An Investigational Study to Evaluate Experimental Medication BMS-986165 in Japanese Participants With Moderate-to-Severe Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for An Investigational Study to Evaluate Experimental Medication BMS-986165 in Japanese Participants With Moderate-to-Severe Psoriasis (NCT03924427), a na phase 3 study. The primary outcome is Static Physician's Global Assessment (sPGA) 0/1 Response as a Number of Participants With a sPGA Score of 0 or 1 at Week 16.

2. Clinical Question

3. Trial Design

The registry describes NCT03924427 as an open-label, single-arm, multi-center Phase 3 study of BMS-986165 in Japanese participants with moderate-to-severe psoriasis. It lists psoriasis as the condition under study and identifies Bristol-Myers Squibb as the sponsor. Enrollment is recorded as 74. The study is marked completed, with a start date of 2019-04-10 and a primary completion date of 2021-03-24.

All participants were assigned to the single study group; the registry describes BMS-986165 as given daily. Because the study is single-arm and allocation is listed as not applicable, there is no concurrent control group for a like-for-like comparison. The study is also open-label, with masking listed as none. These design features matter when interpreting outcome counts: a change observed during the study cannot, on its own, separate the treatment effect from other explanations such as the natural course of disease or expectations during assessment.

The primary endpoint is a binary response at Week 16. It counts participants with an sPGA score of 0 or 1 and at least a 2-point improvement from baseline. The registry defines the analysis population as all treated participants and specifies non-responder imputation (NRI). Although two outcome measures are listed, the registry record reports no analyses for the primary endpoint. The endpoint result is therefore not reported in the registry record.

The registry’s safety summary lists 74 participants at risk for serious adverse events and 74 at risk for other adverse events. Its group label is “Deucravacitinib 6 mg QD,” while the intervention field names BMS-986165. The record does not explain this naming difference. No randomized treatment comparison or control-group safety estimate is available from this study design.

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: All treated participants

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 Static Physician's Global Assessment (sPGA) 0/1 Response as a Number of Participants With a sPGA Score of 0 or 1 at Week 16, measured over Week 16.

The primary endpoint is the number of participants with an sPGA score of 0 or 1 at Week 16, provided the score also represents at least a 2-point improvement from baseline. The registry specifies non-responder imputation for this endpoint and identifies all treated participants as the analysis population.

The sPGA is described as a 5-point assessment of the average appearance of psoriatic lesions, considering erythema, scale, and induration. Its categories run from clear (0) and almost clear (1), through mild (2) and moderate (3), to severe (4); higher scores denote more severe disease activity. The endpoint therefore combines a status at Week 16 with a required improvement from baseline. A score of 0 or 1 alone would not meet the stated response definition if the required improvement were absent.

As a binary endpoint, each participant is classified as meeting or not meeting the response definition under the specified analysis approach. Counts of responders can be useful for describing how many participants reached a prespecified clinical state by a particular time. They do not, by themselves, describe the size of change for each participant or establish what would have happened under a different treatment.

The registry record does not report the Week 16 response count or an analysis estimate. Therefore, the observed response rate, its uncertainty, and any comparison with another group are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a binary endpoint mean?

In general, a binary endpoint classifies each participant into one of two outcome categories, such as meeting or not meeting a prespecified response definition. The primary outcome in this study is reported as a count of participants who meet its definition. That definition is not based on a single score alone: it requires an sPGA score of 0 or 1 at Week 16 and at least a 2-point improvement from baseline. The count is meaningful only in relation to the endpoint definition and the population being analyzed.

The registry identifies all treated participants as the population for the primary endpoint and specifies NRI. The result count itself is not reported in the registry record. Consequently, there is no posted estimate to interpret for the primary outcome, and no confidence interval or other measure of its statistical uncertainty is reported there.

What does non-responder imputation mean?

In general, non-responder imputation is a rule for handling some missing outcome assessments in a binary response analysis: participants with missing response information are counted as not having responded, according to the specified approach. This can make an analysis more conservative than treating missing outcomes as responses, but it does not eliminate uncertainty about why data are missing. Its implications depend on the missingness pattern and the exact analysis rules.

The registry names NRI for the Week 16 endpoint but does not report the number of missing assessments, the number treated as non-responders because of missing information, or additional sensitivity analyses. The specific operational details beyond the stated method are not reported in the registry record. It is therefore not possible to assess from the record how much the endpoint result, if reported, would depend on missing-data handling.

What can a single-arm study estimate?

In general, a single-arm study can describe outcomes observed in its enrolled group. Without a concurrent comparison group, it cannot directly estimate the difference between outcomes under the intervention and outcomes under an alternative condition. A response count can be clinically descriptive, but it does not by itself isolate the cause of the response. Comparisons with historical or external groups would require additional information and assumptions; no such comparison is reported in the registry record.

Open-label status also has interpretive relevance. In general, knowledge of treatment assignment can influence behavior, reporting, or assessment. The primary endpoint uses a physician’s global assessment, so masking status is important context for readers. The registry lists masking as none. It does not report whether assessment procedures included other safeguards or how assessors were organized.

How should planning illustrations be understood?

In general, sample-size planning estimates how many participants may be needed for a future study under chosen assumptions. Such calculations are not observed power for a completed study and do not establish that an effect occurred. The planning assumptions listed for this record specify a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is expressed as a stated fraction of the observed effect. The record says these calculations are planning illustrations, not the trial’s own design.

Those assumptions describe a hypothetical two-arm planning exercise, whereas the actual trial is single-group. Thus, planning illustrations based on equal allocation between two arms should not be mistaken for this study’s design or for a randomized comparison conducted in this trial. The record says participant counts are expressed per arm for non-time-to-event outcomes and total events for time-to-event outcomes. The registry record does not report the trial’s sample-size justification or its design rationale.

What is the role of statistical significance and precision?

In general, a confidence interval describes a range of values compatible with the data and an analysis model, while a p-value addresses how unusual data at least as extreme as those observed would be under a specified null hypothesis. Neither measure substitutes for the endpoint definition, study design, or clinical interpretation. A narrow interval can indicate greater statistical precision than a wide interval, but precision does not remove bias or establish causality.

No primary endpoint estimate, confidence interval, or p-value is reported in the registry record. The statistical analysis plan, including any planned model, adjustment, or interim analyses, is not reported in the registry record. Therefore, there is no basis in the posted information for describing a sponsor analysis or recalculated result for the primary endpoint.

For safety, the record provides affected-participant counts and selected serious-event terms. These are descriptive summaries. In general, event counts can be influenced by follow-up duration, definitions, and ascertainment; the registry record does not provide detail sufficient to characterize those factors beyond the reported at-risk counts. Because the study has no control group, these summaries do not estimate comparative risks.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Plaque Psoriasis 6 mg QD", "Generalized Pustular Psoriasis 6 mg QD", "Erythrodemic Psoriasis 6 mg QD")
n      <- c(63, 3, 8)
events <- c(52, 0, 4)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Plaque Psoriasis 6 mg QD  63  52  82.5  70.9  90.9  71.4  90.0  71.3  89.9
ARM  Generalized Pustular Psoriasis 6 mg QD  3  0  0.0  0.0  70.8  0.0  56.1  0.6  60.2
ARM  Erythrodemic Psoriasis 6 mg QD  8  4  50.0  15.7  84.3  21.5  78.5  21.2  78.8

11. Multiplicity, Missing Data and Analysis Populations

The registry lists two outcome measures and zero analyses. It does not report the primary endpoint result or describe a statistical analysis plan. In particular, the registry record does not report whether a multiplicity-control procedure was planned for multiple outcomes, whether the primary endpoint was tested alongside other endpoints, or how any family of statistical tests would have been handled. It is not appropriate to infer a testing strategy from the number of listed outcomes alone.

The primary endpoint specifies NRI, a method that treats missing response information according to a non-responder rule. The registry does not report how many Week 16 assessments were missing, how many participants were analyzed, or whether any additional missing-data sensitivity analyses were conducted. The listed primary population is all treated participants, but the record does not provide further details about analysis-population definitions or exclusions.

In general, missing-data methods encode assumptions about outcomes that are not observed. NRI gives a defined classification rule, but a reader still needs information about the amount and pattern of missingness to judge how influential the rule may be. Those details, along with sensitivity analyses, are not reported in the registry record.

The record also does not report interim analyses, stopping rules, or a sample-size justification. These omissions do not establish that such procedures were absent; they mean that they are not reported in the registry record. Without endpoint results and fuller analysis details, multiplicity, missingness, and population choices cannot be assessed beyond the method and population labels that are stated.

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: covid-19 (1.4%), pneumonia (1.4%), hodgkin's disease (1.4%), normal pressure hydrocephalus (1.4%), asthma (1.4%).

The safety summary lists 5 participants affected by serious adverse events among 74 at risk, and 40 affected by other adverse events among 74 at risk. Deaths are listed as 0. These figures describe the study group; they are not comparisons with a control group. The study is single-arm, so the counts cannot establish whether the intervention changed the frequency of these events relative to another treatment or no treatment.

The serious-event terms listed are COVID-19, Pneumonia, Hodgkin's disease, Normal pressure hydrocephalus, and Asthma. Each term is reported at 1.4%. These term-specific percentages should be read as the registry’s reported values, not as estimates of comparative risk. The record does not provide further information about event timing, duration, causality assessment, or whether participants experienced more than one event.

The safety summary labels its group “Deucravacitinib 6 mg QD,” while the intervention field names BMS-986165 and describes daily dosing. The registry record does not explain the difference in naming. The listed at-risk counts and event counts are descriptive and should be interpreted with that record-level limitation in mind.

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

The registry record establishes that this was a completed, open-label, single-arm Phase 3 study of daily BMS-986165 in Japanese participants with moderate-to-severe psoriasis. It defines a primary Week 16 response outcome based on sPGA status and improvement from baseline, and it specifies NRI for the analysis. It also provides selected safety counts for the study group.

The record does not report the primary endpoint result. It therefore does not show how many participants met the response definition, what proportion that count represents, or how precisely an estimate was measured. It also does not report an analysis comparing outcomes with a control group. No conclusion about the intervention’s causal effect can be drawn from the listed design and endpoint definition alone.

The safety figures indicate how many participants were reported as affected in the study group, with deaths listed as 0 and selected serious-event terms reported at 1.4% each. Without a concurrent control group, these counts do not show whether the events were more or less common than under another condition. They also should not be treated as proof of a cause-and-effect relationship.

More generally, statistical significance, if reported, would not by itself establish clinical importance or remove limitations of an open-label single-arm design. Likewise, a planning illustration is not a result from the trial and is not observed power. Here, the registry record does not provide an endpoint analysis to evaluate for significance or precision. The defensible interpretation is limited to the study design, the endpoint definition, and the descriptive safety information actually reported.

14. Why This Trial Matters Statistically

This study is statistically informative as an example of the difference between a clearly defined endpoint and a reported endpoint result. The registry specifies a binary response definition, a time point, an analysis population, and a missing-data method. Those elements are essential for understanding what an estimate would mean. Yet the primary endpoint result and its analysis are not reported in the registry record, so the definition cannot be converted into an observed response estimate or an assessment of precision.

The single-arm design is also central to interpretation. It can describe outcomes in the enrolled group, but it does not provide a concurrent contrast. This distinction helps prevent a response count from being interpreted as proof that the intervention caused the response. Open-label status adds another consideration for an endpoint based on physician assessment, because knowledge of treatment assignment may matter to assessment in general.

The record illustrates why safety summaries should be read separately from efficacy outcomes. It reports affected-participant counts and selected serious-event terms, but those are descriptive and have no control-group comparison. Further, the safety group label differs from the intervention name, and the registry does not explain that difference. Preserving such record-level uncertainties is part of careful statistical reporting.

Finally, the planning assumptions describe a hypothetical two-arm calculation rather than the actual single-arm study. Treating planning illustrations as observed results or as trial design details would blur the distinction between prospective planning and evidence collected in a trial. The record supports a useful discussion of endpoint definition, missing-data handling, study design, and descriptive safety reporting, while leaving the primary outcome’s result unreported.

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 primary limitation for interpreting efficacy is that the Week 16 response count and statistical analysis are not reported in the registry record. There is therefore no primary endpoint estimate or measure of its uncertainty to assess. The record lists two outcome measures but no analyses.

The study has no concurrent comparator and is open-label. These features prevent a randomized like-for-like comparison and limit causal interpretation of any observed outcome. The primary endpoint involves a physician’s assessment, and masking is listed as none. The registry record does not describe additional assessment safeguards.

Although NRI is specified, the registry does not report the amount or pattern of missing outcome data, the number classified as non-responders because of missing information, or sensitivity analyses. It also does not report the statistical analysis plan, interim analyses, or sample-size justification. These details are not reported in the registry record; their absence from the record does not establish that they were absent from study conduct.

The safety summary is descriptive, with no control group for comparison. The record does not provide further detail about event timing, duration, or causality assessment. It labels the safety group “Deucravacitinib 6 mg QD,” whereas the intervention field names BMS-986165; the relationship between those names is not reported in the registry record. These limitations mean that safety counts should be attributed to the registry summary without resolving the naming difference or inferring comparative risk.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: An Investigational Study to Evaluate Experimental Medication BMS-986165 in Japanese Participants With Moderate-to-Severe Psoriasis — NCT03924427.
• Registry record last updated 2022-11-02; status last verified 2022-10.
• Results first posted 2022-11-02.
• 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

NCT03924427 is listed as a completed, open-label, single-arm, multi-center Phase 3 study sponsored by Bristol-Myers Squibb. It investigated daily BMS-986165 in Japanese participants with moderate-to-severe psoriasis. The registry lists enrollment of 74, a start date of 2019-04-10, and a primary completion date of 2021-03-24.

The primary endpoint is the number of treated participants with an sPGA score of 0 or 1 at Week 16 and at least a 2-point improvement from baseline, using NRI. The endpoint result and its analysis are not reported in the registry record. The safety summary reports 5 participants with serious adverse events among 74 at risk, 40 with other adverse events among 74 at risk, and 0 deaths. Its group label differs from the intervention name, and the registry does not explain the difference.