Restylane Perlane Lidocaine 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 Perlane Lidocaine for Correction of Midface Volume Deficit and/or Midface Contour Deficiency (NCT03097783), a randomized na study. The primary outcome is Percent Responders With 1 Point Improvement on the Medicis Midface Volume Scale.

2. Clinical Question

3. Trial Design

The registry describes a randomized, multi-center, evaluator-blinded, no-treatment controlled study with a parallel model and single masking. The study is marked completed. Its listed intervention was Restylane Perlane Lidocaine; the intervention description allows a single injection and an optional touch-up injection in the midface. The comparator arm received no treatment. The registry classifies the intervention as a device and lists the phase as NA.

The registry enrollment is 169. The posted outcome gives an intervention-arm denominator of 110 and a no-intervention denominator of 37. These are the denominators associated with the responder counts in the outcome record; they are not a substitute for a participant flow account. Reasons for any difference between the enrollment figure and the posted outcome denominators are not reported in the registry record.

The study start is listed as 2017-04-26 and primary completion as 2018-03-23. These dates describe the registry record and do not, by themselves, explain recruitment, follow-up completion, or the timing of analysis. The registry says summaries were to be done separately for Group A and B, with statistical inference using only Group B. How those groups correspond to the posted intervention and no-intervention arms is not reported in the registry record. The masking description identifies evaluator blinding, but the record does not give further details about who remained unaware of assignment or how masking was maintained.

The primary endpoint was assessed at 6 month. Additional operational details, including the full visit schedule, eligibility criteria, allocation procedure, and original design assumptions, are not reported in the registry record. The registry lists no secondary outcomes and no analysis records, although it does post primary outcome counts and a comparison.

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

Analysis population for the primary outcome, as defined in the registry: All summaries will be done separately for Group A and B. For statistical inference,only Group B will be used.

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 Percent Responders With 1 Point Improvement on the Medicis Midface Volume Scale, measured over 6 month.

The primary endpoint is the number and percentage of participants classified as responders on the Medicis Midface Volume Scale (MMVS) at 6 month. A responder was defined as having at least 1 point improvement from baseline on both sides of the face, according to a blinded evaluator. The endpoint therefore requires improvement on the right and left midface, rather than improvement on only one side.

The MMVS is a four-grade scale of midface fullness. Its categories range from fairly full midface to substantial loss of fullness, with intermediate grades describing mild or moderate loss. Because higher grades describe greater loss of fullness, a decrease from baseline represents improvement under the stated definition. The registry outcome does not report the distribution of scale scores or the number of participants who improved by more than the responder threshold.

A binary responder outcome turns a scale assessment into a yes-or-no classification against a predefined threshold. In general, this can make a clinical comparison easier to interpret as the proportion meeting a specified criterion. It also discards information about the amount of change beyond that threshold: participants meeting the threshold are grouped together even if their score changes differ, and those not meeting it are grouped together despite any smaller changes. The registry record does not report the scale’s measurement properties, the rationale for the responder threshold, or the handling of missing side-specific assessments.

7. Results Posted in the Registry

• No Intervention Arm: 21.6% (8/37) versus 60.9% (67/110) on control; risk difference -39.3 percentage points (95% CI -55.4 to -23.2), risk ratio 0.35 (0.19–0.67); unadjusted two-proportion z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

What does a responder comparison represent?

The endpoint classifies participants as responders or nonresponders according to the stated MMVS criterion. For a binary outcome, each participant contributes to one of those categories, and the arm-level responder proportion is the number of responders divided by the corresponding arm denominator. The posted counts and denominators are 67 of 110 for Restylane Perlane Lidocaine and 8 of 37 for no intervention. The accompanying proportions are reported as 0.609 and 0.216.

A risk difference expresses the difference between two proportions on the original probability scale. In this registry comparison, the reported estimate is -0.393 and the contrast is oriented as no-intervention minus intervention. A negative value therefore corresponds to a lower responder proportion for no intervention in the posted comparison. The scale is directly linked to percentage-point differences when proportions are expressed as percentages, but no conversion or additional estimate is needed to interpret the reported value.

How do relative measures differ?

A relative risk compares the proportions by division, while an odds ratio compares the odds of responding in the two groups. Both express the contrast on a relative rather than an absolute scale. The registry reports a relative risk of 0.355 and an odds ratio of 0.177, with their respective confidence intervals. These measures can look numerically different because they use different scales, particularly when the outcome is not rare. They summarize the same responder outcome and do not provide separate evidence about additional outcomes.

For a binary endpoint, the choice of scale affects how the size of a contrast is communicated. The risk difference keeps the comparison in the original proportion units and is often useful for describing the absolute separation between groups. Relative measures describe how one group’s outcome relates proportionally to the other group’s outcome. None of these summaries, by itself, conveys uncertainty; that is why the estimate is read alongside its confidence interval and the reported p-value.

What do the confidence interval and p-value say?

General explanation: a confidence interval describes a range of values compatible with the data under the assumptions of the analysis procedure. It communicates the precision of an estimate as well as its direction. It is not a range containing a known true value with certainty, and it does not account for limitations that were not included in the analysis, such as unreported missing-data procedures.

The risk-difference interval is -0.554 to -0.232. The relative-risk interval is 0.189 to 0.667, and the odds-ratio interval is 0.074 to 0.423. Each interval is on a different scale, so the numeric bounds cannot be compared as if they measured the same quantity. The unadjusted p-value is <0.001. General explanation: a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be under that hypothesis and the analysis assumptions. It is not the probability that the null hypothesis is true or a measure of clinical importance.

The registry calls the p-value unadjusted, but does not report the precise test, its assumptions, or whether any other analysis was considered. The confidence interval method is also not reported in the registry record. The displayed estimates should therefore be described as registry-reported results rather than treated as independently reproducible calculations.

What role do randomization and blinding play?

General explanation: random assignment is intended to make treatment groups comparable in expectation, including with respect to factors that are not measured. It does not ensure that every feature of the groups is identical, and it does not resolve issues such as loss to follow-up or deviations after assignment. A parallel design assigns participants to one group for comparison over the study period.

Evaluator blinding can reduce the chance that knowledge of group assignment influences the outcome assessment. This is relevant when an endpoint depends on an evaluator’s rating. The registry identifies evaluator blinding but does not explain who else was masked, whether participants or treating investigators knew assignment, or how the masking was implemented. Because the comparator was no treatment, the record also does not provide details of procedures intended to manage differences in expectations or contact between groups.

What is not available about the analysis?

The registry does not report the original statistical plan, the chosen inference test, missing-data methods, adjustment for baseline variables, or a detailed definition of the analysis population. The primary outcome description states that summaries would be performed separately for Group A and B and that statistical inference would use only Group B, but the relation between those groups and the posted arm-level results is not reported in the registry record. The record lists no analysis records even though a primary comparison is posted. These gaps mean that the analysis cannot be fully reconstructed from the registry information alone.

10. Confidence Intervals and Precision

Precision is reflected in the width of an estimate’s confidence interval: narrower intervals generally indicate less statistical uncertainty under the analysis assumptions, while wider intervals indicate more. The interval should be considered together with the effect estimate and the scale on which it is expressed. A risk difference, relative risk, and odds ratio have different units and interpretations, so their interval widths are not directly comparable.

For the risk difference, the reported estimate is -0.393 and the interval extends from -0.554 to -0.232. For the relative risk, the estimate is 0.355 and the interval extends from 0.189 to 0.667. For the odds ratio, the estimate is 0.177 and the interval extends from 0.074 to 0.423. All three are summaries of the same responder comparison, not three separate endpoint findings. The risk-difference interval lies below zero, while the relative-measure intervals lie below one; those reference values correspond to no contrast on their respective scales.

The posted interval widths reflect the data and the method used to construct them, but the registry record does not name that method. They also do not capture every source of uncertainty. For example, the record does not explain missing outcome handling, the relation between the stated Group B inference population and the arm-level outcome summaries, or whether other analytic choices were prespecified. Such omissions limit how fully the precision can be assessed.

The denominators differ between the posted arms, and the no-intervention outcome count is smaller than the intervention outcome count. The confidence intervals are important in reading the comparison because a point estimate alone can make the result appear more exact than the available data justify. The intervals quantify sampling uncertainty only insofar as the underlying analysis assumptions are appropriate; they do not address bias, generalizability, or the uncertainty created by unreported methods.

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 are planning illustrations based on the observed effect, not the trial’s original sample-size calculation. The registry record does not report the trial’s own design assumptions or sample-size justification.

The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set at the stated fraction of the observed effect. The listed scenarios are planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. For each scenario, the 80% power column gives the participants per arm associated with an 80% chance of detecting an effect of that specified size under those assumptions, if the assumed effect and analysis model were correct. The 90% power column gives the corresponding planning figure for a 90% chance.

The figures are 24 and 31 participants per arm for planning at 100% of the observed effect; 44 and 59 for 75% of the observed effect; and 101 and 134 for 50% of the observed effect, for the 80% and 90% power targets respectively. Smaller effects require more participants under these assumptions, as reflected by the increasing figures across the scenarios. A curve, if used to display these planning scenarios, should be read as showing how the planning requirement changes with the assumed effect size, not as evidence about the trial’s observed outcome beyond the reported estimates.

This is not observed power. It does not estimate the chance that this completed study detected an effect after seeing its results. It is a forward-looking illustration derived from the observed effect and the stated planning assumptions, and should not be mistaken for the unreported assumptions used to design the trial.

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 = 0.609; treatment proportion p₁ = 0.216; average p̄ = 0.413.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6962 = 1.3646.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6384 = 0.5373.
4. n = (1.3646 + 0.5373)² / (-0.3929)² = 23.4, rounded up to 24 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 <- 0.609090909090909                          # control proportion
p1 <- 0.216216216216216                          # 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(3097783)
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 = 24 (80% power), 31 (90% power)
 75% of observed effect: n per arm = 44 (80% power), 59 (90% power)
 50% of observed effect: n per arm = 101 (80% power), 134 (90% power)
power.prop.test: 23.4 
Simulated power at n = 24 per arm: 0.827 (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 and no secondary outcomes. It also lists no analysis records, although a primary arm comparison and its unadjusted p-value are posted. The record does not say whether additional outcomes, time points, subgroup analyses, or alternative models were examined outside the posted registry results.

Multiplicity arises when several statistical hypotheses are tested. General explanation: considering many tests can increase the chance that at least one result appears unusual by chance, so a prespecified plan may define which outcomes are confirmatory and whether adjustment is needed. The registry record does not report a multiplicity strategy. Because it does not identify other analyses or the full analysis plan, the degree to which multiplicity is relevant cannot be determined from this record.

The endpoint description states that summaries are to be done separately for Group A and B and that statistical inference uses only Group B. The posted responder summaries are displayed for the intervention and no-intervention arms, but the relationship between the group labels and these arm results is not reported in the registry record. That ambiguity matters when judging which population the inference represents. The record also does not report whether the posted arm counts include all randomized participants, all participants with an assessment, or another analysis population.

Missing data can affect a binary outcome if participants without an assessment are excluded, classified in a particular way, or handled using another method. The registry record does not report the number of missing primary outcome assessments, reasons for missingness, or any imputation or sensitivity analysis. It also does not report the handling of protocol deviations, treatment discontinuation, or optional touch-up injections in the analysis. These details are needed to understand precisely which participants contributed to the posted outcome and how robust the result may be to alternative assumptions.

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.

The registry posts serious adverse event figures separately for the Restylane Perlane Lidocaine and no-intervention arms. The serious-event at-risk counts are 110 and 37, and the serious-event affected counts are 0 in each arm. The posted other-adverse-event at-risk counts are also 110 and 37, with affected counts of 0 in each arm. Deaths are listed as 0 in both arms.

These are the registry’s reported counts for the categories shown. They do not establish that no events of any kind occurred; the record gives zero affected counts in the posted serious and other adverse-event summaries. The registry does not provide event narratives, event timing, severity beyond the serious classification, or a fuller account of how adverse events were collected and coded. It lists no top serious adverse-event terms.

General explanation: safety counts should be read with their denominators and the definitions and observation period used to collect them. A zero count in a posted category is not evidence that the underlying risk is exactly zero, particularly when the record does not describe collection methods and follow-up completeness. The safety summaries do not, by themselves, establish a comparative safety conclusion.

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

The posted results describe a difference in the six-month responder outcome between participants assigned to Restylane Perlane Lidocaine and those assigned to no intervention. The responder definition requires at least 1 point improvement from baseline on both sides of the face as rated by a blinded evaluator. The arm counts, proportions, risk difference, relative measures, confidence intervals, and unadjusted p-value summarize that specific outcome and comparison.

They do not describe every aspect of midface change. A binary responder measure does not show the full distribution of MMVS scores, the amount of improvement among responders, or changes among those who did not meet the threshold. The registry record does not report participant-level data, a broader set of outcomes, or longer-term results. The findings therefore should not be generalized beyond the endpoint, time point, and study groups described in the record.

The randomized design is relevant to interpreting a between-group comparison, and evaluator blinding is relevant to a rating-based outcome. However, the registry does not report enough methodological detail to confirm how randomization and masking were implemented, how missing outcomes were handled, or which participants were included in statistical inference. Its statement that inference uses Group B is not connected to the posted arm summaries in a way that can be resolved from the registry record.

The result does not establish that every participant experienced the same response, nor does it establish an individual outcome. The posted statistical comparison also does not by itself determine the importance of the observed difference; clinical relevance depends on considerations not reported in the registry record, including the rationale for the response threshold and the context of the outcome. The safety counts are limited to the adverse-event categories and counts posted. Overall, the record supports a description of the reported responder comparison, while leaving important analytic and clinical context unavailable.

16. Why This Trial Matters Statistically

This trial is statistically notable as a randomized comparison using a clearly defined binary responder outcome and an evaluator-blinded assessment. The endpoint requires improvement on both sides of the face, making its classification rule explicit in the registry record. The comparison is also presented on multiple scales: risk difference, relative risk, and odds ratio. Reading those summaries together illustrates why the scale of an effect estimate matters even when each measure arises from the same binary outcome.

The confidence intervals add essential information beyond the point estimates. They show the range of uncertainty reported for the comparison and help prevent the point estimate from being read as exact. The unadjusted p-value offers another inferential summary, but the registry does not report its test method or the broader analysis plan. These omissions are a useful reminder that a small p-value cannot replace transparent reporting of methods, populations, and missing-data handling.

The stated distinction between Group A and Group B is especially relevant: the registry says summaries are separate and inference uses only Group B, but does not identify how those groups relate to the posted arm counts. This limits the reader’s ability to connect the population plan to the reported comparison. The registry also lists no analysis records while posting a primary comparison, so the derivation and exact analysis population cannot be fully assessed.

The planning illustration shows how sample-size requirements depend on the assumed effect size and desired power, under stated assumptions. Its figures are not evidence that the completed trial had a particular probability of success. Separating forward-looking planning from observed results is important when interpreting power calculations based on an effect estimated from the same study. Taken together, the record offers a useful statistical example of effect scales, uncertainty, and the importance of complete analysis reporting.

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.

Several limitations specific to this registry record constrain interpretation. Although enrollment is listed as 169, the posted primary outcome denominators are 110 for Restylane Perlane Lidocaine and 37 for no intervention. The registry does not explain the relationship between the enrollment figure and these outcome denominators, provide a participant flow account, or state whether all randomized participants were assessed at the primary time point.

The outcome description says summaries are to be separated for Group A and B and that statistical inference uses Group B only. The posted outcome, however, presents arm-level counts and a comparison without identifying the corresponding group. The inference population therefore cannot be mapped confidently to the reported contrast from the registry record alone.

The record does not report the original statistical plan, randomization method, exact test, confidence interval method, missing-data procedure, analysis population definition, or sensitivity analyses. It also does not explain how optional touch-up injections or deviations from assigned treatment were handled. The primary endpoint is a rating-based binary classification; details about assessor training, assessment reliability, and the rationale for the threshold are not reported in the registry record.

The registry lists no secondary outcomes and no analysis records. It does not provide a fuller account of outcome collection, other evaluated measures, or follow-up beyond the primary timeframe. Safety reporting is limited to posted counts for serious and other adverse events and deaths, without event narratives or collection details. These limitations do not alter the reported numbers, but they restrict the conclusions that can be drawn about their derivation, completeness, and broader meaning.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Restylane Perlane Lidocaine for Correction of Midface Volume Deficit and/or Midface Contour Deficiency — NCT03097783.
• Registry record last updated 2023-11-03; status last verified 2021-06.
• Results first posted 2021-07-21.
• 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

The registry describes a completed, randomized, multi-center, parallel-group, evaluator-blinded study comparing Restylane Perlane Lidocaine with no treatment for midface volume deficit and/or contour deficiency. The primary outcome was the proportion of responders at 6 month, defined as at least 1 point improvement from baseline on both sides of the face on the MMVS, assessed by a blinded evaluator.

The posted counts are 67 of 110 in the intervention arm and 8 of 37 in the no-intervention arm. The registry reports a risk difference of -0.393, relative risk of 0.355, odds ratio of 0.177, and unadjusted p-value <0.001, with confidence intervals for each effect measure. Serious and other adverse-event affected counts are 0 in both arms, and deaths are listed as 0.

Important analysis details, including missing-data handling, the exact statistical methods, and the mapping of the stated Group B inference population to the posted arm summaries, are not reported in the registry record.