Study of Dupilumab for the Treatment of Patients With Prurigo Nodularis, Inadequately Controlled on Topical Prescription Therapies or When Those Therapies Are Not Advisable (LIBERTY-PN PRIME): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Dupilumab for the Treatment of Patients With Prurigo Nodularis, Inadequately Controlled on Topical Prescription Therapies or When Those Therapies Are Not Advisable (LIBERTY-PN PRIME) (NCT04183335), a randomized phase 3 study. The primary outcome is Percentage of Participants With Improvement (Reduction) in Worst Itch Numeric Rating Scale (WI-NRS) Scores by Greater Than or Equal to (>=) 4 Points From Baseline to Week 24.

2. Clinical Question

3. Trial Design

LIBERTY-PN PRIME (NCT04183335) is a randomized, quadruple-masked, parallel-group phase 3 study sponsored by Sanofi. The registry lists an enrollment of 151 and a completed study. The recorded study start was 2019-12-12, and the primary completion date was 2021-11-12. The condition listed is neurodermatitis; the trial title and objectives describe prurigo nodularis.

The two groups received dupilumab or matched placebo, each alongside stable-dose topical corticosteroids or topical calcineurin inhibitors. The dupilumab regimen began with 600 mg subcutaneously on Day 1 and continued with 300 mg every two weeks for 24 weeks. Placebo followed the matching schedule. The record also lists moisturizers among the interventions, but does not specify their use by group in the arm descriptions.

The primary objective was to evaluate itch response in participants with prurigo nodularis who were inadequately controlled on topical prescription therapies or for whom those therapies were not advisable. The primary endpoint assessed the percentage reaching a reduction of at least 4 points on WI-NRS from baseline to Week 24. Secondary objectives covered other itch measures, skin lesions, health-related quality of life, safety, and immunogenicity.

The record identifies randomization, quadruple masking, and a parallel-group model, but does not report the allocation sequence method, the identities of the masked parties, the trial's original sample-size justification, or detailed site information. The protocol's analysis plan and any planned interim analyses are not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: A total of 151 participants were randomized in 1:1 ratio to receive study interventions (placebo or dupilumab) by interactive response technology (IRT).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Analysis was performed on intent-to-treat (ITT) population which included all participants with a treatment kit number allocated and recorded in the IRT database and were analyzed according to the treatment group allocated by randomization regardless of if treatment kit was used or not.

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: Analysis was performed on randomized population.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With Improvement (Reduction) in Worst Itch Numeric Rating Scale (WI-NRS) Scores by Greater Than or Equal to (>=) 4 Points From Baseline to Week 24, measured over Baseline, Week 24.

The primary endpoint is the percentage of participants whose worst-itch score improved by at least 4 points from baseline to Week 24. WI-NRS asks participants to rate the intensity of their worst itch over the past 24 hours on an 11-point scale from 0, no itch, to 10, worst imaginable itch. Higher scores indicate more severe itch.

This is a binary response endpoint: each participant either meets the specified improvement threshold or does not. The reported percentages therefore describe the proportions reaching that threshold in each randomized group. They do not show the full distribution of individual score changes, nor do they describe how far beyond the threshold responders improved. The registry identifies the primary analysis population as intent-to-treat, with participants analyzed according to randomized assignment whether or not they used the treatment kit.

A threshold endpoint can make a result easier to interpret as the share reaching a defined level of improvement, while also discarding information about changes that fall short of or exceed the cutoff. It should be read alongside continuous itch outcomes, which retain information about score changes across the scale. The registry includes a percent-change WI-NRS outcome among the secondary measures.

The endpoint's time frame is baseline to Week 24. It does not establish the pattern of change at every point during the trial or what happens after the recorded treatment period.

7. Results Posted in the Registry

• Dupilumab 300 mg Q2W: 60.0% (45/75) versus 18.4% (14/76) on control; risk difference 41.6 percentage points (95% CI 27.5 to 55.7), risk ratio 3.26 (1.96–5.41); unadjusted two-proportion z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Percentage of Participants With Investigator's Global Assessment For Prurigo Nodularis-Stage (IGA PN-S) Scores of 0 or 1 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:
  • Dupilumab 300 mg Q2W: 48.0% (36/75) versus 18.4% (14/76) on control; risk difference 29.6 percentage points (95% CI 15.3 to 43.9), risk ratio 2.61 (1.54–4.42); 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 Dupilumab 300 mg Q2W than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants With Both an Improvement (Reduction) in WI-NRS Scores by >=4 Points and an IGA PN-S Scores of 0 or 1 From Baseline 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:
  • Dupilumab 300 mg Q2W: 38.7% (29/75) versus 9.2% (7/76) on control; risk difference 29.5 percentage points (95% CI 16.7 to 42.3), risk ratio 4.20 (1.96–8.99); 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 Dupilumab 300 mg Q2W than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent Change From Baseline in WI-NRS Scores at Week 24

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Dupilumab 300 mg Q2W: mean -48.89 versus -22.22 on control; difference -26.67 (95% CI -42.40 to -10.94), standardized effect d = -0.56; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Dupilumab 300 mg Q2W than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover several related dimensions: itch response and score change, prurigo nodularis lesion assessment, health-related quality of life, skin pain, anxiety and depression scores, and other itch measures. The numerical secondary results available in the record show a broadly consistent pattern across the posted lesion, combined itch-and-lesion, and itch score outcomes. These measures complement the primary endpoint by asking whether the group pattern extends beyond the primary threshold-based itch response.

The secondary endpoints are not all independent confirmations. The combined response incorporates both an itch reduction and a lesion assessment, and other itch outcomes overlap conceptually with the primary WI-NRS measure. A continuous score change also summarizes the outcome differently from a binary response. Taken together, the secondary results offer additional perspectives, but they do not replace the primary endpoint or establish the same question repeatedly.

The registry lists 20 posted secondary outcomes, while the record does not supply numerical results for every one of those outcomes in the information summarized for this analysis. Conclusions should therefore be limited to the outcomes with reported results rather than generalized to every secondary objective.

Unadjusted secondary p-values carry less weight when many outcomes are examined because repeated testing can increase the chance of apparently small p-values. The registry record does not report a multiplicity adjustment or a testing hierarchy. Secondary findings are consequently most useful as context and support for the primary result, not as standalone confirmatory evidence.

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

• Percentage of Participants With Investigator's Global Assessment For Prurigo Nodularis-Stage (IGA PN-S) Scores of 0 or 1 at Week 24
• Percentage of Participants With Both an Improvement (Reduction) in WI-NRS Scores by >=4 Points and an IGA PN-S Scores of 0 or 1 From Baseline at Week 24
• Percent Change From Baseline in WI-NRS Scores at Week 24
• Change From Baseline in Health-Related Quality of Life (HRQoL) as Measured by Dermatology Life Quality Index (DLQI) at Week 24
• Change From Baseline in Skin Pain-NRS at Week 24
• Change From Baseline in Hospital Anxiety and Depression Scale (HADS) Total Score at Week 24
• Probability of Participants With an Improvement (Reduction) in WI-NRS Scores by >=4 Points From Baseline at Week 24
• Change From Baseline in WI-NRS Scores at Week 12 and 24

9. Statistical Interpretation

10. Statistical Methods Explained

For the primary endpoint, the outcome is a binary indicator: whether a participant achieved the prespecified WI-NRS reduction threshold by Week 24. A group percentage estimates the proportion meeting that response definition among the analyzed participants. Comparing group percentages can be expressed as a risk difference, a risk ratio, or an odds ratio. These statistics describe different scales of contrast and should not be read as if they were the same quantity.

What does the risk difference express?

The recalculated risk difference is 0.416, with a 95% confidence interval from 0.275 to 0.557. A risk difference subtracts the response proportion in the comparison group from the response proportion in the other group. It is expressed on the probability scale, so it describes the difference in the proportions meeting the response definition. The recalculation uses the posted group summaries and is unadjusted; it is not the sponsor's model-based estimate.

The risk difference is often intuitive because it stays on the outcome's percentage scale. Its value depends on the event proportions in the groups and on the endpoint definition. It does not describe the relative contrast, which is what a risk ratio or odds ratio addresses. The registry's recalculated comparison also lists relative measures, but interpreting any relative measure requires keeping its scale distinct from absolute percentage-point differences.

Why is the sponsor's odds ratio different in form?

The sponsor reports a Cochran-Mantel-Haenszel odds ratio of 6.5, with a 95% confidence interval from 2.78 to 15.41 and p < 0.001. Odds are the probability of an event divided by the probability of no event. An odds ratio compares those odds across groups; it is not a ratio of response percentages. The Cochran-Mantel-Haenszel approach is a method for estimating an association across strata. The specific strata used and further details of the sponsor's implementation are not reported in the registry record.

The unadjusted re-calculation and sponsor-reported analysis need not have identical estimates or intervals because the measure and analysis method differ. The sponsor result is the trial's reported inferential analysis. The unadjusted calculation is a separate, transparent comparison based on the posted summaries; it should not be mistaken for a replacement of the sponsor's prespecified analysis.

What does a p-value say?

A p-value describes how compatible the observed data are with a specified null model, under the assumptions of the statistical procedure. A small p-value is not the probability that the null hypothesis is true, and it does not quantify the size or clinical importance of a difference. The sponsor reports p < 0.001 for the primary analysis. The recalculated unadjusted comparison reports p < 0.001. These values arise from their respective analyses and should be interpreted alongside the effect estimates and confidence intervals.

The registry reports the primary population as intent-to-treat. In general, an intent-to-treat analysis follows randomized assignment, which preserves the comparison created by randomization as far as the analysis population and outcome data allow. Here, the record specifies that participants with an allocated and recorded treatment kit number were analyzed according to allocated group, regardless of whether the kit was used. It does not describe how missing Week 24 outcomes were handled, so the exact role of missing data in the analysis cannot be assessed from this record.

Why do secondary outcomes need cautious interpretation?

Multiple outcomes create multiple opportunities for apparently notable results. If each is tested without adjustment, the chance of at least one small p-value under a collection of null hypotheses can increase. An adjustment can account for the multiplicity, but the registry information does not report whether a formal adjustment was planned or used for the secondary outcomes. It also does not report a hierarchy or gatekeeping strategy for those outcomes. Consequently, secondary findings are best viewed as supporting descriptions rather than as a set of equally definitive tests.

Some measures are correlated or overlapping. For example, the combined response requiring both an itch improvement and a lesion score is related to, but more restrictive than, either component considered separately. Correlation means that secondary results do not represent wholly independent replications of the primary finding. A continuous change measure and a binary response measure can also differ in sensitivity to the shape of the outcome distribution and to the selected response cutoff.

The registry lists least-squares means and an ANCOVA comparison for the percent-change WI-NRS outcome. ANCOVA is a regression-based method that can compare groups while accounting for included covariates. The specific covariates and details of model diagnostics are not reported in the registry record. The recalculated continuous comparison is based on posted summary statistics and is not a substitute for that adjusted model.

General statistical interpretation also depends on assumptions about the outcome and analysis. For binary outcomes, the estimate and precision depend on the observed event proportions and participant counts. For continuous outcomes, the model and uncertainty calculations depend on the distribution and variance structure. The record does not provide enough diagnostic information to evaluate those assumptions independently.

11. Confidence Intervals and Precision

The primary sponsor-reported odds ratio is 6.5, with a 95% confidence interval from 2.78 to 15.41. This interval is wide enough to leave substantial uncertainty about the magnitude of the odds contrast, while its reported limits remain above the null value of an odds ratio of 1. The interval is on the odds-ratio scale; it does not directly give a range for the difference in response percentages.

The unadjusted recalculated risk difference is 0.416, with a 95% confidence interval from 0.275 to 0.557. Its limits are on the risk-difference scale, where a value of zero represents no difference in response proportions. The distinct scales and analysis methods mean that the two intervals cannot be compared as if they estimated the same parameter.

A confidence interval is a range of values compatible with the data and the method used to calculate it. In general, a 95% confidence procedure would produce intervals covering the target parameter in 95% of repeated samples under its assumptions. It does not mean that there is a 95% probability that this particular interval contains the true value. The interval reflects sampling uncertainty, not every source of uncertainty, such as limitations in measurement or applicability to other populations.

The registry reports group percentages for the primary endpoint but does not provide separate confidence intervals for each group percentage in the listed results. The comparison intervals are more useful for assessing the uncertainty in the contrast. Precision is also influenced by the number of observed outcomes and the analysis method; the record's reported estimates should be interpreted in the context of the trial population and endpoint definition.

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 illustrations based on the observed effect, not the trial's original design calculation. For the non-time-to-event outcomes in this trial, the entries mean participants per arm, rather than a total across groups. As a general convention, time-to-event planning entries refer to the total number of events; no such endpoint is the focus of the results.

The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to a stated fraction of the observed effect: 100%, 75%, or 50%. These are hypothetical planning scenarios. The original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the estimated participants per arm under those assumptions for a study designed to have an 80% chance of detecting the selected effect if that effect is the true one. The 90% power column expresses the corresponding planning target for a 90% chance. Power is a property of a planned study under assumptions; it is not a measure of the probability that a particular result is true.

The sample-size table and curve should be read as scenarios rather than as a reconstruction of the actual trial design. Planning for a smaller effect requires more participants per arm than planning for a larger effect, because smaller group differences are harder to distinguish from sampling variation. The displayed calculations are based on the observed effect and are not observed power.

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 = 0.184; treatment proportion p₁ = 0.600; average p̄ = 0.392.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6904 = 1.3533.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6247 = 0.5258.
4. n = (1.3533 + 0.5258)² / (0.4158)² = 20.4, rounded up to 21 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 <- 0.184210526315789                          # control proportion
p1 <- 0.6                          # 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(4183335)
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 = 21 (80% power), 27 (90% power)
 75% of observed effect: n per arm = 36 (80% power), 47 (90% power)
 50% of observed effect: n per arm = 74 (80% power), 98 (90% power)
power.prop.test: 20.4 
Simulated power at n = 21 per arm: 0.817 (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 sponsor's primary result is a Cochran-Mantel-Haenszel odds ratio of 6.5, with a 95% confidence interval from 2.78 to 15.41 and p < 0.001. This is the trial's reported analysis. The separate recalculation uses the posted group summaries to estimate an unadjusted risk difference of 0.416, with a 95% confidence interval from 0.275 to 0.557, and reports p < 0.001.

These estimates are not conflicting versions of the same measure. One is an odds ratio from the sponsor's Cochran-Mantel-Haenszel analysis; the other is an unadjusted difference in response proportions. Odds ratios and risk differences use different scales, and adjustment or stratification can also affect an estimate. Details of the sponsor's strata are not reported in the registry record.

The trial's reported analysis should be distinguished from the summary-statistic re-calculation. The latter helps show the absolute contrast in the observed response proportions, but does not reproduce the sponsor's method or replace the sponsor's inferential result. The registry record does not flag a discrepancy between the two analyses.

15. Multiplicity, Missing Data and Analysis Populations

The primary endpoint is clearly identified as the Week 24 WI-NRS response. The record also describes numerous secondary outcomes, spanning itch, lesions, quality of life, skin pain, anxiety and depression, safety, and immunogenicity. Evaluating several endpoints raises a multiplicity question: without an appropriate strategy, the overall chance of false-positive findings across a family of tests can exceed the chance associated with a single test.

The registry record does not report whether secondary hypotheses were arranged in a prespecified hierarchy, whether p-values were adjusted for multiplicity, or whether some secondary analyses were considered exploratory. It also does not provide a complete statistical analysis plan. The posted secondary p-values should therefore not automatically be interpreted as confirmatory evidence at the same strength as the primary analysis.

The primary analysis population is described as intent-to-treat. It included participants with a treatment kit number allocated and recorded in the IRT database, analyzed according to randomized assignment regardless of kit use. This description is useful, but it does not answer every population question. The registry record does not report detailed rules for handling participants with missing endpoint data, protocol deviations, or other exclusions from individual analyses.

Missing data can affect both the estimate and its precision, particularly if the chance of an unavailable measurement differs between groups or is related to the unobserved outcome. Appropriate methods depend on the amount, pattern, and plausible causes of missingness. The record does not report the Week 24 missing-data count by group, the imputation method, sensitivity analyses, or assumptions about missing outcomes. Those details are needed to assess how robust the endpoint analysis is to incomplete follow-up.

The registry does not report interim analyses, stopping rules, or the original sample-size justification. These omissions do not establish that such procedures were absent; they mean that they cannot be assessed from 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: acute myocardial infarction (2.7%), covid-19 (1.3%), covid-19 pneumonia (1.3%), sepsis (1.3%), hodgkin's disease (1.3%).

The registry reports serious adverse events in 8 of 75 participants at risk in the placebo group and 5 of 75 participants at risk in the dupilumab group. Other adverse events are reported in 15 of 75 participants at risk in the placebo group and 14 of 75 participants at risk in the dupilumab group. No deaths are reported in either group.

These are descriptive counts over the recorded follow-up. They do not, by themselves, establish whether an event was caused by treatment, whether event types differed in severity or duration, or whether the groups had comparable exposure time. The record lists several serious-event terms and percentages but does not assign each listed term to a treatment group in the information.

Adverse-event comparisons require context, including event definitions, ascertainment, timing, and participant exposure. The registry figures should be read as a summary of reported events, not as a complete causal assessment of safety. Broader safety interpretation is limited by the information reported in the registry record.

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

The primary result describes a difference between randomized groups in the proportion of participants meeting a specified itch-response threshold at Week 24. The posted percentages are 60.0% for dupilumab and 18.4% for placebo. The sponsor's analysis reports an odds ratio of 6.5, with a 95% confidence interval from 2.78 to 15.41 and p < 0.001. The unadjusted recalculation gives a risk difference of 0.416, with a 95% confidence interval from 0.275 to 0.557.

These results concern participants who met the study's eligibility description, received the assigned study regimen alongside specified topical background therapy, and were assessed at the stated time point. They do not establish what would occur in every person with prurigo nodularis, under different treatment conditions, or over a longer period. The registry information does not establish persistence of the measured response after the 24-week treatment period.

The threshold endpoint does not describe every participant's degree of improvement. Participants just below the cutoff and participants with little change are grouped together as not meeting the response definition; responders may have different amounts of improvement beyond the cutoff. The continuous itch outcome and lesion measures offer other views, but no single measure captures every aspect of the condition.

The results also do not prove that every observed event or outcome was caused by the assigned treatment. Randomization supports a group comparison, but interpretation still depends on the analysis, missing outcome handling, measurement, and follow-up. The registry record does not report enough detail to assess every such issue. These findings are statistical evidence about the outcomes measured in this trial, not individualized medical guidance or a complete evaluation of treatment choices.

18. Why This Trial Matters Statistically

This trial illustrates why clinical results are best read through both the outcome definition and the effect scale. The primary endpoint is not a general label of improvement: it is the proportion achieving a specified change in a daily itch rating by a fixed assessment time. The group percentages answer a direct response question, while the risk difference and odds ratio express the contrast in different ways.

It also demonstrates the value of distinguishing the sponsor's analysis from an unadjusted calculation using summary data. The sponsor reports a Cochran-Mantel-Haenszel odds ratio; the recalculation expresses the difference in response proportions. Both can inform interpretation, but they are not interchangeable and do not necessarily target an identical statistical quantity.

Precision matters alongside the point estimate. Confidence intervals communicate uncertainty about the comparison and should be read on the scale for which they were calculated. A small p-value does not describe the size of the effect, and statistical evidence does not remove uncertainty about generalizability or missing data.

Finally, the secondary outcomes show why multiplicity matters. Trials often assess related outcomes to characterize different aspects of response, but numerous tests can make isolated secondary findings appear more persuasive than they are. Understanding the endpoint family, analysis population, and unreported analysis details helps keep conclusions proportional to the available evidence.

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.

The primary endpoint is a self-reported rating of worst itch over the preceding 24 hours. Such a measure captures participants' experience, but the registry record does not provide information about measurement completion, day-to-day variability, or the handling of missing daily ratings. The response definition also depends on a threshold: it does not preserve the full amount of change for each participant.

The primary assessment is specified at Week 24. The registry results do not establish durability beyond that assessment or describe the full time course of response. The study population was restricted to participants with prurigo nodularis whose topical prescription therapies were inadequate or not advisable, so the findings should not automatically be extended to populations outside that description.

Background topical therapy was part of both group regimens, which means the comparison concerns dupilumab versus matched placebo added to topical background treatment. The arm descriptions specify stable-dose topical corticosteroids or topical calcineurin inhibitors. The registry also lists moisturizers among interventions but does not detail their use in the arm descriptions.

The record does not report the original sample-size justification, full statistical analysis plan, missing-data methods, multiplicity strategy, or detailed methods for sponsor stratification. It also does not provide numerical results for every listed secondary outcome in the information summarized for this analysis. These gaps limit independent assessment of the analysis choices and the strength of secondary conclusions.

Safety figures are event counts and do not establish causality. The registry information does not provide enough detail on event timing, exposure, or group attribution for every listed serious-event term to support a comprehensive safety comparison.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study of Dupilumab for the Treatment of Patients With Prurigo Nodularis, Inadequately Controlled on Topical Prescription Therapies or When Those Therapies Are Not Advisable (LIBERTY-PN PRIME) — NCT04183335.
• Registry record last updated 2025-09-17; status last verified 2025-09.
• Results first posted 2022-12-12.
• 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

NCT04183335, LIBERTY-PN PRIME, was a completed randomized, quadruple-masked, parallel-group phase 3 study sponsored by Sanofi. It evaluated dupilumab versus matched placebo, each added to topical background therapy, in participants with prurigo nodularis inadequately controlled on topical prescription therapies or for whom those therapies were not advisable.

The primary endpoint was the percentage with at least a 4-point improvement in WI-NRS from baseline to Week 24. The registry reports 60.0% in the dupilumab group and 18.4% in the placebo group. The sponsor reported a Cochran-Mantel-Haenszel odds ratio of 6.5, with a 95% confidence interval from 2.78 to 15.41 and p < 0.001. An unadjusted re-calculation reports a risk difference of 0.416, with a 95% confidence interval from 0.275 to 0.557.

Secondary outcomes address itch, lesions, quality of life, and other measures. The registry reports serious adverse events and other adverse events by group, with no deaths reported. Missing-data handling, multiplicity methods, and the original sample-size justification are not reported in the registry record.