Restylane Volyme for Correction of Midface Volume Deficit and/or Midface Contour Deficiency: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Restylane Volyme for Correction of Midface Volume Deficit and/or Midface Contour Deficiency (NCT03289052), a randomized na study. The primary outcome is Percentage of Responders.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group, evaluator-blinded, no-treatment controlled study sponsored by Galderma R&D. The record identifies the study as completed and lists enrollment of 168. It gives a start date of 2017-12-01 and a primary completion date of 2019-01-31. The phase is listed as NA.

The intervention was Restylane Volyme, described as a single midface injection with an optional touch-up injection. The comparator was no treatment. The official study title characterizes the trial as multi-center and evaluator-blinded. The registry’s masking field says single; the registry record does not describe other masking arrangements. The design is listed as randomized and parallel, but details of sequence generation, allocation concealment, or the randomization procedure are not reported in the registry record.

The posted outcome results include Group A, Group B-treatment Arm, and Group B-control Arm. The control arm is identified as the no-treatment group. The record’s outcome labels do not explicitly explain how Group A relates to the named intervention descriptions, so its treatment status should not be inferred from its label alone. The treatment and control groups are assessed at different reference points: 6 months after last treatment for the treatment group and 6 months after randomization for the control group.

The primary outcome is the percentage of responders, with response defined by improvement on the MMVS on both sides of the face. The record lists one outcome measure and no posted analyses. Further details about the original statistical analysis plan, analysis populations, handling of missing outcome data, and any planned interim assessments 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.

Overall Study

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Population: All summaries will be done separately for Group A (20subjects) and B(148 subjects). For statistical inference, only Group B will be used.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Responders, measured over 6 month.

The primary endpoint is the percentage of participants classified as responders at the six-month assessment. A responder had to show at least 1 point of improvement from baseline on the MMVS on both sides of the face concurrently, as judged by the blinded evaluator. The assessment was timed 6 months after last treatment in the treatment group and 6 months after randomization in the control group.

The MMVS is a Four-Point scale used by the evaluator and treating investigator to rate the severity of midface volume deficiency on the right and left sides. The record describes its range from Fairly Full (1) to Substantial Loss of Fullness (4). The responder definition therefore combines a change from baseline with a requirement that improvement be present on both sides. It converts those ratings into a binary outcome: each participant either meets the stated responder criterion or does not.

A binary responder measure offers a clinically interpretable summary of how many participants met a prespecified threshold, rather than describing the full distribution of scale changes. That is a general statistical rationale, not evidence about why this particular endpoint was selected. The registry does not report the endpoint’s development rationale or further validation details. The posted proportions and confidence intervals describe the measured responder outcome; they do not show every participant’s score, the amount of change beyond the threshold, or the pattern of change across visits.

7. Results Posted in the Registry

• Group A: 80.0% (16/20) versus 75.7% (28/37) on control; risk difference 4.3 percentage points (95% CI -18.0 to 26.6), risk ratio 1.06 (0.79–1.41); unadjusted two-proportion z-test p = 0.710.
• Group B-treatment Arm: 87.4% (97/111) versus 75.7% (28/37) on control; risk difference 11.7 percentage points (95% CI -3.4 to 26.9), risk ratio 1.15 (0.95–1.40); unadjusted two-proportion z-test p = 0.089.

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical methods help distinguish the observed data from the uncertainty and assumptions involved in interpreting them. The registry reports binary responder percentages and confidence intervals, while the comparison statistics are unadjusted recalculations from posted summary statistics. The record lists no analyses, so those recalculations should not be presented as the sponsor’s own analysis.

What does a responder percentage describe?

A responder percentage summarizes the proportion of participants who met a defined yes-or-no criterion. In this study, response requires at least 1 point of improvement from baseline on the MMVS on both sides of the face concurrently. Participants who do not meet every part of that definition are not counted as responders for this endpoint. The measure therefore discards some detail: it does not show how far each participant’s score changed, or whether a non-responder improved on one side but not both. This is a general feature of dichotomizing a continuous or ordinal measure, not a claim about an unreported analysis.

Arm-level percentages are useful for describing the results within each group. A comparison between groups asks a separate question: how far apart are their response probabilities, and how uncertain is that estimated separation? The registry comparison is expressed as a risk difference. In general, a risk difference is the difference between the event proportions in two groups; its value is centered on no difference when the groups have the same event proportion. The recalculated risk-difference intervals for both posted comparisons include no difference.

What do the confidence intervals add?

A confidence interval gives a range of values compatible with the data under the method’s assumptions. It communicates precision: narrower intervals indicate more concentrated estimates, while wider intervals leave more uncertainty. A 95% confidence interval does not mean that 95% of participants fall inside the interval, nor does it give a probability that a particular fixed effect lies in the realized interval. It is a repeated-sampling property of the procedure in general. The registry reports 95% confidence intervals for the responder percentages.

When an interval for a difference includes no difference, the data are compatible with no separation as well as with values on either side of it under that interval method. This does not prove that the groups are identical. Likewise, a p-value describes how unusual the observed data or a more extreme result would be under a specified null model and its assumptions. It does not measure the size or clinical importance of an effect, and it is not the probability that the null hypothesis is true. The recalculated unadjusted p-values are 0.71 for Group A versus control and 0.089 for Group B-treatment Arm versus control.

Why are the comparisons described as recalculated?

The registry record contains arm-level counts and percentages but lists no analyses. The risk-difference comparisons and associated unadjusted p-values are recalculated from the posted summary statistics. They do not incorporate an adjustment for baseline characteristics or other variables. The record does not report an original model or a sponsor analysis to compare with these recalculations. The discrepancy indicator is false, so no conflicting sponsor analysis is identified in the registry record.

Unadjusted comparisons can be informative as simple summaries, but their interpretation depends on design and analysis details. Randomization is reported, but the method of randomization, allocation concealment, analysis population, and handling of missing outcome data are not described in the available record. Without those details, it is not possible to assess whether the reported outcome denominators represent all randomized participants, participants with observed outcomes, or another analysis set.

Why can over-dispersion matter in other settings?

General statistical context: over-dispersion occurs when observed variability is greater than a model assumes. If a model treats observations as less variable than they really are, standard errors may be too small and confidence intervals may be too narrow. Methods that allow for extra variability can improve uncertainty estimates when their assumptions fit the data. The posted primary outcome is binary, and the registry does not report a model-based analysis or an over-dispersion assessment; this explanation is general and does not imply that over-dispersion was present in this study.

What does the planning exercise represent?

The sample-size planning illustration uses a stated fraction of the observed effect and assumptions of a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It gives participants per arm for 80% or 90% power. These figures are hypothetical planning quantities based on the observed effect, not the enrollment achieved in this trial and not observed power. They do not reveal the trial’s original design rationale, which is not reported in the registry record. Because smaller target effects are harder to distinguish from random variation under otherwise similar assumptions, planning for a smaller effect requires more participants.

Every statistical summary depends on choices about the endpoint, population, timing, and method. Here, the endpoint timing differs between treatment and control as described in the registry, and the record does not explain the rationale for those reference points. The confidence intervals and unadjusted comparisons should therefore be interpreted as summaries of the posted outcome data, not as a complete account of all design or analysis decisions.

10. Confidence Intervals and Precision

The responder percentages are accompanied by 95% confidence intervals. Group A’s estimate is 80.0%, with an interval from 56.3% to 94.3%. Group B-treatment Arm’s estimate is 87.2%, with an interval from 79.4% to 92.8%. Group B-control Arm’s estimate is 76.7%, with an interval from 57.7% to 90.1%. The intervals indicate that the estimates are not equally precise: those for Group A and the control group cover wider ranges than the interval for Group B-treatment Arm.

That difference in precision is consistent with the posted group sizes: Group A has 20, Group B-treatment Arm has 111, and Group B-control Arm has 37. In general, estimates from smaller groups tend to be less precise, although precision also depends on the event proportion and the method used to calculate the interval. This is a general statistical explanation; it does not identify the interval method, which is not reported in the registry record.

The recalculated risk-difference intervals for Group A versus control and Group B-treatment Arm versus control both span no difference. Thus, the comparisons leave uncertainty about the direction and size of the underlying difference. A confidence interval that includes no difference is not proof of equal response probabilities; it indicates that the posted data and method do not isolate a difference from no difference with precision.

Confidence intervals communicate uncertainty in estimates, not the spread of individual responses. The responder outcome reduces an underlying rating pattern to a binary classification, so the intervals do not describe variation in MMVS scores or the magnitude of improvement among responders. The registry does not report further outcome distributions, missing-data details, or the interval calculation method.

11. 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 planning figures are participants per arm, not total events. They use a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The assumed effect is a stated fraction of the observed effect. The rows describe planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect.

For Group A compared with control, planning for 100% of the observed effect gives 1,447 participants per arm for 80% power and 1,937 participants per arm for 90% power. Planning for 75% of the observed effect gives 2,618 participants per arm for 80% power and 3,504 participants per arm for 90% power. Planning for 50% of the observed effect gives 5,990 participants per arm for 80% power and 8,018 participants per arm for 90% power.

For Group B-treatment Arm compared with control, planning for 100% of the observed effect gives 172 participants per arm for 80% power and 229 participants per arm for 90% power. Planning for 75% of the observed effect gives 324 participants per arm for 80% power and 433 participants per arm for 90% power. Planning for 50% of the observed effect gives 769 participants per arm for 80% power and 1,029 participants per arm for 90% power.

In general, the 80% column represents the planning target for a design with an 80% chance of detecting the specified effect under the assumptions; the 90% column represents a higher chance and therefore requires more participants per arm in these illustrations. Smaller effects need more participants to distinguish them from random variation. These are planning illustrations based on the observed effect, not observed power. The trial’s original sample-size assumptions and justification are not reported in the registry record.

12. 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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.757; treatment proportion p₁ = 0.800; average p̄ = 0.778.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5874 = 1.1512.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5866 = 0.4937.
4. n = (1.1512 + 0.4937)² / (0.0432)² = 1,446.9, rounded up to 1,447 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
p0 <- 0.756756756756757                          # control proportion
p1 <- 0.8                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3289052)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 1,447 (80% power), 1,937 (90% power)
 75% of observed effect: n per arm = 2,618 (80% power), 3,504 (90% power)
 50% of observed effect: n per arm = 5,990 (80% power), 8,018 (90% power)
power.prop.test: 1446.9 
Simulated power at n = 1,447 per arm: 0.801 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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.

13. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and no posted secondary outcomes. It lists no analyses. The record does not report a prespecified statistical analysis plan, a hierarchy of hypotheses, or a multiplicity adjustment. Multiplicity arises when several hypotheses or comparisons are examined: without an appropriate plan, the chance of at least one apparently notable result can increase. This is general statistical context, not a claim that any particular testing strategy was used in this trial.

Two unadjusted recalculated comparisons are reported: Group A against Group B-control Arm, and Group B-treatment Arm against Group B-control Arm. The registry does not report whether these comparisons were prespecified, whether other comparisons were planned, or how the investigators intended to account for multiple testing. The unadjusted p-values therefore should be read as descriptive comparison statistics rather than as a complete multiplicity-controlled analysis.

Missing outcome data can affect an estimate if participants with missing assessments differ from those whose outcomes are observed. The registry record does not report the amount or pattern of missing data, the method used to handle missing outcomes, or sensitivity analyses. It also does not state whether the posted denominators correspond to all randomized participants or to an analysis subset. Those omissions prevent a full assessment of possible missing-data bias.

The record does not identify an intention-to-treat, per-protocol, or other analysis population for the primary endpoint. It does not report protocol deviations or how such deviations were handled. These details matter because an analysis population defines which participants contribute to an estimate and can affect its interpretation. No assumptions about those choices should be inferred from the arm labels or group sizes alone.

Randomization is recorded, but the sequence-generation and allocation-concealment methods are not reported in the registry record. The study is described as evaluator-blinded, and masking is listed as single; further details about who was masked are not reported in the available record. These reporting gaps do not invalidate the posted outcome figures, but they limit the ability to evaluate the full analysis process and the robustness of the comparisons.

14. 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

Serious events with the highest arm-level rate: lung adenocarcinoma stage 0 (5.0%), skin papilloma (0.9%).

The serious adverse event figures describe participants recorded as affected among those at risk in each group. Group A had 1 serious adverse event among 20 at risk. Group B-treatment Arm had 1 serious adverse event among 111 at risk. Group B-control Arm had 0 serious adverse events among 37 at risk. No deaths were recorded in any of the three groups. The record reports no other adverse events in these groups.

These counts are descriptive and do not, by themselves, establish whether an event was caused by the intervention. A zero recorded count does not establish that an event is impossible, especially when the group is limited in size. The registry’s listed serious-event terms include Lung adenocarcinoma stage 0 at 5.0% and Skin papilloma at 0.9%. The record does not provide enough context in this summary to reconcile those term percentages with the affected counts, or to establish their relationship to the treatment.

The adverse-event figures should be interpreted alongside the limits of registry reporting. The available information does not describe event ascertainment, follow-up duration for safety, severity grading, or causal attribution. These safety counts are not a comprehensive assessment of all possible harms.

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

The posted data show that the recorded proportion meeting the responder definition was 80.0% in Group A, 87.2% in Group B-treatment Arm, and 76.7% in Group B-control Arm. The group-level confidence intervals express uncertainty around those percentages. The unadjusted recalculated comparisons have p-values of 0.71 for Group A versus control and 0.089 for Group B-treatment Arm versus control, and both risk-difference intervals include no difference.

These results do not establish that the groups have identical response rates, nor do they establish a causal effect. The comparison estimates are recalculated from posted summary statistics, and the registry lists no analyses. The record does not report the original analysis plan, missing-data approach, analysis populations, or multiplicity strategy. Those limitations affect how strongly the comparative results can be interpreted.

The endpoint captures whether participants met a specific threshold for improvement on both sides of the face at the assessment time. It does not convey the full distribution of MMVS changes, the extent of change among responders, or other aspects of outcome. The timing differs by group: 6 months after last treatment for treatment and 6 months after randomization for control. The registry does not explain the rationale for that timing structure.

The results also do not establish long-term outcomes, effects on outcomes that were not posted, or safety beyond the adverse-event information in the record. No secondary outcomes are posted. The serious adverse event counts and listed terms are descriptive; the registry information does not establish causation or provide a complete safety assessment.

The careful interpretation is therefore limited to the registry’s reported responder proportions, confidence intervals, and unadjusted recalculated comparisons at the stated assessment. The numbers show observed outcomes and their uncertainty, not a definitive conclusion about benefit, lack of benefit, or individual outcomes.

16. Why This Trial Matters Statistically

This trial illustrates why an observed proportion and a between-group comparison answer different questions. The arm-level responder percentages describe the frequency of meeting the endpoint within each group. The risk-difference comparisons address how the groups differ, while their confidence intervals show the uncertainty around that separation. Looking only at the percentages can obscure the uncertainty, particularly when group sizes are unequal and interval widths vary.

The endpoint also demonstrates the consequences of a threshold-based outcome. A participant must meet the improvement criterion on both sides of the face to count as a responder. This creates a straightforward binary result, but it leaves out the size and pattern of change that a continuous or ordinal outcome distribution might preserve. Statistical interpretation must stay aligned with the actual endpoint definition rather than treating the responder percentage as a complete description of facial ratings.

The registry record distinguishes posted results from analysis details: it gives group counts and outcome percentages, but lists no analyses. The unadjusted comparisons are recalculations from the posted summary statistics. Recognizing that distinction prevents a descriptive recalculation from being mistaken for a prespecified or adjusted sponsor analysis.

Finally, the planning illustration makes the role of assumptions visible. Its sample sizes depend on the assumed fraction of the observed effect, power target, and stated design assumptions. It is a planning aid, not evidence that the trial had adequate power or that its original design used those assumptions. The original sample-size rationale is not reported in the registry record.

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.

The registry record leaves important design and analysis details unreported. Although the study is described as randomized and evaluator-blinded, the methods for generating and concealing allocation are not reported. The masking field says single, but the record does not identify all parties who were masked. Group A is not explicitly mapped to the intervention description in the outcome labels, which limits interpretation of that group’s result.

The treatment and control assessment times are defined differently: treatment is assessed 6 months after last treatment, while control is assessed 6 months after randomization. The registry does not report the reason for this difference or whether any additional timing rules applied. Treatment is described as a single injection with an optional touch-up, but the record does not state how often touch-up injections occurred.

The registry lists no analyses and no secondary outcomes. It does not report the original statistical analysis plan, analysis populations, missing-data methods, sensitivity analyses, multiplicity handling, or baseline characteristics. The comparison statistics are unadjusted recalculations from the posted summary statistics, so they do not replace a full trial analysis. The interval calculation methods are also not reported.

The response outcome is binary and based on a threshold requiring improvement on both sides. The posted percentages do not provide the full distribution of MMVS change or information about people who may have improved without meeting the full responder definition. The registry’s safety information is limited to the listed adverse-event counts and terms; details on ascertainment, follow-up, severity, and causal assessment are not reported in the registry record.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Restylane Volyme for Correction of Midface Volume Deficit and/or Midface Contour Deficiency — NCT03289052.
• Registry record last updated 2023-05-12; status last verified 2023-04.
• Results first posted 2021-03-15.
• 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

NCT03289052 is a completed randomized, parallel-group, evaluator-blinded, no-treatment controlled study sponsored by Galderma R&D. The record lists enrollment of 168 and dates from 2017-12-01 to primary completion on 2019-01-31. The intervention was Restylane Volyme, described as a single injection with an optional touch-up; the comparator was no treatment.

The primary endpoint was the percentage of responders at the six-month assessment, defined as at least 1 point of improvement from baseline on the MMVS on both sides of the face concurrently. Posted response percentages were 80.0% for Group A, 87.2% for Group B-treatment Arm, and 76.7% for Group B-control Arm, with 95% confidence intervals reported for each. The record lists no analyses and no secondary outcomes. Unadjusted comparison statistics are recalculated from posted summary data. Details of the original analysis plan, missing-data handling, and analysis populations are not reported in the registry record.