This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for A Study of Two Types of Absorbable Surgical Sutures in the Suturing of Thyroid Surgery Incision (NCT03792737), a randomized na study. The primary outcome is Wound Healing Grade.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT03792737 |
| Phase | NA |
| Condition | Sutures |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Enrollment | 501 |
| Arms in the primary outcome | 3 |
| Lead sponsor | Ethicon, Inc. |
| Results posted | Yes |
2. Clinical Question
Population
People undergoing thyroid surgery with an incision closed using the specified absorbable sutures. The registry record lists enrollment of 501; the reported primary outcome is among participants assessed for wound healing 5-7days after surgery.
Intervention
Two investigational suture combinations were evaluated. One used Spiral PDS Plus for continuous ribbon-muscle suturing; the other used Spiral MONOCRYL Plus for continuous subcuticular suturing. Both combinations also used VICRYL Plus for interrupted platysma suturing and the other listed control suture at the remaining closure layer.
Comparator
The control combination used PDS Plus for continuous ribbon-muscle suturing, VICRYL Plus for interrupted platysma suturing, and MONOCRYL Plus for continuous subcuticular suturing.
Primary question
What percentage of assessed participants had Grade A healing of the surgical incision at 5-7days in each study group? The registry reports group percentages with 95% confidence intervals. A statistical analysis comparing each investigational group with control is not reported in the registry record.
The clinical question concerns two different suture-device combinations rather than a single device considered in isolation. Each investigational combination changes one closure component while retaining the specified sutures at other layers. The comparison therefore addresses the tested combinations and cannot by itself separate the contribution of each suture from the rest of the closure approach.
The registry describes the objective as evaluating efficacy and safety in thyroid surgery. The primary endpoint captures early wound healing, while the posted secondary outcomes include closure time, pain, wound evaluation, and health-related quality of life. These outcomes describe different aspects of the procedure and recovery; they should not be treated as interchangeable measures of the same clinical effect.
3. Trial Design
The registry describes a prospective, multicenter, randomized controlled study with a parallel-group model and double masking. The record lists enrollment of 501 and status as completed. The study began on 2019-04-01, and primary completion is recorded as 2019-12-12. The phase is listed as NA. Ethicon, Inc. is identified as the sponsor.
Three groups are described: two investigational combinations and a control combination. In investigational group 1, Spiral PDS Plus was used for continuous suturing of the ribbon muscles, VICRYL Plus for interrupted suturing of the platysma, and MONOCRYL Plus for continuous subcuticular suturing. Investigational group 2 used PDS Plus for the ribbon muscles, VICRYL Plus for the platysma, and Spiral MONOCRYL Plus for continuous subcuticular suturing. The control group used PDS Plus, VICRYL Plus, and MONOCRYL Plus at those respective closure layers.
Random allocation and double masking are stated in the registry, but the method of sequence generation, concealment of allocation, and practical details of masking are not reported in the registry record. The record does not state whether masking applied identically to participants, clinicians, outcome assessors, or all of them. The protocol’s sample-size justification and the planned statistical analysis are not reported in the registry record.
The primary outcome is Grade A healing of the surgical incision, expressed as a percentage and assessed at 5-7days. The registry also lists secondary outcomes including incision closure time, postoperative incisional pain measured with a visual analogue scale, wound evaluation, and health-related quality-of-life measures. The posted numerical secondary results cover incision closure time, the Modified Hollander Wound Evaluation Scale, and EQ-5D-5L. Numerical results for the other listed secondary measures are not reported in the registry record.
Group counts vary by outcome in the posted results. This can occur when outcome availability differs, but the reasons for the observed counts and the rules used to define each analysis population are not reported in the registry record. Enrollment should therefore not be assumed to be the denominator for every outcome.
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: one subject didn't participate screen visit and randomize, but receive IP(group 2) treatment by mistake. investigator collect his safety information. so in protocol enrollment plan is 501 subjects, but actually received screen and randomization is 500 patients.
Overall Study
| Stage | Investigational Group 1 | Investigational Group 2 | Control groupEdit |
|---|---|---|---|
| STARTED | 166 | 167 | 167 |
| Safety Analysis Set | 162 | 161 | 162 |
| Full Analysis Set | 162 | 160 | 162 |
| COMPLETED | 160 | 159 | 158 |
| NOT COMPLETED | 6 | 8 | 9 |
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: Full Analysis Population(FAS): FAS consists of all the enrolled subjects who were randomized and at least post-baseline effectiveness endpoint evaluation.
| Characteristic | Unit | Investigational Group 1 | Investigational Group 2 | Control groupEdit | Total |
|---|---|---|---|---|---|
| Participants analysed | 162 | 160 | 162 | 484 | |
| Age, Continuous | years | 40.1 (SD 10.66) | 41.2 (SD 10.84) | 40.3 (SD 11.32) | 40.5 (SD 10.93) |
| Sex: Female, Male: Female | Participants | 107 | 118 | 111 | 336 |
| Sex: Female, Male: Male | Participants | 55 | 42 | 51 | 148 |
| Race/Ethnicity, Customized: Han | Participants | 158 | 157 | 155 | 470 |
| Race/Ethnicity, Customized: Other | Participants | 4 | 3 | 7 | 14 |
6. Primary Endpoint
The registry lists the primary outcome as Wound Healing Grade, measured over 5-7days.
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | 95% Confidence Interval |
| Unit | percentage |
| Endpoint classification | not reduced to a single comparison |
The primary endpoint is the percentage of participants with Grade A healing of the surgical incision, assessed 5-7days after surgery. It is a binary healing classification summarized as a proportion: each assessed participant contributes to the count classified as Grade A or not Grade A, and the group result expresses the share classified as Grade A. The registry gives a 95% confidence interval alongside each group percentage to convey uncertainty in that estimated proportion.
Wound healing is used because it directly describes the early condition of the incision following closure. In this study, it provides an outcome aligned with the stated objective of evaluating suture-device efficacy and safety in thyroid surgery. It is distinct from closure time, pain, clinician-rated appearance, and quality of life, which capture other procedural or recovery dimensions.
The endpoint description identifies the measure and assessment timeframe, but the grading criteria for Grade A healing and the assessor procedures are not reported in the registry record. The registry reports group percentages of 99.35% for investigational group 1, 98.73% for investigational group 2, and 99.36% for the control group. Their respective 95% confidence intervals are 96.44 to 99.98, 95.47 to 99.85, and 96.48 to 99.98.
These are group-level estimates, not a reported test of whether one combination differs from another. A treatment comparison, its uncertainty, and an associated inferential analysis for this count outcome are not reported in the registry record. The observed percentages can therefore describe the recorded healing results, but should not be read as proof of equivalence or as evidence of a statistically established difference.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The primary outcome results describe high Grade A healing percentages in all three groups at the specified early assessment. The posted estimates are 99.35% for investigational group 1, 98.73% for investigational group 2, and 99.36% for control. The 95% confidence intervals are relatively broad at their lower ends compared with the point estimates, reflecting uncertainty around the group proportions despite the high estimates. The intervals overlap substantially.
Those observations are descriptive. The registry does not report a formal comparison of either investigational combination against control for the primary count outcome, nor does it report a prespecified noninferiority or equivalence margin. Overlapping confidence intervals do not establish equivalence, and the point estimates alone cannot determine whether a difference is statistically or clinically meaningful. The study’s primary comparative conclusion is therefore not reported in the registry record.
The posted secondary continuous-outcome comparisons are recalculated, simple unadjusted comparisons using the group summary statistics. For incision closure time, the reported mean differences versus control are -0.349 for investigational group 1 and -0.436 for investigational group 2, with respective 95% confidence intervals of -1.078 to 0.380 and -1.153 to 0.281. Both intervals include zero. The unadjusted p-values are 0.348 and 0.234.
For the Modified Hollander Wound Evaluation Scale, the mean difference for investigational group 1 is 0.1, with a 95% confidence interval of -0.007 to 0.207 and an unadjusted p-value of 0.068. The reported mean difference for investigational group 2 is 0.0, with a 95% confidence interval of -0.091 to 0.091 and an unadjusted p-value of 1.0. For EQ-5D-5L, the differences are 0.014 and 0.005, with respective intervals of -0.011 to 0.039 and -0.021 to 0.030; the unadjusted p-values are 0.276 and 0.715. Each of these intervals includes zero. These recalculations do not replace a sponsor analysis; no sponsor-reported analyses are listed, and no discrepancy is flagged in the record.
An interval that includes zero indicates that the posted summary statistics are compatible with no mean difference as well as with differences in either direction at the interval’s stated confidence level. An unadjusted p-value is not the probability that a treatment is effective, nor does a value above a conventional threshold establish that groups are the same. Interpretation also depends on the outcome scale, clinical relevance, design, and analysis plan, which is not reported in the registry record.
Overall, the posted results allow a descriptive account of the primary proportions and secondary group summaries. They do not provide a reported primary comparative analysis, a stated decision threshold for clinically important differences, or an adjustment for the multiple outcomes and comparisons. The results should consequently be read as a limited set of registry-reported estimates rather than as a definitive ranking of the suture combinations.
9. Statistical Methods Explained
The posted results mix a proportion endpoint with continuous outcomes. Their summaries and comparisons answer different statistical questions, and the level of inferential detail varies across outcomes. The registry lists the primary healing percentages with confidence intervals, while the secondary mean differences and associated tests are simple, unadjusted recalculations from posted summary statistics. No sponsor-reported analyses are listed.
What does a confidence interval communicate?
A confidence interval describes the uncertainty around an estimated quantity under the statistical procedure used to form it. For the primary outcome, each interval accompanies a group percentage and indicates a range of values compatible with the observed data and the interval method. It is not a range containing every participant’s outcome, and it is not a probability statement that the fixed underlying proportion lies in the displayed interval.
For continuous outcomes, the confidence intervals for mean differences describe uncertainty in the estimated group contrast. A range crossing zero includes no mean difference, while also allowing values on either side. That does not by itself demonstrate equivalence: equivalence requires a prespecified margin and a suitable analysis. Neither a margin nor a primary inferential comparison is reported in the registry record.
How should group means and standard deviations be read?
A mean is a measure of the group’s average outcome. A standard deviation describes variation among observations around that group mean; it is not the uncertainty in the mean and is not a confidence interval. The posted group summaries give means and standard deviations for incision closure time, the Modified Hollander Wound Evaluation Scale, and EQ-5D-5L. The group sizes used in those summaries are outcome-specific, so the enrollment figure should not be substituted as the denominator for every outcome.
The recalculated mean differences compare each investigational group with control. Their signs depend on the subtraction order used for the contrast. A positive or negative sign should not be called beneficial without knowing how the outcome scale is oriented and what direction represents a preferable result. The registry’s outcome descriptions do not establish a clinically important difference for these measures.
What do the unadjusted p-values mean?
The listed p-values are unadjusted values for simple comparisons derived from posted group summaries. They assess compatibility of the data with a no-difference model under the assumptions of the comparison. They are not probabilities that the null hypothesis is true, and they do not measure the size or clinical importance of an effect. Because the comparisons are unadjusted, they do not account for the number of outcomes and contrasts considered.
These recalculations are not the sponsor’s analysis. The record lists no sponsor-reported analyses for the posted secondary results. The registry record does not report the original analysis plan, any covariate adjustment, or whether the sponsor used a different model or analysis population. If a sponsor analysis were to conflict with a recalculation, the sponsor’s own analysis would take precedence; the record does not flag a discrepancy.
Why does over-dispersion matter for count outcomes?
General statistical explanation: proportion data arise from counts, and methods often rely on assumptions about how much variability those counts have. If observations vary more than the model expects, that is called over-dispersion. Standard errors can then be too small if the extra variability is ignored, making confidence intervals too narrow and tests too optimistic. The record does not report a model-based comparison for the primary count outcome, so no claim about its handling of over-dispersion can be made.
How should planning illustrations be interpreted?
Planning illustrations based on an observed effect are hypothetical design calculations, not evidence about the achieved power of this completed study. They show how a future two-arm study’s required participants per arm would change if the target effect were a stated fraction of the observed effect, under the stated assumptions. The assumptions listed for these illustrations are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They do not establish the original trial’s design rationale, and the original sample-size justification is not reported in the registry record.
Observed power should not be inferred from these planning quantities. In particular, an observed effect from a completed study is uncertain, and using it as the target for a new design can produce unstable planning estimates. The illustrations are useful for showing the sensitivity of future sample-size requirements to the assumed effect, but they do not repair the absence of a reported primary analysis or establish what size of effect matters clinically.
10. Multiplicity, Missing Data and Analysis Populations
The registry lists multiple secondary outcomes and more than one investigational-versus-control comparison for the posted continuous measures. Testing several outcomes and contrasts creates a multiplicity issue: when each test is considered separately without adjustment, the overall chance of at least one chance finding can increase. The registry record does not report whether a hierarchy of outcomes, multiplicity adjustment, or another strategy for controlling this issue was prespecified.
The posted secondary p-values are unadjusted recalculations. They should not be interpreted as confirmatory evidence across the full family of outcomes. No correction should be presumed, and no adjusted p-values or simultaneous confidence intervals are reported in the registry record. The record also does not state which secondary measures were intended to support formal conclusions and which were exploratory.
Missing-data handling is not reported in the registry record. Although the number of participants contributing to summaries differs by endpoint, the record does not explain whether those differences reflect missed assessments, exclusions, unavailable measurements, or different analysis definitions. It does not describe imputation, complete-case analysis, sensitivity analyses, or assumptions about participants without observed outcomes. Therefore, the extent and possible influence of missing data cannot be assessed from the posted information.
Analysis populations are also not described in sufficient detail. The record does not state whether results use an intention-to-treat, per-protocol, safety, or other defined population, nor does it provide participant flow or reasons for exclusion. The primary endpoint’s analysis denominator and the rules used to classify participants are not explained beyond the posted group counts. These omissions make it difficult to judge whether the results reflect all randomized participants or a selected subset.
The original statistical plan, sample-size justification, interim-analysis policy, and prespecified decision criteria are not reported in the registry record. In their absence, the posted estimates can be described, but it is not possible to assess their alignment with a fully specified confirmatory analysis plan.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Investigational Group 1 | 4 | 162 | 2.5% |
| Investigational Group 2 | 4 | 161 | 2.5% |
| Control groupEdit | 2 | 162 | 1.2% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Investigational Group 1 | 0 of 162 |
| Investigational Group 2 | 0 of 161 |
| Control groupEdit | 0 of 162 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Investigational Group 1 | 44 of 162 |
| Investigational Group 2 | 46 of 161 |
| Control groupEdit | 50 of 162 |
Most frequent serious adverse event terms
| Event term | Organ system | Investigational Group 1 | Investigational Group 2 | Control groupEdit |
|---|---|---|---|---|
| Papillary thyroid cancer | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 162 | 1 of 161 | 0 of 162 |
| Post procedural haemorrhage | Injury, poisoning and procedural complications | 0 of 162 | 1 of 161 | 1 of 162 |
| Breast adenoma | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 162 | 0 of 161 | 0 of 162 |
| Haemangioma | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 162 | 0 of 161 | 0 of 162 |
| Metastatic lymphoma | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 0 of 162 | 0 of 161 | 1 of 162 |
| Supraventricular tachycardia | Cardiac disorders | 0 of 162 | 1 of 161 | 0 of 162 |
| Asthenia | Gastrointestinal disorders | 1 of 162 | 0 of 161 | 0 of 162 |
| Skin oedema | Skin and subcutaneous tissue disorders | 0 of 162 | 1 of 161 | 0 of 162 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Investigational Group 1 | Investigational Group 2 | Control groupEdit |
|---|---|---|---|---|
| Productive cough | Respiratory, thoracic and mediastinal disorders | 30 of 162 | 32 of 161 | 31 of 162 |
| Cough | Respiratory, thoracic and mediastinal disorders | 27 of 162 | 25 of 161 | 29 of 162 |
| Hypocalcaemia | Metabolism and nutrition disorders | 6 of 162 | 16 of 161 | 16 of 162 |
Serious events with the highest arm-level rate: papillary thyroid cancer (0.6%), post procedural haemorrhage (0.6%), supraventricular tachycardia (0.6%), skin oedema (0.6%), breast adenoma (0.6%).
The registry records serious adverse events among participants considered at risk in each group. Investigational group 1 has 4 serious adverse event-affected participants among 162 at risk; investigational group 2 has 4 among 161 at risk; and the control group has 2 among 162 at risk. Deaths are recorded as 0 in each group. These are recorded counts, not a comparative safety analysis.
The listed serious event terms include Papillary thyroid cancer, Post procedural haemorrhage, Supraventricular tachycardia, Skin oedema, Breast adenoma, and Haemangioma, each shown with 0.6%. The registry does not provide enough detail in the registry record to determine the relationship of each listed term to study treatment or to interpret those terms as a causal pattern.
Serious adverse event counts should be read separately from other adverse events. The record also reports other adverse-event-affected counts of 44 among 162 at risk in investigational group 1, 46 among 161 at risk in investigational group 2, and 50 among 162 at risk in the control group. Differences in counts alone do not establish a treatment-related safety difference. Definitions, event timing, severity detail, and a formal comparative safety analysis are not reported in the registry record.
12. What the Result Does, and Does Not, Mean
The posted data establish what the registry reports for the measured outcomes: group percentages for early Grade A wound healing, group means and standard deviations for selected secondary outcomes, recalculated mean contrasts, and adverse event counts. They offer a descriptive view of the observed results in this study’s three suture-combination groups. The primary percentages are high in each group, and the listed secondary comparisons do not show confidence intervals excluding zero.
Those observations do not establish that the devices are equivalent, that one is superior, or that a particular combination produces a clinically meaningful difference. Such conclusions require an appropriate comparative analysis, prespecified criteria for interpreting effects, and adequate information about the analysis population and missing outcomes. The registry record does not report a formal primary comparison or an equivalence or noninferiority framework.
Likewise, the secondary p-values do not show that there is no difference. A non-significant result can reflect a small effect, imprecise estimation, or both. Confidence intervals help convey the range of uncertainty, but interpretation also depends on what differences would matter to patients and clinicians; the registry does not report thresholds for clinical importance for these measures.
The trial description supports conclusions only about the specific combinations and clinical setting studied. Since each investigational group differs from control at a particular closure layer while sharing other listed sutures, the data do not isolate the effects of each material independently. The registry also does not describe enough about masking procedures, outcome assessment, missingness, or the statistical plan to assess all potential sources of bias.
Safety counts are similarly descriptive. Recorded serious events and deaths are relevant observations, but event counts without a reported comparative safety analysis do not establish that the combinations have the same or different safety profiles. These registry results are therefore best understood as a bounded record of observed outcomes, not as medical advice or a definitive judgment about treatment choice.
13. Why This Trial Matters Statistically
This study illustrates why the type of endpoint matters when interpreting a clinical trial. The primary outcome is a percentage based on a healing classification, whereas the posted secondary comparisons concern group means. Each requires a suitable summary and analysis, and a descriptive group estimate is not automatically a treatment contrast. Here, the registry provides primary group percentages and confidence intervals but no reported formal comparison for that endpoint.
The record also shows why uncertainty and clinical importance should be considered together. A point estimate gives a compact description of the observed data, while a confidence interval conveys precision. Neither alone answers whether a difference matters in practice. Without a prespecified margin or threshold, high healing percentages and overlapping intervals cannot demonstrate equivalence or noninferiority.
Multiple secondary outcomes make interpretation more demanding. Unadjusted comparisons can be useful for exploration, but they do not control the overall error risk across a collection of tests. Registry readers need to distinguish those recalculations from a sponsor-reported confirmatory analysis, especially when the statistical plan and multiplicity strategy are not reported.
Finally, differences in outcome-specific participant counts and the absence of reported analysis populations matter. A result is only as interpretable as its denominator, outcome definition, and missing-data assumptions. This record offers several useful descriptive summaries, but important design and analysis details remain unreported. The statistical lesson is not that the results are uninformative; it is that the strength of a conclusion must match the level of information and analysis documented.
14. 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 are specific to interpreting this registry record. First, the primary outcome is reported as group percentages with confidence intervals, but a direct comparison with control is not reported in the registry record. The clinical grading definition for Grade A healing, assessment procedures, and assessor masking are also not described in the available record. Without those details, reproducibility and risk of assessment bias are difficult to evaluate.
Second, the groups represent combinations of sutures used at different incision layers. The contrast therefore does not isolate every component as an independent intervention. Findings apply to the combinations as described, and cannot identify the effect of a single material without further design or analysis information.
Third, participant counts vary across outcomes, while participant flow, reasons for missing measurements, and analysis-population definitions are not reported in the registry record. The influence of missing data cannot be assessed. The record also does not provide the statistical analysis plan, sample-size justification, primary comparison method, or multiplicity strategy.
Fourth, several listed secondary measures do not have numerical results in the registry record. The posted mean comparisons are simple unadjusted recalculations rather than sponsor-reported analyses. Although no discrepancy is flagged, they do not substitute for a prespecified analysis and should be interpreted cautiously, particularly in the context of multiple outcomes.
Finally, the registry entries do not report thresholds for clinically important differences or a formal equivalence framework. The observed estimates alone cannot establish that the suture combinations are meaningfully alike or different. These limitations constrain the conclusions that can be drawn from the posted record, even though the record does provide useful descriptive results.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: A Study of Two Types of Absorbable Surgical Sutures in the Suturing of Thyroid Surgery Incision — NCT03792737.
- Registry record last updated 2022-04-05; status last verified 2022-02.
- Results first posted 2021-01-29.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
NCT03792737 is a completed, prospective, multicenter, randomized, double-masked, parallel-group study sponsored by Ethicon, Inc. The registry lists enrollment of 501, phase NA, a start date of 2019-04-01, and primary completion on 2019-12-12. It evaluated two investigational absorbable suture combinations against a control combination in thyroid surgery.
The primary endpoint was the percentage of participants with Grade A surgical-incision healing at 5-7days. Group percentages and 95% confidence intervals are posted, but a formal primary comparison is not reported in the registry record. Numerical secondary results are posted for incision closure time, the Modified Hollander Wound Evaluation Scale, and EQ-5D-5L; other listed secondary results are not reported in the registry record.
The registry records serious adverse event counts, other adverse event counts, and 0 deaths in each group. Analysis populations, missing-data methods, the original statistical plan, and a multiplicity strategy are not reported in the registry record. Consequently, the reported results are primarily descriptive, and the recalculated secondary comparisons should not be mistaken for sponsor-reported confirmatory analyses.