Dose-Response Profile of A-101 in Subjects With Seborrheic Keratosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Dose-Response Profile of A-101 in Subjects With Seborrheic Keratosis (NCT02160626), a randomized phase 2 study. The primary outcome is Mean Per Subject Percentage Target Lesions Judged Clear by the Physician's Lesion Assessment (PLA).

2. Clinical Question

The trial’s stated objective was to evaluate the dose-response relationship of two A-101 concentrations against matching vehicle. The endpoint concerns the percentage of a participant’s target lesions judged clear, not a direct measure of overall health or change in every lesion. The registry also lists two secondary outcomes: change from baseline in the Physician’s Lesion Assessment and the number of participants with at least 3 of 4 target lesions judged clear at Visit 8.

The primary comparison is therefore about the average lesion-clearance percentage across the specified analysis population. It does not, by itself, establish how an individual participant’s lesions responded, whether effects persisted after Visit 8, or how results would generalize beyond the enrolled study population. The registry record does not report details about the participants’ demographic or clinical characteristics beyond the condition and target-lesion description.

3. Trial Design

This was a randomized, double-blind, parallel-group, vehicle-controlled phase 2 study. The registry lists Aclaris Therapeutics, Inc. as sponsor and describes the study as completed. The study start is recorded as 2014-06 and primary completion as 2014-12. Enrollment is recorded as 172.

Participants were assigned to A-101 Vehicle, A-101 (32.5%) Topical Solution, or A-101 (40%) Topical Solution. The arm descriptions identify vehicle as placebo topical solution and the two active concentrations as low and high dose, respectively. The study’s stated focus was the response of individual seborrheic keratosis lesions designated as target lesions. Double masking means that the trial was designed so that treatment assignment was concealed from participants and investigators as described in the registry; further details about who specifically was masked are not reported in the registry record.

The primary endpoint is reported at Visit 8, using the mean per-participant percentage of target lesions judged clear on the Physician’s Lesion Assessment. The primary analysis population is defined in the record as the number of participants completing the study per protocol. The arm counts reported for this endpoint are 57.0 for vehicle, 56.0 for the 32.5% solution, and 56.0 for the 40% solution. These endpoint counts should not be treated as a replacement for the stated enrollment figure, because the endpoint population is specifically described as study completers per protocol.

The registry record does not report the randomization sequence method, allocation concealment details, exact visit schedule beyond the stated endpoint timeframes, treatment duration, eligibility criteria, or the trial’s original statistical analysis plan. The record also does not report the original sample-size justification or planned assumptions for the trial’s design. Those omissions limit how fully the design and analysis decisions can be reconstructed from the registry record alone.

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: Overall number of participants = number of participants completing the study per protocol.

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 Mean Per Subject Percentage Target Lesions Judged Clear by the Physician's Lesion Assessment (PLA), measured over Baseline, visit 8.

The primary endpoint is the mean per-participant percentage of target lesions judged clear on the Physician’s Lesion Assessment at the end of the study, Visit 8. The lesion assessment uses a four-point scale, with 0 indicating clear and 3 indicating the most severe lesion. The endpoint first expresses each participant’s target lesions as a percentage judged clear, then summarizes those participant-level percentages using a mean. It is therefore not simply a count of clear lesions across the full study.

This measure is used to capture lesion-level clearance in a way that can be compared across randomized groups. Reporting the percentage at the participant level gives each participant’s assessment a role in the group mean, rather than treating all lesions as though they came from separate participants. The endpoint is continuous, so its mean and standard deviation describe the group’s central value and spread.

Interpretation depends on the scale’s direction: higher percentages indicate a greater share of target lesions judged clear. The endpoint is assessed at Visit 8, and the record does not report whether a later follow-up assessed durability. Nor does the primary measure alone describe symptoms, quality of life, or outcomes beyond the assessed target lesions. The registry defines its primary population as participants completing the study per protocol; details about how incomplete observations were handled are not reported in the registry record.

7. Results Posted in the Registry

• A-101 (32.5%) Topical Solution: mean 26.79 versus 4.82 on control; difference 21.97 (95% CI 11.23 to 32.71), standardized effect d = 0.76; z-test p = <0.001.
• A-101 (40%) Topical Solution: mean 45.09 versus 4.82 on control; difference 40.27 (95% CI 29.79 to 50.75), standardized effect d = 1.43; z-test p = <0.001.

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.

Mean Change From Baseline to Visit 8 in the Physician's Lesion Assessment

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • A-101 (32.5%) Topical Solution: mean -0.77 versus -0.32 on control; difference -0.45 (95% CI -0.68 to -0.22), standardized effect d = -0.72; z-test p = <0.001.
  • A-101 (40%) Topical Solution: mean -0.91 versus -0.32 on control; difference -0.59 (95% CI -0.84 to -0.34), standardized effect d = -0.87; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for A-101 (32.5%) Topical Solution than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for A-101 (40%) Topical Solution than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Proportion of Subjects Who Had at Least 3 of 4 Target Lesions Judged to be Clear on the Physician Lesion Assessment (PLA =0) at Visit 8.

• 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:
  • A-101 (32.5%) Topical Solution: 16.1% (9/56) versus 0.0% (0/57) on control; risk difference 16.1 percentage points (95% CI 6.5 to 25.7); unadjusted two-proportion z-test p = 0.002.
  • A-101 (40%) Topical Solution: 19.6% (11/56) versus 0.0% (0/57) on control; risk difference 19.6 percentage points (95% CI 9.2 to 30.0); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for A-101 (32.5%) Topical Solution than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for A-101 (40%) Topical Solution than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes follow a pattern broadly consistent with the primary result: both A-101 groups have more favorable posted group summaries than vehicle on the lesion-assessment measures. The continuous change outcome is reported as a larger decrease in Physician’s Lesion Assessment scores for the A-101 groups, while the binary outcome records participants reaching the stated clearance criterion in the active groups and none in vehicle. The registry reports statistically significant comparisons for these secondary measures using ANCOVA and Cochran-Mantel-Haenszel methods.

These outcomes complement rather than replace the primary endpoint. The change score uses the lesion-assessment scale over time, while the binary measure applies a threshold requiring at least 3 of 4 target lesions to be clear. Their agreement in broad direction offers related evidence from different summaries of lesion status, but the outcomes are not interchangeable. The record does not report whether the secondary measures were intended to confirm the primary finding or how they were ranked for interpretation.

Secondary results generally carry less weight when many outcomes or comparisons are examined without a stated multiplicity strategy. Repeated testing can increase the chance of at least one apparently notable result arising by chance. The registry record does not report a multiplicity adjustment or a prespecified hierarchy for these secondary outcomes. Their p-values should therefore be read as reported, without assuming that they account for all testing across outcomes and comparisons.

The secondary analyses also have method-specific limitations. ANCOVA is listed for the continuous change outcome, but the covariate specification is not reported. Cochran-Mantel-Haenszel is listed for the binary outcome, but its stratification details are not reported. The recalculated comparisons use posted summaries and are not substitutes for those sponsor analyses. Taken together, the secondary findings support a similar descriptive pattern, while the primary endpoint remains the central result specified in the registry record.

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

• Mean Change From Baseline to Visit 8 in the Physician's Lesion Assessment
• Proportion of Subjects Who Had at Least 3 of 4 Target Lesions Judged to be Clear on the Physician Lesion Assessment (PLA =0) at Visit 8.

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is a continuous outcome: each participant contributes a percentage of target lesions judged clear, and the group result is reported as a mean and standard deviation. A mean summarizes the center of the observed values, while a standard deviation describes how dispersed participant values are around that center. These answer different questions. A group may have a clear average difference while individual participant outcomes still vary widely.

What does the mean difference represent?

The recalculated mean difference is the active-group mean minus the vehicle-group mean, as represented by the posted estimates. A positive difference means the active group’s average percentage of clear target lesions was higher. The recalculated differences are unadjusted comparisons based on the posted summary statistics. They are not adjusted for baseline characteristics or other covariates. The registry record’s primary outcome description does not report a covariate-adjusted estimate.

For the 32.5% comparison, the recalculated mean difference is 21.97, and for the 40% comparison it is 40.27. These are percentage-point differences on the endpoint scale, not relative percentage increases. The associated recalculated confidence intervals and p-values express uncertainty and compatibility with a no-difference value under the simple comparison method. They should be distinguished from the sponsor’s reported ANOVA p-values, which come from the registry analysis.

How should confidence intervals be read?

A confidence interval is a range of values compatible with the observed data and the method’s assumptions. It shows precision as well as direction: a narrower interval indicates greater precision, while a wider interval indicates less precision. The 95% intervals around the primary recalculated differences exclude zero. This is consistent with the corresponding unadjusted p-values being <0.001. A confidence interval does not mean that the true effect has a 95% probability of being inside that particular interval; it is a procedure with a long-run coverage interpretation under its assumptions.

The interval is about the group contrast, not the range of outcomes among participants. The standard deviations for the arm-level means describe observed variability; they are not confidence intervals. The registry does not provide sponsor-reported confidence intervals for the primary contrasts, so the intervals discussed for those contrasts are the simple recalculated ones.

What do the registry’s tests add?

The registry lists ANOVA for the two primary vehicle comparisons. ANOVA is a model-based method for assessing differences among group means. The posted registry results give p< 0.001 for the comparison of vehicle with the 32.5% solution and p=.0001 for vehicle with the 40% solution. The registry record does not state the exact ANOVA specification, whether the comparisons were adjusted for other variables, or whether any multiplicity correction was used.

A p-value describes how unusual data at least as incompatible with the null hypothesis would be if that hypothesis and the test assumptions held. It is not the probability that the null hypothesis is true, nor does it quantify the size or importance of a difference. The trial’s reported p-values and the recalculated p-values use different analysis routes and should not be treated as though they were the same calculation.

Why can analysis choices matter?

Unadjusted comparisons use only the posted group summaries. An analysis that includes covariates or other design details can produce different standard errors and p-values. The registry record identifies the method as ANOVA for the primary comparisons but does not supply the model specification or the participant-level data needed to reproduce that analysis. The recalculated results are therefore useful as a transparent summary-statistic check, not a replacement for the sponsor’s analysis.

For continuous outcomes, model assumptions about the distribution of residuals and the suitability of the mean as a summary can influence inference. The record does not report diagnostic checks or alternative analyses. General statistical principle: strong skew or unusual observations can make a mean-based analysis sensitive to the distribution, and uncertainty estimates should reflect the analysis structure. Whether that issue materially affected this trial cannot be determined from the registry summaries.

For the binary secondary endpoint, the outcome is whether a participant had at least 3 of 4 target lesions judged clear. The registry reports Cochran-Mantel-Haenszel tests for the group comparisons. This method can assess an association across strata, but the strata and other details are not reported in the registry record. The recalculated risk differences are based on the posted counts and denominators and are not the same as the registry’s test results.

For the secondary mean change outcome, the registry reports ANCOVA. ANCOVA compares outcomes while accounting for a covariate, but the registry record does not identify the covariate specification. The posted simple recalculations compare group means without that model adjustment. This distinction is important when reading the recalculated estimates alongside the sponsor’s reported analysis: both describe the same general group contrast, but they need not produce identical numerical inference.

General statistical principle: over-dispersion occurs when observed variability is greater than a model expects. In count or binary settings, ignoring it can make uncertainty appear too small. This trial’s primary endpoint is continuous, and the record does not report an over-dispersion assessment. The concern is included as a general modeling consideration, not as a claim that over-dispersion occurred in this study.

11. Confidence Intervals and Precision

The recalculated primary mean differences are 21.97 for the 32.5% solution versus vehicle and 40.27 for the 40% solution versus vehicle. Their 95% confidence intervals are 11.23 to 32.71 and 29.79 to 50.75, respectively. Both intervals lie above zero, so the recalculated contrasts are directionally positive across the ranges of values compatible with these methods and data.

The widths of the intervals convey the precision of the mean-difference estimates. They do not describe the distribution of individual participant outcomes. The primary endpoint standard deviations are 15.26 for vehicle, 38.1 for the 32.5% group, and 37.06 for the 40% group. These values show that participant-level percentages varied within groups; a group mean does not imply that participants had similar outcomes.

The registry record does not provide confidence intervals for its ANOVA comparisons. The intervals above are recalculated from posted summary statistics and should be interpreted as unadjusted rather than as the sponsor’s model-based intervals. Differences between the recalculated and reported test results can arise from analysis method or model specification. The registry record does not provide enough detail to identify the specific source of any numerical difference.

Precision is not the same as clinical importance. The interval estimates statistical uncertainty in the group contrast; the record does not state a threshold for a clinically meaningful difference. Nor do these intervals account for questions not represented in the simple recalculation, such as unreported analysis choices or the effect of multiple comparisons.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size figures are planning illustrations based on the observed effect, not the trial’s original design calculations. For these continuous-outcome comparisons, the figures mean participants per arm, not total events. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; the target effect is the stated fraction of the observed effect. The original trial’s design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives an illustrative per-arm sample size for a design that would have an 80% chance of detecting the specified effect under those assumptions, if the assumed effect and model conditions held. The 90% power column uses a higher probability of detecting that same effect, and therefore generally requires more participants per arm. These are design-planning quantities; they are not probabilities that the observed trial result is correct.

Rows for 100%, 75%, and 50% of the observed effect illustrate how planning changes when the assumed effect is smaller than the observed estimate. Smaller effects are harder to distinguish from random variation and require more participants per arm for the same target power and significance level. The displayed estimates should be interpreted cautiously because the observed effect may be imprecise or larger than an effect expected in a future study. This is not observed power.

The illustration is specific to the stated assumptions and comparisons. It does not incorporate unreported design features, adjustments, loss to follow-up, multiplicity, or other operational considerations. The registry record does not report the assumptions used to choose enrollment for the original study, so these planning values should not be read as an explanation of why the trial enrolled as it did.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 21.970; pooled standard deviation σ = 28.927.
2. n = 2 × (1.96 + 0.842)² × 28.927² / 21.970² = 27.2, rounded up to 28 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- 21.97                      # observed difference in means
sigma <- 28.9266135136723                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(2160626)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 28 (80% power), 37 (90% power)
 75% of observed effect: n per arm = 49 (80% power), 65 (90% power)
 50% of observed effect: n per arm = 109 (80% power), 146 (90% power)
power.t.test: 28.2 
Simulated power at n = 28 per arm: 0.800 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The registry’s own primary analyses compare vehicle with each A-101 concentration using ANOVA. It reports p< 0.001 for vehicle versus the 32.5% solution and p=.0001 for vehicle versus the 40% solution. The registry does not report the corresponding sponsor-analysis effect estimates or confidence intervals.

The posted recalculations use the arm-level means, standard deviations, and endpoint counts to estimate unadjusted mean differences and confidence intervals. They yield mean differences of 21.97 and 40.27, with p-values <0.001 for both comparisons. These recalculations are useful for interpreting the magnitude and precision of the group contrasts from summary statistics, but they do not reproduce the registry’s ANOVA model.

The reported ANOVA results and the recalculations point in the same direction and both indicate evidence of differences from vehicle under their respective methods. Numerical p-values should not be expected to match exactly when methods differ. The registry record does not specify the ANOVA model in enough detail to determine why the reported p-values differ from the simple recalculated results. No discrepancy is flagged for this trial, and the recalculations should remain clearly distinguished from the sponsor’s reported analysis.

15. Multiplicity, Missing Data and Analysis Populations

The trial includes a primary endpoint, two secondary outcomes, and multiple comparisons with vehicle. The registry record reports tests for both active concentrations against vehicle on each posted outcome. It does not report a multiplicity adjustment, a testing hierarchy, or an indication that secondary outcomes were gated on the primary result. Without those details, the reported p-values should not be interpreted as though they necessarily control the overall chance of a false-positive finding across all comparisons.

Multiplicity does not automatically invalidate individual results. It changes the context in which a collection of tests is interpreted: the more hypotheses examined, the more important it is to know whether adjustments or prespecified priorities were used. The primary endpoint has a clearer role because it is identified as primary, but the registry record does not provide the full statistical analysis plan needed to verify the testing strategy.

The primary analysis population is described as participants completing the study per protocol. This is not described as an intention-to-treat population in the registry record. The record does not report the number randomized to each arm, the number excluded from the per-protocol population by reason, or how missing Visit 8 assessments were handled. It also does not report imputation methods, sensitivity analyses for missing data, or whether participants were analyzed according to assigned treatment regardless of adherence.

These omissions matter because exclusions or incomplete observations can affect which participants contribute to the endpoint means. A per-protocol completion population can differ from all randomized participants, and the direction of any resulting bias cannot be determined from the posted summaries alone. The registry’s stated primary population and endpoint counts should therefore be kept in view when generalizing the results.

Other analysis details are also not reported in the registry record, including the primary model specification, covariate adjustments, diagnostic checks, and handling of protocol deviations. No interim analyses or stopping rules are reported in the registry record. These gaps limit assessment of the full analysis strategy, but they do not change the descriptive values and methods that the registry does report.

16. 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: atrial fibrillation (1.8%), laceration (1.8%), breast cancer (1.7%).

The safety summary reports serious adverse events in 1 participant in the A-101 Vehicle group, 0 in the 32.5% group, and 2 in the 40% group. The corresponding numbers at risk for this summary are 58, 57, and 57. Deaths are reported as 0 in each group. These are counts from the registry record; they do not establish that an event was caused by study treatment.

The registry separately reports other adverse events affecting 15 participants in the vehicle group, 9 in the 32.5% group, and 17 in the 40% group. Those are not the serious adverse event counts. The listed serious-event terms include Atrial Fibrillation at 1.8%, Laceration at 1.8%, and Breast Cancer at 1.7%; the record does not give enough detail in these fields to connect every listed term to a particular group or to assess causality.

Safety counts should be read with their denominators and the study’s duration in mind. The registry record does not report event-level timing, severity grading beyond serious classification, relatedness assessments, or detailed exposure time. The small counts cannot support broad comparisons of safety risk, and the absence of reported deaths does not establish the absence of other safety concerns.

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

The posted primary results show higher mean percentages of target lesions judged clear at Visit 8 in both A-101 concentration groups than in the vehicle group. The estimated differences are positive, and the recalculated 95% confidence intervals exclude zero. The registry’s own ANOVA comparisons also report small p-values for both active-versus-vehicle contrasts.

These findings describe the outcome measured in this trial, in the reported per-protocol completion population and at the stated assessment time. They do not establish that every participant benefited, that every target lesion cleared, or that a particular participant would have the group-average result. The endpoint is an average of participant-level percentages, and variability within the groups remains relevant.

The results also do not establish persistence beyond Visit 8, effects on lesions outside the target-lesion assessments, or outcomes such as symptoms and quality of life. Those matters are not reported in the registry record. A randomized, double-blind design supports comparisons between assigned groups, but the registry information alone does not resolve every concern about missing data, protocol deviations, or analysis choices.

The increasing group means across the two concentrations and vehicle are descriptively compatible with a dose-response pattern. However, a formal dose-response analysis or direct statistical test comparing the two A-101 concentrations is not reported in the registry record. Separate comparisons against vehicle are not equivalent to a test of the difference between concentrations.

Statistical evidence of a difference should not be confused with a judgment about clinical importance. The registry record does not define a threshold for a meaningful change in this measure. Nor do the results determine how findings apply to people outside the study’s enrolled population. They provide evidence about a specific endpoint, comparison, and assessment time, with limitations in the analysis details available from the registry record.

18. Why This Trial Matters Statistically

This trial illustrates how a continuous lesion-level endpoint can be summarized at the participant level. The primary measure is not a raw count of all lesions across groups; it is the mean of each participant’s percentage of target lesions judged clear. That distinction affects what the group mean represents and prevents lesions from being mistaken for independent participants.

It also shows why effect estimates and uncertainty add information beyond p-values. The recalculated mean differences and confidence intervals describe the scale and precision of the comparisons, while the registry’s ANOVA p-values report the sponsor analysis’s inferential results without providing estimates or intervals. Readers can therefore separate the question of whether the data are inconsistent with no difference from the question of how large and precisely estimated the contrast is.

The trial’s stated dose-response objective highlights another statistical distinction: two active groups may each differ from a common control without the registry having established a statistically tested difference between the active concentrations. A pattern in group means is informative descriptively, but a formal trend or direct concentration contrast would require an analysis that is not reported in the registry record.

Finally, the record demonstrates why analysis population, multiplicity, and missing-data details matter. The primary result is based on participants completing the study per protocol, while the full handling of incomplete assessments and the testing strategy are not reported. These details affect how confidently readers can connect a numerical result to the randomized population and interpret multiple outcome comparisons. Statistical interpretation therefore requires attention to the endpoint definition and analysis context as well as the headline estimates.

19. 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 registry record describes the primary analysis population as study completers per protocol, rather than specifying an intention-to-treat analysis. It does not report how many participants were excluded from the primary analysis, why exclusions occurred, or how missing Visit 8 measurements were handled. This limits assessment of the potential influence of incomplete follow-up or protocol deviations.

The primary recalculations use group-level summary statistics and are unadjusted. They cannot reproduce the registry’s ANOVA analyses without the model specification or participant-level data. The registry does not report the covariates, diagnostic procedures, or other model details for those analyses. It also does not report a direct comparison between the two A-101 concentrations or a formal dose-response test.

Multiplicity handling is not reported, despite results for more than one outcome and more than one active-versus-vehicle comparison. The registry record also does not report a clinically meaningful threshold for the primary measure, so the clinical importance of the estimated differences cannot be judged from the endpoint values alone.

Generalizability is constrained by the information available: the record identifies seborrheic keratosis and target lesions but does not report detailed participant characteristics or eligibility criteria. The primary outcome is assessed at Visit 8, and longer-term follow-up results are not reported in the registry record. Safety summaries include event counts, but detailed timing, relatedness, and exposure information are not reported.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Dose-Response Profile of A-101 in Subjects With Seborrheic Keratosis — NCT02160626.
• Registry record last updated 2019-01-03; status last verified 2018-12.
• Results first posted 2018-12-07.
• 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.

23. Record Summary

NCT02160626 is a completed, randomized, double-blind, vehicle-controlled, parallel-group phase 2 study of A-101 topical solution for seborrheic keratosis. It compared A-101 Vehicle with 32.5% and 40% solutions, with a stated objective of evaluating the dose-response relationship in individual target lesions.

The primary endpoint was the mean per-participant percentage of target lesions judged clear on the Physician’s Lesion Assessment at Visit 8. Both active groups had higher reported mean values than vehicle, and the recalculated unadjusted comparisons had positive estimated differences with 95% confidence intervals above zero. The registry reports ANOVA p-values for both comparisons.

Interpretation is limited by unreported details about the original sample-size assumptions, analysis specifications, multiplicity, and missing-data handling. The primary population is described as participants completing the study per protocol. Secondary outcomes show a broadly similar pattern, but their results do not replace the primary endpoint or establish an unreported direct comparison between A-101 concentrations.