Multi-national, Safety and Performance Study of New Ostomy Product Compared to Standard Care: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Multi-national, Safety and Performance Study of New Ostomy Product Compared to Standard Care (NCT01517178), a randomized phase 3 study. The primary outcome is Degree of Output Under the Base Plate (Leakage)..

2. Clinical Question

3. Trial Design

The registry describes a phase 3, randomized, open-label, controlled, comparative, multinational crossover study. In a crossover design, participants receive or use more than one study condition at different times, so each person may contribute information under both conditions. The record names the new ostomy base plate and standard-care base plate as the two products. It does not report the randomized sequence assigned to participants or the details of how sequence was balanced.

The study description specifies a one-week run-in on the new base plate and two test periods, each lasting two weeks. Participants were to change their base plates on an as-needed basis and follow their usual changing pattern throughout the study. Investigator-collected information was planned at the inclusion, crossover and termination visits; participants were also to complete questionnaires during the test periods. The primary outcome timeframe is each product’s two-week assessment period.

The registry lists enrollment of 33 and a study target of 100 in the description. The posted primary outcome includes 22 participants for each product group. These figures describe different record elements; the registry does not explain the relationship between the planned target, enrollment and outcome-group counts. The study is marked terminated. Its listed start and primary-completion dates are 2011-05 and 2011-06. The reason for termination is not reported in the registry record.

Because the study was open-label, masking was not used. The record does not state whether outcome assessors were masked. It also does not report the reasons for the selected crossover schedule, how carryover between periods was addressed, or what statistical approach was planned for repeated measurements within participants.

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: A total of 33 subjects were enrolled in the trial. Of these, 6 discontinued during the New ostomy base plate run-in period prior to period 1 and were excluded from the Intention-To-Treat analysis set (no performance data obtained). 27 subjects comprised the intention-to-treat population.

Period 1

Reasons for not completing this period:

Period 2

Reasons for not completing this period:

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 Degree of Output Under the Base Plate (Leakage)., measured over Each test product was assessed for 2 weeks..

The primary endpoint is the degree of output under the base plate, described as leakage. It is a continuous measure recorded on a 24-point leakage-assessment scale. A score of 0 indicates no leakage and a score of 24 indicates maximum leakage. The registry reports the mean and standard deviation for each product group, with each product assessed over two weeks.

The endpoint directly represents the study’s stated primary objective: to document whether the new base plate reduces leakage under the base plate compared with standard-care base plates. A numeric scale can capture gradations in the degree of leakage rather than classifying participants only as having or not having leakage. Reporting a mean summarizes the group’s average score, while the standard deviation describes the spread of individual scores around that mean.

For this scale, a lower score corresponds to less leakage, based on the stated scale anchors. The observed mean was 6.5 for the new base plate and 4.6 for standard care. The registry’s estimated mean difference, expressed as new base plate compared with standard care, was 1.9. Thus, the posted means are numerically higher for the new base plate. The confidence interval is wide enough to include values on either side of zero, so the posted estimate is not precise about the direction or size of the underlying difference.

The registry does not provide a separate definition of how the score was derived from observations, who completed the assessment, or how repeated assessments during a test period were combined. Those measurement details are not reported in the registry record.

7. Results Posted in the Registry

• New Ostomy Base Plate: mean 6.50 versus 4.60 on control; difference 1.90 (95% CI -0.65 to 4.45), standardized effect d = 0.44; z-test p = 0.144.

8. Statistical Interpretation

9. Statistical Methods Explained

What does the mean difference represent?

The mean difference compares the average leakage score under the new base plate with the average under standard care. The registry reports the new-base-plate mean as 6.5 and the standard-care mean as 4.6, and reports their mean difference as 1.9. The sign and direction matter: the comparison is defined as new base plate relative to standard care. On the stated scale, higher scores represent more leakage, so a positive difference points toward a higher average score under the new base plate in the posted data.

A mean is a summary of the group’s observations. It does not imply that every participant had a score equal to that value, nor does it show the distribution of individual responses. The standard deviations, 5.0 for the new base plate and 3.5 for standard care, describe variability in the reported measurements. They are not confidence intervals and do not indicate the precision of the mean difference by themselves.

What does the p-value say?

The registry reports an unadjusted p-value of 0.144. In general, a p-value describes how unusual data at least as discrepant as those observed would be under a specified null model, assuming that model and its assumptions hold. It is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of a difference. The label unadjusted means the posted value is not identified as adjusted for multiple comparisons. The record does not state whether any adjustment was planned or used.

A p-value above a conventional significance threshold does not establish that the products have the same mean. To assess what differences remain compatible with the data, the confidence interval is also needed. In this trial, the interval includes zero and extends into positive and negative values. That combination indicates uncertainty about both the direction and magnitude of the mean difference.

Why does the crossover structure matter?

General statistical explanation: in a crossover study, the same participant can be assessed under more than one condition. Measurements from one person tend to be related, so an analysis can use the within-person difference rather than treat all observations as unrelated. That approach can account for stable differences between participants, but it depends on the design and analysis being appropriate. Crossover studies may also require attention to period effects, treatment sequence and carryover, where effects or experiences from one period influence a later period.

The registry describes a crossover design and two product test periods, but the posted primary summaries do not give a paired difference, its standard error, the within-person correlation, or a model specification. The analysis method used for the posted comparison is therefore not reported in the registry record. It cannot be confirmed from these summaries whether the crossover pairing or period structure was included in the calculation.

What is the role of the standard deviation?

General statistical explanation: the standard deviation describes how dispersed measurements are around their mean. Larger dispersion makes a mean less precise for a given sample size, all else equal. Here, the reported standard deviations are 5.0 and 3.5, alongside group counts of 22 for each product. However, in a crossover comparison, marginal group standard deviations alone do not reveal the dispersion of each participant’s difference between products. The missing paired information is therefore important when judging the precision of the crossover contrast.

General statistical explanation: over-dispersion means that observed variability is greater than a statistical model expects. When a model understates variability, standard errors can be too small and intervals too narrow. The registry does not report an over-dispersion assessment or a model for the endpoint, so no conclusion about that issue can be made for this trial.

What can be inferred from the confidence interval?

A confidence interval gives a range of values compatible with the data under the method used to calculate it. In repeated use of the same method under its assumptions, intervals constructed at a stated confidence level would cover the true parameter at the corresponding long-run rate. The registry does not state the confidence level or method used for the posted interval. The reported interval crosses zero, so the results do not sharply distinguish a negative from a positive mean difference. It also reaches a positive upper limit of 4.45, which leaves room for a notable difference in that direction.

The registry record lists the interval and p-value but does not give a full statistical analysis plan, model details, handling of missing observations, or analysis population. Those omissions prevent a detailed audit of how the estimate and uncertainty were obtained. General statistical concepts explain how such measures are usually interpreted; they do not establish which exact method the study used.

10. Confidence Intervals and Precision

The registry reports a mean difference of 1.9 for new base plate compared with standard care, with a confidence interval whose lower limit is negative and whose upper limit is 4.45. The interval therefore includes zero and covers both possible directions of the difference. In relation to the scale, that means the posted data do not pin down whether the mean score is higher or lower under the new base plate in the underlying study population. The point estimate alone gives a single best estimate under the reported calculation, but it should not be read without the interval.

The interval is broad relative to the point estimate, indicating limited precision in the estimated contrast. Its span permits a range of plausible values, rather than tightly locating the mean difference. The registry does not state the confidence level or the method used to calculate this interval. In addition, it does not show a paired confidence interval or report the within-participant variability expected to be relevant for a crossover analysis. The interval can therefore be described as posted, but its assumptions cannot be independently assessed from the available record.

The reported standard deviations are 3.5 for standard care and 5.0 for the new base plate. Those figures show that individual scores varied around the group means. They do not, by themselves, determine the precision of a crossover contrast because the relationship between each participant’s measurements under the two products is not reported.

The p-value of 0.144 is consistent with the interval’s inclusion of zero, but it does not resolve the uncertainty. Neither measure proves that there is no difference. The registry summaries support a cautious reading: the estimated mean is higher for the new base plate, while the confidence interval allows effects in either direction and does not establish a precise difference.

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 sample-size calculations are planning illustrations based on the observed effect in the posted results, not the original trial design. The registry states the assumptions: a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect set at a stated fraction of the observed effect. The entries are participants per arm, not total events. The record’s note about total events applies to time-to-event calculations; this outcome is continuous.

The 80% power column describes the number of participants per arm that the illustration estimates would be needed for an 80% chance of detecting the selected effect if that effect were the true one and the planning assumptions held. The 90% column gives the corresponding per-arm count for a higher target chance of detection. These are design-planning quantities, not descriptions of the study’s observed power. This is not observed power.

For planning based on 100% of the observed effect, the illustration gives 81 participants per arm for 80% power and 109 per arm for 90% power. For 75% of the observed effect, it gives 144 per arm for 80% power and 193 per arm for 90% power. For 50% of the observed effect, it gives 324 per arm for 80% power and 434 per arm for 90% power. Smaller effects require more participants to detect under the same assumptions, which is why the illustrated counts increase as the assumed effect gets smaller.

These figures should not be interpreted as a reconstruction of the original enrollment target or as a recommendation. The registry does not report the trial’s original sample-size justification or the assumptions used to set its planned target. The calculations are based on the observed contrast and do not account, in the posted description, for a crossover-specific paired analysis. Their assumptions and scope differ from the study’s own design rationale, which is not reported in the registry record.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 1.900; pooled standard deviation σ = 4.316.
2. n = 2 × (1.96 + 0.842)² × 4.316² / 1.900² = 81.0, rounded up to 81 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 <- 1.9                      # observed difference in means
sigma <- 4.31566912540802                     # 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(1517178)
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 = 81 (80% power), 109 (90% power)
 75% of observed effect: n per arm = 144 (80% power), 193 (90% power)
 50% of observed effect: n per arm = 324 (80% power), 434 (90% power)
power.t.test: 82 
Simulated power at n = 81 per arm: 0.794 (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 study description names secondary objectives concerning performance and safety, but the registry posts no secondary outcome results. It lists one outcome measure and no analyses. The record therefore does not give secondary estimates or tests with which to assess their results. The stated primary hypothesis concerns reduction in leakage under the base plate.

Multiplicity arises when several outcomes, time points, comparisons or subgroup analyses are tested. In general, testing many hypotheses can increase the chance of at least one apparently unusual result. Methods to manage that issue may include defining a primary outcome in advance or adjusting inference across a family of tests. The registry does not report a multiplicity strategy, whether secondary outcomes were formally tested, or whether any adjustment was planned or applied. The posted p-value is identified as unadjusted.

Missing-data handling is also not described. The record does not report how incomplete questionnaires, missed visits, unavailable measurements or withdrawals were handled, or whether any imputation method was used. The study is marked terminated, but the reason for termination and its consequences for data collection are not reported. The posted outcome counts are 22 for each product group; the relationship of those counts to total enrollment of 33 and the target of 100 is not explained.

The analysis population is not reported in the registry record. It is not stated whether the posted result includes all randomized participants, only participants completing both product periods, or another defined group. Nor does the record explain whether participants were analyzed according to their randomized sequence, actual product exposure, or some other rule. These details matter particularly for a crossover study, where the availability of measurements under both conditions and the handling of period sequence can affect the analysis.

Without a statistical plan or analysis-population definition, it is not possible to determine whether the posted result follows the intended analysis, how missing observations may have affected it, or how any additional testing was handled. These are gaps in the record, not evidence that a particular procedure was or was not used.

14. 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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: infection in parastomal prosthetic mesh (3.3%).

The registry reports serious adverse events for 0 of 21 participants at risk in the standard-care group and 1 of 30 participants at risk in the new-base-plate group. These counts describe the recorded serious events and the listed groups at risk; they do not establish that the product caused or prevented an event. The record does not provide event timing, participant-level details, relatedness assessments, or an explanation for the difference in group counts at risk.

The registry also lists “Infection in parastomal prosthetic mesh” as a serious adverse-event term with a frequency of 3.3%. The record does not provide further clinical context for that term. No deaths are listed in the adverse-event data. The absence of a listed death count should not be interpreted as a broader safety conclusion beyond what the registry reports.

Other adverse events are reported for 0 of 21 participants at risk in the standard-care group and 13 of 30 in the new-base-plate group. Serious and other adverse events are different reporting categories; the latter count should not be read as a count of serious events. The registry summaries do not give the full event listings, severity details for other events, or an account of how events were collected. Small group counts and the limited detail in the record make the safety summaries descriptive rather than a comprehensive comparative assessment.

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

The registry’s primary result is a mean leakage score of 6.5 for the new ostomy base plate and 4.6 for standard care, with 22 participants reported in each outcome group. The mean difference, defined as new base plate compared with standard care, is 1.9. Since lower scores correspond to less leakage on the stated scale, the observed averages are numerically higher under the new base plate. The interval around the difference includes zero and extends in both directions, and the unadjusted p-value is 0.144.

These statistics do not establish that the products have the same mean, nor do they establish a reliable difference in either direction. A non-significant p-value is not evidence of equivalence. An equivalence conclusion would require a defined equivalence margin and an analysis designed to evaluate it; such information is not reported in the registry record. The confidence interval is more informative about uncertainty than the point estimate alone, but the registry does not state its confidence level or method.

The study is described as randomized and crossover, but the posted result does not identify a paired analysis. The outcome-group counts, enrollment count and planned target also differ, and the record does not explain the relationship among them. The study is marked terminated, with no termination reason reported. These features restrict interpretation of how completely the posted summaries reflect the intended design and study population.

The results should be read as descriptive evidence from the participants and measurements represented in the registry, not as a complete account of all possible outcomes or as proof of product performance. The registry states that safety and performance were secondary objectives, but no secondary results are posted. The adverse-event counts add limited descriptive information, but they do not resolve questions about comparative safety or causation. The overall statistical message is an uncertain estimated difference, with insufficient reported analysis detail to establish a precise within-participant contrast.

16. Why This Trial Matters Statistically

This study highlights why the design and the reported analysis need to be considered together. A crossover trial can make a within-participant comparison, which may be informative because each participant experiences both product conditions. But the value of that design depends on the analysis representing the pairing and accounting appropriately for the periods. The registry identifies a crossover model, while the posted outcome summaries give separate means and standard deviations and do not show the paired contrast. That gap makes it difficult to evaluate whether the primary comparison used the design’s within-person information.

The endpoint is a graded score rather than a simple event count. Its scale runs from no leakage to maximum leakage, and the mean difference offers a concise comparison of average scores. At the same time, averages do not show the distribution of individual experiences. The standard deviations indicate variation in scores, and the confidence interval indicates substantial uncertainty in the estimated mean difference.

The record also illustrates the difference between a trial’s stated objectives and its posted results. It describes secondary performance and safety objectives, but only the primary outcome result is available. It gives total enrollment and a planned target alongside smaller outcome-group counts, without explaining the flow from one to the other. Those distinctions matter when assessing how much information the posted estimate represents.

Finally, the planning illustrations are separate from the trial’s original design justification. They use fractions of the observed effect and stated planning assumptions, but do not establish what enrollment would have been appropriate for a paired crossover analysis. The trial’s own sample-size rationale is not reported. Keeping the descriptive result, its uncertainty, the design, and the planning illustration distinct is essential to a disciplined statistical reading.

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 arise from the information reported for this specific study. First, although the registry describes a crossover design with two product periods, it does not report a within-participant estimate, paired variability, or the analysis model. A comparison based only on marginal means and standard deviations cannot show how the paired observations were handled. Sequence allocation, period effects and carryover handling are also not reported.

Second, the listed outcome counts are 22 for each product, while total enrollment is 33 and the study description states a planned target of 100. The registry does not explain the difference among those figures, provide participant flow, or identify which participants contributed to the primary analysis. The termination reason is also not reported. These omissions leave uncertainty about completion and the scope of the analyzed data.

Third, details of endpoint measurement are limited. The score anchors and two-week assessment period are described, but how repeated observations were combined, who completed the leakage assessment, and how missing assessments were handled are not reported. The confidence-interval method and confidence level are not stated. The registry also does not provide a full statistical plan or explain whether any additional analyses were conducted.

Finally, the standard-care products could come from several manufacturers and brands, so the comparator is not a single uniform product. The study was open-label, and masking details for outcome assessment are not reported. No secondary outcome results are posted. These limitations do not invalidate the posted summaries, but they constrain how precisely and broadly the comparison can be interpreted.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Multi-national, Safety and Performance Study of New Ostomy Product Compared to Standard Care — NCT01517178.
• Registry record last updated 2015-03-13; status last verified 2015-03.
• Results first posted 2015-03-13.
• 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 randomized, open-label, phase 3, multinational crossover study comparing a new ostomy base plate with participants’ standard-care base plates. Its primary endpoint was the degree of leakage under the base plate, measured on a 24-point scale over two-week product periods. The study is marked terminated, and the record lists enrollment of 33.

The posted primary outcome includes 22 participants per product group. Mean scores were 4.6 for standard care and 6.5 for the new base plate; the reported mean difference was 1.9, with an interval spanning zero and an unadjusted p-value of 0.144. The registry posts no secondary outcome results. It does not report the crossover-specific analysis details, analysis population, missing-data methods, original sample-size rationale or termination reason. The posted data therefore describe an uncertain mean difference, with important design and analysis details unavailable in the registry record.