Use of Etanercept in the Treatment of Moderate to Severe Lichen Planus: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Use of Etanercept in the Treatment of Moderate to Severe Lichen Planus (NCT00285779), a randomized phase 2 study. The primary outcome is The Percentage of Patients Achieving a Response in Mucosal Disease (or Cutaneous Disease if no Mucosal Disease) at 12 Weeks.

2. Clinical Question

3. Trial Design

The registry describes NCT00285779 as a phase 2, randomized, triple-masked, parallel-group pilot study. Its official title identifies the study as multicenter and double-blind, while the registry’s masking field says triple. The record does not explain the difference between those descriptions or specify which participants, investigators, or other roles were masked. The sponsor was Stanford University.

Enrollment was 27. Participants were assigned to etanercept or placebo. The etanercept arm received injections twice weekly for weeks 1–12; the placebo arm received normal saline injections on the same schedule. The registry identifies lichen planus as the condition under study and describes interest in physical signs of mucosal and cutaneous disease, disease-related itching and pain, and serious adverse events.

The registry lists the study start as 2006-08 and primary completion as 2009-11. Its status is terminated. The reason for termination and the timing of any decision to terminate are not reported in the registry record, so the status alone does not establish why the study ended or how termination affected the analysis.

The primary analysis population is described as intention to treat, with all participants who received at least one dose of study drug included. The primary outcome used last observation carried forward for missing data. The record does not report the randomization procedure, allocation concealment, treatment adherence, the number or pattern of missing observations, or detailed participant characteristics. A sample-size justification, interim analyses, and a full statistical analysis plan 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.

Placebo-controlled Period (wk 1-12)

Open Label Period (wk 12-24)

Follow-up Period (wk 24-32)

Analysis population for the primary outcome, as defined in the registry: Intention to treat analysis (all participants received at least one dose of study drug). Missing data imputed using Last Observation Carried Forward (LOCF).

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 The Percentage of Patients Achieving a Response in Mucosal Disease (or Cutaneous Disease if no Mucosal Disease) at 12 Weeks, measured over 12 weeks.

The primary endpoint is the percentage of participants achieving a response in mucosal disease at 12 weeks, or in cutaneous disease if a participant had no mucosal disease. It uses a physician global assessment scale running from 0, clear, through 4, severe disease. Participants were required to have a baseline score of at least 3. A responder had to reach a score of 0 or 1, or improve by at least 2 points on the scale.

This endpoint turns a physician’s assessment into a binary outcome: each participant is classified as a responder or not a responder under the stated rule. Reporting the percentage makes the arm-level response frequency visible, while a comparison can express the difference between those frequencies. The endpoint is clinically oriented in the sense that it uses assessed disease signs and a prespecified response definition, rather than a laboratory measurement alone.

The registry does not report a rationale for selecting this endpoint, the validation details for the assessment, or whether the response threshold was established before the study began. It also does not report separate primary results for mucosal and cutaneous disease. The primary measure therefore addresses the combined decision rule as registered, not each disease location as an independent primary comparison.

7. Results Posted in the Registry

• Etanercept: 0.0% (0/13) versus 28.6% (4/14) on control; risk difference -28.6 percentage points (95% CI -52.2 to -4.9); unadjusted two-proportion z-test p = 0.037.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Count of Patients Achieving a Response in Cutaneous or Mucosal Disease at 24 Weeks

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Etanercept: 30.8% (4/13) versus 35.7% (5/14) on control; risk difference -4.9 percentage points (95% CI -40.4 to 30.5), risk ratio 0.86 (0.29–2.53); unadjusted two-proportion z-test p = 0.785.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Etanercept and the control. The interval gives the range of effects that remain compatible with the data.

The registry identifies a broad set of secondary outcomes, including response at 24 weeks, physician-assessed surface area for oral, genital, and skin disease, and cutaneous target-lesion assessments. These measures extend the questions beyond the primary 12-week response, but the registry record does not provide a complete set of numerical results in the registry record for this analysis. The overall direction or consistency of all secondary findings therefore cannot be characterized from the outcome titles alone.

For the 24-week response comparison, the posted counts are 5 of 14 for placebo and 4 of 13 for etanercept. The recalculated risk difference is -0.050, with bounds from -0.404 to 0.305 and an unadjusted p-value of 0.785. The registry reports a Fisher Exact p-value of >1.000 for this outcome. The record flags a discrepancy, so the sponsor’s analysis takes precedence over the recalculation. The interval includes values on either side of zero and is broad, so this secondary comparison is imprecise.

Secondary outcomes can provide context about different disease manifestations and later assessments, but they generally carry less weight than a prespecified primary outcome when many outcomes are examined. Multiple unadjusted comparisons increase the chance that some results may appear notable by chance alone. The registry lists 14 secondary outcomes and 40 analyses, but does not report a multiplicity-adjustment strategy. These outcomes should consequently be read as exploratory unless the analysis plan establishes otherwise, and they do not overturn or independently confirm the primary result.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Count of Patients Achieving a Response in Cutaneous or Mucosal Disease at 24 Weeks
• The Physician Assessment of Surface Area of Disease (PSAD) for Oral Disease at 12 and 24 Weeks
• The Physician Assessment of Surface Area of Disease (PSAD) for Genital Disease at 12 and 24 Weeks
• The Physician Assessment of Surface Area of Disease (PSAD) for Skin Disease at 12 and 24 Weeks
• Cutaneous Target Lesion Scores - Erythema, at 12 and 24 Weeks
• Cutaneous Target Lesion Scores - Elevation, at 12 and 24 Weeks
• Cutaneous Target Lesion Scores - Scale, at 12 and 24 Weeks
• Cutaneous Target Lesion Scores - Total, at 12 and 24 Weeks

9. Statistical Interpretation

10. Statistical Methods Explained

The outcome is binary at the participant level: a person either meets the response rule or does not. For a binary outcome, an arm percentage describes the proportion classified as having the event of interest. The posted primary results give the response percentages and the corresponding arm counts. These summaries are useful for seeing what happened in each group, but percentages alone do not convey the uncertainty in a treatment contrast.

What does a risk difference express?

A risk difference compares the event proportions in two groups by subtracting one group’s proportion from the other. In this result, the recalculated contrast is expressed for etanercept relative to placebo. A negative value indicates that the response proportion was lower in the etanercept arm in the posted data. The risk difference is an absolute contrast, rather than a relative comparison such as a risk ratio. It therefore describes the separation between the two response proportions on the probability scale.

The recalculated risk difference is -0.286. Its interval bounds are -0.522 and -0.049. Those values come from a simple unadjusted recalculation of the posted summary statistics; they are not a substitute for the sponsor’s analysis. The confidence level for these bounds is not reported in the registry record. A confidence interval is a range generated by a statistical procedure to represent uncertainty around an estimate. Wider intervals generally indicate less precision, and narrow intervals indicate greater precision, under the assumptions of the method.

Why is there more than one p-value?

The registry reports the sponsor’s test as Fisher Exact, with p = 0.098. Fisher’s exact test is a method for comparing categorical outcomes that calculates probabilities using the observed group counts under a null model. The posted recalculation gives an unadjusted p-value of 0.037. Since the record flags a discrepancy, the sponsor’s analysis takes precedence. The registry does not report enough information to explain the difference between the sponsor result and the recalculation. A p-value is conditional on an analysis method and its assumptions; it is not an estimate of the probability that the null hypothesis is true, and it does not measure the importance of the observed difference.

The primary analysis population is described as intention to treat, including all participants who received at least one dose of study drug. The registry also says missing data were imputed using last observation carried forward. Under that approach, a participant’s last recorded outcome is carried forward to a later assessment when the later value is missing. This is an assumption about how the unobserved outcome relates to the last observed value. If disease status changes after the last observation, carrying that value forward may not represent the missing outcome. The registry does not state how many observations were missing, why they were missing, or whether alternative assumptions were examined.

What does the planning illustration mean?

A sample-size calculation uses assumptions about the effect to detect, the significance level, allocation, and statistical method to estimate a future study’s required enrollment. The registry’s planning illustration is based on the observed effect for the 24-week secondary response comparison, not on the primary 12-week endpoint and not on the trial’s original design. Its assumptions are a two-sided significance level of 0.05, equal allocation, and a normal approximation. The illustration includes scenarios planning for 100%, 75%, and 50% of the observed effect, with values for participants per arm for 80% power and participants per arm for 90% power.

These are planning illustrations, not observed power and not evidence about what the trial was designed to detect. The record does not report the study’s own sample-size justification. General statistical reasoning also cautions that planning from a noisy observed effect can produce unstable estimates of future requirements, especially when the original trial is small. The illustration should therefore be read as conditional on its stated assumptions, rather than as a definitive enrollment recommendation.

Over-dispersion is a concern for outcomes whose variability exceeds what a simple model assumes; models that ignore it can misstate uncertainty. The primary endpoint is binary, and the record identifies a Fisher Exact sponsor analysis and an unadjusted recalculation, not an over-dispersed count model. Accordingly, over-dispersion is not a reported feature of this primary analysis. More generally, the choice of statistical method matters because methods can differ in how they handle sparse event counts, missing data, and uncertainty.

11. Confidence Intervals and Precision

The recalculated primary risk difference is -0.286, with interval bounds of -0.522 and -0.049. The bounds span a substantial range of possible contrasts, so the estimate is not precise. The interval describes uncertainty around the recalculated estimate under its method; the confidence level is not reported in the registry record. The interval should not be presented as the sponsor’s interval, because the sponsor’s reported result is a Fisher Exact p-value and no sponsor confidence interval is posted.

Confidence intervals are useful because they show a range of values compatible with the data and the assumptions of the interval procedure. A point estimate alone can conceal how uncertain a result is. Here, the posted group counts are small, and the interval is wide. That combination means the estimated contrast should not be treated as a stable measure of the effect size. The interval’s bounds are both negative, but this fact pertains to the recalculation and does not resolve the discrepancy with the sponsor’s p-value of 0.098.

Precision is different from clinical importance. Statistical uncertainty concerns how much the estimated contrast might vary under repeated sampling and the method’s assumptions. Clinical importance requires a judgment about what size of difference matters in context; a threshold for that judgment is not reported in the registry record. The primary endpoint also combines mucosal disease and, for participants without mucosal disease, cutaneous disease. The record does not provide separate estimates that would show whether precision differs by disease location.

Missing-data imputation adds another source of uncertainty. The primary analysis used last observation carried forward, but the amount and pattern of missing data are not reported. The interval therefore does not by itself show how sensitive the result is to different missing-data assumptions. The sponsor’s own analysis takes precedence over the simple recalculation, while the broad recalculated interval remains a reminder that the observed contrast is estimated with limited precision.

12. Analyses Reported by the Sponsor

The sponsor’s reported primary analysis is a Fisher Exact test with p = 0.098. The recalculated analysis uses the posted arm summaries to produce an unadjusted risk difference of -0.286, interval bounds of -0.522 to -0.049, and p = 0.037. These results differ. The registry record flags a discrepancy, so the sponsor’s own analysis takes precedence over the recalculation.

The recalculation is useful as a transparent, simple comparison of the posted counts, but it does not establish that the sponsor used the same procedure, data handling, or assumptions. The registry does not report a detailed explanation for the difference, a full statistical analysis plan, or further information that would allow the sponsor’s test to be reconstructed. The sponsor’s p-value should not be replaced by the recalculated value, nor should the recalculated interval be attributed to the sponsor.

Both results concern the same registered primary response question, but a p-value is tied to the analysis used to obtain it. The difference in p-values underscores the importance of reading the posted sponsor result separately from an unadjusted recalculation. Neither value alone establishes treatment benefit, lack of benefit, or clinical importance.

13. Multiplicity, Missing Data and Analysis Populations

The registry reports a primary outcome alongside numerous secondary outcomes and analyses. It lists 14 secondary outcomes and 40 analyses. When many statistical comparisons are conducted, the chance of obtaining apparently notable results by chance can increase. Multiplicity procedures are used in some studies to account for that issue, but an adjustment method is not reported in the registry record. The posted unadjusted secondary p-values therefore should not be treated as if they accounted for the full set of comparisons.

The record identifies the primary analysis population as intention to treat, defined as all participants who received at least one dose of study drug. It also says missing primary outcome data were imputed using last observation carried forward. This describes the stated approach, but the registry does not report how many values were missing, the reasons for missingness, or whether missingness differed by treatment arm. It does not report sensitivity analyses using alternative imputation or missing-data methods. The impact of the imputation choice cannot therefore be assessed from the registry record.

The registry does not report the original sample-size justification, a complete statistical analysis plan, or interim analyses. These omissions limit assessment of whether the analyses and outcome hierarchy followed a prespecified plan. They also prevent a clear assessment of how the terminated status affected recruitment, follow-up, or the final analysis. The reason for termination is not reported in the registry record.

These limits do not invalidate the posted results, but they constrain how strongly they can be interpreted. In particular, the secondary outcomes are more vulnerable to selective emphasis when multiplicity handling is unspecified, while the primary result is complicated by the difference between the sponsor’s reported analysis and the simple recalculation. The record’s description of the analysis population and LOCF method is informative, but it does not answer questions about missingness or robustness.

14. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pneumonia (4.2%).

The registry reports serious adverse events among 0 of 14 participants at risk in the placebo group and 1 of 24 at risk in the etanercept group. For other adverse events, it reports 4 of 14 at risk in the placebo group and 14 of 24 at risk in the etanercept group. The serious-event groups’ denominators differ from those in the posted primary efficacy results. The registry record does not explain the difference, so these safety figures should be read using their own reported at-risk denominators rather than assumed to match the efficacy analysis population.

Pneumonia is listed among the top serious adverse event terms at 4.2%. The record does not provide enough detail in the reported details to determine the full event context, timing, relatedness to study treatment, or whether events occurred in the same or different participants. Deaths are not reported in the registry record. With the small reported groups and limited detail, the counts describe the recorded events but do not establish comparative safety or causation.

Serious adverse event counts are not interchangeable with counts of all other adverse events. The two categories should be kept distinct, and the reported denominators should be retained when interpreting each category.

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

The primary result describes response under a specific physician-assessed rule at 12 weeks. The posted data show response percentages of 28.6% for placebo and 0.0% for etanercept, with the recalculated contrast favoring a higher response proportion in the placebo arm. The sponsor’s reported Fisher Exact analysis differs from the unadjusted recalculation, and the registry record indicates that the sponsor’s analysis takes precedence.

This does not establish that etanercept is ineffective, that placebo is effective, or that either treatment caused the observed responses. A small pilot study can produce unstable estimates, and the recalculated interval is broad. The record does not report a confidence level for that interval, a full statistical analysis plan, or the reason the study was terminated. The available results cannot answer how participants with different disease locations or characteristics might respond.

The result also does not establish the clinical importance of the observed contrast. The registry does not report a threshold for a clinically meaningful difference. Nor does a p-value give the probability that a treatment works or that a result is due to chance. It summarizes compatibility with a null model under a particular statistical procedure.

Secondary outcomes and adverse event counts offer additional descriptive information, but the secondary analyses are numerous and no multiplicity adjustment is reported. The safety record uses at-risk denominators that differ from the primary efficacy denominators, and the registry does not explain why. These details limit how far the findings can be generalized or combined into a single conclusion. The results are best understood as registry-reported observations from a terminated pilot study, not as definitive evidence about treatment effects.

16. Why This Trial Matters Statistically

This study illustrates several statistical issues that arise in small clinical trials. Binary response outcomes can be communicated through arm percentages and counts, but the treatment contrast and its uncertainty are also important. Here, the counts show sparse events, and the recalculated interval is broad. That makes it especially important to distinguish the observed data from the precision of an estimated contrast.

The record also illustrates why the sponsor’s reported analysis and an unadjusted recalculation should not be conflated. The primary Fisher Exact p-value is 0.098, while the recalculated p-value is 0.037. The registry flags a discrepancy, so the sponsor’s analysis takes precedence. Differences in methods or data handling can matter, and a registry record that does not provide a full analysis plan may not allow readers to identify the reason.

Multiplicity is another central issue. Many secondary outcomes and analyses are listed, yet no adjustment strategy is reported. A collection of unadjusted comparisons can invite overinterpretation if attention is drawn selectively to particular findings. The secondary results are therefore most useful as exploratory context, not as independent confirmation of the primary outcome.

Finally, the stated intention-to-treat population, LOCF imputation, terminated status, and differing safety denominators all affect interpretation. The study highlights how transparent reporting of analysis populations, missingness, prespecified methods, and reasons for study completion helps readers assess the strength and limits of clinical evidence.

17. 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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several limitations are specific to the information reported for this trial. The registry describes the study as terminated but does not report the reason for termination or how that status affected recruitment, follow-up, or analysis. The trial is identified as a pilot, yet the original sample-size justification is not reported. The planning illustration is based on the observed effect for a secondary outcome and is not evidence of the trial’s intended design or observed power.

The primary result has a discrepancy between the sponsor’s Fisher Exact analysis and the unadjusted recalculation. The sponsor’s analysis takes precedence, but the registry does not report enough detail to explain the difference. The primary interval’s confidence level is not reported, and its broad bounds indicate limited precision. The outcome definition combines mucosal disease with cutaneous disease when mucosal disease is absent; separate primary estimates by disease location are not reported.

The stated use of last observation carried forward is not accompanied by information about the amount, timing, or causes of missing data, or by sensitivity analyses. The record also does not report the randomization method, allocation concealment, adherence, or which roles were masked. It gives no full statistical analysis plan or multiplicity adjustment despite numerous analyses.

Safety denominators differ from the primary efficacy denominators, and the reason is not reported. Event descriptions are limited, including for the serious-event term listed in the record. Together, these gaps constrain assessment of precision, robustness, and generalizability; they should not be filled by assumptions about the protocol or the circumstances of termination.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Use of Etanercept in the Treatment of Moderate to Severe Lichen Planus — NCT00285779.
• Registry record last updated 2018-03-21; status last verified 2018-03.
• Results first posted 2015-03-03.
• 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.

21. Record Summary

NCT00285779 is a randomized, triple-masked, parallel-group phase 2 pilot study of etanercept versus placebo for moderate to severe lichen planus, sponsored by Stanford University. Enrollment was 27. Etanercept and normal saline placebo were administered by injection twice weekly for weeks 1–12. The registry lists the study as terminated; its reason for termination is not reported.

The primary endpoint was response at 12 weeks, defined by a physician global assessment threshold or improvement from baseline. Posted response percentages were 28.6% for placebo and 0.0% for etanercept. The recalculated unadjusted comparison differs from the sponsor’s reported Fisher Exact analysis; the sponsor’s analysis takes precedence. The record also lists numerous secondary outcomes and adverse event results, with limitations in multiplicity reporting, missing-data detail, and safety denominator explanation.