Influence of Flat-knitted Compression Stockings Class I and II on Venous Malformations: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Influence of Flat-knitted Compression Stockings Class I and II on Venous Malformations (NCT04637997), a randomized na study. The primary outcome is Volume Difference of Malformation to Baseline (no Compression) While Wearing Compression Stockings Class I and II Determined by MRI.

2. Clinical Question

3. Trial Design

The registry describes a randomized, double-masked crossover study of flat-knitted compression stockings class I and class II for venous malformations. Enrollment is recorded as 18. The trial status is completed. The registry lists a start date of 2017-10-01 and a primary completion date of 2019-03-01.

Participants were assigned to one of two treatment sequences. One sequence wore class I between investigation day 28 and day 56, then class II between day 56 and day 84. The other sequence wore class II first, followed by class I. Thus, the design permits comparison of the two compression classes within a crossover framework, while the registry’s posted summary comparison reports a mean difference between classes. It does not report a sequence-adjusted or period-adjusted analysis.

The primary endpoint is the volume difference of a malformation from baseline without compression while wearing each class, determined by MRI. Its stated timeframe is one day. The registry identifies the primary outcome population as all randomized participants who received both classes of stockings. The arm summaries each report 18 observations, but the record does not explain how observations from the crossover periods were handled in the posted summary statistics.

The record does not report the original sample-size justification, the trial’s prespecified statistical analysis plan, or the handling of period or sequence effects. It also does not describe the masking procedures in detail. These omissions limit what can be concluded about how the planned analysis relates to the registry’s displayed unadjusted 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: Intention-to-treat population (ITT): all randomized participants that received flat-knitted compression stockings class I and class II after the randomization.

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 Volume Difference of Malformation to Baseline (no Compression) While Wearing Compression Stockings Class I and II Determined by MRI, measured over one day.

The primary endpoint is the MRI-determined volume difference of a venous malformation from baseline without compression while wearing class I and class II stockings. Volume is reported in millilitres. The endpoint is continuous: each measurement can take a range of values rather than being assigned to a category. The registry specifies the mean and standard deviation as the summary measures.

MRI provides a non-invasive way to assess malformation volume, according to the endpoint description. Comparing measurements obtained while wearing compression with a no-compression baseline is intended to quantify how the measured volume differs under each condition. Comparing the two compression classes addresses whether their reported mean volume differences vary from one another.

The posted results give the mean volume difference for each class and a mean difference comparing class II with class I. They do not give the baseline mean, the class-specific change from baseline as a separate result, or a confidence interval for either class-specific estimate against baseline. Therefore, the reported comparison directly describes the difference between classes, not the evidence for change from baseline under either class. The registry’s stated timeframe is one day, but it does not further explain the measurement schedule within that timeframe.

7. Results Posted in the Registry

• Compression Stockings Class II: mean 23.70 versus 16.38 on control; difference 7.32 (95% CI -7.24 to 21.88), standardized effect d = 0.33; z-test p = 0.324.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous, and the registry summarizes it using a mean and standard deviation. A mean describes the arithmetic average of observations. A standard deviation describes how dispersed observations are around that average. It is not the standard error of the mean and does not itself show how precisely the mean has been estimated.

The registry’s comparison is a mean difference, with class I as the reference and class II as the comparison. The estimate of 7.32 ml is the difference between the posted class means. A positive estimate in this direction means the reported class II mean is greater than the reported class I mean. The estimate alone does not indicate whether that difference is statistically distinguishable from zero or clinically important; those questions require uncertainty and substantive context.

What does the confidence interval describe?

A confidence interval expresses uncertainty around an estimated quantity. Under the assumptions of the analysis, a 95% confidence interval is produced by a method that, over repeated studies, would include the underlying quantity at the stated rate. It does not mean there is a 95% probability that this particular interval contains the true value. For the posted mean difference, the interval extends from -7.238 to 21.88 ml. Its inclusion of zero indicates that the data do not rule out no mean difference at the conventional two-sided significance threshold associated with the reported p-value.

How should the p-value be read?

The p-value is 0.324 and is identified as unadjusted. A p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the analysis assumptions were true. It is not the probability that the null hypothesis is true, and it does not measure the magnitude of the observed difference. A relatively large p-value can occur when an estimate is imprecise, as can happen when the data do not sharply distinguish among plausible values.

Why does the crossover design matter?

In a crossover study, participants receive both conditions in a planned order, so measurements from a participant may be related. General statistical practice accounts for this dependence rather than treating every observation as independent. Period effects, sequence effects, and possible carryover can also matter in crossover designs. These are general considerations, not claims that any such effect occurred in this trial. The registry record does not report the statistical model or whether these factors were addressed. Consequently, the displayed mean difference and confidence interval should be interpreted as the posted unadjusted comparison, without assuming that they account for crossover features.

What does over-dispersion mean in general?

Over-dispersion is a concern for outcomes such as counts when the observed variability exceeds what a chosen model assumes. It is not the main issue for this continuous volume outcome. For continuous measurements, the standard deviation communicates observed spread, while an appropriate analysis must still reflect the design and dependence structure. The registry gives arm-level standard deviations but does not report a model-based assessment of distributional assumptions.

Which analysis details are available?

The registry identifies the primary outcome population as the intention-to-treat population consisting of all randomized participants who received both stocking classes. It reports a mean difference, confidence interval, and unadjusted p-value. It does not report the trial’s full statistical analysis plan, a model specification, covariate adjustment, missing-data methods, or an analysis accounting explicitly for treatment order or period. The record also reports no analysis entries. This absence does not establish that no analyses were performed; it means the registry record does not report them.

The arm-level estimates are 16.38 ml for class I and 23.7 ml for class II, each with 18 observations. The comparison includes an estimated pooled standard deviation of 22.28 ml and a standardized effect estimate of 0.329. These are descriptive or derived summaries, not substitutes for the original analysis plan. In particular, a standardized effect does not convey the endpoint’s scale as directly as the difference in millilitres, and it does not resolve limitations arising from the crossover design or uncertainty in the estimate.

10. Confidence Intervals and Precision

The estimated mean difference comparing class II with class I is 7.32 ml. Its 95% confidence interval ranges from -7.238 to 21.88 ml. Because the interval crosses zero, the posted result is compatible with no difference in mean volume difference between classes. It is also compatible with a negative difference, where the class II mean is lower, and with a positive difference, where it is higher. The interval therefore does not pinpoint the direction or size of a class-to-class difference with precision.

The interval is wide relative to the point estimate. This indicates substantial statistical uncertainty in the comparison. The p-value of 0.324 is consistent with that uncertainty, but the interval is more useful for seeing the range of values that remain compatible with the data under the analysis assumptions. Neither measure establishes that the classes are equivalent: an equivalence conclusion requires a prespecified margin and an analysis designed for that question, neither of which is reported in the registry record.

The arm standard deviations are 18.28 ml for class I and 25.67 ml for class II. These describe variability among the reported measurements rather than precision of the estimated difference. The record does not provide a paired standard deviation or a detailed crossover model, so the contribution of within-participant correlation to the comparison’s precision cannot be assessed from the posted summary alone.

The confidence interval concerns the difference between classes, not either class’s contrast with no compression. A baseline comparison and its uncertainty are not reported. The distinction matters because an uncertain class-to-class comparison does not answer whether measurements under either class differ from baseline.

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 illustrations give participants per arm, not total events. They are based on the observed effect and assume a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is set as a stated fraction of the observed effect. The trial’s own original sample-size assumptions and justification are not reported in the registry record.

For planning for 100% of the observed effect, the illustration lists 146 participants per arm for 80% power and 195 participants per arm for 90% power. For planning for 75% of the observed effect, it lists 259 participants per arm for 80% power and 347 participants per arm for 90% power. For planning for 50% of the observed effect, it lists 582 participants per arm for 80% power and 779 participants per arm for 90% power.

In plain language, the 80% power column represents the planned number of participants per arm under the stated assumptions for a study designed to have an 80% chance of detecting the chosen effect if that effect is real. The 90% column uses the same idea with a higher target chance of detection. Smaller effects are harder to detect, so the illustrations require more participants when the target effect is a smaller fraction of the observed effect. These figures are planning illustrations, not observed power.

The calculations use a two-arm equal-allocation assumption, while the trial itself is described as a randomized crossover. The registry does not report the original design assumptions or show that these planning illustrations account for pairing, treatment sequence, or period effects. They should therefore be read as hypothetical planning references under their stated assumptions, not as a reconstruction of the trial’s original design.

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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 7.320; pooled standard deviation σ = 22.283.
2. n = 2 × (1.96 + 0.842)² × 22.283² / 7.320² = 145.5, rounded up to 146 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
delta <- 7.32                      # observed difference in means
sigma <- 22.283483794057                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(4637997)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 146 (80% power), 195 (90% power)
 75% of observed effect: n per arm = 259 (80% power), 347 (90% power)
 50% of observed effect: n per arm = 582 (80% power), 779 (90% power)
power.t.test: 146.4 
Simulated power at n = 146 per arm: 0.797 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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 three outcome measures and one posted secondary outcome. The secondary outcome is quality of life at baseline without compression compared with classes I and II, measured with the Short Form-12 Health Survey at day 56 or day 84. The registry does not provide a posted result for that secondary outcome in the record, so its estimate and uncertainty cannot be described.

The record reports zero analysis entries. This does not show that no analyses were conducted; it means no analysis details are reported in the registry record. The record does not describe a multiplicity adjustment, a hierarchy of outcomes, or which analyses were prespecified. Multiple outcomes or comparisons can increase the chance of at least one apparently notable result when many tests are conducted. Whether that issue affects interpretation depends on the planned analysis and the comparisons actually made, which are not reported.

The primary outcome population is defined as all randomized participants who received both classes of stockings. That definition is reported, but the record does not give the number of participants with observed primary outcome measurements, explain whether all eligible measurements were included, or describe how missing measurements were handled. It does not report reasons for missingness, imputation methods, or sensitivity analyses. The enrollment and arm summaries alone do not establish whether missing primary outcome data occurred.

The crossover design also raises analysis-population questions, including how observations from each treatment period were paired and whether sequence or period was considered. The registry does not report those details. No specific missing-data mechanism or statistical adjustment should be assumed from the posted summaries. These gaps limit assessment of the robustness of the result and the family of comparisons to which the unadjusted p-value applies.

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 adverse-event summaries report no serious adverse events for class I and no serious adverse events for class II. Each group lists 18 participants at risk, with zero affected by a serious adverse event. The record also lists zero other adverse events in each group and zero deaths.

These figures describe the registry’s recorded counts; they do not establish that no adverse events occurred outside the reported categories or observation periods. The record does not provide event descriptions, follow-up duration for safety, or details about how events were collected and attributed in the crossover periods. It also does not report a comparative statistical analysis of adverse events.

With no serious events recorded in either group, the posted counts do not estimate a comparative risk difference with useful precision. The absence of recorded events in these groups should not be interpreted as proof that serious events cannot occur. The safety summary is a description of the registry record, not a basis for medical advice or a broad safety conclusion.

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

The posted primary-outcome summaries show mean volume differences of 16.38 ml while wearing class I stockings and 23.7 ml while wearing class II stockings. The unadjusted comparison estimates that the class II mean is 7.32 ml higher than the class I mean. Its 95% confidence interval, from -7.238 to 21.88 ml, includes zero and spans differences in either direction. The p-value is 0.324.

These figures do not provide precise evidence of a difference between classes in the posted comparison. They also do not establish equivalence. A failure to distinguish the classes in this comparison is not the same as demonstrating that their effects are the same; the confidence interval allows a range of possible differences, and the registry does not report an equivalence margin or an equivalence analysis.

The endpoint is defined relative to baseline without compression, but the posted comparison is between class I and class II. Baseline outcome values and class-specific baseline contrasts are not reported. Therefore, these results cannot by themselves answer whether either compression class changes malformation volume relative to no compression.

The trial’s crossover design is relevant to interpretation because measurements under both classes may be related within a participant. The registry does not report whether the comparison accounts for that relationship, treatment period, or sequence. The posted results should be understood as the registry’s unadjusted comparison rather than assumed to be a fully specified crossover analysis.

The findings are limited to the recorded sample and endpoint. The registry does not report the original sample-size rationale, missing-data methods, or a detailed statistical plan. No clinical recommendation follows from the summary statistics alone. The result is an estimate with substantial uncertainty, not a definitive statement about treatment benefit, lack of benefit, or safety.

16. Why This Trial Matters Statistically

This trial raises a useful statistical distinction between the question posed by an endpoint and the comparison actually reported. The primary endpoint refers to volume difference from baseline without compression under each stocking class. The posted inferential comparison is class II versus class I. Those comparisons answer different questions, and the absence of reported baseline contrasts means that the central no-compression comparison cannot be assessed from these results.

The randomized crossover structure is also important. Crossover designs can make efficient use of within-participant comparisons when repeated measurements are analysed in a way that reflects their dependence. Randomized treatment order is reported, but the registry does not specify whether the posted estimate accounts for within-participant pairing, treatment period, or sequence. Recognizing this gap prevents readers from treating a simple summary comparison as proof of a design-adjusted result.

The interval and point estimate illustrate why statistical significance alone is not an adequate summary. The confidence interval includes zero and allows differences in both directions, while the point estimate is only one of the values compatible with the data. The arm-level standard deviations also show that measurements vary appreciably. Together, these features emphasize the value of reporting uncertainty and analysis details alongside means.

Finally, the sample-size illustrations are conditional planning exercises based on the observed effect, not evidence about the trial’s original design or its achieved power. They make clear that planning for smaller effects requires larger samples under the stated assumptions. The registry does not report the original sample-size rationale, so the illustrations cannot establish whether the study was designed to detect a clinically meaningful difference.

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.

The reported enrollment is 18, and the confidence interval for the class-to-class mean difference is wide. The result is therefore imprecise, with compatible values ranging from a negative to a positive difference. The registry does not report a clinically important difference threshold, so the practical importance of values within that interval cannot be judged from the record.

The endpoint description concerns change from baseline without compression, but only the class-to-class comparison and the arm-level means are posted. Baseline values and separate estimates of each class compared with baseline are not reported. This prevents direct interpretation of the stated baseline question.

Although the trial is randomized and crossover, the statistical model is not reported. The record does not say whether the summary comparison accounts for within-participant correlation, period, sequence, or carryover. These features can affect estimates and uncertainty in crossover analyses. This is a limitation in the information available, not evidence that a particular problem occurred.

The registry does not report missing-data handling, the original sample-size assumptions, a full statistical analysis plan, or multiplicity procedures. It lists three outcome measures but posts one secondary outcome description without results in the summarized record. Details of masking and the timing of MRI assessments are also not reported beyond the stated one-day timeframe.

The adverse-event summary records zero serious adverse events in each group, but event ascertainment and safety follow-up details are not reported. These limitations mean the displayed statistics should be read as a concise registry summary rather than a complete account of trial conduct and analysis.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Influence of Flat-knitted Compression Stockings Class I and II on Venous Malformations — NCT04637997.
• Registry record last updated 2021-03-16; status last verified 2021-03.
• Results first posted 2021-03-16.
• 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, double-masked crossover study of flat-knitted compression stockings class I and class II for venous malformations. Enrollment is 18. Participants were assigned to sequences that wore one class during the first treatment period and the other during the next period.

The primary endpoint is MRI-measured volume difference from baseline without compression while wearing each class. The posted mean difference comparing class II with class I is 7.32 ml, with a 95% confidence interval from -7.238 to 21.88 ml and an unadjusted p-value of 0.324. The interval includes zero and indicates substantial uncertainty about the class-to-class difference.

The record does not report baseline contrasts, the crossover analysis model, missing-data methods, or the original sample-size rationale. The posted comparison should not be treated as an answer to whether either class differs from no compression.