Study to Investigate the Safety and Duration of Effect of Different Botulinum Toxin A (NT 201) Dose Groups Following the Treatment of Glabellar Frown Lines: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study to Investigate the Safety and Duration of Effect of Different Botulinum Toxin A (NT 201) Dose Groups Following the Treatment of Glabellar Frown Lines (NCT03806933), a randomized phase 2 study. The primary outcome is Duration of Effect Defined as Time Between Treatment and Relapse to Baseline Status Assessed by the Investigator on the FWS.

2. Clinical Question

3. Trial Design

The registry record describes a prospective, randomized, double-blind, multicenter, parallel-group phase 2 study of NT 201 for moderate to severe glabellar frown lines. Its stated purpose was to investigate safety and duration of effect across different doses. The record lists the study as completed and reports enrollment of 241. The listed start was 2019-01-23 and the primary completion date was 2020-09-10.

Study medication was administered by intramuscular injection into the glabellar area. The posted primary outcome compares Stage 1 and 2 pooled NT 201 20 U with NT 201 50 U, 75 U, and 100 U. The arm descriptions also identify dose groups used in different stages and an open-label extension group. These details indicate that the posted primary comparison is not simply a comparison of every listed arm in a single stage. Further details of allocation procedures, the number of sites, and the exact masking procedures are not reported in the registry record.

The registry record names a safety and duration-of-effect purpose and lists other outcomes based on investigator and participant ratings of the Facial Wrinkle Scale. Some posted secondary results concern ratings at Day 180. The primary endpoint is a time-to-event measure assessed from first treatment up to Day 360. The trial’s original sample-size justification, prespecified statistical analysis plan, and any interim analyses are not reported in the registry record. The posted enrollment should therefore not be treated as evidence of the assumptions used to plan the study.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: In MP, Stage 1, participants received NT 201: 20 unit (U), 50 U or 75 U. Based on safety data of Stage 1, Stage 2 was started, and participants received NT 201 20 U or 100 U. After completion of MP, participants had the opportunity to receive an optional follow-up treatment with NT 201 20 U in OLEX period. As planned, 20 U group data from Stages 1 and 2 were pooled.

Main Period

Reasons for not completing this period:

OLEX Period

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The FAS was subset of participants exposed to study medication for whom any efficacy variable was available.

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: The full analysis set (FAS) was subset of participants exposed to study medication for whom any efficacy variable was available.

6. Primary Endpoint

The registry lists the primary outcome as Duration of Effect Defined as Time Between Treatment and Relapse to Baseline Status Assessed by the Investigator on the FWS, measured over From the time of first treatment up to Day 360.

The primary endpoint is the time from first treatment to the first occurrence of relapse to baseline status, as assessed by the investigator on the Facial Wrinkle Scale at maximum frown. The scale grades severity from 0, none, to 3, severe; the endpoint’s description defines an effect as any improvement of at least 1 point from baseline. If no effect was observed, the duration was set to 0. Follow-up for this endpoint was described as extending up to Day 360.

A time-to-event endpoint retains information about when relapse occurs, rather than reducing follow-up to a single yes-or-no assessment at a fixed visit. Kaplan-Meier analysis is a standard general approach to describing time until an event while accounting for participants whose event time is not observed during the available follow-up. The median duration is the estimated time by which half of the analyzed population has experienced the event, subject to the endpoint definition and analysis. It is not the average duration, nor does it mean that every participant had an event at that time.

The registry record reports 95% confidence intervals for the medians. The endpoint is relevant to the stated question about duration, but its interpretation depends on the investigator’s ratings, the specified relapse definition, and the observed follow-up. Details of censoring and missing-event handling are not reported in the registry record.

7. Results Posted in the Registry

• Stage 1 and 2 Pooled: NT 201 20 U vs NT 201 50 U: hazard ratio 1.03 (95% CI 0.70–1.51), reported p = = 0.881 (as reported in the registry).
• Stage 1 and 2 Pooled: NT 201 20 U vs NT 201 75 U: hazard ratio 0.72 (95% CI 0.49–1.05), reported p = = 0.089 (as reported in the registry).
• Stage 1 and 2 Pooled: NT 201 20 U vs NT 201 100 U: hazard ratio 0.56 (95% CI 0.38–0.83), reported p = 0.004 (as reported in the registry).

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.

Percentage of Participants Rated as None (0) or Mild (1) at Maximum Frown by Investigator's Rating on FWS

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • NT 201 50 U: 8.3% (5/60) versus 8.2% (5/61) on control; risk difference 0.1 percentage points (95% CI -9.7 to 9.9), risk ratio 1.02 (0.31–3.33); unadjusted two-proportion z-test p = 0.978.
  • NT 201 75 U: 16.4% (10/61) versus 8.2% (5/61) on control; risk difference 8.2 percentage points (95% CI -3.4 to 19.8), risk ratio 2.00 (0.73–5.51); unadjusted two-proportion z-test p = 0.168.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NT 201 50 U and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NT 201 75 U and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants Rated as None (0) or Mild (1) at Maximum Frown by Participant's Rating on FWS

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • NT 201 50 U: 10.0% (6/60) versus 6.6% (4/61) on control; risk difference 3.4 percentage points (95% CI -6.4 to 13.3), risk ratio 1.52 (0.45–5.13); unadjusted two-proportion z-test p = 0.492.
  • NT 201 75 U: 19.7% (12/61) versus 6.6% (4/61) on control; risk difference 13.1 percentage points (95% CI 1.4 to 24.9), risk ratio 3.00 (1.02–8.79); unadjusted two-proportion z-test p = 0.032.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NT 201 50 U and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for NT 201 75 U than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Rated as at Least 1-point Improvement Compared to Baseline at Maximum Frown by Investigator's Rating on FWS

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • NT 201 50 U: 43.3% (26/60) versus 32.8% (20/61) on control; risk difference 10.5 percentage points (95% CI -6.7 to 27.8), risk ratio 1.32 (0.83–2.10); unadjusted two-proportion z-test p = 0.232.
  • NT 201 75 U: 52.5% (32/61) versus 32.8% (20/61) on control; risk difference 19.7 percentage points (95% CI 2.5 to 36.9), risk ratio 1.60 (1.04–2.46); unadjusted two-proportion z-test p = 0.028.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NT 201 50 U and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for NT 201 75 U than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary results at Day 180 cover investigator and participant ratings of none or mild severity, and investigator ratings of at least a 1-point improvement from baseline. Across these outcomes, the percentages generally vary across dose groups, but the pattern is not identical for every rating criterion or assessor. The confidence intervals are often broad, reflecting uncertainty in these estimates. The secondary outcomes address fixed-visit ratings, whereas the primary endpoint measures time to relapse; they therefore provide related but not interchangeable information about effect and duration.

Some unadjusted comparisons indicate differences between the pooled 20 U group and a higher-dose group, while others do not. Those comparisons should be considered alongside the primary time-to-event result rather than treated as independent replications. A favorable-looking result for one secondary measure does not settle the primary question, and a result that is not statistically distinguishable from the reference group does not prove equality.

Multiple outcomes and comparisons create more opportunities for chance findings. As a general statistical explanation, when many hypotheses are tested, the chance of at least one apparently notable result can rise unless the analysis accounts for multiplicity. The registry record does not report whether a multiplicity adjustment was planned or applied, or identify a confirmatory hierarchy for the secondary outcomes. Their unadjusted p-values therefore carry less weight than results from a clearly prespecified, multiplicity-controlled analysis. They are best viewed as supportive or exploratory evidence, interpreted with their intervals, outcome definitions, and the primary result.

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

• Duration of Effect Whereby Effect Was Defined as Score of None (0) or Mild (1) at Maximum Frown as Assessed by the Investigator According to FWS
• Duration of Effect Whereby Effect Was Defined by 2-point Improvement From Baseline at Maximum Frown as Assessed by the Investigator According to FWS
• Percentage of Participants Rated as None (0) or Mild (1) at Maximum Frown by Investigator's Rating on FWS
• Percentage of Participants Rated as None (0) or Mild (1) at Maximum Frown by Participant's Rating on FWS
• Percentage of Participants Rated as at Least 1-point Improvement Compared to Baseline at Maximum Frown by Investigator's Rating on FWS
• Percentage of Participants Rated as at Least 1-point Improvement Compared to Baseline at Maximum Frown by Participant's Rating on FWS

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is analyzed as time to relapse. That type of outcome differs from a simple percentage at a fixed visit: the timing of an event matters, and some participants may not have a recorded relapse by the end of their observed follow-up. The registry record says that duration was analyzed using Kaplan-Meier analysis and that confidence intervals were calculated using a log-log transformation.

What does a Kaplan-Meier estimate describe?

As a general statistical explanation, the Kaplan-Meier method estimates how the probability of remaining free of an event changes over time. It incorporates the timing of observed events and can retain information from participants whose event status is not observed through the end of follow-up, provided their observation time is appropriately handled. Such participants are commonly described as censored. The registry record does not report the detailed censoring rules or how missing visits and other incomplete observations were handled, so those implementation details cannot be assessed from the posted description.

The median time is read from the estimated time-to-event curve as the point where the estimated probability of remaining event-free reaches the median threshold. It is a summary of a distribution, not an individual-level guarantee. The primary endpoint also defines duration as zero if no effect was observed. That rule is part of the endpoint definition and affects what the median represents.

How should the hazard ratios be read?

The registry record reports hazard ratios for comparisons of the pooled 20 U group with each higher-dose group, using a Wald chi-square test. As a general explanation, a hazard ratio compares event rates over follow-up under a model; it is not the same quantity as a ratio of medians or a difference in median days. A value of 1 represents equal hazards under the comparison’s coding. Values on either side of 1 indicate a relative difference in the modeled hazard, but the direction must be interpreted using the actual numerator and reference coding. The registry record labels each comparison but does not spell out the coding convention, so a directional claim beyond the reported estimates would require caution.

A Wald test assesses how compatible an estimated model parameter is with a null value under the assumptions used for that test. Its p-value is not the probability that the null hypothesis is true, nor is it a measure of the size or importance of an effect. A confidence interval adds information about the range of values reasonably compatible with the estimate under the analysis. For the 20 U versus 100 U comparison, the reported interval does not include 1; the intervals for the other reported comparisons do include 1. These statements describe the reported analyses and do not account for any unreported multiplicity procedure.

Why use a confidence interval?

In general, a confidence interval communicates uncertainty around an estimate. A narrower interval indicates greater statistical precision under the method used, while a wider interval indicates less precision. The reported 95% confidence intervals for medians and hazard ratios are not interchangeable: they quantify uncertainty for different estimands and are produced by different procedures. Overlap or non-overlap between separate intervals is not, by itself, a substitute for a direct test of the difference between groups.

The secondary outcomes are binary at a specified assessment: a participant either meets the stated rating criterion or does not. The posted results give percentages and 95% confidence intervals at Day 180. The associated simple, unadjusted comparisons use risk differences in the analysis material. As a general explanation, a risk difference compares the two group proportions in absolute terms. An unadjusted comparison does not account for multiple outcomes or comparisons unless a separate procedure is applied. The registry record does not report such a procedure.

What is not available about the analysis?

The FAS is described as participants exposed to study medication for whom any efficacy variable was available. That description identifies a population rule but does not fully specify the analysis set for every endpoint. The registry record does not report the original statistical analysis plan, detailed missing-data methods, a multiplicity strategy, or the model assumptions for the hazard-ratio analyses. These omissions limit how fully the posted analysis can be reproduced or evaluated. The registry record lists 12 outcome measures and 3 analyses, but those counts do not reveal the complete prespecification or hierarchy of outcomes.

11. Confidence Intervals and Precision

The primary median estimates have confidence intervals that indicate uncertainty in the estimated time to relapse. For the pooled 20 U group, the median was 175 days and the 95% confidence interval was 142 to 185 days. For 50 U, the interval was 182 to 205 days around a median of 185 days; for 75 U, 182 to 217 days around 210 days; and for 100 U, 183 to 237 days around 215 days. These intervals are not exact bounds on every participant’s duration. They express uncertainty in the group-level median estimate under the reported analysis.

The hazard-ratio intervals also show uncertainty. The interval for 20 U versus 50 U, 0.7 to 1.51, spans 1, as does the interval for 20 U versus 75 U, 0.49 to 1.05. The interval for 20 U versus 100 U, 0.38 to 0.83, does not span 1. The degree of precision differs across comparisons, and the estimates should be read together with their intervals rather than by p-values alone.

As a general explanation, confidence intervals describe sampling uncertainty under the method and assumptions used; they do not cover every possible source of bias, measurement error, or incomplete reporting. Nor does overlap between intervals for separate medians directly test whether groups differ. The registry record does not report sufficient detail about censoring, missing observations, or model diagnostics to judge those sources of uncertainty. The 95% intervals therefore help characterize statistical precision, but do not remove the need for caution about analysis assumptions and study design.

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 sample-size justification. The registry record does not report the original design assumptions. The listed illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; it considers detecting 100%, 75%, or 50% of the observed effect. For the time-to-event comparisons, the figures are total events required, using the Schoenfeld approach. For the other comparisons, they are participants per arm.

The 80% power column describes the illustrative number of events or participants needed for an 80% chance of detecting the specified effect under those assumptions, if the assumed effect and analysis conditions hold. The 90% power column describes the corresponding requirement for a 90% chance. These are planning targets, not a guarantee that a study with that size will detect an effect. The values vary substantially by comparison and assumed effect, so they should be interpreted within each comparison rather than as a single universal requirement.

Smaller effects require more information to distinguish them from chance variation: in these illustrations, planning for 75% or 50% of the observed effect requires more events or participants than planning for the full observed effect. The observed effects are estimates from this study and may not match the effects in a future study. The figures are not observed power; they are hypothetical sample-size calculations under stated assumptions. They should not be used to infer that the completed trial was adequately or inadequately powered, because the registry record does not report its original planning assumptions.

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

d is the total number of events needed (Schoenfeld's formula) with 1:1 allocation and proportional hazards.

Worked calculation for this trial

1. Hazard ratio HR = 1.030, so ln(HR) = 0.0296.
2. d = 4 × (1.96 + 0.842)² / [ln(1.030)]² = 35,933.0, rounded up to 35,934 events in total 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
hr <- 1.03                              # observed hazard ratio
events_needed <- function(power, frac = 1) ceiling(round(4 * (z_a + qnorm(power))^2 / log(hr^frac)^2, 6))   # Schoenfeld, 1:1 allocation
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: events = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(events_needed(0.80, f), big.mark = ","), format(events_needed(0.90, f), big.mark = ",")))

# Simulation: given d total events under proportional hazards, events in the treatment arm are Binomial(d, hr / (1 + hr)).
# The score (log-rank type) statistic is (D1 - d / 2) / sqrt(d / 4).
set.seed(3806933)
d    <- events_needed(0.80)
reps <- 20000
D1 <- rbinom(reps, d, hr / (1 + hr))
z  <- (D1 - d / 2) / sqrt(d / 4)
cat(sprintf("Simulated power with %s events: %.3f (%d replicates)\n", format(d, big.mark = ","), mean(abs(z) > z_a), reps))

Output from running the code

100% of observed effect: events = 35,934 (80% power), 48,105 (90% power)
 75% of observed effect: events = 63,881 (80% power), 85,519 (90% power)
 50% of observed effect: events = 143,733 (80% power), 192,417 (90% power)
Simulated power with 35,934 events: 0.802 (20000 replicates)

The simulation uses the fact that, with d events in total and proportional hazards, the number of events in the treatment arm is binomial. It is an approximation that conditions on the total number of events, and it should land close to the target power.

14. Analyses Reported by the Sponsor

The primary hazard ratios and their Wald chi-square tests are sponsor-reported analyses. The posted primary medians and their confidence intervals are also reported as outcome summaries. The comparisons are 20 U versus 50 U, 20 U versus 75 U, and 20 U versus 100 U; the reported hazard ratios are 1.03, 0.72, and 0.56, respectively, with the confidence intervals and p-values stated in the interpretation.

There is no flagged discrepancy between the sponsor-reported results and the accompanying analysis material. For this time-to-event outcome, the stated interpretation uses the sponsor’s reported hazard ratios rather than attempting to derive new hazard ratios from the median summaries. A hazard ratio cannot be reconstructed from medians alone, and the registry record does not provide enough participant-level data or model detail to reproduce the sponsor’s analysis independently.

As a general statistical principle, when a recalculation from posted summary statistics conflicts with the sponsor’s own analysis, the sponsor’s reported analysis takes precedence for describing the trial result, while the discrepancy should be made explicit. That situation is not flagged for these results. The sponsor’s analysis remains subject to the reporting limitations noted elsewhere, including the absence of a detailed analysis plan and fuller descriptions of the model and missing-data handling in the registry record.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists 12 outcome measures and 3 analyses, and it identifies multiple secondary measures based on investigator and participant Facial Wrinkle Scale ratings. The posted material also includes more than one dose-group comparison. When several outcomes or comparisons are examined, multiplicity is a concern: as a general statistical explanation, multiple testing can increase the chance that at least one result appears statistically notable by chance. A prespecified testing hierarchy or adjustment can address this concern, but the registry record does not report whether such an approach was planned or applied.

The record does not report the original statistical analysis plan, a prespecified order for testing outcomes, or whether the secondary analyses were intended to be confirmatory. The unadjusted secondary results should therefore not be interpreted as if each were a separate definitive test. The primary analysis is also read in the context of the stated comparisons and reported methods; the record does not provide enough information to assess whether the reported p-values were adjusted across comparisons.

The primary population is described as the FAS: participants exposed to study medication for whom any efficacy variable was available. That definition does not tell the reader how many participants were included in every endpoint analysis or how missing values were handled. The registry record does not report detailed missing-data procedures, censoring rules, or sensitivity analyses for incomplete observations. In a time-to-event analysis, how follow-up ends without a recorded relapse can matter; for fixed-visit secondary outcomes, the handling of unavailable ratings can affect the percentages. These details are not reported in the registry record, so the potential impact of missing data cannot be evaluated fully.

The record also does not report interim analyses or stopping rules. Their absence from the report should not be read as proof that none occurred. Overall, the available descriptions identify the stated analysis population and methods but leave important aspects of multiplicity and missing-data handling unspecified.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: appendicitis (1.7%).

The posted serious adverse event figures show zero serious adverse events in the pooled NT 201 20 U group, NT 201 50 U group, and NT 201 75 U group, and one in the NT 201 100 U group. The corresponding serious-event analysis populations are listed as 62, 60, 61, and 58. The record lists zero deaths in each group. It also identifies appendicitis at 1.7% among the top serious-event terms; the registry record does not specify in that listing which group the term relates to.

These figures are descriptive safety counts. They do not establish whether an event was caused by study treatment, and the record does not provide enough detail to judge seriousness criteria, timing, or individual clinical context. A zero count in a group does not demonstrate that an event cannot occur, particularly when the number observed is limited. Likewise, the single reported serious event in the 100 U group is not, by itself, evidence of a dose-related pattern.

The posted safety summary also lists other adverse events, but serious events and other adverse events are distinct categories. The serious-event figures should be read as counts within the reported group populations, not as a complete account of safety or as a comparison adjusted for differences in exposure or follow-up.

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

The results describe a randomized, double-blind phase 2 study of NT 201 dose groups in participants with moderate to severe glabellar frown lines. The primary endpoint is a defined investigator-assessed time to return to baseline status, observed from first treatment up to Day 360. The posted medians range from 175 days in the pooled 20 U group to 215 days in the 100 U group. The sponsor-reported hazard-ratio comparison for 20 U versus 100 U has a 95% confidence interval that excludes 1, while the intervals for the comparisons with 50 U and 75 U include 1.

These findings summarize group-level estimates for the outcome and analysis reported in the registry. They do not establish that every participant followed the group median, that the effect lasted for a particular individual, or that differences in medians alone fully describe differences over time. The hazard ratios and medians are different summaries, and interpretation of hazard-ratio direction depends on comparison coding that is not fully detailed in the record.

The posted results do not establish a treatment recommendation, a benefit-risk judgment, or the result that would occur in a different population or setting. No untreated or placebo comparison is included in the posted primary comparisons. The secondary outcomes are fixed-visit ratings and include multiple unadjusted comparisons; they provide context but do not replace the primary analysis. Confidence intervals describe statistical uncertainty under the reported methods, not all sources of bias or uncertainty.

The registry record does not report the original sample-size assumptions, detailed missing-data procedures, the full statistical analysis plan, or a multiplicity strategy. Those gaps limit how strongly the results can be interpreted beyond the specific estimates and comparisons posted. Safety counts are also descriptive and do not establish causation. The results should therefore be understood as a report of measured outcomes and their precision, rather than a complete account of all possible effects or risks.

18. Why This Trial Matters Statistically

This trial is statistically interesting because the main outcome is time to relapse rather than a single rating at one visit. Time-to-event methods use both whether an event occurs and when it occurs, and the registry reports both median durations and hazard-ratio comparisons. Reading those measures together helps distinguish a typical time estimate from a comparison of event hazards over follow-up.

The dose-group pattern also illustrates why estimates need uncertainty alongside them. The medians vary across groups, but the pairwise hazard-ratio intervals do not all give the same degree of evidence against a ratio of 1. A result for one comparison should not be generalized automatically to every dose comparison. The interval estimates show that precision differs, and the analysis depends on the endpoint definition and the time-to-event methods used.

The secondary outcomes highlight another practical issue: a trial can measure several related outcomes through different assessors and definitions. These measures may provide useful context, but multiple unadjusted tests increase the risk of chance findings. Without a reported multiplicity strategy or testing hierarchy, secondary p-values deserve a more cautious interpretation than a single clearly prespecified primary analysis.

Finally, the registry record identifies an analysis population and a method but leaves important planning and implementation details unreported. The sample-size illustrations are not a substitute for the trial’s original design justification, and the available record does not describe all missing-data or model assumptions. For clinical researchers and biostatisticians, these features underscore the value of interpreting effect estimates, confidence intervals, analysis populations, and reporting completeness together.

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 provides a concise description of the primary endpoint and says it was analyzed with Kaplan-Meier methods, but it does not give detailed censoring rules, missing-data procedures, or sensitivity analyses. These are relevant for a time-to-event outcome because incomplete follow-up can affect how much information contributes to the estimated duration. The reported FAS definition is also broad: it includes exposed participants for whom any efficacy variable was available, but does not specify the analysis population for every result.

The primary comparison uses a pooled 20 U group from Stage 1 and 2, while other listed dose groups are associated with different study stages. The registry record does not report enough detail to evaluate the implications of pooling across stages or the full structure of allocation and analysis. It also does not provide the hazard-ratio coding convention or full model specification, which limits independent interpretation and reproduction of those analyses.

The record does not report the original sample-size justification, the prespecified statistical analysis plan, multiplicity handling, or interim analyses. The posted secondary results include multiple comparisons without a reported adjustment. Their uncertainty and potential for chance findings warrant caution. The fixed-visit secondary outcomes also measure different rating criteria and assessor perspectives from the primary time-to-relapse endpoint.

Finally, the safety summary gives counts but does not provide detailed event narratives, timing, exposure-adjusted analyses, or attribution in the figures described. The record’s limitations do not invalidate the posted estimates, but they constrain assessment of how robust, reproducible, or generalizable the results are.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study to Investigate the Safety and Duration of Effect of Different Botulinum Toxin A (NT 201) Dose Groups Following the Treatment of Glabellar Frown Lines — NCT03806933.
• Registry record last updated 2023-11-15; status last verified 2023-11.
• Results first posted 2023-10-04.
• 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

The registry record describes a completed, randomized, double-blind, parallel-group phase 2 study of NT 201 for moderate to severe glabellar frown lines. It lists enrollment of 241 and reports primary completion on 2020-09-10.

The primary outcome was median time from first treatment to investigator-assessed relapse to baseline status, measured up to Day 360. Posted medians were 175 days for pooled 20 U, 185 days for 50 U, 210 days for 75 U, and 215 days for 100 U. Sponsor-reported hazard ratios compare the pooled 20 U group with each higher-dose group.

The registry also reports selected Day 180 rating outcomes and descriptive adverse-event counts. It does not report the original sample-size justification, a detailed statistical analysis plan, multiplicity handling, or full missing-data methods.