsor identifies this as an equivalence analysis, interpretation would require the prespecified equivalence margin and its decision rule; those details are not reported in the registry record.

How should confidence intervals and p-values be read?

In general, a confidence interval describes a range of values reasonably compatible with the observed data under the analysis assumptions. It conveys uncertainty about the estimate, not the probability that a specific treatment effect is true. A p-value measures how unusual the data, or more extreme data, would be under a specified null hypothesis and analysis model. It is not the probability that the null hypothesis is true, and it does not measure clinical importance. The recalculated p-values are explicitly unadjusted and should not be confused with the sponsor’s formal ANCOVA analysis.

For a difference between group means, an interval that includes zero does not establish that the groups are identical. It indicates that the data do not narrowly identify the direction and size of the difference under that calculation. Equivalence requires a prespecified acceptable range and an interval that meets the protocol’s criterion. The registry entry reports that an equivalence analysis was used, but the margin and decision details are not reported in the registry record.

Why do some outcome types need different methods?

Continuous outcomes, such as PASI score or percent improvement, are summarized by means and standard deviations or standard errors. Binary outcomes, such as whether a participant reached a response category, are counts within denominators; comparisons can be expressed as risk differences or other relative measures. These summaries answer different questions and their estimates should not be compared as if they were on the same scale. General statistical practice also requires attention to distribution shape, influential observations, and whether the chosen model fits the outcome. The registry record does not report diagnostic checks or alternative model analyses.

When variability is greater than a simple model assumes, standard errors can be too small and confidence intervals too narrow. This is a general reason to check model assumptions. The registry record does not describe over-dispersion checks, and it is not appropriate to infer whether they were needed from the aggregate summaries alone.

How do randomization and the later switch affect comparisons?

Randomization supports a fair initial comparison by reducing systematic differences between assigned groups, on average. The primary Week 12 endpoint occurs before the described Week 16 re-randomization. Later comparisons distinguish CT-P43 maintenance, EU-Stelara maintenance, and participants switched to CT-P43; those treatment pathways are not interchangeable with the initial two-arm contrast. The record does not report the analysis estimand or handling of treatment changes in detail, so the exact causal interpretation of later summaries is not reported in the registry record.

The registry lists one primary analysis and five secondary outcomes. The recorded outcome count does not establish how many statistical tests were planned or whether multiplicity was controlled. In general, testing multiple outcomes without adjustment increases the chance of at least one apparently notable result arising by chance. The registry record does not report a multiplicity procedure, a hierarchy of secondary hypotheses, or a complete analysis plan. As a result, secondary p-values calculated from summaries are exploratory rather than a substitute for a documented confirmatory strategy.

11. Confidence Intervals and Precision

Precision concerns how narrowly an estimate is determined by the available data and analysis. The recalculated primary mean difference is -2.04, with a 95% confidence interval from -6.905 to 2.825. Because the interval spans zero and permits differences in either direction, the unadjusted result does not pinpoint a single direction or a narrow value for the contrast. The unadjusted p-value is 0.411. These statistics describe the recalculation, not the sponsor’s adjusted analysis.

The sponsor-reported ANCOVA result is a treatment difference of 2.05 with a 90% confidence interval from -0.23 to 4.32. The interval is associated with the sponsor’s equivalence analysis. A 90% interval is not directly interchangeable with the 95% interval from the recalculation: the analyses differ both in confidence level and in method. The registry does not report an equivalence margin, which is necessary for judging whether that interval meets the study’s stated equivalence criterion.

In general, wider intervals indicate less precise estimation, while narrower intervals indicate greater precision, conditional on the assumptions of the analysis. Precision is not the same as clinical importance, and an interval including zero does not prove no difference. Nor does a point estimate alone show how precisely the underlying contrast has been estimated. Here, the recalculated estimate and interval are summaries of posted group-level statistics; they do not recover participant-level information or the sponsor’s ANCOVA model.

The sample sizes used for the endpoint summaries and the spread of the measurements influence precision, but the registry record does not provide all information needed to assess precision under the full primary model. In particular, the covariates, missing-data handling, and equivalence margin are not reported in the registry record. Interpretation should therefore keep the sponsor’s formal analysis distinct from the simple unadjusted recalculation.

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 based on the observed effect, not the trial’s original design calculation. For the continuous and binary outcomes in this study, the figures are participants per arm. They are not total event counts. The assumptions listed for the illustration are a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect set at the stated fraction of the observed effect.

The 80% power column describes a planning scenario in which a study with the listed participants per arm would have an 80% chance of detecting the specified effect under the stated assumptions, if that effect and the model assumptions were correct. The 90% power column describes the corresponding planning scenario at 90% power. These are design probabilities for hypothetical future studies, not probabilities that the observed trial result is true. This is not observed power.

Rows that use 100%, 75%, or 50% of the observed effect illustrate how the required sample size changes when the target effect is varied. Smaller effects require more participants to detect with the same nominal power, all else held constant. The figures are not a recommendation for a future trial: a design would need a scientifically justified target effect, prespecified analysis, outcome variability assumptions, allocation plan, and allowances appropriate to its own setting. The registry record does not report the original sample-size justification or the assumptions used when the trial was planned.

Because these illustrations are derived from observed effects, they should be treated cautiously. Observed effects can be imprecise, and planning from a single estimate can produce misleadingly large or small requirements. The estimates also rely on simplified assumptions and do not reproduce the sponsor’s ANCOVA analysis or any equivalence design considerations. The registry record does not report a sample-size calculation for the equivalence objective.

13. How the Sample Size Is Derived

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

Formula

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

Worked calculation for this trial

1. Observed difference Δ = -2.040; pooled standard deviation σ = 28.002.
2. n = 2 × (1.96 + 0.842)² × 28.002² / -2.040² = 2,957.8, rounded up to 2,958 participants per arm for 80% power.

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

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -2.04000000000001                      # observed difference in means
sigma <- 28.0022796675535                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

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

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(4673786)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 2,958 (80% power), 3,960 (90% power)
 75% of observed effect: n per arm = 5,259 (80% power), 7,040 (90% power)
 50% of observed effect: n per arm = 11,832 (80% power), 15,839 (90% power)
power.t.test: 2958.7 
Simulated power at n = 2,958 per arm: 0.800 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor’s recorded primary analysis is an ANCOVA treatment difference (%) of 2.05, with a 90% confidence interval from -0.23 to 4.32, and is classified as an equivalence analysis. The registry record does not report a p-value for this analysis. It also does not give the equivalence margin or the detailed analysis specification.

The recalculation is a simple, unadjusted comparison of the posted primary endpoint summaries. It gives a mean difference of -2.04 for EU-Stelara relative to CT-P43, with a 95% confidence interval from -6.905 to 2.825 and p=0.411. The sign is reversed because the recalculated contrast is expressed in the opposite group order from the sponsor’s treatment difference. The small difference in the reported point estimates also reflects that these are not the same analysis: one is an adjusted ANCOVA result and the other is an unadjusted summary-based calculation.

The sponsor’s own analysis takes precedence for the trial’s formal primary inference. The recalculation can help readers understand the scale of the posted group summaries, but it should not be used to override the sponsor’s analysis or to declare equivalence. Without the margin and decision rule, the equivalence conclusion cannot be independently checked from the registry record.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when statistical conclusions are drawn across several outcomes, time points, groups, or comparisons. Even if each individual test uses a conventional significance threshold, the chance of at least one false-positive result rises as more tests are considered, unless the testing strategy accounts for that. This is a general statistical concern, not evidence that any particular secondary result in this study is false.

The registry record lists one primary analysis and five secondary outcomes. It does not report whether the sponsor applied a multiplicity adjustment, used a hierarchical testing procedure, or treated the secondary outcomes as exploratory. The number of registered outcomes alone does not establish the number of tests conducted. No multiplicity method or confirmatory sequence should be inferred where one is not reported in the registry record.

Missing-data handling is also important because outcome summaries can depend on which participants have measurements at a given assessment. The registry gives outcome-specific denominators, but does not describe why they differ, how missing values were handled, whether imputation was used, or what sensitivity analyses were conducted. Those details are not reported in the registry record. Consequently, the aggregate data do not establish whether missingness could have influenced the estimates.

The primary analysis population is named as the Modified ITT Set, but the rules defining that population are not reported in the registry record. The registry does not provide a full participant flow or specify how protocol deviations, treatment discontinuations, or post-randomization events were handled in the primary analysis. The sponsor’s primary method is listed as ANCOVA, but its covariates and model details are not reported. The record also does not supply the equivalence margin needed to interpret the registered equivalence analysis.

These omissions do not invalidate the posted results, but they limit independent assessment of the analysis choices and robustness. A full protocol and statistical analysis plan would be needed to establish the intended multiplicity control, population definitions, missing-data assumptions, and model specifications. Those materials are not reported in the registry record.

16. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 3% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: nephrolithiasis (0.8%), respiratory failure (0.8%), covid-19 pneumonia (0.8%), covid-19 (0.8%), guillain-barre syndrome (0.8%).

The safety summaries separate Treatment Period I from the later treatment pathways. During Treatment Period I, serious adverse events affected 4 participants in the CT-P43 group and 4 in the EU-Stelara group. Other adverse events affected 14 and 20 participants, respectively. No deaths are listed for these initial treatment groups.

For Treatment Period II, the registry lists CT-P43 maintenance, EU-Stelara maintenance, and the group switched to CT-P43 separately. Serious adverse events affected 5 participants in CT-P43 maintenance, 3 in EU-Stelara maintenance, and 2 in the switched group. Other adverse events affected 35, 25, and 28 participants, respectively. One death is listed in CT-P43 maintenance; no deaths are listed in the other Treatment Period II groups.

The listed serious adverse event terms include nephrolithiasis, respiratory failure, COVID-19 pneumonia, COVID-19, Guillain-Barre syndrome, and subarachnoid haemorrhage, with percentages recorded in the registry. These are descriptive counts by treatment period and group. The summaries do not establish that an intervention caused an event or support a direct comparison of safety without considering exposure, follow-up, event definitions, and the study’s safety analysis methods. Such details are not reported in the registry record.

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

The primary endpoint summaries show similar group-level mean percent improvement values at Week 12: 77.93 for CT-P43 and 75.89 for EU-Stelara. The sponsor’s formal analysis is an ANCOVA equivalence analysis, while the recalculation is an unadjusted comparison. The estimates and intervals describe the data under their respective methods; neither should be expanded into a claim about outcomes or patients beyond the trial’s measured population and follow-up.

The recalculated confidence interval includes zero, and the sponsor’s 90% interval is reported without an equivalence margin. A failure to establish a difference is not proof that treatments are identical. Similarly, an equivalence analysis requires a prespecified margin and a result meeting its decision criterion; the registry record does not report that margin. The sponsor’s analysis should be treated as the formal analysis, but the available registry information does not allow the equivalence criterion to be independently evaluated.

Secondary outcomes provide additional measurements, including PASI scores, response categories, sPGA status, and quality of life. They are not interchangeable with the primary endpoint, and later outcomes reflect maintenance or switch treatment pathways. The registry summaries do not establish effects on outcomes that were not measured or on follow-up beyond the reported periods.

In general, a clinical trial estimate is conditional on its population, design, definitions, measurement schedule, and analysis assumptions. Here, the primary population is identified as the Modified ITT Set, but its detailed definition is not reported in the registry record. Missing-data procedures, multiplicity control, and the sponsor’s full model specifications are also not reported. The results should therefore be interpreted as statistical summaries of the recorded comparisons, with those limits in mind, rather than as universal conclusions or treatment advice.

18. Why This Trial Matters Statistically

This trial is statistically informative because it uses randomization and an active comparator to assess a defined Week 12 outcome. Random allocation supports a structured comparison between the initial CT-P43 and EU-Stelara groups, while the reported ANCOVA analysis offers the sponsor’s formal model-based estimate. Reporting both group summaries and an adjusted comparison helps readers distinguish the raw scale of the endpoint from the trial’s registered analysis.

The equivalence framing makes the missing design details especially important. Equivalence is not established merely because a conventional test does not detect a difference. A prespecified margin defines what range of differences is considered sufficiently small, and inference depends on comparing the confidence interval with that margin. The registry identifies an equivalence analysis and its 90% interval, but does not report the margin or the decision rule. That gap limits independent statistical interpretation.

The trial also illustrates why follow-up structure matters. The initial randomized comparison is distinct from the post-Week 16 maintenance and switch groups. Later summaries answer questions about different treatment pathways and should not be read as if they preserve the initial two-group allocation unchanged.

Finally, the record includes a range of secondary endpoints and safety summaries. Their interpretation depends on analysis populations, missingness, multiplicity, and exposure time. Those details are not fully reported in the registry record. Statistically, the most useful reading keeps the primary comparison, later pathway summaries, and descriptive safety counts separate, and avoids assigning stronger certainty than the recorded methods and intervals support.

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.

Several trial-specific details needed for a full independent assessment are not reported in the registry record. The equivalence margin and decision rule are absent, although the primary analysis is classified as an equivalence analysis. Without those criteria, the sponsor’s 90% confidence interval cannot be checked against the intended equivalence standard.

The primary outcome is reported for the Modified ITT Set, but the criteria defining that population are not stated. The registry also does not describe missing-data handling, reasons for differences in outcome denominators, or sensitivity analyses. This limits assessment of whether the endpoint summaries could be affected by missing measurements or post-randomization exclusions.

The sponsor’s primary analysis is identified as ANCOVA, but covariates, model specification, and diagnostic checks are not reported. The summary-based recalculation is unadjusted and uses an approximate pooled standard deviation for the primary comparison; it cannot reproduce the sponsor’s model. The reported confidence intervals therefore refer to different analyses and should not be treated as substitutes for one another.

The trial includes a second randomization of the original Stelara group before dosing at Week 16. Later outcomes compare maintenance and switch groups, so they have a different treatment history from the initial Week 12 comparison. The registry record does not provide a detailed estimand or full analysis plan for these later comparisons.

Multiplicity procedures for secondary outcomes, the original sample-size justification, and detailed safety analysis methods are also not reported in the registry record. These limitations affect how confidently the posted secondary and safety summaries can be interpreted, without changing the descriptive values recorded.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study to Compare the Efficacy and Safety of CT-P43 to Stelara in Patients With Plaque Psoriasis — NCT04673786.
• Registry record last updated 2023-06-05; status last verified 2023-06.
• Results first posted 2023-06-05.
• 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 NCT04673786, a completed randomized, active-controlled, double-blind, Phase 3 parallel-group study sponsored by Celltrion. It enrolled 509 participants with moderate to severe plaque psoriasis and compared CT-P43 with Stelara. The primary endpoint is mean percent improvement from baseline in PASI score at Week 12 in the Modified ITT Set.

The posted primary endpoint means are 77.93 for CT-P43 and 75.89 for EU-Stelara. The sponsor reports an ANCOVA treatment difference of 2.05 with a 90% confidence interval from -0.23 to 4.32, classified as an equivalence analysis. An unadjusted recalculation gives -2.04 for EU-Stelara relative to CT-P43, with a 95% confidence interval from -6.905 to 2.825.

The record also lists secondary efficacy outcomes and safety summaries, including later maintenance and switch groups after the Week 16 re-randomization. The equivalence margin, full statistical analysis plan, missing-data methods, and multiplicity procedures are not reported in the registry record.