A Trial to Evaluate the Efficacy and Safety of Different Doses of LEO 138559 in Adults With Moderate-to-severe Atopic Dermatitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Trial to Evaluate the Efficacy and Safety of Different Doses of LEO 138559 in Adults With Moderate-to-severe Atopic Dermatitis (NCT05923099), a randomized phase 2 study. The primary outcome is Percent Change in Eczema Area and Severity Index (EASI) Score.

2. Clinical Question

3. Trial Design

This was a phase 2b, randomized, double-blind, placebo-controlled, multi-site, parallel-group, dose-finding trial. The registry lists an enrollment of 262 and identifies LEO Pharma as the sponsor. The trial status is completed. The recorded start date is 2023-09-20, and the primary completion date is 2024-12-11.

Participants were assigned to one of four LEO 138559 dose regimens or a placebo regimen. The regimens varied in the doses and timing of injections. Dose Regimen 1 used Dose A weekly from Week 0 to Week 3, then every two weeks from Week 4 to Week 16. Dose Regimen 2 used Dose B weekly from Week 0 to Week 2, then every two weeks from Week 4 to Week 16. Dose Regimen 3 used Dose A at Week 0 and Week 2, then Dose C every two weeks from Week 4 to Week 16. Dose Regimen 4 used Dose C at Week 0 and Week 2, then Dose D every two weeks from Week 4 to Week 16. The placebo regimen was weekly from Week 0 to Week 3, then every two weeks from Week 4 to Week 16.

The trial lasted up to 36 weeks, including a screening or washout period of up to 4 weeks, a 16-week treatment period, and a 16-week follow-up period. Injections were administered by clinic staff. Participants were scheduled for clinic visits throughout treatment and follow-up, and completed a daily electronic diary about atopic dermatitis and quality of life. At visits, clinicians assessed atopic dermatitis and side effects. The registry does not report additional details about allocation concealment or the specific procedures used to maintain masking.

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: Participants were randomized 1:1:1:1:1 to 5 different treatment groups (4 different dose regimens of LEO 138559 and placebo).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: For the primary efficacy endpoint, analyzed population was Full Analysis Set (FAS).

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Percent Change in Eczema Area and Severity Index (EASI) Score, measured over From baseline to Week 16.

The primary endpoint was percent change in Eczema Area and Severity Index score from baseline to Week 16. EASI is a validated measure used in clinical practice and trials to assess both the severity and extent of atopic dermatitis. Its score ranges from 0 to 72, with higher scores indicating more severe or extensive disease.

Percent change expresses the change relative to the participant’s baseline score, rather than reporting only the score at follow-up. A negative mean change indicates that the score decreased from baseline; a more negative value represents a larger average decrease. This interpretation describes the direction of the measured score change, not a conclusion about treatment benefit in every participant.

The registry reports least-squares means and 95% confidence intervals for the five groups. Least-squares means are model-based estimates, rather than simple averages necessarily calculated without adjustment. The primary endpoint was assessed in the Full Analysis Set. The registry does not report the detailed model specification or the precise handling of missing Week 16 measurements. EASI provides a structured way to summarize skin severity and extent, but the endpoint alone does not capture every aspect of symptoms, daily functioning, safety, or quality of life.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry presents two related forms of efficacy results: least-squares mean changes within each group and ANCOVA estimates comparing each dose regimen with placebo. They answer different questions. The group estimates describe average change from baseline within each assigned group. The ANCOVA results estimate between-group differences while accounting for factors in the model. The registry names ANCOVA but does not report the model covariates, baseline adjustment details, or other specification choices.

What does a least-squares mean represent?

A least-squares mean is an estimated mean from a statistical model. It can account for modeled factors, so it need not be identical to an unadjusted arithmetic average. The registry reports least-squares mean percent changes and 95% confidence intervals for each group. Because the detailed model is not reported in the registry record, readers cannot assess exactly how covariates or other features affected those estimates.

The EASI change estimates are negative across the groups. Their sign indicates a mean decrease from baseline in the measured score. The value for a group is not an individual response, and the group mean does not show how responses varied among participants. The registry does not post a measure of within-group spread for these least-squares means beyond the confidence intervals.

How should the confidence intervals be read?

A confidence interval gives a range of estimates compatible with the observed data and statistical model at the stated confidence level. Here, the registry reports 95% confidence intervals for the group means and the adjusted contrasts. The interval for a mean concerns uncertainty in that mean; it is not a prediction interval for individual outcomes. For a between-group contrast, an interval spanning zero includes values consistent with no difference under the model. An interval that does not span zero indicates that zero is not among the values in that interval, but does not resolve questions about clinical importance or multiplicity.

What does ANCOVA contribute?

ANCOVA, or analysis of covariance, compares outcomes between groups while adjusting for covariates included in the model. It can improve precision when relevant baseline or design factors are incorporated appropriately. The registry reports the method and the adjusted mean differences, confidence intervals, and p-values, but does not identify the covariates or explain how missing observations were handled. The reported estimates should therefore be interpreted as the registry’s model-based comparisons, without assuming unreported model details.

The contrast values are negative in all four reported comparisons. The registry labels these comparisons as superiority analyses and reports the corresponding p-values. The stated estimates and uncertainty intervals are the principal evidence for the comparisons; a p-value alone does not measure the size or clinical importance of an effect. The registry does not report a multiplicity procedure for the four comparisons, so it is not possible to determine from the record whether the inferential results account for testing several regimens against placebo.

Why can’t the group means replace the reported contrasts?

The displayed group means are model-based estimates, whereas the reported contrasts come from ANCOVA. Subtracting one displayed mean from another would be a simple unadjusted calculation and would not necessarily reproduce the model-adjusted contrast. The registry’s own ANCOVA results are the appropriate reported estimates for these comparisons. No recalculated two-arm continuous-endpoint comparison is available in the registry record, so there is no independent recalculation to set alongside the sponsor’s analysis.

The sample-size material is a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is defined as a stated fraction of the observed effect. Such planning estimates describe hypothetical future-study requirements under their assumptions; they are not observed power for this completed trial. The registry record does not report a sample-size justification for the trial itself or the numerical planning outputs in the information summarized for these results.

In general, planning calculations depend on assumptions about the effect, variability, allocation, and analysis. If the assumed effect is smaller, a study generally needs more information to distinguish it from random variation. These are general statistical principles, not details of the trial’s design rationale. The registry does not report the assumptions used by the sponsor when planning the original trial.

What can the p-values establish?

A p-value measures how incompatible the observed data are with a specified null model, under the assumptions of the analysis. It is not the probability that the null hypothesis is true, and it does not measure the probability that the findings will replicate. The posted values are interpreted alongside the effect estimates and confidence intervals. Because multiplicity handling is not reported, the record does not establish whether the p-values were adjusted for the set of regimen comparisons.

Overall, the methods posted permit readers to identify the endpoint, analysis population, named model, estimates, confidence intervals, and p-values. They do not provide enough detail to reconstruct the model, assess all assumptions, or determine the approach to missing outcomes and multiplicity. Those omissions limit independent evaluation of the inferential analysis.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s ANCOVA analyses for all four comparisons with placebo. Those estimates, confidence intervals, and p-values should be treated as the reported inferential results. The record does not include recalculated two-arm continuous-endpoint estimates, so there is no unadjusted recalculation to compare numerically with the sponsor’s model-based analyses.

The posted group least-squares means are not a substitute for the ANCOVA contrasts. A difference calculated directly from group means would be unadjusted and could differ from the model-based contrast. The registry record does not provide enough information about the ANCOVA specification to reproduce the sponsor’s results independently.

No discrepancy between sponsor and recalculated results is flagged in the record. This does not establish that the analysis has been independently verified; it means the registry does not identify a discrepancy. The reported comparisons remain subject to the limits of the available methodological detail, including the absence of a reported multiplicity procedure and details about missing-data handling.

11. Multiplicity, Missing Data and Analysis Populations

The registry reports four comparisons of LEO 138559 regimens with placebo for the primary endpoint. It does not report whether the p-values or confidence intervals were adjusted for multiple comparisons. Without that information, readers cannot determine whether the reported inferential results control the chance of false-positive findings across the set of comparisons. The posted p-values should therefore be read as the results reported for the individual analyses, with the multiplicity approach not reported in the registry record.

The primary efficacy analysis population is identified as the Full Analysis Set. The registry does not provide a fuller definition of this population, such as its inclusion rules or how participants with incomplete endpoint data were treated. Although enrollment and group sizes are posted, the registry does not state the number of missing Week 16 measurements or describe imputation, model-based handling, or sensitivity analyses for missing outcomes. These details are important because conclusions can depend on which participants contribute to the endpoint analysis and how unavailable measurements are handled.

The registry also lists one secondary outcome: number of treatment-emergent adverse events. It does not provide a complete statistical testing plan for secondary outcomes or state how the primary and secondary analyses relate within a multiplicity strategy. Information about interim analyses, stopping rules, and a prespecified hierarchy of tests is not reported in the registry record.

These omissions do not show that an adjustment or missing-data method was absent from the trial’s full analysis plan; they mean those details cannot be established from the registry record. The available results can be described, but readers should not infer unreported procedures or assume that all sources of uncertainty have been addressed.

12. 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: mania (1.9%), dermatitis atopic (1.9%), joint swelling (1.9%), sympathetic posterior cervical syndrome (1.9%), loss of consciousness (1.9%).

The safety figures report participants affected by serious adverse events and other adverse events within each group. Serious adverse events were reported for 1 participant in Dose Regimen 1, 2 participants in Dose Regimen 2, 1 participant in Dose Regimen 3, 2 participants in Dose Regimen 4, and 0 participants in the placebo group. Other adverse events were reported for 27, 27, 24, 31, and 21 participants, respectively. No deaths were reported in any group.

The registry lists Mania, Dermatitis atopic, Joint swelling, Sympathetic posterior cervical syndrome, Loss of consciousness, and Pulmonary embolism among the top serious adverse-event terms; each is listed as 1.9%. These terms describe events recorded in the trial and should not be treated as evidence that an event was caused by the assigned treatment. The registry does not provide enough detail in these figures to assess event timing, recurrence, severity beyond the serious-event classification, or individual clinical circumstances.

Counts are descriptive and should be interpreted with the group sizes and study context in mind. They do not by themselves establish comparative safety, especially when events are uncommon. The posted results do not provide a full account of adverse-event types or exposure-adjusted rates in the summarized safety information. The registry’s adverse-event counts should be considered alongside, not substituted for, the detailed safety analysis.

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

The efficacy results describe mean EASI score changes through Week 16 in a randomized, double-blind, placebo-controlled trial of adults with moderate-to-severe atopic dermatitis. The posted group estimates are negative, indicating average reductions from baseline in EASI score. The ANCOVA estimates compare each dose regimen with placebo, and the registry reports confidence intervals and p-values for those contrasts.

These results do not show that every participant experienced a reduction, nor do they describe the full range of individual outcomes. A mean can conceal variation in response. The endpoint captures EASI-assessed severity and extent; it does not, by itself, represent every symptom, quality-of-life dimension, or safety outcome. The daily diary and other assessments are described in the trial summary, but the registry record does not provide their results.

The findings concern the analyzed population and the Week 16 assessment. The record does not establish whether the observed changes persisted during follow-up, and it does not report later efficacy estimates in the posted primary results. It also does not provide enough statistical detail to assess missing-data handling or multiplicity adjustment.

The reported p-values and intervals describe uncertainty under the sponsor’s ANCOVA analyses. They do not prove a treatment effect, establish clinical importance, or predict outcomes for a particular person. The registry results are one trial’s evidence, and further conclusions would depend on the full analysis, safety context, and evidence beyond the registry record. No treatment recommendation follows from these statistical results alone.

14. Why This Trial Matters Statistically

This trial is statistically informative because it compares four dose regimens with a shared placebo group using a defined continuous endpoint and reports both group-level estimates and adjusted contrasts. A dose-finding design can help characterize how results vary across regimens, rather than asking only whether a single treatment schedule differs from placebo. The posted estimates show that the observed mean changes and reported contrasts vary among the regimens.

For readers, the distinction between within-group change and between-group comparison is important. The EASI group means describe change from baseline, while the ANCOVA estimates address comparisons with placebo. Treating those quantities as interchangeable could lead to an incorrect reading of the results. Confidence intervals add information about precision, while p-values provide a separate summary of compatibility with a null model.

The registry record also illustrates why transparency about analysis choices matters. It identifies the primary analysis population and statistical method, but does not report model details, missing-data procedures, or multiplicity handling. Those omissions constrain assessment of the strength and robustness of the results, especially when several dose comparisons are reported.

Safety counts complement the efficacy endpoint, but descriptive event counts do not resolve comparative safety questions on their own. Together, the efficacy and safety results show the kinds of evidence a dose-finding trial can contribute, while also making clear why estimates, uncertainty, analysis methods, and reporting completeness need to be considered as a whole.

15. 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 registry record leaves important analysis details unspecified. It names ANCOVA but does not report the covariates, model form, or other specification choices. It identifies the Full Analysis Set for the primary endpoint without defining its membership in detail. Missing Week 16 data, the method used to handle missing outcomes, and sensitivity analyses are not reported in the registry record.

Four dose-regimen comparisons with placebo are reported, but a multiplicity adjustment or testing hierarchy is not described. Consequently, the posted p-values cannot be interpreted as adjusted across all comparisons unless that procedure is documented elsewhere. The record also does not report the sponsor’s original sample-size justification or its interim-analysis plan.

The efficacy results concern the Week 16 EASI endpoint. Results for later efficacy time points are not reported in the registry record summarized for this analysis. The record describes daily diaries and other assessments, but their findings are not included among the posted outcome results. Group means also do not convey individual response distributions.

The safety information presented includes counts of participants with serious and other adverse events, deaths, and selected serious-event terms. These data do not provide a complete clinical account of event timing, duration, recurrence, exposure, or attribution. Small event counts cannot alone establish differences in risk between regimens.

Finally, the results come from a phase 2b trial in adults with moderate-to-severe atopic dermatitis. The registry record does not provide evidence to determine how well the estimates generalize to populations or settings beyond the trial. These limitations define what can be concluded from the posted record; they do not establish that additional analyses or information do not exist elsewhere.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Trial to Evaluate the Efficacy and Safety of Different Doses of LEO 138559 in Adults With Moderate-to-severe Atopic Dermatitis — NCT05923099.
• Registry record last updated 2026-02-12; status last verified 2025-12.
• Results first posted 2026-02-12.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

NCT05923099 is a completed phase 2b, randomized, double-blind, placebo-controlled, multi-site, parallel-group dose-finding trial sponsored by LEO Pharma. It evaluated four subcutaneous LEO 138559 regimens against placebo in adults with moderate-to-severe atopic dermatitis. The registry lists enrollment of 262.

The primary endpoint was percent change in EASI score from baseline to Week 16, analyzed in the Full Analysis Set. The record posts least-squares mean estimates and 95% confidence intervals by group, along with ANCOVA comparisons of each regimen with placebo. It also reports counts for serious and other adverse events and states that no deaths occurred in the groups.

The record does not report the detailed ANCOVA specification, multiplicity procedure, or missing-data approach. These gaps limit independent assessment of the analyses. The posted estimates describe trial results and their statistical uncertainty; they do not establish individual outcomes or conclusions beyond the measured population, endpoint, and assessment time.