Explorative Trial Evaluating the Efficacy and Tolerability of LEO43204 in Moderate to Severe Acne: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Explorative Trial Evaluating the Efficacy and Tolerability of LEO43204 in Moderate to Severe Acne (NCT02575950), a randomized phase 2 study. The primary outcome is Total Lesion Count (Inflammatory and Non-inflammatory).

2. Clinical Question

3. Trial Design

The registry record identifies NCT02575950 as a completed Phase 2 exploratory trial sponsored by LEO Pharma. It lists a randomized allocation, double masking, and a parallel model. The trial title and summary also describe a randomized, placebo-controlled, double-blinded split-face design in which LEO 43204 and vehicle were applied to left and right facial areas. These descriptions are not fully reconciled in the registry record: it does not explain how the parallel-model classification relates to the split-face comparison.

The study is described as single-centre and prospective. Enrollment is listed as 59. The record lists the start as 2016-06 and primary completion as 2017-04, with status completed. The primary outcome was total inflammatory and non-inflammatory lesion count at Week 12 (Day 84). The record also lists inflammatory and non-inflammatory counts separately, investigator global assessment categories, and local skin response outcomes among its secondary measures.

A split-face design compares two treatment areas within the same participant. As a general statistical point, this can control for participant-level characteristics shared by both sides, while requiring the analysis to account appropriately for the within-person pairing. The registry record does not state the side-assignment procedure, the pairing method used in the analysis, or whether any additional design features were used. Its primary reported method is ANCOVA, but the model specification and covariates are not reported in the registry record.

The primary outcome description reports a Week 12 full analysis set of 32 subjects and says 6 discontinued before Week 12. The primary arm summaries list 38 for each area, while the secondary lesion-count summaries list 32 for each area. The registry record does not explain the relationship among those analysis counts, the full analysis set description, and enrollment. They should therefore be read as the denominators attached to their respective posted results, not combined or treated as interchangeable.

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: 19 of the participants enrolled were screening failures. The remaining 40 were enrolled sequentially into 4 cohorts. Progression from one cohort to the next was decided by the Safety Review Committee following a review of local skin responses (LSRs), safety, and tolerability after the last participant in each cohort had completed the Week 2 visit.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The analysis was based on the full analysis set (FAS). At Week 12, FAS comprised 32 subjects as 6 subjects discontinued before Week 12. The overall number of participants analyzed is irrespective of the number of participants providing data or not.

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Total Lesion Count (Inflammatory and Non-inflammatory), measured over At Week 12 (Day 84).

The primary endpoint is total lesion count, defined as the number of inflammatory and non-inflammatory acne lesions in the designated lesion areas. It is assessed at Week 12 (Day 84). The registry record reports the measure as a least-squares mean with a 95% confidence interval.

Lesion count is a quantitative measure of acne signs. Combining inflammatory and non-inflammatory lesions gives a single count intended to reflect both categories in the treated area. The separate categories also appear among the secondary outcomes, allowing the record to report them apart from the combined primary measure. A count is directly interpretable in lesion units, but its statistical meaning depends on the comparison, variability, analysis population, and completeness of follow-up.

Least-squares means are model-based estimates rather than necessarily simple arithmetic averages. In general, they can account for factors included in a statistical model. The registry record names ANCOVA for the reported comparison but does not report the model covariates or further details of the calculation, so the precise adjustment cannot be reconstructed from the record.

The endpoint measures lesion counts at the stated visit; it does not, on its own, describe every aspect of acne, participant experience, durability beyond Week 12, or tolerability. The record lists separate local skin response and investigator assessment outcomes, but those are not part of the definition of the primary endpoint.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the primary ANCOVA estimate represent?

The registry record reports an ANCOVA comparison of final values, expressed as a mean difference. ANCOVA is a general method for comparing group means while adjusting for variables included in the model. Its adjusted estimate can differ from a raw difference between displayed group means. The posted least-squares means and the ANCOVA estimate are therefore related but are not interchangeable summaries. The covariates, model specification, and handling of the split-face pairing are not reported in the registry record, so the sponsor's estimate cannot be reconstructed from the posted summary statistics alone.

For this endpoint, the estimated difference is -9.34 lesions, with a 95% confidence interval from -14.71 to -3.96. The negative sign indicates that the estimated final count was lower in the LEO 43204 area than in the vehicle area under the sponsor's analysis. In general, a confidence interval gives a range of estimates consistent with the observed data and the assumptions of the method. Its width conveys precision; it is not a range containing every participant's result and does not express the probability that the true value lies in the interval.

How should the p-value be read?

The reported p-value is p < 0.001. In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the statistical model were correct. It is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of a difference. The confidence interval adds information about the direction and precision of the estimated difference.

The registry record names ANCOVA and reports the result as a superiority comparison. It does not report the complete hypothesis-testing plan, covariates, model diagnostics, or details of any adjustments to the nominal test. Therefore, interpretation should stay with the analysis as reported rather than assuming an unreported model specification.

Why does the split-face design matter?

In a split-face study, the two treatment areas belong to the same participant. As a general statistical principle, measurements from the two sides may be related because they share participant-level characteristics. A paired analysis can use that relationship, and treating the sides as unrelated observations can misstate uncertainty. The registry record identifies the split-face design but does not say how the sponsor accounted for the paired structure in the primary ANCOVA. This is a limitation on independent verification, not evidence that the reported analysis was necessarily incorrect.

The record also labels the trial model as parallel. Because the title and summary describe a split-face arrangement, the relationship between that classification and the treatment-area comparison is unclear. Further design or analysis detail is not reported in the registry record.

What are the recalculated secondary comparisons?

The secondary lesion-count comparisons are simple, unadjusted recalculations from the posted group means, standard deviations, and group sizes. They do not replace the sponsor's primary ANCOVA and are not sponsor-reported secondary analyses. For inflammatory lesion count, the recalculated mean difference is -2.1; for non-inflammatory lesion count, it is -5.28. In both cases, the estimate is in the direction of a lower mean in the LEO 43204 area. The corresponding unadjusted p-values are 0.088 and 0.219, and both unadjusted confidence intervals include zero.

These calculations use summary statistics rather than individual participant data. They cannot incorporate unreported adjustments or confirm the precise analysis population and dependence structure. General statistical caution is warranted when an analysis is based on summary data: the result may not match a model that uses the original observations, especially when observations are paired or when covariate adjustment is part of the sponsor's method. The registry record does not list sponsor-reported analyses for these two secondary outcomes.

What do the sample-size illustrations mean?

The planning illustrations use the observed secondary effect as a starting point and show hypothetical sample sizes for detecting stated fractions of that effect. Their assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The figures are participants per arm for 80% or 90% power, depending on the stated target. They are planning illustrations, not observed power and not evidence that the completed trial had those planned enrollment targets.

Observed effects can be unstable, particularly when estimated in a small exploratory study. Planning around a fraction of an observed effect makes explicit how the assumed target changes the sample-size requirement, but it does not establish what effect future research should target. The trial's own sample-size rationale and assumptions are not reported in the registry record. No sample-size illustration is available for the primary comparison in the posted recalculations, which are marked as not estimable for a two-arm continuous-endpoint comparison.

What can and cannot be inferred from the record?

The reported primary analysis supports a difference in Week 12 estimated total lesion count under the sponsor's stated ANCOVA. The posted summary does not permit full reproduction of the model or evaluation of all its assumptions. The secondary calculations provide a separate, unadjusted view of two component outcomes, but do not have the status of sponsor-reported analyses. General statistical interpretation should keep those evidence sources distinct, as well as distinguish statistical uncertainty from clinical importance.

10. Analyses Reported by the Sponsor

The sponsor's reported primary analysis is an ANCOVA comparison of final values. It gives a mean difference of -9.34 lesions for LEO 43204 relative to vehicle, with a 95% confidence interval from -14.71 to -3.96 and p < 0.001. That is the analysis to use when describing the registry's primary result. The posted primary recalculation is not estimable for a two-arm continuous-endpoint comparison, so there is no independent summary-statistic recalculation to compare numerically with the sponsor's estimate.

The record does not flag a discrepancy between a recalculation and the sponsor analysis. That does not make the sponsor's model reproducible from the posted information: covariates, model details, and treatment of the split-face pairing are not reported in the registry record. The sponsor's estimate should therefore be described as reported, with its stated interval and p-value, rather than as independently verified.

The secondary lesion-count comparisons are different. The registry record has no sponsor-reported analyses for those outcomes; the posted comparisons are unadjusted recalculations from summary statistics. They should not be presented as if they were the sponsor's prespecified or adjusted findings. Their limitations and the absence of reported multiplicity handling should remain explicit when they are discussed.

11. Multiplicity, Missing Data and Analysis Populations

The record lists a primary outcome and a set of secondary outcomes, but it does not report a multiplicity strategy. When several outcomes or comparisons are assessed, the chance of at least one apparently unusual result can rise even when none of the underlying effects is real. As a general statistical approach, a study may define one primary hypothesis, adjust secondary tests, or treat secondary findings as exploratory. Which approach was planned or used is not reported in the registry record. The unadjusted secondary p-values should not be interpreted as if multiplicity had been addressed.

The primary outcome description states that its Week 12 analysis was based on the full analysis set and says that this set comprised 32 subjects, with 6 discontinuing before Week 12. The primary arm summaries list 38 for each area, while the secondary lesion-count summaries list 32 for each area. The record does not clarify the relationship among those figures or specify how missing Week 12 measurements were handled. It also does not report an imputation method, sensitivity analysis, or reasons for discontinuation.

Missing outcome data can affect estimates when the chance of a missing measurement is related to the outcome or to treatment experience. In general, an analysis that excludes unavailable measurements relies on assumptions about the missingness process; imputation and sensitivity analyses can examine how assumptions affect conclusions. The registry record does not describe such methods, so the impact of missing data cannot be assessed from the posted information.

The analysis population is described in the primary outcome text, but a fuller definition of the full analysis set and its relationship to the listed arm denominators is not reported in the registry record. The record also does not report the trial's sample-size justification, interim analyses, or a complete statistical analysis plan. These omissions limit assessment of prespecification and of how the analysis population, missing data, and multiple outcomes were handled.

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 0% reporting threshold.

Most frequent non-serious adverse event terms

The registry record lists no serious adverse events affecting participants in the non-cutaneous, LEO 43204 0.018%, or vehicle groups, and no deaths in those groups. It lists 40 at risk in each group. These are the serious-event figures recorded for the trial; zero events observed in a study does not establish that an event is impossible or that a treatment is free of risk.

The record also lists other adverse events affecting 2 in the non-cutaneous group, 18 in the LEO 43204 group, and 1 in the vehicle group. These figures are distinct from the serious-event counts and should not be conflated with them. The registry record does not provide serious-event terms, and its list of top serious terms is empty. It does not report further detail on event severity, timing, relatedness assessments, or how the non-cutaneous group relates to the split-face treatment areas.

Safety counts in a completed exploratory trial describe what was recorded during its observation period. They do not by themselves quantify uncommon or longer-term risks, and the record does not supply the detail needed for a broader safety assessment.

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

The primary result is a model-based comparison of Week 12 total lesion counts in a randomized, double-blinded, placebo-controlled split-face trial. The sponsor reported a lower estimated count for the LEO 43204 area than for the vehicle area. Its 95% confidence interval for the mean difference excludes zero, and its reported p-value is p < 0.001. Those figures describe the statistical evidence and precision of the posted primary comparison.

They do not, by themselves, establish how important the difference is to participants. The registry record does not report a threshold for a clinically meaningful change in total lesion count, nor does the statistical result capture every dimension of acne or treatment experience. It also does not establish that the result applies to people outside the trial population, to other treatment routines, or to outcomes beyond Week 12.

The secondary component counts have estimates in the same direction, but their unadjusted intervals include zero. They are exploratory and should not be treated as separate proof of the primary result. The other listed secondary outcomes address investigator assessment and local skin response; their presence in the registry does not supply unreported numerical conclusions.

There are important boundaries to interpretation. The registry record does not clarify the primary analysis denominator in relation to the Week 12 full analysis set description, explain missing-data handling, or report the pairing method for the split-face analysis. Nor does it provide the full ANCOVA specification. These gaps limit independent reproduction and a complete evaluation of assumptions. The result is therefore best understood as the sponsor's reported primary statistical finding in this trial, accompanied by uncertainty about some analysis details—not as a general conclusion about treatment effects or a basis for medical advice.

14. Why This Trial Matters Statistically

This trial is statistically instructive because the treatment comparison is described as split-face, while the registry record also classifies the model as parallel. The split-face feature matters: two facial areas from the same participant are not automatically independent observations. A sound analysis generally needs to reflect the design's within-person relationship. The record names ANCOVA but does not report enough model detail to assess how that relationship was handled.

The record also illustrates why the analysis population and denominators deserve attention. Its primary outcome description refers to a Week 12 full analysis set of 32 subjects and notes 6 discontinuations, while the primary arm summaries list 38 for each area. The secondary lesion-count summaries list 32 for each area. Because the relationship among these figures is not explained, they should not be casually reconciled or used to infer an unreported participant flow.

Another statistical distinction is between a sponsor-reported primary model and simple unadjusted recalculations for secondary outcomes. The former is an ANCOVA analysis; the latter use posted summary statistics and cannot incorporate unreported model features. Their estimates may be useful as exploratory context, but they are not equivalent analyses. Multiple secondary outcomes also make unadjusted results more vulnerable to chance findings if no correction is used.

Finally, planning calculations based on observed effects are not observed power. They illustrate how assumed effect sizes and design assumptions translate into hypothetical participants per arm. They cannot reveal the trial's original sample-size rationale, which is not reported in the registry record. Together, these issues show why reading an estimate requires attention not only to its value and interval, but also to design, analysis population, missingness, multiplicity, and the limits of registry detail.

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 trial is described as exploratory and single-centre, so the record alone does not establish how well its findings generalize beyond its setting and enrolled population. Enrollment is listed as 59, while the primary outcome description, arm summaries, and secondary summaries use different analysis counts. The record does not clarify how those numbers relate or give a participant-flow account that resolves the difference.

The split-face design is not fully connected to the registry's parallel-model classification. The side-assignment method and the analysis treatment of within-participant dependence are not reported. Although the primary method is named as ANCOVA, the registry record does not identify the covariates, detailed model specification, diagnostic checks, or missing-data approach. These omissions limit independent reproduction of the primary estimate and assessment of its assumptions.

The record does not report a sample-size justification, a complete statistical analysis plan, interim analyses, or a multiplicity procedure. Secondary lesion-count results are unadjusted recalculations rather than sponsor-reported analyses, and the listed secondary outcomes cover several distinct measures. This makes secondary findings exploratory and increases the importance of caution when considering multiple comparisons.

The primary endpoint is measured at Week 12 (Day 84). Longer-term outcomes and the clinical-importance threshold for a change in total lesion count are not reported in the registry record. The safety listing gives serious adverse event counts and other adverse event counts, but does not report further context such as event timing or relatedness. These record-level limitations constrain the conclusions that can be drawn without implying that unreported procedures were absent.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Explorative Trial Evaluating the Efficacy and Tolerability of LEO43204 in Moderate to Severe Acne — NCT02575950.
• Registry record last updated 2025-03-06; status last verified 2019-02.
• Results first posted 2019-02-28.
• 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

NCT02575950 is a completed Phase 2 exploratory trial sponsored by LEO Pharma. The registry record describes a randomized, double-blinded, placebo-controlled study in adults with moderate to severe acne and a split-face comparison of LEO 43204 0.018% with vehicle. Enrollment is listed as 59, with the start recorded as 2016-06 and primary completion as 2017-04.

The primary outcome was total inflammatory and non-inflammatory lesion count at Week 12 (Day 84). The sponsor reported an ANCOVA mean difference of -9.34 lesions, with a 95% confidence interval from -14.71 to -3.96 and p < 0.001. The registry record also lists separate lesion-count outcomes, investigator assessment, local skin response, and safety measures. Key details about analysis denominators, missing-data handling, multiplicity, and the split-face model are not reported in the registry record.