A Study to Evaluate the Efficacy and Safety of Imsidolimab (ANB019) in the Treatment of Participants With Acne Vulgaris: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Efficacy and Safety of Imsidolimab (ANB019) in the Treatment of Participants With Acne Vulgaris (NCT04856917), a randomized phase 2 study. The primary outcome is Change From Baseline in Facial Inflammatory Lesion Counts at Week 12.

2. Clinical Question

3. Trial Design

The registry identifies this as a randomized, quadruple-masked, parallel-group Phase 2 study of imsidolimab in participants with acne vulgaris. The three groups were imsidolimab 400/200 mg, imsidolimab 200/100 mg, and placebo. The dose descriptions specify subcutaneous injections on Day 1 and Days 29 and 57. The placebo group received matching placebo on those same scheduled days.

The registry record lists enrollment as 123 and status as completed. The primary completion date is 2022-02-01, and the study start date is 2021-05-15. The sponsor is Vanda Pharmaceuticals. The registry record does not report the trial's original sample-size justification, allocation ratio, or detailed operational description of masking.

The primary outcome was change from baseline in facial inflammatory lesion counts at Week 12. Baseline was defined as the last available measurement before the first dose. The measure counted pustules, papules, and nodular lesions on the forehead, both cheeks, nose, and chin. Secondary outcomes covered changes and percentage changes in inflammatory, non-inflammatory, and total facial lesion counts, as well as facial Investigator's Global Assessment outcomes at several scheduled weeks through Week 20.

The primary population is described as participants in the ITT Analysis Set with available data. The group sizes reported for the primary outcome are 34 for imsidolimab 400/200 mg, 35 for imsidolimab 200/100 mg, and 36 for placebo. These are the analysis counts attached to the endpoint, not a description of every participant's completion or follow-up status.

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: Participants in ITT Analysis Set with available data were analyzed.

5. Baseline Characteristics

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

Population: The Intent-to-Treat (ITT) Analysis Set included all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Facial Inflammatory Lesion Counts at Week 12, measured over Baseline, Week 12.

The primary endpoint is the mean change from baseline in facial inflammatory lesion counts at Week 12. The recorded lesions include pustules, papules, and nodular lesions counted across the forehead, left and right cheeks, nose, and chin. Baseline is the last available measurement taken before the first study-treatment dose. A negative mean change therefore represents a reduction in the counted lesions relative to baseline, while a positive change would represent an increase.

Lesion counts provide a numeric measure of facial inflammatory disease over the specified anatomical areas. Comparing mean changes between randomized groups allows the analysis to describe how much the average count changed in each group and how the changes differed between a regimen and placebo. The endpoint is one part of the study's assessment; it does not capture every aspect of acne or every possible patient experience.

The registry reports a mean and standard deviation for each group. The endpoint population is described as participants in the ITT Analysis Set with available data. The registry record does not report the detailed handling of participants without a Week 12 measurement, the criteria for counting a lesion, or a threshold defining a clinically important difference. Interpretation should therefore distinguish the observed numerical changes from any judgment about their clinical importance.

7. Results Posted in the Registry

• Imsidolimab 400/200 mg: mean -6.80 versus -9.60 on control; difference 2.80 (95% CI -2.95 to 8.55), standardized effect d = 0.23; z-test p = 0.340.
• Imsidolimab 200/100 mg: mean -7.40 versus -9.60 on control; difference 2.20 (95% CI -4.25 to 8.65), standardized effect d = 0.16; z-test p = 0.504.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary measure is continuous: it is a count summarized as a mean change from baseline. The registry lists a mean and standard deviation for each group. The comparisons include a mean difference between each imsidolimab group and placebo. In the simple unadjusted re-calculations, the difference is formed from the posted group summaries and is not an adjusted estimate from the sponsor's model.

What does a mean change represent?

In general, a mean change condenses individual changes into an average. It can describe the overall direction and typical size of change in a group, but it does not show the distribution of individual outcomes. Participants can have changes that differ substantially from the group mean. The standard deviation describes the spread of observed values around the mean; it is not the same as the uncertainty in the mean or the uncertainty in a comparison.

For this endpoint, the group means are -6.8, -7.4, and -9.6 lesions. Their standard deviations are 13.63, 16.38, and 10.66, respectively. The reported spread is large in relation to the mean changes, which indicates considerable variation among the observed changes. In general, variation within groups affects how precisely a difference between group means can be estimated. A mean alone cannot describe that variation.

What is the sponsor's comparison?

The sponsor reports analyses using the method label LRMM and presents least-squares mean differences. A least-squares mean difference is a model-based comparison, rather than a subtraction of the displayed group means alone. The registry record does not provide enough detail to expand the method label or describe the model specification, covariates, or assumptions. The sponsor's reported values are 2.9 for imsidolimab 400/200 mg versus placebo and 1.6 for imsidolimab 200/100 mg versus placebo. Their confidence intervals are reported at the 90% level.

In general, model-based estimates can differ from unadjusted comparisons because the model may use a different structure or account for information beyond the group summaries. The available record does not state the precise reason for the difference in these estimates. The sponsor's reported model results should be read as the sponsor's analysis, while the separate re-calculations should be understood as simple unadjusted comparisons.

What does a confidence interval communicate?

In general, a confidence interval expresses the uncertainty around an estimate under the analysis method. A narrower interval represents greater precision; a wider interval represents less precision. An interval that includes the no-difference value leaves open the possibility of no between-group difference as well as differences in either direction. It does not prove that the groups are the same. The sponsor's 90% intervals for both comparisons include the no-difference value. The registry record does not state the confidence level for the simple re-calculated intervals, so those intervals should not be assigned a level that is not recorded.

Confidence intervals depend on the data and the analysis assumptions. They do not account automatically for every possible source of uncertainty, such as missing measurements, measurement error, or selective reporting. The record describes the primary analysis population as ITT participants with available data, but does not detail the handling of missing Week 12 observations. That limits what can be concluded about how missingness may affect the estimates.

How should p-values be read?

In general, a p-value describes how compatible the observed data are with a specified null hypothesis under the analysis assumptions. It is not the probability that the null hypothesis is true, and it does not measure the clinical importance of an effect. The sponsor reports p = 0.376 and p = 0.618 for the two comparisons. The simple unadjusted re-calculations report p = 0.34 and p = 0.504. These values arise from their respective analyses and should not be interchanged.

A p-value does not summarize uncertainty as fully as an estimate and its interval. Estimates indicate the direction and scale of a contrast, while intervals show a range of values compatible with the data under the chosen method. Here, the sponsor's estimates and intervals convey that the differences are uncertain; the p-values alone should not be used to claim equivalence or to declare clinical relevance.

What does randomization contribute?

In general, random allocation is intended to make treatment groups comparable on average with respect to measured and unmeasured characteristics at the point of allocation. It supports a between-group comparison, but does not guarantee that groups are identical in a particular trial. Masking can reduce the influence of expectations on care or measurement, though the record's quadruple-masking label does not specify which roles were masked or how masking was maintained.

The trial uses a parallel-group design, meaning the assigned groups are followed as separate groups rather than crossing participants between interventions. The posted endpoint analysis compares each imsidolimab regimen with placebo. The registry record does not report a direct comparison between the two imsidolimab regimens, so no comparative conclusion between those regimens should be inferred from the placebo comparisons alone.

What can the group summaries support?

The summaries support descriptions of the observed mean changes and the posted comparisons. They do not provide the individual participant data, the distribution of changes, or a detailed account of missing observations. General statistical interpretation should therefore stay close to the reported means, standard deviations, estimated differences, intervals, and p-values. The registry record also does not report a clinical-importance threshold, a detailed model specification, or the multiplicity strategy for the collection of outcomes.

10. Confidence Intervals and Precision

The sponsor's primary comparisons are accompanied by 90% confidence intervals. For imsidolimab 400/200 mg versus placebo, the least-squares mean difference is 2.9 and the interval runs from -2.47 to 8.19. For imsidolimab 200/100 mg versus placebo, the difference is 1.6 and the interval runs from -3.73 to 6.95. Both intervals include the no-difference value and extend to values on either side of it. This indicates that the estimated contrasts are not precise enough to pin down a single direction or size of difference.

The simple unadjusted re-calculations have intervals from -2.955 to 8.555 for the 400/200 mg comparison and from -4.248 to 8.648 for the 200/100 mg comparison. The confidence level for these re-calculated intervals is not reported in the registry record. They are distinct from the sponsor's model-based 90% intervals and should not be interpreted as if they were the same analysis.

In general, a confidence interval gives a range of values compatible with the data under a stated method, not a guarantee that the true value lies within that particular interval. Wider intervals indicate more uncertainty about the estimated contrast. Here, the reported ranges include both potential benefit-direction and opposite-direction differences under the signed comparison, as well as no difference. The results do not identify a precise between-group effect. The registry record does not report a threshold for a clinically important difference, so statistical precision cannot be translated into a judgment about clinical importance.

11. 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 assumptions. The figures for these continuous-outcome comparisons are participants per arm, not total events. 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 as the stated fraction of the observed effect.

The entries for 100% of the observed effect use the observed contrast as the planning target. Entries for 75% and 50% of that effect represent smaller targets. The estimates are given separately for the 400/200 mg versus placebo comparison and the 200/100 mg versus placebo comparison. They are not the number of people who were enrolled or analyzed in this completed trial.

The 80% power column means the planned chance, under the stated assumptions and if the target effect were true, of detecting an effect using the specified test. The 90% power column uses a higher chance of detection and consequently requires more participants under the same assumptions. In general, smaller effects are harder to distinguish from random variation and require more participants to reach the same planned power. The increasing planning requirements across the smaller effect fractions illustrate that relationship.

These figures are not observed power. They do not retrospectively measure whether the completed trial was adequately powered, nor do they show the probability that an observed finding is correct. The registry record does not report the original sample-size justification, its target effect, or its planned power calculation. The planning figures should therefore be read only as illustrations based on the posted effect estimates and stated calculation assumptions.

12. 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 = 2.800; pooled standard deviation σ = 12.192.
2. n = 2 × (1.96 + 0.842)² × 12.192² / 2.800² = 297.6, rounded up to 298 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 <- 2.8                      # observed difference in means
sigma <- 12.1920198707766                     # 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(4856917)
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 = 298 (80% power), 399 (90% power)
 75% of observed effect: n per arm = 530 (80% power), 709 (90% power)
 50% of observed effect: n per arm = 1,191 (80% power), 1,594 (90% power)
power.t.test: 298.6 
Simulated power at n = 298 per arm: 0.799 (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.

13. Analyses Reported by the Sponsor

The sponsor's own primary analysis reports least-squares mean differences from the LRMM method: 2.9 for imsidolimab 400/200 mg versus placebo and 1.6 for imsidolimab 200/100 mg versus placebo. The corresponding 90% confidence intervals are -2.47 to 8.19 and -3.73 to 6.95, with p-values of 0.376 and 0.618. These are the trial sponsor's reported analyses and are the most direct account of how the registry presents the primary comparisons.

The simple re-calculations use the group means and standard deviations to obtain unadjusted mean differences of 2.8 and 2.2, with p-values of 0.34 and 0.504. They are not a reproduction of the sponsor's model. A model-based estimate can differ from a comparison calculated only from group summaries, and the registry record does not provide the model details needed to explain the exact differences.

The discrepancy flag is false, but the estimates should still be kept distinct because their methods differ. The sponsor's intervals are explicitly reported at the 90% level; the confidence level for the unadjusted re-calculated intervals is not stated in the registry record. Neither set of results establishes a precise between-group difference, and neither p-value should be read as the probability that a treatment effect is true.

14. Multiplicity, Missing Data and Analysis Populations

The registry record lists a primary outcome and numerous secondary outcomes. These include changes and percentage changes in facial inflammatory, non-inflammatory, and total lesion counts, as well as changes in facial Investigator's Global Assessment and the proportion achieving a specified clear or almost-clear assessment with a decrease from baseline. Several outcomes are assessed at multiple scheduled weeks. This creates multiple opportunities to test or summarize different outcomes and time points.

In general, when many statistical comparisons are made, the chance of observing a seemingly notable result by chance can increase. Methods such as a prespecified testing hierarchy or an adjustment to significance thresholds can address this issue, but the registry record does not report a multiplicity adjustment, testing sequence, or which secondary comparisons were intended to be confirmatory. Secondary results should therefore be interpreted as separate outcome-specific findings, not as a single unified test.

The primary population is described as participants in the ITT Analysis Set with available data. That wording identifies the population used but does not explain how missing measurements were handled. The registry record does not report the amount or pattern of missing Week 12 data, an imputation method, a sensitivity analysis for missingness, or whether the primary model included all available visits. Missing-data methods can affect estimates if the participants with observed outcomes differ systematically from those without them.

The registry record also does not provide details of the analysis population beyond that description, including how protocol deviations or treatment discontinuations were handled. The group sizes attached to the primary endpoint are reported, but they do not explain why participants may be absent from the available-data analysis. These reporting gaps limit assessment of the robustness of the primary and secondary findings. They do not show that a particular analysis choice was made; they indicate that the choice is not reported in the registry record.

15. 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: fallopian tube cyst (2.4%).

The safety summary reports serious adverse events affecting 1 participant in the imsidolimab 400/200 mg group and 0 participants in each of the imsidolimab 200/100 mg and placebo groups. The corresponding numbers at risk are 41, 39, and 41. The record also reports other adverse events affecting 8, 6, and 6 participants, respectively. Deaths are reported as 0 in each group.

The registry lists Fallopian tube cyst at 2.4% among the leading serious adverse event terms. The record does not identify a treatment group for that term in the information, so it should not be assigned to a particular group. The serious-event counts and the term listing are separate pieces of the safety summary and should be read as reported.

These figures describe counts in the posted safety record; they are not a comparative statistical analysis of risk. The registry record does not report details such as event severity beyond the serious-event classification, duration, relatedness assessment, or a formal between-group safety comparison. The reported event counts alone cannot establish whether a difference between groups is meaningful, and they do not provide a complete account of an individual's safety experience.

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

The primary results show reductions in mean facial inflammatory lesion counts from baseline in all three groups at Week 12. The reported mean changes were -6.8 for imsidolimab 400/200 mg, -7.4 for imsidolimab 200/100 mg, and -9.6 for placebo. The sponsor's model-based comparisons estimate positive differences relative to placebo, but both 90% confidence intervals include the no-difference value and extend across a range of possible contrasts.

These results do not establish that either imsidolimab regimen produced a greater average reduction than placebo. They also do not establish that the groups had the same outcomes. The intervals are compatible with uncertainty in the direction and size of the difference. The posted data should be described as estimates with substantial uncertainty rather than as proof for or against a particular treatment effect.

Statistical uncertainty is not the only consideration. The registry record does not report a threshold for the smallest clinically important change in lesion counts. It is therefore not possible to use these estimates alone to decide whether a difference of a particular size would matter to participants. The endpoint captures specified facial inflammatory lesions, not every symptom, concern, or consequence associated with acne vulgaris.

The trial's safety summary lists serious adverse event counts, other adverse event counts, and deaths by group. Those counts describe the reported events during the study but do not establish comparative safety. No treatment recommendation follows from these results. They are specific to this completed Phase 2 trial, its endpoint, analyzed population, follow-up schedule, and reported analyses. Further detail about missing data, multiplicity, the model specification, and clinical importance is not reported in the registry record.

17. Why This Trial Matters Statistically

This trial illustrates why group means and between-group comparisons answer different questions. Each mean change describes the average within-group change from baseline, while the mean difference compares the change in an imsidolimab group with the change in placebo. The placebo mean change is more negative than either imsidolimab group mean, and the sponsor's estimated contrasts are positive in the direction implied by that pattern. The comparison intervals nevertheless span the no-difference value, so the apparent ordering of the group means should not be mistaken for a precise estimate of a treatment contrast.

The posted summaries also show how variability affects interpretation. The standard deviations are substantial relative to the group mean changes. A modest-sized group mean difference can be estimated imprecisely when individual outcomes vary, and an estimate should be considered together with its interval rather than in isolation. The sponsor's model-based analysis and the simple unadjusted re-calculation further demonstrate that method matters: the resulting estimates differ, even though they use the same trial endpoint.

The study is also a useful example of the boundary between registry reporting and statistical interpretation. The record identifies a primary endpoint, analysis population, group summaries, sponsor comparisons, and safety counts. It does not report the original sample-size assumptions, detailed missing-data approach, or multiplicity plan. Those omissions constrain interpretation without determining what the unreported choices were.

For clinical researchers, the central statistical lesson is to distinguish a result that is numerically different from one that is estimated precisely, and to distinguish statistical evidence from clinical importance. The Week 12 estimates are informative descriptions of this trial, but their uncertainty and the limits of the registry record remain part of the result.

18. 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.

The primary endpoint analysis includes participants in the ITT Analysis Set with available data, but the registry record does not report the amount or pattern of missing Week 12 observations or the method used to address them. Without those details, it is difficult to assess how the available-data analysis might be affected by missing outcomes or by differences between participants with and without observed measurements.

The sponsor's primary analysis is labeled LRMM, but the registry record does not give a full model specification, covariates, or other details needed to reproduce the model-based estimates. The simple unadjusted re-calculations use group summaries and are not a substitute for the sponsor's analysis. The confidence level for the re-calculated intervals is not reported in the registry record.

The study has a primary endpoint and multiple secondary measures assessed at several time points. A multiplicity strategy is not reported in the registry record. The record also does not report a clinical-importance threshold for a difference in lesion counts, so the clinical meaning of the estimated contrasts cannot be determined from statistical results alone.

The registry record does not report the original sample-size justification, demographic and baseline characteristics needed to assess the analyzed population, or details on adherence and treatment discontinuation. It also does not specify the roles included in quadruple masking. The safety information lists event counts but does not provide a formal comparison or all event-level details. These are limitations of what is reported, not evidence that any particular design or analysis procedure was absent.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Study to Evaluate the Efficacy and Safety of Imsidolimab (ANB019) in the Treatment of Participants With Acne Vulgaris — NCT04856917.
• Registry record last updated 2025-09-22; status last verified 2023-05.
• Results first posted 2023-06-15.
• 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.

22. Record Summary

The registry record describes a completed, randomized, quadruple-masked, parallel-group Phase 2 study of imsidolimab for acne vulgaris, sponsored by Vanda Pharmaceuticals. Enrollment is listed as 123. Participants were assigned to imsidolimab 400/200 mg, imsidolimab 200/100 mg, or matching placebo, with subcutaneous injections on Day 1 and Days 29 and 57.

The primary outcome was change from baseline in facial inflammatory lesion counts at Week 12. Mean changes were -6.8, -7.4, and -9.6 for the two imsidolimab groups and placebo, respectively. The sponsor's two placebo comparisons have 90% confidence intervals that include the no-difference value. The record also lists secondary outcomes and safety counts. Important details about the original sample-size rationale, multiplicity, missing-data handling, and model specification are not reported in the registry record.