Evaluation of Sonelokimab for the Treatment of Patients With Active Moderate to Severe Hidradenitis Suppurativa: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluation of Sonelokimab for the Treatment of Patients With Active Moderate to Severe Hidradenitis Suppurativa (NCT05322473), a randomized phase 2 study. The primary outcome is Percentage of Participants Achieving Hidradenitis Suppurativa Clinical Response (HiSCR) 75 at Week 12.

2. Clinical Question

The primary comparison concerns the proportion meeting a prespecified clinical response threshold, not the average change in lesion counts. Posted primary results were 14.7% in the placebo arm, 43.3% with sonelokimab 120 mg, 34.8% with sonelokimab 240 mg, and 36.4% with adalimumab. These are descriptive arm percentages for the Week 12 endpoint. The registry also reports sponsor analyses comparing each sonelokimab dose with placebo; the listed primary sponsor analyses do not include an adalimumab comparison. The clinical question is therefore best read as a placebo-controlled comparison of each sonelokimab regimen, with the adalimumab arm providing an additional treatment reference rather than a stated primary comparison.

3. Trial Design

The registry describes a Phase 2, randomized, parallel-group, double-blind, placebo-controlled study. Masking is listed as triple. The trial enrolled 234 participants and is marked completed. The registry dates the study start as 2022-04-25 and primary completion as 2023-05-09. It describes the study objective as evaluating the clinical efficacy and safety of subcutaneous sonelokimab in adults with moderate to severe hidradenitis suppurativa.

Part A included four arms: placebo, sonelokimab 120 mg, sonelokimab 240 mg, and adalimumab. The arm descriptions state that participants in the sonelokimab arms also received placebo to maintain blinding with the adalimumab and placebo arms during the Treatment Period. Participants initially assigned placebo were to be re-randomized to a sonelokimab regimen during Part B; those initially assigned adalimumab were to be reallocated to a sonelokimab regimen during Part B. The Part B safety groups reflect these treatment transitions.

The primary endpoint was assessed at Week 12. The primary efficacy population is described as the Full Analysis Set, including all randomized participants assigned treatment for Part A. The registry does not report the trial’s original sample-size assumptions, the details of the randomization procedure, the factors used for stratification if any, or the full masking procedures. It also does not report a detailed statistical analysis plan in the record summarized by these results. Those omissions limit what can be concluded about design choices beyond the stated randomized, parallel, double-blind, placebo-controlled framework.

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: In Part A, participants were randomized (2:2:2:1) to receive either: sonelokimab 120 mg, sonelokimab 240 mg, matching placebo, or adalimumab. In Part B, participants initially randomized to sonelokimab 120 mg or 240 mg continued on the same treatment for the remainder of the study, participants initially randomized to placebo were re-randomized (1:1) to either sonelokimab 120 mg or 240 mg, and participants initially randomized to adalimumab were reallocated to treatment with sonelokimab 240 mg.

Only the first 6 of 9 groups are shown.

Part A

Reasons for not completing this period:

Part B

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The FAS included all randomized participants assigned treatment for Part A.

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 Full Analysis Set (FAS) included all randomized participants assigned treatment for Part A.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Achieving Hidradenitis Suppurativa Clinical Response (HiSCR) 75 at Week 12, measured over At Week 12.

The primary endpoint is the percentage of participants achieving Hidradenitis Suppurativa Clinical Response 75, or HiSCR75, at Week 12. A participant met this threshold with at least a 75% reduction from baseline in abscess and inflammatory nodule count, provided there was no increase from baseline in abscess count or draining fistula count. This combines a substantial improvement in two lesion-count components with a safeguard against worsening in either of the specified lesion categories.

A responder percentage is a binary outcome: each participant is classified as meeting or not meeting the endpoint, and the arm result is the proportion classified as meeting it. This makes the endpoint comparatively direct to interpret as the share of participants reaching a defined response criterion. It does not show the size of improvement among responders beyond the threshold, or describe changes for individual participants. Those questions require other outcome summaries.

The registry reports that non-responder imputation was used for missing primary endpoint data. Under this stated approach, missing observations are treated as non-responses for this analysis. That makes the reported endpoint dependent not only on observed response status but also on the specified missing-data rule. Details such as the amount and reasons for missing data by arm are not reported in the registry record. The endpoint is useful for comparing the frequency of a defined clinical response at a fixed assessment time, but it should be interpreted alongside the analysis method, the missing-data handling, and the confidence intervals for the comparisons.

7. Results Posted in the Registry

• Part A: Sonelokimab 120 mg: 43.3% (29/67) versus 14.7% (10/68) on control; risk difference 28.6 percentage points (95% CI 14.0 to 43.1), risk ratio 2.94 (1.56–5.55); unadjusted two-proportion z-test p = <0.001.
• Part A: Sonelokimab 240 mg: 34.8% (23/66) versus 14.7% (10/68) on control; risk difference 20.1 percentage points (95% CI 5.9 to 34.4), risk ratio 2.37 (1.22–4.59); unadjusted two-proportion z-test p = 0.007.
• Part A: Adalimumab: 36.4% (12/33) versus 14.7% (10/68) on control; risk difference 21.7 percentage points (95% CI 3.2 to 40.1), risk ratio 2.47 (1.19–5.13); unadjusted two-proportion z-test p = 0.013.

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 Achieving HiSCR50 at Week 12

• 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:
  • Part A: Sonelokimab 120 mg: 65.7% (44/67) versus 27.9% (19/68) on control; risk difference 37.7 percentage points (95% CI 22.1 to 53.3), risk ratio 2.35 (1.55–3.57); unadjusted two-proportion z-test p = <0.001.
  • Part A: Sonelokimab 240 mg: 53.0% (35/66) versus 27.9% (19/68) on control; risk difference 25.1 percentage points (95% CI 9.0 to 41.2), risk ratio 1.90 (1.22–2.96); unadjusted two-proportion z-test p = 0.003.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Part A: Sonelokimab 120 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Part A: Sonelokimab 240 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in International Hidradenitis Suppurativa Severity Score System (IHS4) 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 errors.
• Result:
  • Part A: Sonelokimab 120 mg: mean -19.32 versus -7.91 on control; difference -11.41 (95% CI -17.24 to -5.58), standardized effect d = -0.69; z-test p = <0.001.
  • Part A: Sonelokimab 240 mg: mean -14.55 versus -7.91 on control; difference -6.64 (95% CI -12.47 to -0.81), standardized effect d = -0.40; z-test p = 0.026.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Part A: Sonelokimab 120 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Part A: Sonelokimab 240 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Achieving a Dermatology Life Quality Index (DLQI) Total Score of ≤5 at Week 12

• 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:
  • Part A: Sonelokimab 120 mg: 26.8% (15/56) versus 21.6% (11/51) on control; risk difference 5.2 percentage points (95% CI -11.0 to 21.4), risk ratio 1.24 (0.63–2.45); unadjusted two-proportion z-test p = 0.530.
  • Part A: Sonelokimab 240 mg: 33.9% (19/56) versus 21.6% (11/51) on control; risk difference 12.4 percentage points (95% CI -4.4 to 29.1), risk ratio 1.57 (0.83–2.98); unadjusted two-proportion z-test p = 0.155.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Part A: Sonelokimab 120 mg 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 Part A: Sonelokimab 240 mg and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes broaden the assessment beyond whether participants crossed the HiSCR75 response threshold. They include HiSCR50, change in the IHS4 severity score, achievement of a DLQI total score of 5 or less, and improvement in the patient’s global assessment of skin pain among participants with baseline NRS of at least 3. Together, these address a less stringent clinical response threshold, disease severity, skin-related quality of life, and patient-reported pain.

The posted pattern is not uniform across these outcomes. The HiSCR50 arm percentages favor both sonelokimab arms over placebo, and the IHS4 results show larger reductions from baseline in the sonelokimab arms than in placebo. By contrast, the posted DLQI comparisons do not provide clear statistical evidence of a difference from placebo in the listed unadjusted analyses. These are broad descriptions of the outcome pattern; the individual values and analyses are presented with their respective endpoint results. The pain outcome is listed among the secondary outcomes, but its results are not reported in the registry record.

Secondary outcomes can support context for the primary finding, but they do not replace it. Outcomes may differ in clinical meaning, measurement scale, number of evaluable participants, and missing-data patterns. The IHS4 analysis uses a continuous score, whereas the response and DLQI outcomes are binary. Results on these different scales cannot be combined into one overall treatment effect without a prespecified method, which is not reported in the registry record.

Unadjusted secondary p-values carry less weight when several outcomes and comparisons are examined. The chance of at least one apparently unusual result can increase as the number of statistical tests grows, unless an appropriate multiplicity strategy is used. The registry record does not report whether multiplicity was controlled for these secondary analyses or how the outcomes were prioritized. Accordingly, secondary findings are best read as supportive or exploratory evidence rather than as independent confirmation of the primary result. The absence of a clearly reported multiplicity procedure also means that nominal p-values should not be interpreted as if each were the sole prespecified test.

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

• Percentage of Participants Achieving HiSCR50 at Week 12
• Change From Baseline in International Hidradenitis Suppurativa Severity Score System (IHS4) at Week 12
• Percentage of Participants Achieving a Dermatology Life Quality Index (DLQI) Total Score of ≤5 at Week 12
• Percentage of Participants Achieving a Numerical Rating Scale (NRS) 30 in Patient's Global Assessment (PGA) of Skin Pain at Week 12, in Participants With Baseline NRS ≥3

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary: participants either met the HiSCR75 definition at Week 12 or did not. The posted percentages summarize the fraction classified as responders in each arm. A between-arm contrast can be expressed on different scales. The sponsor reports odds ratios from a Cochran-Mantel-Haenszel analysis, while the simple re-calculations report unadjusted risk differences from posted summary statistics. These measures answer related but distinct questions, so their numerical values should not be compared as if they were on the same scale.

What does a risk difference express?

A risk difference is the responder proportion in one arm minus the responder proportion in the comparison arm, on the probability scale. A positive estimate in these comparisons indicates a higher observed responder proportion in the sonelokimab arm than in placebo. The re-calculated values are unadjusted contrasts from the posted counts; they are not substitutes for the sponsor’s analysis. They do not incorporate any adjustment that may be part of the sponsor’s method.

The confidence interval for a risk difference gives a range of values compatible with the estimate under the calculation’s assumptions. Its width reflects uncertainty in the arm proportions as well as the sample sizes. If the interval includes zero, the data are compatible with no difference on this scale under that calculation. If it excludes zero, the interval indicates that the simple unadjusted estimate is away from zero at the confidence level used. These statements describe statistical uncertainty, not clinical importance.

What is an odds ratio?

An odds ratio compares the odds of meeting the endpoint between groups. Odds are distinct from probabilities, and an odds ratio is not a direct percentage-point difference. An odds ratio of 1 represents equal odds between the groups on this scale; values above 1 indicate higher odds in the group named first relative to the comparison group. The sponsor’s posted primary analyses report odds ratios with 95% confidence intervals and p-values. The registry identifies the method as Cochran-Mantel-Haenszel, but the specific strata or adjustment factors used are not reported in the registry record. It is therefore appropriate to name the reported method without asserting what factors it controlled for.

Why do the reported and recalculated estimates differ?

The re-calculations are simple, unadjusted calculations from posted summary statistics. The sponsor’s reported primary results use a different analysis method and an odds-ratio estimand. Differences in the measure and analysis can lead to different numerical estimates, confidence intervals, and p-values. The record also flags a discrepancy. In that circumstance, the sponsor’s own analysis takes precedence for reporting the trial’s primary result. The re-calculated risk differences can still help readers understand the magnitude on a probability-difference scale, but should be clearly distinguished from the sponsor’s primary analysis.

How should p-values be read?

A p-value describes how incompatible the observed data are with a specified null hypothesis, under the assumptions of the analysis. A smaller p-value is stronger evidence against that null hypothesis; it is not the probability that the null hypothesis is true, and it does not measure the probability that a result will replicate. The sponsor reports p < 0.001 for the 120 mg comparison and p = 0.007 for the 240 mg comparison. These are not measures of effect size. The odds-ratio estimates and their confidence intervals provide information about estimated magnitude and precision, while the p-values address evidence against a no-association null on the analysis scale.

What does non-responder imputation mean?

The registry states that non-responder imputation was used for missing primary endpoint data. In this approach, a missing endpoint observation is classified as a non-response for the analysis. This is one way to produce a complete binary endpoint classification when Week 12 status is unavailable. Its interpretation depends on the number and pattern of missing observations and on whether the rule is appropriate for the missingness process. The amount, timing, and reasons for missing endpoint data by arm are not reported in the registry record. The registry identifies the Full Analysis Set as all randomized participants assigned treatment for Part A, but does not describe additional population exclusions or the handling of all other analysis sets.

Why do sample-size illustrations use observed effects?

The planning illustrations are based on observed effects and stated assumptions rather than the trial’s original design specification. They show how a hypothetical future two-arm comparison might be sized for different fractions of the observed effect, under the listed statistical assumptions. Such calculations are sensitive to the assumed response rates and effect size. They are not evidence that the current trial had a particular probability of detecting an effect. The registry’s own original sample-size justification and its design assumptions are not reported in the registry record.

General statistical context: confidence intervals, p-values, and planning calculations each answer different questions. Confidence intervals describe uncertainty around an estimated effect; p-values assess compatibility with a null hypothesis under a model; sample-size planning estimates the participant count needed for a chosen design and assumed effect. None of these alone establishes clinical importance, and none replaces scrutiny of the endpoint definition, missing-data handling, analysis population, or the reported primary method.

11. Confidence Intervals and Precision

Precision concerns how much uncertainty surrounds an effect estimate. A confidence interval gives a range of values compatible with the data and analysis assumptions; narrower intervals indicate greater precision on that scale, while wider intervals indicate more uncertainty. It is not a guarantee that the true effect lies in the interval, nor does it describe the range of individual participant outcomes.

For the sponsor-reported primary comparison of sonelokimab 120 mg with placebo, the odds ratio was 4.823 and the 95% confidence interval was 2.055 to 11.316. For sonelokimab 240 mg versus placebo, the odds ratio was 3.133 and the 95% confidence interval was 1.350 to 7.270. Both intervals lie above 1 on the odds-ratio scale, consistent with the reported p-values for those comparisons. The intervals are also broad enough to show uncertainty about the size of the odds ratio; the point estimates alone should not be read as exact effects.

The unadjusted re-calculated risk-difference intervals are expressed on a different scale. For the 120 mg comparison, the estimate was 0.286, with an interval from 0.140 to 0.431. For the 240 mg comparison, the estimate was 0.201, with an interval from 0.059 to 0.344. These estimates and intervals are simple re-calculations and do not replace the sponsor analyses. The registry flags a discrepancy, so the sponsor’s own analysis takes precedence.

The posted arm percentages are based on fewer than 100 participants in each Part A arm: the primary analysis reports 68 participants in placebo, 67 in sonelokimab 120 mg, 66 in sonelokimab 240 mg, and 33 in adalimumab. These group sizes help contextualize why the effect estimates are uncertain, but sample size alone does not determine interval width. The registry does not report confidence intervals for the primary arm percentages themselves. In addition, the record does not report details about the strata or adjustment factors in the sponsor analysis. Precision should therefore be judged using the sponsor’s reported intervals for its own analysis and treated separately from the unadjusted re-calculated intervals.

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 illustrations express required sample size as participants per arm for the binary and continuous outcomes represented. They are not totals across both arms and do not represent total event counts. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The target effect is set to a stated fraction of the observed effect. The original sample-size justification and assumptions used to design this trial are not reported in the registry record.

The 80% power column gives the hypothetical number of participants per arm for a design with an 80% chance of detecting the assumed effect under the stated planning assumptions, if that assumed effect and model are correct. The 90% power column gives the corresponding per-arm count for a design with a 90% chance under those same assumptions. These are design targets, not descriptions of the probability that the completed trial detected its true effect. These figures are not observed power.

Rows planning for 100%, 75%, or 50% of an observed effect illustrate how sample size depends on the effect assumed for planning. A smaller target effect generally requires more participants to distinguish it from random variation at the same significance level and target power. The calculations use the observed effect as a starting point, which can be an optimistic or unstable planning basis, especially when estimates come from a trial with limited group sizes. The numbers are therefore illustrations for hypothetical future comparisons, not recommendations and not evidence of the trial’s original design rationale.

For binary outcomes, the planning assumptions use event proportions; for continuous outcomes the calculation uses a mean difference and an estimated variability. Where the underlying analysis differs from the simple calculation, the illustration should not be mistaken for a replication of the sponsor’s full method. The registry’s original power assumptions, anticipated effect size, and any allowances for loss to follow-up or multiplicity are not reported in the registry record.

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 = 0.147; treatment proportion p₁ = 0.433; average p̄ = 0.290.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6417 = 1.2577.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6090 = 0.5126.
4. n = (1.2577 + 0.5126)² / (0.2858)² = 38.4, rounded up to 39 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 <- 0.147058823529412                          # control proportion
p1 <- 0.432835820895522                          # 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(5322473)
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 = 39 (80% power), 51 (90% power)
 75% of observed effect: n per arm = 64 (80% power), 85 (90% power)
 50% of observed effect: n per arm = 131 (80% power), 174 (90% power)
power.prop.test: 38.4 
Simulated power at n = 39 per arm: 0.823 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The registry reports sponsor analyses for the primary endpoint comparing each sonelokimab dose with placebo. The Cochran-Mantel-Haenszel odds ratio for sonelokimab 120 mg was 4.823, with a 95% confidence interval from 2.055 to 11.316 and p < 0.001. For sonelokimab 240 mg, the odds ratio was 3.133, with a 95% confidence interval from 1.350 to 7.270 and p = 0.007. These are the sponsor’s own analyses and take precedence where the registry flags a discrepancy.

The re-calculations use posted summary counts to estimate unadjusted risk differences. They produce a different effect measure and do not reproduce the sponsor’s Cochran-Mantel-Haenszel analysis. For example, the 120 mg re-calculated risk difference is 0.286, while the sponsor reports an odds ratio of 4.823; these quantities are not directly comparable because they use different scales. The same distinction applies to the 240 mg comparison. No attempt should be made to treat the re-calculated p-values as a correction or replacement for the sponsor’s reported p-values.

The registry does not explain the flagged discrepancy or provide enough detail to establish exactly which analytical choices account for it. The sponsor’s analysis is therefore the primary reference for the trial’s reported inferential result. The re-calculations serve as an unadjusted cross-check from the posted summaries and can add a different descriptive perspective, but they do not supersede the sponsor results.

15. Multiplicity, Missing Data and Analysis Populations

The primary endpoint has two sponsor-reported placebo comparisons, one for each sonelokimab dose. The registry record reports p-values and confidence intervals for these comparisons, but does not report whether the primary comparisons were adjusted for multiplicity, whether a hierarchy or gatekeeping procedure was specified, or how the family of primary hypotheses was defined. The same information is not reported for the multiple secondary endpoints and their comparisons. Without those details, the posted p-values should be read as the results of the stated analyses, not assumed to have a particular familywise error interpretation.

Missing primary endpoint values were handled with non-responder imputation, as stated in the endpoint description. The record identifies the Full Analysis Set as all randomized participants assigned treatment for Part A. It does not report the number of missing Week 12 observations by arm, the reasons for missingness, or sensitivity analyses that test alternative assumptions. Non-responder imputation is an explicit rule, but it does not establish that missingness is unrelated to outcome or show how conclusions might change under other missing-data assumptions.

The registry gives outcome-specific participant counts for some analyses that differ from the primary Full Analysis Set counts. For example, the IHS4 and DLQI outcomes have smaller posted analysis counts than the primary endpoint arms. This indicates that the analyses are not all based on the same number of participants, but the record does not explain the reasons for each outcome’s analysis count or how missing values were handled for every secondary endpoint. It is not appropriate to assume that the primary endpoint’s non-responder imputation rule was applied to all secondary measures.

The listed analysis methods include Cochran-Mantel-Haenszel for the sponsor’s binary comparisons and Mixed Model Repeated Measures for the sponsor’s IHS4 comparisons. The registry does not provide the full model specifications, covariates, repeated-measure covariance structure, or analysis populations for each sponsor result. It also does not report interim analyses or a complete statistical analysis plan. These omissions restrict independent evaluation of multiplicity, missing-data assumptions, and model choices.

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: abortion spontaneous (3.1%), anorectal varices haemorrhage (1.5%), cerebrovascular accident (1.5%), genital pain (1.5%), cardiac failure chronic (1.5%).

For Part A, the registry reports serious adverse events in 2 of 68 participants in the placebo arm, 2 of 67 in the sonelokimab 120 mg arm, 1 of 66 in the sonelokimab 240 mg arm, and 0 of 33 in the adalimumab arm. Deaths were reported as 0 in each Part A arm. These are participant counts within the registry’s safety groups; they are not estimates of comparative risk adjusted for exposure or follow-up.

The registry also reports other adverse events in 29 of 68 placebo participants, 39 of 67 participants receiving sonelokimab 120 mg, 36 of 66 receiving sonelokimab 240 mg, and 21 of 33 receiving adalimumab. Those counts should be read separately from serious adverse events. The record lists serious adverse-event terms including abortion spontaneous, anorectal varices haemorrhage, cerebrovascular accident, genital pain, chronic cardiac failure, and Proteus infection, with the displayed percentages attached to those terms.

Part B includes treatment transitions, so its groups represent different treatment histories and should not be combined casually with Part A or treated as directly comparable parallel groups. The registry does not report a detailed exposure-adjusted safety analysis, event duration, severity grading, or follow-up time for these counts. Small numbers of serious events also make arm-to-arm comparisons imprecise. These registry counts describe reported events; they do not establish causation or provide a complete safety assessment.

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

The primary posted data show that a greater proportion of participants in each sonelokimab arm met the HiSCR75 definition at Week 12 than in the placebo arm. The sponsor’s reported odds-ratio analyses also give confidence intervals above 1 for both sonelokimab comparisons with placebo. These results describe the randomized trial’s posted analysis under the endpoint definition and non-responder imputation rule.

The results do not show that every participant improved, nor do they describe how much each individual’s disease changed. A responder threshold compresses varied participant experiences into a yes-or-no classification. The additional secondary outcomes capture other aspects of disease severity, quality of life, and pain, but their results are not uniformly conclusive, and the pain outcome is not reported in the registry record.

The primary findings do not establish that one sonelokimab dose is better than the other. The sponsor’s reported primary analyses compare each dose with placebo; a direct sponsor-reported dose-to-dose comparison is not reported in the registry record. Similarly, the adalimumab arm’s posted percentage is descriptive in this context. The registry does not report sponsor primary analyses comparing adalimumab directly with the other arms.

Statistical significance does not by itself establish clinical importance, long-term benefit, or applicability beyond the enrolled study population. The record does not report the original sample-size justification, multiplicity strategy, full analysis plan, or detailed missing-data sensitivity analyses. The confidence intervals quantify uncertainty under their respective analyses but cannot resolve these unreported design and analysis details. The study is a Phase 2 trial, and its posted results should be interpreted as evidence from this trial rather than as a complete basis for conclusions about treatment selection or use.

No medical recommendation follows from these statistics. They describe trial outcomes and their uncertainty, not an individual participant’s likely outcome. Decisions about care require clinical assessment and evidence beyond the registry results summarized in this record.

18. Why This Trial Matters Statistically

Statistically, this trial illustrates why an endpoint definition and analysis method matter as much as an arm percentage. HiSCR75 is a threshold-based binary outcome with an explicit rule for lesion-count changes. The sponsor’s analysis reports an odds ratio, while an unadjusted re-calculation from the posted counts expresses the same broad comparison as a risk difference. Each scale has a different interpretation, and keeping them distinct prevents readers from treating unlike estimates as if they were interchangeable.

The study also shows the importance of reporting uncertainty. The sponsor’s confidence intervals place bounds around the odds-ratio estimates, while the arm percentages alone offer no such measure of precision. At the same time, finite group sizes and the registry’s flagged discrepancy call for attention to which analysis is being interpreted. The sponsor’s reported analysis takes precedence, and the simple calculations are best viewed as an additional descriptive check.

Another statistical issue is consistency across outcomes. The secondary outcomes cover response, severity, quality of life, and pain, but they do not all point with equal clarity in the same inferential direction, and the pain result is not reported in the registry record. Multiple outcomes and comparisons make multiplicity procedures important, yet those procedures are not reported. This affects how strongly secondary p-values can be interpreted.

Finally, the registry makes clear that missing primary endpoint data were classified as non-responses, but does not show the amount or pattern of missingness by arm. Transparency about missing observations, analysis populations, and sensitivity checks is important for understanding whether conclusions depend on particular assumptions. These features make the record useful for teaching how to read trial results cautiously: identify the estimand, distinguish sponsor analyses from recalculations, inspect uncertainty, and note information that is not reported.

19. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several trial-specific limits affect interpretation. The primary endpoint is a binary threshold at Week 12. It distinguishes participants who meet HiSCR75 from those who do not, but does not convey the degree of improvement for participants within either category. The posted primary percentages should therefore be understood as response proportions rather than full summaries of disease change.

The sponsor reports primary comparisons for each sonelokimab dose versus placebo, but the registry does not report a sponsor primary comparison between the two doses or a sponsor primary comparison involving adalimumab. The adalimumab arm’s result is consequently descriptive alongside the primary placebo comparisons. The registry also flags a discrepancy between sponsor results and simple re-calculations. Because the calculations use different methods and effect scales, the sponsor’s own analysis takes precedence.

The registry does not report the original sample-size justification, full statistical analysis plan, details of any multiplicity control, or a full description of the factors included in the Cochran-Mantel-Haenszel analysis. It also does not report the quantity and reasons for missing Week 12 observations by arm or sensitivity analyses for the non-responder imputation approach. These omissions prevent a complete independent assessment of how design and analysis choices influence the reported findings.

Secondary analyses have outcome-specific participant counts and methods, and the registry does not explain all count differences or missing-data rules for each measure. One listed secondary outcome, the pain assessment, has no posted result in the record. Safety figures are counts by treatment group and do not include exposure-adjusted comparisons or detailed follow-up information. Part B includes treatment transitions, which complicate simple comparisons with the original Part A arms. These limits do not negate the posted results, but they constrain the breadth and certainty of conclusions that can be drawn from the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Evaluation of Sonelokimab for the Treatment of Patients With Active Moderate to Severe Hidradenitis Suppurativa — NCT05322473.
• Registry record last updated 2026-09-09; status last verified 2024-05.
• Results first posted 2026-09-09.
• 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

This completed Phase 2 study randomized 234 adults with active moderate to severe hidradenitis suppurativa in a parallel-group, double-blind, placebo-controlled design; masking is listed as triple. Part A included placebo, sonelokimab 120 mg, sonelokimab 240 mg, and adalimumab. The primary outcome was HiSCR75 at Week 12, with non-responder imputation for missing data and the Full Analysis Set defined as all randomized participants assigned treatment for Part A.

The sponsor reported Cochran-Mantel-Haenszel odds ratios for each sonelokimab dose versus placebo. The registry flags a discrepancy with simple unadjusted re-calculations, so the sponsor’s analyses take precedence. Secondary outcomes address response, severity, quality of life, and pain; the pain result is not reported in the registry record. Multiplicity procedures, original sample-size assumptions, and detailed missing-data information are also not reported. Serious adverse events and deaths are listed by Part A and Part B treatment groups, with no deaths reported in the listed groups.