A Study to Evaluate Safety and Efficacy of PF-06826647 For Moderate To Severe Plaque Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate Safety and Efficacy of PF-06826647 For Moderate To Severe Plaque Psoriasis (NCT03895372), a randomized phase 2 study. The primary outcome is Percentage of Participants With a Psoriasis Area and Severity Index 90 (PASI 90) Response Up to Week 16 - Investigational Treatment Period.

2. Clinical Question

3. Trial Design

This was a phase 2, randomized, double-blind, placebo-controlled, parallel study of PF-06826647 in participants with moderate to severe plaque psoriasis. The registry lists an enrollment of 179 and describes the study as completed. The study start date is 2019-06-27, and the primary completion date is 2020-05-21. It was sponsored by Pfizer.

The stated purpose was to collect additional safety and tolerability data, further explore clinical efficacy, and support selection of an oral dose and dosing regimen for future clinical development. That purpose describes the study’s aims; it does not establish that a dose was selected or that a particular regimen produced a specific clinical result.

Several treatment regimens are listed. PF-06826647 and placebo regimens were administered orally during a 16-week investigational treatment period. Some PF-06826647 dose-level regimens are described as continuing for 24 weeks in an extension period after the investigational treatment period. The registry also lists safety groups with treatment sequences that begin with placebo or a PF-06826647 dose and then continue with PF-06826647. The allocation ratio, detailed randomization procedures, and dose-specific assignment counts are not reported in the registry record.

The primary outcome was the percentage of participants with a PASI 90 response, assessed at Week 16. Other listed outcomes include PASI response thresholds, physician global assessment categories, changes in PASI, and change in peak-pruritus numerical rating scale scores. The registry lists 25 outcome measures and 36 analyses. The full protocol, the statistical analysis plan, and details of how each analysis related to the study aims are not reported in the registry record.

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: This was a Phase 2b, randomized, double blind, placebo controlled, parallel group, and multicenter study in participants with moderate to severe plaque psoriasis.

Only the first 6 of 8 groups are shown.

Investigational Treatment Period

Reasons for not completing this period:

Extension Treatment Period

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The analysis population included all randomized participants who received at least 1 dose of investigational product (PF-06826647 or placebo) after non-responder imputation applied (the participants discontinued due to coronavirus disease 2019 were removed).

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: Demographic and baseline characteristics were summarized by randomized treatment group for all randomized and treated participants.

Only the first 6 of 9 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With a Psoriasis Area and Severity Index 90 (PASI 90) Response Up to Week 16 - Investigational Treatment Period, measured over Baseline up to Week 16.

The primary endpoint is the percentage of participants with a PASI 90 response up to Week 16. PASI combines investigator assessments of erythema, induration, and scaling across body regions with the percentage of body surface area affected. The score represents both lesion severity and the extent of psoriasis involvement; higher PASI scores represent greater severity. A PASI 90 response is defined as at least a 90% reduction in PASI relative to baseline.

This kind of threshold endpoint turns a change in a continuous score into a binary outcome: each participant either meets the response definition or does not. The percentage of participants meeting the threshold can be interpreted as the proportion achieving a substantial reduction according to this prespecified score definition. It is different from the average change in PASI: a group average can describe overall change while not identifying how many individuals crossed a particular response threshold.

The registry specifies that the statistical analysis was for data at Week 16, with the timeframe described as baseline up to Week 16. It lists a 90% confidence interval as the dispersion measure. However, the response counts, percentage estimate, confidence interval limits, and any dose-versus-placebo estimate are not reported in the registry record. The endpoint definition therefore explains what the intended measure represents, but does not establish the observed response in any group.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary at the participant level: a participant either satisfies the PASI 90 response definition at Week 16 or does not. The group percentage is the number of participants meeting the definition relative to the analysis denominator. For a binary endpoint, both parts matter. A percentage without its denominator gives limited information about how much data support the estimate, and different denominators can make superficially similar percentages have different precision.

What does PASI 90 measure?

PASI is a composite score based on the investigator’s assessment of erythema, induration, and scaling in four body regions, adjusted for the proportion of body surface area affected and the size of each region relative to the whole body. The score ranges from 0.0 to 72.0, can vary in increments of 0.1, and higher values represent greater psoriasis severity. PASI 90 defines response by relative reduction from an individual participant’s baseline score rather than by reaching one fixed final score. This gives the endpoint a common threshold across participants whose baseline scores may differ.

A threshold can make an outcome easier to communicate as a proportion achieving a defined response, but it also discards information about the magnitude of change within each category. Participants just below the threshold and participants with little change are both counted as nonresponders under that definition; those just above it and those with a larger reduction are both counted as responders. Continuous PASI change outcomes, which are also listed in the registry, address a different question by retaining more information about score changes.

How should the confidence interval be understood?

The primary outcome lists a 90% confidence interval. In general, an interval describes uncertainty around an estimated quantity using a specified method. It is not a guarantee that the true value lies within the particular calculated limits, and it is not a measure of clinical importance. Interpreting an interval requires the estimate, its limits, the underlying denominator, and the method used to construct it. Those numerical results and construction details are not reported in the registry record.

If the goal is to compare groups, the relevant estimate would need to express a contrast between them, with an uncertainty interval appropriate to that contrast. A confidence interval around a response percentage in one group alone does not establish the size or precision of a between-group difference. The registry entries available for this analysis do not report a specific dose-versus-placebo contrast or its interval.

What does non-responder imputation do?

The primary analysis population description says that non-responder imputation was applied. In general, this approach classifies participants with missing response data as not having achieved the response. It makes an explicit assumption about missing outcomes rather than estimating them from the observed values. Such an approach can be conservative in some settings, but its effects depend on why data are missing and on the pattern of missingness; the label alone does not demonstrate that bias has been eliminated.

The population description also says participants who discontinued due to coronavirus disease 2019 were removed. This is distinct from classifying missing outcomes as nonresponse: those participants were excluded from the population described for the primary analysis. The number removed and the reasons and timing of other missing outcome data are not reported in the registry record. The handling of missing data for secondary outcomes is also not reported in the registry record.

What does multiplicity mean for this study?

The registry lists numerous outcome measures and analyses. In general, testing multiple outcomes, treatment groups, or time points can increase the chance of at least one apparently notable finding arising by chance if each test is interpreted separately. Statistical plans may address this through prespecified testing sequences or other adjustments, or may treat analyses as exploratory. The registry record does not report whether multiplicity was controlled, which outcomes were confirmatory, or what hierarchy, if any, was used. The number of listed measures alone cannot answer those questions.

The sample-size assumptions describe planning illustrations 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. Such calculations are planning illustrations, not observed power. The protocol’s own sample-size justification and whether the trial was designed around those assumptions are not reported in the registry record. The numerical planning estimates are not reported in the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 25 outcome measures and 36 analyses, including the primary PASI 90 response and several secondary clinical outcomes. With multiple analyses, multiplicity is relevant because separate testing can increase the chance of a false-positive result across the set of analyses. The registry record does not report whether adjustments were made, which outcomes were treated as confirmatory, whether a testing hierarchy was specified, or how results from multiple doses and outcomes were to be interpreted. No multiplicity procedure should be inferred from the outcome list alone.

For the primary outcome, the stated analysis population included all randomized participants who received at least one dose of investigational product, after non-responder imputation was applied. Participants who discontinued due to coronavirus disease 2019 were removed from that population. The registry does not report the number of participants removed for this reason or the numbers with missing primary-outcome data in each treatment group.

Non-responder imputation is a missing-data rule that treats missing response information as failure to meet the response threshold. In general, this may affect response estimates if missingness is related to outcome or differs across groups. Excluding participants for a stated discontinuation reason is a separate population decision. The registry record does not report sensitivity analyses examining alternative assumptions, nor does it describe missing-data handling for the listed secondary outcomes. Consequently, the robustness of the primary analysis to missing-data assumptions cannot be evaluated from the information reported.

The analysis population is not described as every enrolled participant without qualification: it is restricted to randomized participants who received at least one dose, with the stated handling of discontinuations. The registry does not provide group-specific analysis denominators in the registry record for the primary endpoint. Enrollment alone cannot substitute for those denominators.

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: hypoacusis (9.1%), viral sepsis (9.1%), fibrin d dimer increased (9.1%), sars-cov-2 test positive (9.1%), presyncope (9.1%).

The safety record gives counts of participants at risk and counts affected by serious adverse events, other adverse events, and deaths for treatment sequence groups. For example, the Placebo QD to PF-06826647 200 mg QD Group lists 23 participants at risk for serious events and 0 affected; its other-event counts are 23 at risk and 14 affected. The PF-06826647 200 mg QD to PF-06826647 200 mg QD Group lists 45 at risk for serious events and 3 affected, and 45 at risk for other events and 29 affected. These are group-specific descriptive counts.

The listed serious-event counts are 0 among 23, 1 among 22, 0 among 11, 1 among 11, 0 among 12, 1 among 11, 3 among 45, and 0 among 43 for the eight listed groups, in the order recorded. Deaths are listed as 0 in every group. The counts should be read with their corresponding group denominators; the groups are not all the same size. The treatment-group labels also include sequences, so they identify a treatment path rather than a simple single-period assignment.

Other adverse events are reported separately from serious adverse events and should not be conflated with them. The record also lists serious-event terms with percentages, including Hypoacusis, Viral sepsis, Fibrin D dimer increased, SARS-CoV-2 test positive, Presyncope, and Hypertension. The context and denominators for those term percentages are not reported in the registry record. These safety counts do not by themselves establish a causal relationship or provide a formal comparison between groups.

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

The registry record establishes what investigators intended to measure: the percentage of participants meeting a PASI 90 response definition at Week 16. It also describes a randomized, double-blind, placebo-controlled phase 2 design and the analysis population for that endpoint. These design details help a reader understand the planned question, but they are not a substitute for the observed response estimates.

The primary response counts, percentages, confidence interval limits, and comparative estimates are not reported in the registry record. Accordingly, the record information available for this analysis cannot show the magnitude or precision of the primary outcome, establish how the PF-06826647 groups compared with placebo, or support a conclusion about the clinical effect of any dose. This absence of reported results should not be interpreted as a finding of no effect.

The study’s stated goals included gathering safety and tolerability information, exploring efficacy, and informing future dose and regimen selection. The record’s stated aims do not demonstrate that a regimen was selected or that findings were definitive. As a phase 2 study with several listed dose-level regimens and outcome measures, its design description points to an exploratory development question; the registry record does not report the protocol’s formal status for each analysis or its decision criteria.

The safety figures show reported event counts in the listed groups, including zero deaths in each. They are descriptive summaries. Without additional information about event definitions, exposure, follow-up, and comparative analyses, the counts cannot establish whether treatment caused an event or whether risks differed between regimens.

In general, a clinical result is best interpreted by considering its estimate, uncertainty, analysis population, missing-data assumptions, and prespecified analysis plan together. For this trial, several of those numerical results and methodological details are not reported in the registry record. The design and endpoint can be described, but the efficacy findings cannot be reconstructed from the information recorded.

13. Why This Trial Matters Statistically

This trial raises common statistical questions in clinical development: how to compare multiple dose-level regimens, how to summarize a threshold response, and how to interpret outcomes when a study includes multiple measures and analyses. The primary endpoint turns PASI change into the proportion achieving a defined reduction. That is a direct and understandable summary, but it does not convey the full distribution of score changes, which is why continuous PASI outcomes can provide complementary information.

Randomization and double blinding are important design features because, in general, random allocation supports comparison of groups and masking can reduce differences in care or assessment arising from knowledge of treatment assignment. Those design features do not guarantee that every potential source of bias is absent, and the registry record does not give enough procedural detail to assess how randomization and masking were implemented.

The study also illustrates why analysis populations and missing-data rules need to be explicit. The primary analysis description specifies receipt of at least one dose, non-responder imputation, and removal of participants who discontinued due to coronavirus disease 2019. These decisions affect which participants contribute and how missing response information is treated. Their implications depend on the number and distribution of affected participants, which are not reported in the registry record.

Multiple outcomes and analyses make prespecification important. Without a reported statistical analysis plan or multiplicity approach, readers cannot determine which findings were intended to be confirmatory or how a collection of results should be interpreted. Finally, the registry’s safety counts show why denominators and event categories matter: serious events, other events, and deaths are distinct summaries, and descriptive counts are not a substitute for comparative analysis.

The record therefore offers useful design and measurement details while leaving key inferential information unavailable. Distinguishing what the study planned to assess from what its posted results establish is central to sound statistical interpretation.

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 main limitation for interpreting efficacy is that numerical primary-outcome results are not reported in the registry record. The PASI 90 response definition and analysis population are described, but the group-specific counts, percentages, confidence intervals, and comparisons are not. Secondary outcome results are likewise not reported in the registry record in the registry record for this analysis. As a result, neither the size nor the precision of an efficacy estimate can be discussed.

The registry lists an overall enrollment of 179, but group-specific primary-analysis denominators are not reported. The listed safety groups have different numbers at risk, and those counts should not be substituted for the primary-outcome denominators. The record also does not report how many participants were removed after discontinuing due to coronavirus disease 2019 or the extent of other missing outcome data.

Some methodological details that would affect interpretation are not reported in the registry record: randomization procedures, allocation ratio, the full statistical analysis plan, the sample-size justification, any interim analyses, and whether multiplicity was controlled. The listed sample-size assumptions describe planning illustrations, but the actual planning estimates and the trial’s own justification are not reported in the registry record.

The safety information is also limited to descriptive counts and listed event terms. The registry entries available do not include a full account of event definitions, exposure-adjusted summaries, or formal between-group safety comparisons. The term percentages are listed without their denominators or further context in the registry record. These limitations restrict interpretation of the available safety summaries and prevent causal conclusions from the counts alone.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Study to Evaluate Safety and Efficacy of PF-06826647 For Moderate To Severe Plaque Psoriasis — NCT03895372.
• Registry record last updated 2021-08-27; status last verified 2021-08.
• Results first posted 2021-08-27.
• 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

NCT03895372 is a completed phase 2 randomized, double-blind, placebo-controlled, parallel study of PF-06826647 in participants with moderate to severe plaque psoriasis. The record lists an enrollment of 179, a start date of 2019-06-27, and a primary completion date of 2020-05-21. The primary outcome is the percentage of participants with a PASI 90 response at Week 16, defined as at least a 90% reduction in PASI relative to baseline.

The primary analysis population included randomized participants who received at least one dose, with non-responder imputation and removal of participants who discontinued due to coronavirus disease 2019. The registry lists multiple secondary outcomes and safety counts across treatment sequence groups. Numerical primary efficacy results and key details of the statistical plan are not reported in the registry record.