Clinical Study to Evaluate the Correction of Wrinkles and Folds and Safety of YVOIRE Classic Versus Restylane in Nasolabial Fold Intradermal Injection: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Clinical Study to Evaluate the Correction of Wrinkles and Folds and Safety of YVOIRE Classic Versus Restylane in Nasolabial Fold Intradermal Injection (NCT03738020), a randomized na study. The primary outcome is Average of Wrinkle Severity Rating Scale (WSRS) Score Evaluated by the Evaluating Investigator at Week 26 (Visit 7) After the Final Treatment With the Investigational Medical Device.

2. Clinical Question

This is an active-controlled comparison rather than a comparison with no treatment. The central statistical issue is not simply whether the two observed means are equal. A non-inferiority conclusion requires a prespecified margin and an analysis that shows the uncertainty around the treatment contrast stays within that margin, with the contrast direction and analysis population interpreted according to the trial plan. Those details are not reported in the registry record.

3. Trial Design

The registry identifies NCT03738020 as a completed randomized clinical study sponsored by LG Life Sciences. The recorded enrollment is 58. The recorded start is 2009-01 and primary completion is 2009-10. The phase is listed as NA. Its stated condition is temporary correction of wrinkles.

The official title describes a randomized, multicenter, single-blind, active-controlled study with a matched-pairs design. The registry’s separate design entries, however, list masking as double and model as parallel. The primary outcome population is described as a split-face design. These descriptions do not align fully. The record does not explain how the matched-pairs and split-face descriptions relate to the parallel model, or why the title’s single-blind wording differs from the double-masking entry. The design should therefore be described with that qualification rather than treated as unambiguously documented.

The two listed treatment arms are HA IDF and Restylane. Each has an outcome denominator of 58. Because the record also describes a split-face population, those arm counts should not be summed or interpreted as a count of unique participants. The record does not report the randomization sequence, allocation concealment, or how paired observations were handled in the statistical analysis.

The study’s stated purpose was to evaluate non-inferiority in wrinkle correction and safety. Its single posted primary outcome is the investigator-evaluated average WSRS score at Week 26 (Visit 7) after final treatment. The record lists no secondary outcomes and reports no analyses. The sample-size justification, planned analysis population, protocol deviations, and details of the statistical plan are not reported in the registry record.

4. Participant Flow and Accounting

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

Before assignment: spilt-face design

Overall Study

Analysis population for the primary outcome, as defined in the registry: Spilt-face design

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: spilt-face design

6. Primary Endpoint

The registry lists the primary outcome as Average of Wrinkle Severity Rating Scale (WSRS) Score Evaluated by the Evaluating Investigator at Week 26 (Visit 7) After the Final Treatment With the Investigational Medical Device, measured over Week 26 (Visit 7).

The primary endpoint is the average Wrinkle Severity Rating Scale score evaluated by the investigator at Week 26 (Visit 7) after the final treatment. The WSRS is a five-category scale describing the appearance and depth of a fold. Its categories run from absent, meaning no visible fold, through mild, moderate, and severe, to extreme. The record supplies descriptive criteria for these levels, including whether a fold is visible at rest or when stretched.

As a general statistical interpretation, an ordinal rating scale represents ordered categories: a higher category indicates greater described severity. The registry reports the endpoint as a mean, which treats the category scores numerically for the summary. That mean can convey the group’s average recorded score, but it does not show how many observations fell into each category or the shape of the score distribution. The registry provides standard deviations alongside the means.

The endpoint is a measure of wrinkle severity at the specified follow-up visit, not a reported change from baseline. Baseline WSRS values and a baseline-adjusted analysis are not reported in the registry record. The timing is explicitly tied to Week 26 after final treatment; the record does not describe how this visit relates to any variation in treatment timing. The investigator rating offers a structured outcome, but the registry does not report whether raters were trained, how ratings were standardized, or how missing assessments were handled.

7. Results Posted in the Registry

• Restylane: mean 2.56 versus 2.56 on control; difference 0.00 (95% CI -0.24 to 0.24), standardized effect d = 0.00; z-test p = 1.000.

8. Statistical Interpretation

9. Statistical Methods Explained

The posted primary measure is continuous in the registry’s analysis classification, and its summary is a mean with a standard deviation. The analysis also reports a mean difference, an interval, and an unadjusted p-value. These are familiar summaries for comparing average scores, but their interpretation depends on the study design and the details of the statistical plan, which are not fully reported.

What does a mean difference represent?

In general, a mean difference is the contrast between the average outcome values in two groups, using a specified ordering of the groups. Here, the posted mean is 2.56 for each treatment and the reported mean difference is 0.0. Because the arm means are equal as displayed, the point estimate indicates no difference between those displayed averages. The record does not provide a separate explanation of the comparison’s sign convention, so the positive and negative sides of the interval should not be assigned a treatment-favoring direction without that information.

A mean compresses the observed scores into one summary. It does not disclose how observations are distributed across the five WSRS categories or whether participants’ scores are clustered in particular categories. The standard deviations of 0.68 and 0.66 describe variability around each arm’s mean, but do not substitute for category counts or a distributional display. The registry does not report those details.

What does the interval add?

As a general explanation, an interval around an estimate conveys the uncertainty associated with that estimate under the statistical method used. The reported interval for the mean difference extends from -0.244 to 0.244. It includes 0.0, consistent with the equal means at the displayed precision. The confidence level and the method used to form the interval are not reported in the registry record. The interval should not be interpreted as a range containing a known proportion of individual participants’ outcomes; it concerns the estimated treatment contrast.

For a non-inferiority question, the interval must be judged against a margin selected before examining results. The registry states a non-inferiority objective but does not report that margin. Without it, the interval cannot be classified as sufficiently narrow or positioned to satisfy the trial’s intended non-inferiority criterion. A result that does not show a statistically detectable difference under a conventional difference test is not automatically a non-inferiority result.

Why might pairing matter?

As a general statistical principle, measurements from two sides of the same person can be related. A matched-pairs or split-face analysis should account for that relationship rather than treating the two sides as unrelated observations. Accounting for pairing can affect the estimated uncertainty because it uses information about within-person differences. The official title calls the design matched pairs, the outcome population says split-face, and the model entry says parallel. The registry does not resolve this inconsistency or state how pairing was incorporated into the reported estimate and interval.

The arm results list 58 observations for each product. Those counts do not establish the number of unique participants in a split-face study, and they should not be added. The record’s enrollment is 58, but it does not provide a participant flow account or explain the relationship between enrollment and the arm-specific denominators.

How should the p-value be read?

In general, a p-value describes how compatible the observed data are with a specified null hypothesis under the assumptions of the test. The posted unadjusted p-value is 1.0. The registry does not identify the exact test, its assumptions, or whether the test accounts for the stated paired design. The p-value does not give the probability that the treatments are identical, nor does it quantify the probability that the result will replicate. It also does not replace an interval or a non-inferiority margin.

The word “unadjusted” indicates that the displayed p-value is not described as multiplicity-adjusted. Since the record lists one primary outcome and no secondary outcomes, the registry does not expose a broader set of outcome tests for assessing multiplicity. It does not report whether there were additional analyses that were not posted, a hierarchy of tests, or a prespecified approach to multiplicity.

What can planning illustrations tell readers?

As a general concept, a sample-size calculation can estimate the number of participants per arm needed for a future study under stated assumptions about the effect to detect, significance level, allocation, and statistical model. Such a planning illustration is not an observed result and is not the trial’s achieved power. The registry’s planning description specifies a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the target effect expressed as a fraction of the observed effect. It states that non-time-to-event illustrations are expressed as participants per arm. The registry record does not report the trial’s own sample-size justification, and the planning assumptions do not establish what was used to design this study.

The registry reports no analysis entries. Consequently, details such as an intention-to-treat or per-protocol population, covariate adjustment, handling of missing values, sensitivity analyses, and model diagnostics are not reported in the registry record. Those omissions limit independent assessment of how the posted comparison was produced.

10. Confidence Intervals and Precision

The reported interval for the mean difference runs from -0.244 to 0.244 around the point estimate of 0.0. It includes the null value of 0.0, so the posted estimate is compatible with no difference in mean score. It also includes contrasts on either side of that value. The interval’s confidence level and construction method are not reported in the registry record, which limits how fully its statistical coverage can be interpreted.

Precision is not the same as whether a result is clinically important or meets a non-inferiority objective. To assess non-inferiority, the interval must be compared with the prespecified margin and interpreted using the planned contrast direction. The registry does not report a margin, so the interval cannot be judged against the trial’s intended non-inferiority threshold. Equal displayed means and an interval containing 0.0 are not, by themselves, proof of equivalence or non-inferiority.

The arm standard deviations are 0.68 for HA IDF and 0.66 for Restylane. They describe the spread of scores around the arm means; they do not describe uncertainty in the treatment contrast in the same way as the interval. The registry lists 58 outcome observations in each arm, while also describing the population as split-face. It does not explain the analysis of within-person dependence. Since pairing can affect the uncertainty of a contrast, the absence of that detail matters when interpreting precision.

The posted result is also limited to the Week 26 endpoint. Baseline scores and change scores are not reported, nor is the distribution across WSRS categories. The interval therefore concerns the reported mean comparison, not all possible ways of summarizing the outcome or the treatment effect over time.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and no secondary outcomes. It reports no analyses. This makes the posted result set narrow, but it does not establish that the study performed only one statistical test. The protocol, complete statistical analysis plan, and any additional analyses are not reported in the registry record.

As a general statistical issue, testing multiple outcomes, time points, subgroups, or analysis variants can increase the chance of obtaining an apparently notable result by chance if no multiplicity approach is planned. The record does not report whether there were multiple planned tests or how any multiplicity would have been handled. The displayed p-value is explicitly unadjusted. There is not enough registry information to determine the role of that value within a broader testing strategy.

Missing-data methods are not reported. The registry gives outcome denominators for both arms, but does not describe whether all enrolled participants contributed an outcome, how missing Week 26 assessments were handled, or whether any participants were excluded from the analysis. No imputation method, sensitivity analysis, or missingness summary is posted. The presence of an outcome denominator alone does not explain the completeness of follow-up or the handling of absent measurements.

The analysis population is also not reported. In a non-inferiority study, the choice and handling of analysis populations can be important; as a general consideration, intention-to-treat and per-protocol analyses may provide complementary perspectives. The registry does not identify either population or say whether more than one was analyzed. The stated split-face and matched-pairs descriptions also make the handling of paired observations relevant, but that method is not reported.

These gaps do not change the posted numerical result, but they constrain its interpretation. Readers cannot determine from the registry alone whether missing data, analysis-population choices, multiplicity, or paired structure affected the reported estimate and interval.

12. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports zero participants affected by serious adverse events in the HA IDF group and zero in the Restylane group, each with 58 at risk. A separate Systemic entry also reports zero affected by serious adverse events, with 58 at risk. No serious adverse-event terms are listed. The record does not explain the relationship between the Systemic entry and the two treatment-arm entries, so those categories should not be combined or treated as independent groups.

For other adverse events, the registry reports 3 affected in the HA IDF group and 3 in the Restylane group, each with 58 at risk. The Systemic entry reports 5 affected, with 58 at risk. These are registry counts; the record does not provide event descriptions, severity details, timing, or a causal assessment for these entries. The counts should not be added across entries, because their relationship is not explained.

Deaths are listed as null, which means death information is not reported in the registry record; it does not establish that no deaths occurred. Safety counts describe what the registry reports for the recorded categories and denominators. They do not, by themselves, establish comparative safety, particularly without event definitions, follow-up details, or an analysis accounting for the study’s design.

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

The posted results show the same displayed mean WSRS score for HA IDF and Restylane at Week 26: 2.56 in each arm. The reported mean difference is 0.0, the interval is -0.244 to 0.244, and the unadjusted p-value is 1.0. These statistics describe the recorded average-score comparison at that visit. They do not report change from baseline, the distribution of severity categories, or individual responses.

The study’s stated purpose was to evaluate non-inferiority, but the registry does not report the non-inferiority margin or sufficient detail about the planned analysis. The numerical result therefore cannot be used on its own to conclude that the prespecified non-inferiority objective was met. Nor does an equal displayed mean prove that the treatments are equivalent in every relevant respect. A difference test, an equivalence assessment, and a non-inferiority assessment address distinct questions.

The record also does not resolve the differences between its design descriptions: the official title refers to single blinding and matched pairs, the masking entry says double, the model entry says parallel, and the outcome population is described as split-face. How the analysis handled paired observations is not reported. That uncertainty affects interpretation of the reported precision.

The safety entries report no participants affected by serious adverse events in either treatment arm, while other adverse-event counts are listed as 3 for each arm. A separate Systemic category is also present. The record does not report deaths, event details, or enough information to interpret the relation among safety categories. These counts are descriptive and do not alone establish a comparative safety conclusion.

In short, the registry supports a description of equal reported group means and the associated interval and p-value. It does not provide enough statistical-plan information to convert those observations into a definitive non-inferiority or equivalence conclusion. Missing-data methods, analysis populations, and the confidence level for the interval are also not reported.

14. Why This Trial Matters Statistically

This trial illustrates why the label of a study objective and the evidence needed to answer it must be considered together. The registry describes a non-inferiority aim, but does not report the margin that defines how much difference would be acceptable. Without that boundary, an estimated difference and interval cannot be judged against the intended criterion. The point estimate being 0.0 is not a substitute for the missing margin.

It also illustrates the importance of consistent design reporting. The record includes randomized and active-controlled descriptions, but its entries differ on masking and study model, while the title and outcome description refer to matched pairs and split-face assessment. Paired measurements can require different uncertainty calculations than independent groups. Readers need a clear account of the analysis structure to assess whether the interval reflects the design.

The outcome is a mean score on a scale defined by ordered severity categories. Reporting the mean and standard deviation is useful for a concise group comparison, but does not show how scores are distributed across categories. Category counts or other distributional summaries would answer complementary questions. The registry posts no secondary outcomes or analysis entries.

Finally, the record demonstrates the distinction between descriptive safety counts and a complete comparative safety analysis. The serious-event counts are zero in the listed groups, but event definitions, follow-up details, and the meaning of the separate Systemic entry are not reported. Statistical interpretation depends not only on a point estimate, but also on the design, outcome scale, uncertainty, analysis plan, and completeness of reporting.

15. 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 in the registry record restrict interpretation of this trial. The design descriptions are internally inconsistent: the official title calls the study single-blind and matched-pairs, while the masking entry says double and the model entry says parallel. The primary outcome population is described as split-face. The record does not clarify the intended design or explain how the analysis reflected it.

The stated non-inferiority purpose cannot be evaluated fully because the non-inferiority margin and detailed statistical plan are not reported. The confidence level and method for the reported interval are also absent. Although the registry reports a mean difference, interval, and unadjusted p-value, it does not identify the test, its assumptions, or the contrast direction in explanatory terms.

The record does not report baseline WSRS values, change from baseline, category-level outcome distributions, or secondary outcomes. It lists no analyses. The analysis population, missing-data handling, participant flow, protocol deviations, and sensitivity analyses are not reported. The relationship between enrollment of 58 and the arm denominators of 58 each is not explained, and the arm counts should not be used to infer a number of unique participants in this split-face study.

Safety reporting is limited to affected counts in the listed categories. Event descriptions and causal assessments are not reported; deaths are listed as null, so death information is not reported in the registry record. The relation between the Systemic entry and treatment-arm entries is not specified. The registry also does not report the trial’s sample-size justification, so the planning description should not be treated as evidence of the study’s original design rationale.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Clinical Study to Evaluate the Correction of Wrinkles and Folds and Safety of YVOIRE Classic Versus Restylane in Nasolabial Fold Intradermal Injection — NCT03738020.
• Registry record last updated 2019-12-18; status last verified 2019-11.
• Results first posted 2019-12-18.
• 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.

19. Record Summary

NCT03738020 is a completed randomized, active-controlled study comparing HA IDF (YVOIRE Classic) with Restylane for nasolabial-fold wrinkle correction and safety. The registry records enrollment of 58 and lists the primary outcome as the investigator-evaluated average WSRS score at Week 26 (Visit 7) after final treatment.

The posted means are 2.56 in both arms, with a mean difference of 0.0, an interval from -0.244 to 0.244, and an unadjusted p-value of 1.0. Serious adverse events are reported for zero affected participants in each treatment arm. The record’s design descriptions do not fully agree, and the non-inferiority margin, analysis population, missing-data methods, and statistical plan are not reported in the registry record. Thus, the posted summaries describe the comparison but do not by themselves establish that a non-inferiority criterion was met.