Evaluating the Safety and Efficacy of Deucravacitinib Compared to Placebo Hidradenitis Suppurativa (HS).: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluating the Safety and Efficacy of Deucravacitinib Compared to Placebo Hidradenitis Suppurativa (HS). (NCT05997277), a randomized phase 2 study. The primary outcome is Median Change From Baseline in Number of Inflammatory Lesion Counts (Including Combined Counts of Inflammatory Nodules (N) and Abscesses (A)/AN Count) at Week 16..

2. Clinical Question

3. Trial Design

The registry classifies NCT05997277 as a Phase 2, randomized, double-masked, parallel-group study of deucravacitinib compared with placebo for moderate-to-severe HS. Beth Israel Deaconess Medical Center is listed as the sponsor. The study began on 2023-11-30, had a primary completion date of 2025-02-25, and is recorded as terminated. The reason for termination is not reported in the registry record.

The brief summary describes a single-center proof-of-concept study with a planned enrollment of 30 patients aged 18 and over. The registry records enrollment of 7. That difference makes it important to distinguish the intended study size from the number recorded as enrolled; the record does not explain why the study ended with this enrollment or whether all enrolled participants contributed endpoint data.

The study schedule described in the summary includes a 4-week screening period, a 16-week treatment period, and a 4-week follow-up period. Follow-up was described as a phone call 4 weeks after the last study-drug dose. The active regimen is described as deucravacitinib 6 mg by mouth twice daily for 16 weeks, while the placebo regimen is described as one tablet by mouth twice daily for 16 weeks.

Randomization and double masking are design features that can reduce certain sources of bias when implemented successfully. The registry does not report details of sequence generation, allocation concealment, masking procedures, or departures from assigned treatment. It also does not report a protocol-level account of the planned analysis. The posted endpoint results should therefore be read as descriptive summaries, not as a complete account of how the trial was intended to estimate a treatment effect.

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

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: 7 subjects were analyzed for all collected data

6. Primary Endpoint

The registry lists the primary outcome as Median Change From Baseline in Number of Inflammatory Lesion Counts (Including Combined Counts of Inflammatory Nodules (N) and Abscesses (A)/AN Count) at Week 16., measured over Baseline and Week 16.

The primary endpoint is the median change from baseline to Week 16 in the number of inflammatory lesions per subject. The count combines inflammatory nodules and abscesses, and the registry defines each nodule or abscess as one unit. The endpoint description states that an increase represents an additional single unit of disease relative to baseline.

Lesion counts focus on observable features of HS and provide a way to track change over the treatment period. A change score compares the Week 16 count with the participant’s baseline count, rather than reporting the Week 16 count alone. Reporting the median emphasizes the middle of the observed changes and can be useful when a small group or an uneven distribution makes the mean less representative. The registry identifies the inter-quartile range as the dispersion measure.

The reported median change is -2.0 in the deucravacitinib group and -9.0 in the placebo group. Both values are negative, which indicates a decrease in the count relative to baseline according to the endpoint’s direction. The group summaries do not show each participant’s change, and the record does not report an inferential comparison between groups. Without that comparison and information about uncertainty, the medians alone cannot establish how precisely the groups differed or whether the observed difference is compatible with chance variation.

The endpoint is reported at Week 16, following the described treatment period. The registry does not report additional endpoint details such as assessment procedures, assessor training, or how missing Week 16 measurements were handled.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary outcome as a median change in inflammatory lesion counts, with the inter-quartile range as the dispersion measure. A median is the central value after observations are ordered. It is less affected by unusually large or small observations than an arithmetic mean, which can be useful when the distribution is skewed. The inter-quartile range describes the central spread of the observed values. Neither summary, on its own, quantifies uncertainty in a comparison between randomized groups.

What does the change score represent?

A change score is formed by comparing a participant’s follow-up measurement with that participant’s baseline measurement. The registry defines the outcome as a change in the number of inflammatory nodules and abscesses from baseline to Week 16. By the endpoint’s stated convention, an increase corresponds to an additional lesion-count unit relative to baseline. The posted arm medians are -2.0 for deucravacitinib and -9.0 for placebo. These group summaries do not reveal the baseline or Week 16 distributions separately, nor do they show the individual changes contributing to each median.

Why does the small enrollment matter?

With few observations, a single participant’s result can influence a group summary substantially. The record reports 5 participants in the deucravacitinib arm and 2 in the placebo arm. Such small groups provide limited information about the range of possible outcomes and make estimates especially sensitive to which participants are observed. Randomization can help balance prognostic characteristics over repeated trials, but it does not guarantee balance in a particular small trial. The registry does not report baseline characteristics that would allow readers to assess the observed group balance.

The brief summary describes a planned enrollment of 30, whereas the registry records enrollment of 7. The record does not state why enrollment stopped at this level or whether the endpoint summaries include all enrolled participants. These uncertainties constrain interpretation of both the descriptive results and the study’s ability to answer its stated question.

What can an inferential comparison add?

An inferential analysis estimates a group contrast and describes its uncertainty under stated assumptions. For example, a confidence interval gives a range of values compatible with the data and analysis method, while a p-value measures the compatibility of the data with a specified null model. These measures are not posted for the primary outcome. The registry records no analyses, so there is no sponsor-reported statistical comparison to interpret. No analysis method, covariate adjustment, or model specification is reported in the registry record.

The assumptions described for a separate planning illustration are a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation; the effect to detect is described as a stated fraction of the observed effect. These are assumptions for planning illustrations, not evidence that the trial was designed or analyzed using those assumptions. The registry does not report the trial’s own sample-size justification, and the planned enrollment described in the summary should not be treated as proof of a particular power target.

Why can over-dispersion matter?

General statistical context: count outcomes can vary more than a simple model assumes, a condition often called over-dispersion. When that occurs, a model that understates variability can give misleadingly narrow uncertainty estimates or overly optimistic tests. Analysts may use methods suited to the observed count distribution or robust uncertainty estimates, depending on the design and data. This is a general consideration for count outcomes, not a claim about the distribution or analysis in this trial. The registry does not report a model for the lesion counts or diagnostics addressing dispersion.

The median summary is a descriptive approach; it does not require a reader to assume a particular count model. But a comparison still requires a clearly described method if the aim is to quantify uncertainty or support an inferential claim. With no posted analysis, the available results cannot establish whether any particular model or test was used.

What is not established by a planning calculation?

General statistical context: a sample-size planning calculation asks how many observations might be needed under specified assumptions to detect a selected effect with a chosen operating characteristic. It is not an observed outcome and should not be confused with power calculated after seeing the data. A calculation based on an observed effect is especially dependent on that estimate, which can be unstable when the observed groups are small. The assumptions noted in the registry describe planning illustrations; they do not establish the study’s original sample-size rationale or the precision of the posted endpoint results.

In this record, the main methodological limitation is not a disagreement between a reported analysis and a recalculation: no analysis is posted for comparison. As a result, interpretation must remain at the level of arm-level descriptive summaries and recorded safety counts. Details of missing-data handling, analysis populations, and the intended statistical plan are not reported in the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists one outcome measure and no posted secondary outcomes. It records zero analyses. Because no inferential results are posted, there is no reported multiplicity procedure, such as an adjustment for testing several outcomes or contrasts. The registry record does not report whether additional outcomes or analyses were planned outside the posted record.

Multiplicity is a general concern when many outcomes, time points, subgroups, or statistical tests are examined: the chance of observing an apparently notable result can increase as the number of tests grows. A prespecified testing strategy can clarify which result is primary and how other analyses are interpreted. The available record does not provide enough information to determine whether such a strategy was specified or used.

The registry does not report how missing endpoint measurements were handled, whether any Week 16 observations were missing, or whether analyses used all randomized participants or another analysis population. The arm counts reported for the primary result are 5 for deucravacitinib and 2 for placebo. Those counts do not, on their own, establish how many participants had complete data at every study visit or how participants were included in the endpoint summary.

Missing-data methods can affect interpretation because an analysis of observed outcomes may differ from one that accounts for unavailable measurements. General statistical context: the consequences depend on why data are missing and on the assumptions made by the selected method. No imputation method, sensitivity analysis, or missingness description is reported in the registry record, so the influence of missing data cannot be assessed.

The trial is recorded as terminated, but the reason and any resulting changes to planned analyses are not reported in the registry record. Without information on analysis populations, missingness, and the prespecified statistical plan, the posted summaries cannot be taken as a complete account of the intended analysis.

11. 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 0% reporting threshold.

The registry records 0 serious adverse events among 5 participants at risk in the deucravacitinib group and 0 among 2 participants at risk in the placebo group. It also records 0 other adverse events in each group and 0 deaths in each group. These are event counts for the participants represented in the posted safety summary.

A zero count means that no events in the listed category were recorded for the group in this summary. It does not establish that the risk is absent, particularly when the groups are small. The counts do not provide a precise comparison between treatments, and no inferential safety analysis is posted. The registry does not report the definitions used for the serious and other adverse-event categories, exposure-adjusted rates, or details about event collection and follow-up.

The absence of a recorded event in these small groups should therefore be interpreted narrowly: the posted record lists no serious adverse events, other adverse events, or deaths among the stated numbers at risk. It cannot exclude uncommon harms or determine whether risk differs between groups. The record lists no serious adverse-event terms.

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

The posted results show a median change in inflammatory lesion counts of -2.0 in the deucravacitinib arm and -9.0 in the placebo arm from baseline to Week 16. The endpoint counts inflammatory nodules and abscesses together, with each lesion contributing one unit. Both medians indicate a decrease relative to baseline under the endpoint’s stated direction. The results also show no serious adverse events, other adverse events, or deaths recorded in either group.

These findings are descriptive. The record reports only 5 participants in the deucravacitinib arm and 2 in the placebo arm, and it contains no posted inferential analysis. The arm summaries do not estimate a treatment contrast with a confidence interval, and they do not show how individual participant outcomes were distributed. The medians alone cannot establish whether the observed pattern reflects a reliable difference between groups.

The registry summary describes a planned enrollment of 30, but the recorded enrollment is 7. The study is marked terminated, and the reason is not reported in the registry record. The record also does not explain whether every enrolled participant contributed to the endpoint summary or how missing observations were addressed. These gaps limit assessment of the completeness and precision of the results.

The posted figures therefore do not establish that deucravacitinib is effective or ineffective, nor do the safety counts establish that either treatment is free from harm. They document arm-level endpoint summaries and event counts in a small terminated pilot study. A more complete assessment would require reported statistical analyses, clear analysis populations, information about missing data, and further evidence. Those items are not reported in the registry record.

13. Why This Trial Matters Statistically

This trial illustrates the difference between a randomized design and an informative estimate. Randomization is a method for reducing systematic differences between groups, but a randomized comparison can still be highly uncertain when enrollment is small. Here, the registry records 7 participants, with 5 in the deucravacitinib arm and 2 in the placebo arm. The planned enrollment in the brief summary is 30. The gap between intended and recorded enrollment makes transparent reporting of recruitment, endpoint availability, and analysis especially important.

The study is described as a pilot and proof-of-concept trial, terms that signal an exploratory role rather than a definitive test. The posted medians provide a preliminary description of change in lesion counts, but without a comparison estimate and uncertainty measure, readers cannot determine how robust the apparent numerical pattern is. A median can convey the center of observed participant changes, while an inferential analysis is needed to quantify uncertainty around a contrast under specified assumptions.

The record also underscores the importance of registry completeness. Information about the reason for termination, missing-data handling, analysis populations, and statistical methods would help readers judge how results were generated and whether they reflect the planned analysis. Those details are not reported in the registry record. The safety counts are similarly best understood in context: zero recorded events in small groups is a description of what was observed, not a precise estimate of safety.

Statistically, the most useful reading is cautious and specific. The registry offers endpoint and safety summaries, but it does not report analyses that support a formal efficacy or safety comparison. Recognizing the distinction between descriptive data, a planned study design, and an inferential conclusion is central to interpreting a small terminated trial.

14. 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 strongest trial-specific limitation is the small recorded enrollment: 7 participants, compared with the 30 described as planned in the brief summary. The registry does not explain the difference or the reason the study was terminated. As a result, readers cannot determine from the record whether termination was related to recruitment, operational issues, safety, or another cause.

The endpoint results are reported as group medians and dispersion information, but no inferential analyses are posted. There is no reported estimate of the between-group contrast, confidence interval, p-value, or adjusted analysis. The recorded arm sizes are unequal, and the placebo group includes 2 participants, limiting the amount of information available from that group. A small sample also makes the summaries sensitive to individual observations.

The registry does not report baseline participant characteristics, individual outcome data, adherence, actual treatment exposure, or whether all enrolled participants contributed to the endpoint. It does not describe missing-data handling or analysis populations. Consequently, it is not possible to assess baseline comparability, completeness of endpoint data, or the robustness of the summaries to alternative assumptions.

Further design and analysis details are also not reported, including the randomization procedure, masking implementation, statistical analysis plan, and sample-size justification. The record identifies inter-quartile range as the dispersion measure, but does not describe additional modeling or diagnostic work for the count outcome. Finally, the safety summaries do not include event terms for serious events, exposure-adjusted rates, or a comparative safety analysis. These limitations restrict interpretation to the descriptive information recorded in the registry.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Evaluating the Safety and Efficacy of Deucravacitinib Compared to Placebo Hidradenitis Suppurativa (HS). — NCT05997277.
• Registry record last updated 2026-05-29; status last verified 2026-05.
• Results first posted 2026-05-29.
• 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.

18. Record Summary

NCT05997277 is a Phase 2 randomized, double-masked, parallel-group pilot study of deucravacitinib versus placebo for moderate-to-severe HS, sponsored by Beth Israel Deaconess Medical Center. The registry records enrollment of 7 and status as terminated. The brief summary describes a planned enrollment of 30 and a 16-week treatment period.

The primary outcome is median change from baseline to Week 16 in inflammatory lesion counts, combining nodules and abscesses. The posted median changes are -2.0 for deucravacitinib and -9.0 for placebo. The registry records 0 serious adverse events, 0 other adverse events, and 0 deaths in each arm. No statistical analyses are posted. The reason for termination, missing-data handling, analysis populations, and statistical plan are not reported in the registry record.