Investigating the Safety and Performance of a New 2-piece Ostomy Product Compared With SenSura Click 2-piece: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Investigating the Safety and Performance of a New 2-piece Ostomy Product Compared With SenSura Click 2-piece (NCT01957553), a randomized na study. The primary outcome is Preference.

2. Clinical Question

The question is framed around product preference after participants had experience with both products in a randomized crossover design. The posted results report preference for the Coloplast test product and for SenSura, with the stated preference percentages of 65.0 and 35.0. That contrast describes the choices recorded for this endpoint. It does not, on its own, establish why participants made those choices or how preference relates to other aspects of ostomy care. The registry record does not report a separate primary question about an objective performance measure, nor does it post secondary outcome results.

3. Trial Design

The registry record describes a randomized, unmasked crossover investigation of a new two-piece ostomy product compared with SenSura Click. The condition is listed as ileostomy - stoma, and the intervention entries identify the Coloplast test product and SenSura as devices. Enrollment is listed as 130. The study status is completed, with the record listing a start of 2013-09 and primary completion of 2013-12. The phase is recorded as NA.

In a crossover design, participants receive or use both compared products in a sequence rather than remaining in only one product group throughout the comparison. The record describes two sequences: one starts with the Coloplast test product and crosses over to SenSura; the other starts with SenSura and crosses over to the Coloplast test product. Allocation is listed as randomized. Masking is listed as none, so the record does not describe the trial as blinded.

The primary endpoint asks participants which product they preferred at the end of the investigation. Its timeframe is recorded as 21+1 days. The posted results list 114.0 for each preference category, with 65.0% preferring the Coloplast test product and 35.0% preferring SenSura. These result denominators should not be interpreted as the number enrolled or as a complete account of participant flow. The registry record does not explain the difference between the enrollment figure and the endpoint denominators, or provide a detailed account of withdrawals, exclusions, or missing endpoint information.

The sponsor is Coloplast A/S. The registry record does not report the original sample-size justification, details of the randomization procedure, the length or handling of any transition between products, or the statistical plan used by the investigators. Those aspects should not be inferred from the crossover label alone.

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: 130 subjects were randomised, however 3 of these were not exposed to a product and where not included in the safety population. The participant flow below is generated based on the safety population.

Test Period 1 (21 +- 1 Days)

Reasons for not completing this period:

Test Period 2 (21 +- 1 Days)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The ITT population was constituted by all randomized subjects with valid informed consent who had applied at least one test product and had valid information for the primary endpoint preference, or valid information for at least one product with respect to one of the secondary endpoints., who included all subject who contributed with endpoint data

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: Baseline data are summarized with the subjects included in the ITT population. Two subjects where exposed to a product but did not register any endpoint data. These subjects are only found in the safety population.

6. Primary Endpoint

The registry lists the primary outcome as Preference, measured over 21+1 days.

The primary endpoint is preference: participants were asked which product they preferred, the test product or SenSura, at the end of the investigation. Results are expressed as a percentage of participants. The timeframe is recorded as 21+1 days. The posted categories report 65.0% preferring the Coloplast test product and 35.0% preferring SenSura.

Preference is a participant-reported outcome. It can capture an overall judgment after experience with the products, which may matter when evaluating devices intended for ongoing personal use. Unlike an outcome based on a specific clinical event, a preference response records which option an individual favors; it does not quantify the reason for that choice or how strongly the product is preferred. The registry record does not report additional detail about the wording or response options beyond asking which product was preferred.

In a crossover investigation, the preference question follows experience with both products across the assigned sequence. The result therefore concerns the final choice in this study context, rather than a simple comparison of two independent groups each using only one product. Sequence, order, and experience may be relevant to interpretation, but the registry record does not report analyses of those factors. Nor does it post secondary endpoint results that could provide other perspectives on product performance or safety. The endpoint is useful for describing the recorded preference distribution, but it should not be treated as a substitute for other outcomes that are not reported.

7. Results Posted in the Registry

• SenSura: 35.1% (40/114) versus 64.9% (74/114) on control; risk difference -29.8 percentage points (95% CI -42.2 to -17.4), risk ratio 0.54 (0.41–0.72); unadjusted two-proportion z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary at the response level: a participant's preference is recorded for one of the two products. The posted summaries express each preference category as a percentage of participants. General explanation: for a binary outcome, a percentage describes the share of the analyzed observations falling into a specified category. It does not convey the intensity of preference or the reasons underlying the response.

What does the risk difference describe?

The registry reports a risk difference for the comparison labeled SenSura. In general, a risk difference subtracts one event proportion from another. For a preference outcome, the meaning depends on how the categories are coded and which category is used as the event. The posted comparison has a negative estimate for SenSura, while the endpoint summaries show a larger percentage preferring the test product. These entries point in the same direction: fewer recorded preferences for SenSura than for the test product. The registry record does not explain the coding convention in words, so the estimate should be interpreted alongside the stated product categories and direction of the posted percentages.

What does the p-value tell the reader?

The reported unadjusted p-value is <0.001. General explanation: a p-value assesses how compatible the observed data are with a specified null model, assuming that model and the test's assumptions hold. It is not the probability that the null hypothesis is true, nor does it measure the probability that the result occurred by chance in an everyday sense. The term “unadjusted” indicates that the record labels this value as unadjusted; the registry does not describe an adjustment for multiple comparisons. It also does not identify the test used, whether it was designed for paired crossover data, or the precise null hypothesis and assumptions.

Why does the crossover structure matter?

In a crossover design, participants encounter both products in a sequence. This differs from a parallel-group design, in which participants stay in one assigned group for the comparison. General explanation: data from the same participant across conditions can be related, and analyses may need to account for that relationship. Order, sequence, and possible carryover can also be relevant to a crossover comparison. The registry describes two randomized sequences, but it does not report whether the preference comparison used paired methods, adjusted for sequence, or assessed order or carryover. It would be inappropriate to assume a particular method from the design label alone.

The posted preference comparison gives 74 responses for the Coloplast test product and 40 for SenSura, and lists 114.0 in each category. Those are the endpoint counts recorded for the comparison. They are not enough to reconstruct the crossover analysis or its correlation structure, and no additional calculations are needed to describe the posted result. The separate arm summaries display 65.0% and 35.0%; those reported percentages should be distinguished from any new estimate calculated from counts.

What does an interval estimate add?

The comparison includes a confidence interval for the risk difference. General explanation: a confidence interval presents a range of values compatible with the observed data under a specified procedure and its assumptions. It conveys uncertainty about the estimate, rather than guaranteeing that the true value lies in a particular realized interval. Here, the posted interval is wholly on the negative side for the SenSura comparison, which is consistent with the reported direction. The registry record does not state the confidence level or interval method. It also does not provide enough methodological detail to assess whether the calculation accounted for paired crossover observations.

The interval and p-value address related but different questions. The p-value is evidence against a null model under the test used; the interval communicates a range of effect estimates under an interval procedure. Neither describes the practical significance of a preference pattern without context, and neither explains what shaped participant choices.

What is not documented about the analysis?

The registry record lists one outcome measure and zero posted analyses. It posts a primary result and a comparison, but does not give a full statistical analysis plan. The original sample-size assumptions, the planned handling of the crossover structure, any covariate adjustments, the confidence level, and the statistical test are not reported in the registry record. The population description for the primary endpoint is also truncated after “who includ,” so its full definition cannot be recovered from the record. These omissions limit independent assessment of the analysis, even though the direction and reported significance of the preference result are clear.

General explanation: over-dispersion is a concern for count data when variability exceeds what a chosen model expects. It is not the issue directly represented by this binary preference endpoint, and the registry record does not report a count model or a dispersion parameter. For binary preference data, the more immediate methodological questions are the definition of the analyzed population, the handling of incomplete responses, and whether the analysis reflects the paired nature of the crossover. Those details are not reported, so no particular analysis method should be attributed to the investigators.

10. Confidence Intervals and Precision

The comparison reports a confidence interval for the risk difference, and its bounds are both on the negative side for the contrast labeled SenSura. This interval direction is consistent with the posted preference summaries, in which 35.0% preferred SenSura and 65.0% preferred the Coloplast test product. The registry record does not state the confidence level, the interval calculation method, or whether the procedure accounts for the crossover pairing.

General explanation: a confidence interval is a way to express statistical uncertainty around an estimate. A narrower interval generally indicates greater precision under the method's assumptions, while a wider interval indicates more uncertainty. An interval wholly on one side of zero is commonly interpreted as inconsistent with a zero difference at the corresponding confidence level, but that interpretation depends on the interval procedure and the underlying analysis. Because the confidence level and method are not reported, the interval should not be assigned an undocumented level of certainty.

The result is based on the preference comparison listed with 114.0 observations in each category, while enrollment is listed as 130. The registry record does not explain the endpoint denominator or report a complete participant flow, so precision should be understood in relation to the posted analyzed information rather than the enrollment figure alone. The interval reflects sampling uncertainty as modeled; it does not account automatically for possible missing-data bias, selection into the analyzed population, or limitations in outcome measurement. Those sources of uncertainty are not quantified in the registry record.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm, not total events. The sample-size illustration assumes a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It uses the observed effect as its starting point and considers detecting 100% of the observed effect, 75% of the observed effect, or 50% of the observed effect. The original trial design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the number of participants per arm that the illustration estimates would be needed to have an 80% chance of detecting the specified effect under those assumptions, if that effect and the model assumptions were correct. The 90% power column gives the corresponding per-arm planning figure for a 90% chance. For the 100% observed-effect scenario, the figures are 43 participants per arm for 80% power and 57 for 90% power. For planning around 75% of the observed effect, the figures are 77 and 103 participants per arm. For planning around 50% of the observed effect, the figures are 172 and 229 participants per arm.

These are planning illustrations, not observed power and not a report of the study's original target or design rationale. Smaller effects require more participants under the stated assumptions, which is why the figures increase as the assumed effect becomes a smaller fraction of the observed one. The calculation is a simplified illustration based on the posted observed effect; it does not show that the trial was designed around that effect, nor does it account for design features that are not specified in the calculation assumptions.

12. How the Sample Size Is Derived

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

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.649; treatment proportion p₁ = 0.351; average p̄ = 0.500.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.7071 = 1.3859.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6749 = 0.5680.
4. n = (1.3859 + 0.5680)² / (-0.2982)² = 42.9, rounded up to 43 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
p0 <- 0.649122807017544                          # control proportion
p1 <- 0.350877192982456                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1957553)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 43 (80% power), 57 (90% power)
 75% of observed effect: n per arm = 77 (80% power), 103 (90% power)
 50% of observed effect: n per arm = 172 (80% power), 229 (90% power)
power.prop.test: 42.9 
Simulated power at n = 43 per arm: 0.792 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Multiplicity, Missing Data and Analysis Populations

The registry record lists one outcome measure, the primary endpoint of preference, and zero posted analyses. It does not report secondary endpoint results. The comparison includes an unadjusted p-value of <0.001, but the registry record does not describe a multiplicity plan or state whether any other statistical tests were conducted. Because the number and selection of analyses are not fully documented, the unadjusted p-value should not be treated as evidence that multiplicity was formally addressed.

The primary endpoint population is described as an ITT population composed of randomized subjects with valid informed consent who had applied at least one test product and had valid information for the primary endpoint preference, or valid information for at least one product with respect to one of the secondary endpoints. The recorded description is incomplete, ending after “who includ.” The full criteria, including how the stated alternative involving secondary endpoints was applied, are not reported in the registry record. The result should therefore be described using the population wording that is present, without assuming a conventional or complete intention-to-treat analysis.

Enrollment is listed as 130, while the preference results list 114.0 for each product category. The registry record does not explain the difference, report how many participants lacked a valid preference response, or state whether missing information was imputed, excluded, or handled in another way. The posted result alone cannot establish that missingness had no effect on the comparison.

General explanation: multiplicity can arise when several outcomes, comparisons, subgroups, or analyses are tested, increasing the chance of at least one apparently unusual result under a collection of null hypotheses. A prespecified plan can clarify which result is primary and how additional tests are interpreted. Missing-data methods also matter because the analyzed participants may differ from those without recorded outcomes. In this investigation, the registry record does not report enough detail to assess either issue fully.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: copd (0.8%), pain in chest (0.8%), rectal bleeding/inflammtion of the intestine (0.8%), sclerosing angiomatoid nodlar tranformation (0.8%), a cystic lesion in operation area (0.8%).

The adverse-event entries report serious events for the Test Product group with 4 events among 124 at risk, and for the SenSura group with 1 event among 120 at risk. Other adverse events are reported as 27 among 124 at risk for the Test Product group and 22 among 120 at risk for SenSura. These are the registry's reported counts and denominators; no additional rates are calculated. The record does not state whether the groups correspond to particular exposure periods in the crossover or explain the different numbers at risk.

The deaths entries are null for both groups, so deaths are not reported in the registry record. The listed serious-event terms include COPD, pain in chest, rectal bleeding/inflammtion of the intestine, Sclerosing angiomatoid nodlar tranformation, A cystic lesion in operation area, and Atrial fibrillation, each shown with 0.8%. These entries should be read as the terms and percentages recorded, not as a complete description of all events or a causal assessment.

The adverse-event summaries do not establish whether an event was caused by a product. The registry record does not provide event timing, severity detail beyond the serious/non-serious groupings, adjudication methods, or a crossover-specific safety analysis. These limitations matter when comparing the group figures.

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

The posted result answers a focused question: which product did participants say they preferred at the end of the investigation? The reported preference percentages are 65.0% for the Coloplast test product and 35.0% for SenSura. The comparison reports an unadjusted p-value of <0.001 and an interval estimate whose direction is consistent with more preferences for the test product. These results describe the preference responses recorded in the registry, not every possible feature of product performance.

Preference is meaningful as a participant-reported judgment, but it does not tell readers why one product was chosen, how strongly it was preferred, or whether the difference matters in a particular setting. The record does not report additional measures that could explain the choice or establish how preference relates to safety or other outcomes. Nor does a statistical comparison demonstrate that a device is suitable for any individual.

The investigation was randomized and used a crossover sequence, but it was unmasked. Participants were described as using both products, and preference was asked at the end. The posted record does not report how sequence or order was considered in analysis, whether a carryover effect was assessed, or the method used for the p-value and interval. These missing details limit a full assessment of how the design was reflected in the statistical comparison.

The enrollment entry is 130, while the preference comparison lists 114.0 in each product category. The registry does not explain participant flow or missing preference information, and the primary population definition is truncated. As a result, the posted percentages should be interpreted as results for the recorded endpoint analysis, not assumed to represent every enrolled participant.

In short, the data show a clear numerical preference pattern in favor of the test product among the recorded responses, with the posted statistical test reporting <0.001. They do not by themselves establish causes of preference, outcomes beyond the recorded endpoint, complete safety comparisons, or the result that would be obtained under different populations or methods.

16. Why This Trial Matters Statistically

This investigation is statistically notable because it uses a participant preference endpoint in a randomized crossover design. Preference is not the same kind of outcome as a count of clinical events: it is a choice made after experience with both products. The crossover structure can make within-participant information relevant, so the statistical method should reflect how observations relate to sequence and order. The registry record describes the design but does not report whether the posted comparison accounts for those features.

The posted summaries make the direction of preference easy to understand: 65.0% favored the Coloplast test product and 35.0% favored SenSura. The reported p-value is <0.001, and the interval estimate is wholly on the negative side for the comparison labeled SenSura. Together, these entries describe a pronounced observed preference imbalance and statistical evidence against the null model used for the posted test. The exact practical meaning depends on context that the registry record does not provide.

The record also illustrates why statistical interpretation depends on reporting completeness. Enrollment is 130, but the endpoint categories each list 114.0; the population definition is truncated, and missing-data handling is not reported. The confidence level and analysis method are also absent. These are not merely technical details: they affect how readers assess the population represented, uncertainty, and whether the analysis matches the crossover design.

The sample-size illustration is another distinct statistical element. It explores planning under effect sizes expressed as fractions of the observed effect, rather than documenting the original rationale for this trial. Keeping that planning exercise separate from the observed result prevents readers from confusing a retrospective illustration with the trial's design assumptions.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several trial-specific limitations affect interpretation of the preference comparison. The study was unmasked, so participants knew which product they were using. The registry record does not describe whether the question wording, product presentation, or assessment process was standardized in a way that could reduce influence on reported preference.

The crossover sequences are described, but the record does not report how long participants used each product beyond the overall endpoint timeframe of 21+1 days, how transitions were handled, or whether sequence and order effects were assessed. The statistical method for the comparison is not identified, and it is not stated whether the analysis accounted for within-participant pairing. The confidence level and interval method are also not reported.

Enrollment is listed as 130, while the endpoint comparison lists 114.0 for each category. Participant flow, reasons for missing or invalid endpoint information, and the handling of missing responses are not reported in the registry record. The primary population description is truncated, which prevents a complete assessment of exactly who contributed to the result.

The registry record lists zero posted analyses and no secondary outcome results. It does not report the original sample-size rationale, a multiplicity strategy, or a detailed statistical plan. Safety summaries provide event counts and denominators, but do not explain the group exposure periods or establish causality. These gaps constrain evaluation of the completeness and robustness of the posted findings.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Investigating the Safety and Performance of a New 2-piece Ostomy Product Compared With SenSura Click 2-piece — NCT01957553.
• Registry record last updated 2014-09-08; status last verified 2014-09.
• Results first posted 2014-09-08.
• 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 completed registry record describes a randomized, unmasked crossover investigation of the Coloplast test product and SenSura in people with an ileostomy. Enrollment is listed as 130, with a start of 2013-09 and primary completion of 2013-12. The primary endpoint was participant preference at 21+1 days.

The posted preference results are 65.0% for the test product and 35.0% for SenSura, with an unadjusted p-value of <0.001. The comparison lists 74 and 40 preference responses, respectively, and 114.0 for each category. The record also reports serious and other adverse-event counts, but does not report deaths.

Important analysis details are not reported in the registry record, including the statistical test, handling of missing data, confidence level, crossover-specific analysis methods, and original sample-size rationale. The ITT population description is truncated, and no secondary results are posted.