Study Evaluating the Mechanism of Action of PF-04965842 Monotherapy for Moderate-to-severe Atopic Dermatitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study Evaluating the Mechanism of Action of PF-04965842 Monotherapy for Moderate-to-severe Atopic Dermatitis (NCT03915496), a randomized phase 2 study. The primary outcome is Fold-Change From Baseline in Atopic Dermatitis Biomarkers in Lesional and Non-lesional Skin at Week 12.

2. Clinical Question

The trial was designed to investigate a mechanism of action by relating efficacy outcomes to changes in skin and blood biomarkers. This is a different emphasis from a trial whose main question is limited to improvement in symptoms or clinical signs. Clinical outcomes, including measures of itch, investigator assessment, and eczema severity, were listed among secondary outcomes. Their numerical results are not reported in the registry record.

3. Trial Design

This was a Phase 2a, randomized, double-blind, placebo-controlled, parallel-group, multicenter study sponsored by Pfizer. The registry lists quadruple masking. Participants were assigned to PF-04965842 100 mg once daily, PF-04965842 200 mg once daily, or matching placebo once daily, with a 1:1:1 allocation. Treatment was planned for 12 weeks.

The registry describes approximately 51 participants as the planned enrollment in the study summary. The enrollment field records 46. These are distinct registry entries: the record does not explain the difference, so the reason should not be inferred. It also does not report the group-specific number randomized or the number who completed treatment.

The study began on 2020-06-18, had a primary completion date of 2021-11-16, and is listed as completed. The summary states that participants who completed the 12-week study treatment could choose to enter the long-term extension study B7451015 (NCT03422822). Participants who discontinued early were to undergo a 4-week off-treatment follow-up period.

The design included laboratory and tissue measures as well as clinical outcomes. The primary outcome concerned fold-changes in biomarkers in lesional and non-lesional skin at Week 12. Listed secondary outcomes included skin and blood biomarkers, lymphocyte subsets, itch response, investigator assessment, and eczema severity. The registry record does not report the full protocol, sample-size justification, or details of the randomization procedure beyond the stated allocation.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The analysis population included all participants randomly assigned to study intervention and who took at least 1 dose of study intervention. Number Analyzed in each row refers to the number of participants measured and analyzed for each parameter at Week 12 visit.

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: Baseline analysis population included all participants randomly assigned to study intervention and who took at least 1 dose of study intervention. Participants were analyzed according to the intervention they actually received.

6. Primary Endpoint

The registry lists the primary outcome as Fold-Change From Baseline in Atopic Dermatitis Biomarkers in Lesional and Non-lesional Skin at Week 12, measured over Baseline, Week 12.

The primary endpoint was mean fold-change from baseline at Week 12 in selected atopic dermatitis biomarkers in lesional and non-lesional skin. The listed markers covered general inflammation (MMP12), hyperplasia (KRT16), Th2 immune response (CCL17, CCL18, CCL26), and Th22 immune response (S100A8, S100A9, S100A12). Expression levels from RT-PCR were normalized to the housekeeping gene RPLP0 by negatively transforming Ct values to -dCt.

These measures were chosen to characterize biological changes in affected and non-lesional skin. In general, biomarkers can help describe biological processes that accompany a condition or change during treatment; they do not, by themselves, establish the size of a clinical benefit. The trial summary says the study aimed to investigate mechanism of action by correlating efficacy outcomes with changes from baseline in skin and blood biomarkers.

The registry specifies a mean and standard deviation for the primary measure and says the timeframe was baseline and Week 12. The analysis population included randomized participants who took at least 1 dose. The number analyzed was parameter-specific: it referred to participants measured and analyzed for that biomarker at the Week 12 visit. Numerical estimates, variability, and comparisons for these primary measures are not reported in the registry record, so the magnitude and precision of the biomarker changes cannot be evaluated from the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a randomized, double-blind, placebo-controlled, parallel-group study. Randomization assigns participants to study groups using a chance-based process. In general, this can reduce systematic differences between groups at assignment, although it does not guarantee identical groups, especially in a study with limited enrollment. Double-blinding is intended to limit the influence of knowledge of assigned treatment on participant experience and outcome assessment. The registry separately lists quadruple masking; it does not specify which roles were masked or provide further masking details.

What does the mean describe?

The primary parameter was the mean of a continuous measure. In general, a mean summarizes the average observed value in a group, while a standard deviation describes the spread of participant measurements around that average. The standard deviation is not the same as the uncertainty around the mean or around a treatment-group comparison. Confidence intervals are commonly used to express uncertainty in an estimate; such intervals are not reported for the primary endpoint in the registry record.

The measured quantity was fold-change from baseline at Week 12. The registry states that expression levels from RT-PCR were normalized to RPLP0 by negatively transforming Ct values to -dCt. It identifies separate biomarkers and lesional and non-lesional tissue. Those details matter because each marker and tissue type represents a distinct measurement. A group average for one marker should not be treated as a summary of all the biomarkers or both tissue types.

Why is the analysis population specified?

The primary outcome population included all participants randomly assigned to study intervention who took at least 1 dose. The registry also defines the number analyzed for each row as the number measured and analyzed for that parameter at the Week 12 visit. In general, these definitions distinguish the participants included in the study population from those with an available measurement for a particular outcome. The record does not provide the parameter-specific counts or explain how missing Week 12 measurements were handled.

An analysis restricted to participants with a measurement can be affected if missingness is related to treatment, outcome, or participant characteristics. This is a general concern, not evidence that such bias occurred in this trial. The registry record does not report the amount or pattern of missing data, an imputation method, or a sensitivity analysis for missing outcomes.

How should treatment comparisons be assessed?

A treatment comparison should be read together with its estimated difference and a measure of uncertainty. In general, an estimate conveys the observed contrast, while a confidence interval conveys a range of values compatible with the data under the method's assumptions. A p-value addresses compatibility with a specified statistical null model; it does not measure the clinical importance of an effect. No numerical primary endpoint estimates, confidence intervals, or p-values are reported in the registry record.

The study has two active doses and a placebo group, and its primary outcome spans multiple biomarkers and tissue types. The registry does not identify a single primary comparison among those possibilities. The skip note states that the primary outcome has several categories or time points and was not reduced to one comparison. Consequently, a single effect estimate should not be assumed to represent every marker, tissue, or dose comparison.

What does multiplicity mean in this setting?

In general, testing many outcomes or comparisons creates more opportunities for a nominally unusual result to occur by chance. Statistical methods can address this through a prespecified testing hierarchy or adjustment, but the registry record does not report such a plan or an adjustment for multiplicity. It also does not report whether interim analyses were planned or conducted. Neither a correction nor an absence of one should be inferred from the outcome list alone.

The sample-size assumptions describe a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is described as a stated fraction of the observed effect. In general, such an illustration is a planning calculation, not observed power and not a trial result. The record does not report a sample-size justification for the trial itself. The primary outcome was not reduced to one comparison, so the stated skip indicates that it was not used to produce a single comparison-based illustration.

Why can over-dispersion matter?

Over-dispersion is a general issue when data vary more than a chosen statistical model expects. If a model understates variability, its uncertainty estimates may be too narrow. The primary endpoint is described as a continuous measure summarized by a mean and standard deviation; the registry does not report a model for the primary outcome or identify over-dispersion as an issue. No claim about model fit can therefore be made from the record.

10. Multiplicity, Missing Data and Analysis Populations

The primary outcome covers several biomarkers and both lesional and non-lesional skin. The listed secondary outcomes add multiple biomarker families, clinical measures, and assessment times. The registry lists 28 outcome measures and zero analyses. It does not report a statistical plan defining a primary comparison across these measurements, a hierarchy of tests, or a multiplicity adjustment. In general, when many outcomes or comparisons are examined, the chance of a nominally notable finding can increase; the record does not say how this concern was addressed.

Numerical results for the primary and secondary outcomes are not reported in the registry record. The record therefore does not provide outcome-specific estimates, confidence intervals, or p-values with which to evaluate magnitude, precision, or statistical compatibility. The stated sample-size assumptions describe a planning illustration based on an observed effect and are not a substitute for a reported trial analysis or a sample-size justification.

The primary analysis population was defined as randomized participants who took at least 1 dose. For each biomarker, the number analyzed referred to participants measured and analyzed at Week 12. This parameter-specific definition does not reveal how many measurements were missing or why. The registry record does not report missing-data handling, imputation, sensitivity analyses, or an analysis population based on all randomized participants regardless of treatment received.

These reporting gaps limit assessment of whether the analyses followed a prespecified plan and whether missing measurements or multiple testing affected interpretation. They do not establish that the trial used an inappropriate method; the relevant details are not reported in the registry record.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: eczema herpeticum (6.2%), periorbital cellulitis (6.2%), sepsis (6.2%).

The registry lists serious adverse events, other adverse events, and deaths separately for the three groups. For serious adverse events, the recorded figures are 0 of 16 for abrocitinib 100 mg QD, 0 of 14 for abrocitinib 200 mg QD, and 1 of 16 for placebo. For other adverse events, the figures are 10 of 16, 7 of 14, and 7 of 16, respectively. Deaths are recorded as 0 in each group.

These are descriptive counts among the participants listed as at risk in each group. They do not, on their own, establish whether an event was caused by study treatment or whether groups differ reliably. In general, safety comparisons require attention to event definitions, follow-up, exposure, and uncertainty; those details are not fully reported in the registry record.

The record lists eczema herpeticum, periorbital cellulitis, and sepsis among the top serious adverse event terms, each with 6.2%. The listed information does not give an arm-specific breakdown for those terms, so they should not be assigned to a particular treatment group. The counts are not evidence that an event was treatment-related. Interpret the group counts and the term list as separate registry summaries, not as a complete causal assessment.

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

This trial's central statistical question concerned changes in selected skin biomarkers during 12 weeks of treatment with abrocitinib or matching placebo. The registry defines the measures, tissues, population, and treatment groups. It does not report numerical primary endpoint results, so it cannot show the observed magnitude, direction, or precision of biomarker changes.

The design also listed clinical outcomes, including itch response, investigator assessment, and eczema severity. These outcomes could provide information distinct from laboratory and tissue biomarkers. However, their numerical results are not reported in the registry record. The endpoint descriptions alone do not establish whether clinical outcomes changed or how the groups compared.

In general, a biomarker endpoint may help characterize biological activity, but it is not automatically a direct measure of how participants feel or function. A biomarker result, if reported, would need to be interpreted alongside clinical outcomes, uncertainty, and the analysis plan. Here, those numerical results and analysis details are not available in the registry record.

The safety entries are descriptive counts and selected event terms. They do not by themselves determine causality or comparative risk. Likewise, randomization, masking, and the completed status describe trial conduct and record status, not the size or certainty of an effect.

The defensible conclusion is therefore about the scope of the study and what was recorded, rather than about treatment efficacy: this was a randomized Phase 2a biomarker-focused trial with two active doses and placebo, and the registry record does not report the numerical efficacy analyses needed to assess its primary or secondary outcomes.

13. Why This Trial Matters Statistically

This study is statistically notable for connecting tissue-level biomarkers with clinical outcomes in a randomized, placebo-controlled design. Its primary endpoint covered markers associated with inflammation, hyperplasia, and immune response, measured in lesional and non-lesional skin. That design makes clear that a trial can be organized around biological mechanism rather than a single clinical response measure.

The endpoint structure also raises interpretive questions that matter in biostatistics. Multiple biomarkers, tissue types, treatment groups, and secondary outcomes create a need for clear prespecification of comparisons and transparent handling of multiplicity. The registry record does not report a testing hierarchy or adjustment strategy. Without that information, a reader cannot determine how a set of potential findings was intended to support an overall claim.

Population definitions are another important feature. The primary outcome population required random assignment and at least 1 dose, while the number analyzed was specific to each Week 12 measurement. This makes outcome-specific denominators and missing-data procedures important for interpretation, but those details are not reported in the registry record.

Finally, the record illustrates the difference between a trial design and an analyzable result. It identifies the comparison, endpoint, and selected safety counts, but numerical primary and secondary outcome analyses are absent. Statistical interpretation depends not only on a well-described question but also on estimates and uncertainty that allow readers to assess what the observations show.

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 principal limitation for statistical interpretation is that numerical results for the primary endpoint are not reported in the registry record. The same is true for the listed secondary outcomes. Without estimates and measures of uncertainty, the size and precision of biomarker or clinical comparisons cannot be assessed.

The primary endpoint involves multiple biomarkers in two tissue settings, but the record does not specify a single primary comparison or report a multiplicity strategy. It does not provide the statistical model, confidence intervals, p-values, or details of any interim analyses. These omissions prevent assessment of how comparisons were selected and analyzed; they do not establish that a particular method was or was not used.

The registry describes approximately 51 participants as planned enrollment and records enrollment of 46. It does not explain the difference or provide group-specific analyzed counts for the primary endpoint. Although the endpoint population and parameter-specific Week 12 analysis counts are defined, actual counts and missing-data handling are not reported.

The study was Phase 2a and focused on adults with moderate-to-severe atopic dermatitis. The registry does not provide numerical efficacy results that would support assessment of the findings within this population, and the record alone does not establish how broadly findings would apply beyond it. Safety information is limited to group counts and selected serious-event terms; event-level details and arm-specific counts for those terms are not reported in the registry record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Study Evaluating the Mechanism of Action of PF-04965842 Monotherapy for Moderate-to-severe Atopic Dermatitis — NCT03915496.
• Registry record last updated 2023-02-08; status last verified 2023-01.
• Results first posted 2023-02-08.
• 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

The registry record describes NCT03915496, a completed, randomized, double-blind, placebo-controlled, parallel-group, multicenter Phase 2a study sponsored by Pfizer. It evaluated abrocitinib 100 mg QD and 200 mg QD against matching placebo in adults with moderate-to-severe atopic dermatitis, with treatment planned for 12 weeks.

The primary endpoint was mean fold-change from baseline at Week 12 in selected biomarkers from lesional and non-lesional skin. The record lists 28 outcome measures and zero analyses. Numerical primary and secondary outcome results are not reported in the registry record. Enrollment is recorded as 46, while the study summary describes approximately 51 participants as planned enrollment; the record does not explain the difference.

The registry includes descriptive serious and other adverse event counts and deaths by group. Those entries do not provide a complete causal or comparative safety assessment. Missing-data methods, multiplicity procedures, the trial's sample-size justification, and detailed statistical analyses are not reported in the registry record.