Baricitinib (LY3009104) in the Treatment of Cutaneous Lichen Planus: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Baricitinib (LY3009104) in the Treatment of Cutaneous Lichen Planus (NCT05188521), a non-randomized phase 2 study. The primary outcome is Physician Global Assessment (PGA) of Skin Overall Response.

2. Clinical Question

3. Trial Design

This completed Phase 2 study evaluated baricitinib in participants with cutaneous lichen planus. The registry record lists Aaron R. Mangold as sponsor and reports a start date of 2022-01-11 and primary completion on 2023-05-17. Enrollment was 12.

The allocation is described as non-randomized, the masking as none, and the model as sequential. Participants with cutaneous lichen planus were to receive baricitinib for a 16 weeks treatment period. The listed interventions are baricitinib 2 mg and baricitinib 4 mg. The record also describes a dose escalation extension: participants who responded to 2 mg but had not achieved PGA 0 could receive 4 mg for 12 weeks.

This sequence matters when interpreting any comparison between the groups. Entry to the extension depends on a participant’s response during the earlier treatment period. The extension group is therefore selected rather than formed as an equivalent control group. The record itself cautions that the arms are not a like-for-like control comparison.

The registry record does not report the number assigned to each treatment sequence, the detailed schedule of assessments, the duration of follow-up after treatment, or a statistical analysis plan. It also does not report whether any participants discontinued treatment or were excluded from an analysis. These details cannot be inferred from the total enrollment or the group descriptions.

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.

Baricitinib 2mg Initial Study

Reasons for not completing this period:

Baricitinib 4mg Extension Study

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: A total of twelve participants were enrolled in the overall study, which contained a dose escalation extension. Five of the twelve completed the dose escalation extension, resulting in a total of seventeen participants analyzed for the Baseline Measures overall.

6. Primary Endpoint

The registry lists the primary outcome as Physician Global Assessment (PGA) of Skin Overall Response, measured over Week 16.

The primary endpoint is Physician Global Assessment (PGA) of Skin Overall Response, recorded as a count of participants at Week 16. The assessment grades skin status from Grade 0, completely clear with no evidence of disease and 100% improvement, through Grade 6, worse than at baseline by at least 25%. The registry record describes the scale but does not report the number of participants at each grade or a responder cutoff used for the primary outcome.

As a general measurement concept, a clinician-rated global assessment condenses an evaluation of disease status into an ordered scale. Such a scale can make changes easier to communicate, but a count of participants does not by itself show how large or how consistent those changes were. The distribution across grades, the definition of a response, and the analysis method are important for understanding a result.

The endpoint is assessed at a specified time, Week 16, making the timing part of its interpretation. The registry record does not report the observed endpoint result, uncertainty around it, or how participants with missing Week 16 assessments were handled. Therefore, the endpoint’s measurement framework is described, but its trial result cannot be evaluated from the reported primary outcome information.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary outcome as a count of participants assessed by PGA at Week 16. It does not report the statistical test, model, effect estimate, confidence interval, or p-value for that outcome. Consequently, the method used to analyse the primary endpoint is not reported in the registry record. The outcome description alone does not reveal whether the analysis used grades, a defined response threshold, or another summary.

What does a participant count represent?

As a general statistical concept, a count of participants with an event or outcome category records how many people meet a specified definition. Interpretation depends on that definition and on the number of people assessed. A count without its corresponding analysis population, denominator, and handling of missing assessments can be difficult to compare across groups. In this study, the registry gives total enrollment and safety denominators, but does not provide primary endpoint counts or an analysis denominator.

When outcomes are binary, a common summary is the proportion of participants meeting the event definition. General methods for comparing such outcomes can estimate differences between groups, but the choice of method depends on the design and the available data. No such primary endpoint comparison is reported in the registry record. In particular, an unadjusted recalculation cannot be made without posted primary outcome counts. No recalculated primary result is available to compare with a sponsor analysis.

What do confidence intervals and p-values convey?

As a general explanation, a confidence interval expresses the precision of an estimated effect under the assumptions of the analysis. A narrower interval indicates greater precision, while a wider interval indicates greater uncertainty. A p-value describes how compatible the observed data are with a specified null model, under the assumptions of the test; it is not a measure of the probability that a treatment works. Neither statistic is reported for the primary endpoint in the registry record, so neither the size nor the precision of a primary effect can be assessed.

The non-randomized, sequential structure also matters for methods. General statistical adjustment can account for measured differences when appropriate data and a prespecified model are available, but it cannot automatically remove differences that were not measured. The record does not report an adjustment strategy, covariates, model specification, or a comparative control group. The response-based selection into the extension is an additional reason not to interpret outcomes across groups as if assignment had been random.

How should the planning illustration be understood?

The registry record describes a sample-size planning illustration using a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It describes the target effect as a stated fraction of the observed effect. These are planning assumptions, not a description of the trial’s own design or a report of statistical power observed in the completed study. Any resulting sample sizes are hypothetical planning quantities, not the number of participants actually enrolled. The registry record does not report that this illustration was the study’s original sample-size justification.

More generally, planning calculations depend on an assumed effect, variability, analysis method, and target power. A calculation based on an observed effect is especially dependent on the uncertainty in that estimate: an unstable observed effect can yield an unstable planning target. It does not show that the completed trial had adequate power or that its result is conclusive. The actual trial enrolled 12 participants; the record does not report a prespecified target enrollment or the assumptions used to choose it.

Over-dispersion is a general concern when count outcomes vary more than a statistical model expects. It can make standard errors too small if the model does not allow for the extra variability. The primary outcome is described as a participant count, but the registry does not report a model for it or evidence that over-dispersion was assessed. It would therefore be inappropriate to claim that this issue affected the analysis. More broadly, no model diagnostics or sensitivity analyses are reported.

The record lists 9 outcome measures and 8 analyses, but does not describe the analysis populations, missing-data procedures, multiplicity strategy, or any interim analyses. The absence of these details limits the ability to reproduce the analysis or determine how choices among outcomes and analyses were handled. These methods are not reported in the registry record, so no particular procedure should be assumed.

10. Multiplicity, Missing Data and Analysis Populations

The registry record lists 9 outcome measures and 8 analyses. Secondary outcomes include changes in Modified CAILS Score of the Cutaneous Index Treatment, skin lesion count, Pruritus Numerical Rating Scale, and Overall Skindex-16 Assessment; these outcome names appear more than once in the listing. The record does not explain the repeated entries or identify which analyses correspond to each outcome.

As a general statistical concern, testing several outcomes can increase the chance of obtaining at least one apparently notable result by chance. A prespecified multiplicity strategy may control that risk or designate outcomes with different priorities. No multiplicity adjustment, hierarchy, or prespecified distinction among secondary analyses is reported in the registry record. The primary result itself is also not reported, so the relationship between primary and secondary findings cannot be assessed.

The record does not describe how missing outcome data were handled, whether any participants lacked assessments, or which participants were included in each analysis population. It does not report an intention-to-treat population, a per-protocol population, or a missing-data sensitivity analysis. These procedures are not reported in the registry record. Their absence from the record does not establish that data were missing; it means the handling cannot be evaluated.

Interim analyses and stopping rules are also not reported in the registry record. Without those details, it is not possible to determine whether any outcome monitoring or analysis decisions were planned during the study. These gaps limit reproducibility and make it harder to distinguish prespecified analyses from exploratory ones.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: hospitalization due to fall (8.3%).

The registry reports serious adverse events for 12 participants at risk in the Cutaneous LP group and 5 participants at risk in the Dose Escalation Extension Group. The corresponding counts affected are 1 and 0. Other adverse events are reported for 8 participants at risk of 12 in the Cutaneous LP group and 4 at risk of 5 in the extension group. Deaths are reported as 0 in each group.

The top serious adverse event term is Hospitalization due to fall, reported as 8.3%. The record does not state in this listing whether the event was judged related to treatment. An adverse event recorded during a study is not, by itself, evidence that treatment caused it.

These are descriptive counts from small groups, not a randomized safety comparison. The extension group was selected according to response during the earlier treatment period, and the groups are not like-for-like controls. The counts do not establish comparative risk or rule out events that were not observed. The registry record does not provide further detail about event timing, severity beyond the serious classification, or causal attribution.

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

The registry record establishes that a Phase 2 study of baricitinib in cutaneous lichen planus was completed, with enrollment of 12 participants and a sequential, non-randomized, unmasked design. It describes a Week 16 PGA primary outcome and a response-based dose escalation extension. It does not report the primary endpoint results, so the posted information does not show how participants were distributed across PGA grades or how many met a response definition.

That absence is central to interpretation. A treatment effect cannot be estimated from an endpoint description alone. There is no reported primary comparison, measure of uncertainty, or p-value to assess. The registry record also does not identify a randomized control group, so even a before-and-after change would not by itself establish that the change was caused by treatment.

The dose escalation group answers a different descriptive question from an independently assigned 4 mg group. Its participants were selected because they responded to 2 mg but had not achieved PGA 0. A comparison with the initial group would combine dose differences with differences in treatment history and selection.

Safety counts provide a record of reported events, not a causal conclusion. The counts are limited in size, and the registry does not provide a like-for-like comparison. Likewise, a zero count for deaths in the reported groups does not establish that a risk is absent.

As a general principle, a study’s design, outcome definition, analysis population, and uncertainty all shape what can be concluded. Here, several of those analysis details are not reported in the registry record. The responsible interpretation is therefore narrow: the study design and some adverse event counts are described, while the primary clinical outcome result and its precision are not available in the registry record.

13. Why This Trial Matters Statistically

This trial is statistically notable because its sequential design links treatment exposure to response. The extension group consists of participants who responded to 2 mg but had not reached PGA 0, then received 4 mg for 12 weeks. That structure may describe a treatment pathway, but it does not create a randomized comparison of doses. Recognizing the selection mechanism prevents a descriptive group contrast from being mistaken for a causal treatment estimate.

The study also illustrates why outcome definitions matter. PGA is an ordered assessment ranging from completely clear skin to a grade worse than baseline, while the primary outcome is described as a count of participants. The record does not identify a responder threshold or publish the Week 16 grade counts. Without those details and results, readers cannot assess the endpoint’s distribution or the magnitude of any change.

Enrollment was 12, so the reported adverse event counts represent a small study population. Small counts are inherently limited in precision, and the extension group is smaller still. This is a general statistical limitation of sparse event data, not evidence that an unreported event occurred or that a particular safety conclusion follows.

Finally, the record separates study completion from result availability. A completed study can still have important outcome and analysis details not reported in its registry record. In this case, the design and safety counts can be described, but the primary efficacy result, uncertainty, and analysis procedures are not available. That distinction is important for transparent 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 principal limitation for interpreting this trial is that the registry record does not report the primary endpoint result. Although the Week 16 PGA measure is described, participant counts by grade, the response definition, and an estimate of effect are not reported. The primary question therefore cannot be answered from the registry information.

The study is non-randomized, unmasked, and sequential, with no like-for-like control comparison identified in the record. The dose escalation extension is restricted to participants who responded to 2 mg but had not reached PGA 0. Differences between the initial group and extension group therefore cannot be attributed to dose alone.

Enrollment was 12. The small study population limits the amount of information available for estimating outcomes and describing less common events. The record also does not report group-specific enrollment for the initial treatment sequence, the analysis populations, or whether all enrolled participants contributed Week 16 data.

Further details needed to evaluate reproducibility are not reported in the registry record. These include the statistical analysis plan, methods for missing data, multiplicity handling, interim analyses, covariate adjustment, and analysis diagnostics. The registry lists 9 outcome measures and 8 analyses but does not explain how they were mapped or prioritized. Safety listings do not provide causal attribution or event timing. These limitations restrict both efficacy interpretation and comparison of safety outcomes.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Baricitinib (LY3009104) in the Treatment of Cutaneous Lichen Planus — NCT05188521.
• Registry record last updated 2024-06-11; status last verified 2024-05.
• Results first posted 2024-06-11.
• 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

NCT05188521 is a completed Phase 2 study of baricitinib in cutaneous lichen planus, sponsored by Aaron R. Mangold. The record reports enrollment of 12, a non-randomized allocation, no masking, and a sequential model. The main treatment period was 16 weeks with 2 mg baricitinib; selected participants who responded but had not reached PGA 0 could receive 4 mg for 12 weeks in an extension.

The primary outcome was a participant count for PGA of Skin Overall Response at Week 16. The registry record describes the grade scale but does not report the primary result, a responder cutoff, or its statistical uncertainty. Safety listings report serious and other adverse event counts and 0 deaths in each group. The record does not report the statistical analysis plan, missing-data methods, or multiplicity approach.