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 Safety and Performance of New 2-piece Ostomy Product Concept Compared With SenSura Click in Subjects With Ileostomy (NCT01800890), a randomized na study. The primary outcome is Degree of Leakage.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT01800890 |
| Phase | NA |
| Condition | Subjects With an Ileostomy |
| Allocation | Randomized |
| Design model | Crossover |
| Masking | None (open label) |
| Enrollment | 31 |
| Arms in the primary outcome | 4 |
| Lead sponsor | Coloplast A/S |
| Results posted | Yes |
2. Clinical Question
Population
People with an ileostomy took part in the investigation. The registry record reports enrollment of 31, while the outcome summaries list product-specific participant counts. It does not report further eligibility details or a separate definition of the population used for the primary analysis.
Intervention
The products being evaluated were Coloplast Test Product A, Coloplast Test Product B, and Coloplast Test Product C. Participants in the randomized sequences tested different combinations of products, with the order randomized within each sequence. The registry describes the products as devices.
Comparator
SenSura Click was the comparator device. The results label this group as SenSura. The registry describes three sequences, each including SenSura and two of the Coloplast products; it does not describe a sequence that includes every product for every participant.
Primary question
The primary endpoint was degree of leakage, rated on a four-point scale during a 10-day timeframe. The posted results compare the average ratings for each Coloplast test product with the average for Product A and compare SenSura with Product A. The registry does not report a formal non-inferiority or equivalence question.
The investigation asks how leakage ratings during use of the tested ostomy products compare. Its randomized crossover structure means participants tested products in an assigned order rather than being described as staying on one product throughout. That structure can make within-person comparisons relevant: each participant may contribute information under more than one product. However, the posted summary comparisons are not reported as paired or sequence-adjusted analyses.
The endpoint uses a scale with ordered response categories, from no leakage through starting to leak, leakage, and sudden leakage. The registry reports the mean of that measure for each product. The clinical question is therefore about average recorded scale scores, not the proportion of participants experiencing any leakage, the time to leakage, or a separate measure of product preference. Those outcomes are not reported in the registry record.
3. Trial Design
The registry describes a randomized, unmasked, crossover investigation. It was marked completed and listed as a device study. The record gives an enrollment of 31. The reported start was 2013-02 and primary completion was 2013-04. The phase was listed as not applicable.
Participants were assigned to one of three treatment sequences. One sequence included Coloplast A, Coloplast B, and SenSura Click; another included Coloplast C, Coloplast B, and SenSura Click; and the third included Coloplast A, Coloplast C, and SenSura Click. The order of the products was randomized within each sequence. Thus, not every participant is described as testing all four products. The record does not explain why these particular combinations were selected or how the allocation to sequences was balanced.
Masking was listed as none. The registry does not report blinding of participants, investigators, or outcome assessors beyond that entry. The reported primary endpoint was degree of leakage during a 10-day timeframe, assessed at every baseplate change. The record does not clarify whether the 10 days applied separately to each product period, how transitions between products were handled, or whether any washout period was used.
The registry outcome summaries give participant counts of 19 for Product A, 18 for Product B, 18 for Product C, and 27 for SenSura. These are product-level counts; they should not be treated as separate randomized groups in a conventional parallel-group trial, because the described design is crossover. The safety summaries give different at-risk counts for some products. The registry record does not explain the difference between the outcome and safety counts.
The record lists one primary outcome measure and no posted secondary outcome measures. It does not report a statistical analysis plan, the method used to account for repeated measurements or sequence, or a sample-size justification. It also does not report details of missing outcome data or participant flow through each product period.
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: Thirty-one subjects signed the informed consent, but 2 subjects were screen failures and did not test any products. These two subjects are not included in the participant flow below.
Only the first 6 of 9 groups are shown.
Test Period 1
| Stage | Test A/ Test B/ SenSura | Test A/ Test C/ SenSura | Test B/ SenSura/ Test A | Test B/ SenSura/ Test C | Test C/ Test B/ SenSura | Test C/ SenSura/ Test A |
|---|---|---|---|---|---|---|
| STARTED | 3 | 3 | 3 | 3 | 4 | 4 |
| COMPLETED | 3 | 3 | 3 | 2 | 4 | 4 |
| NOT COMPLETED | 0 | 0 | 0 | 1 | 0 | 0 |
Test Period 2
| Stage | Test A/ Test B/ SenSura | Test A/ Test C/ SenSura | Test B/ SenSura/ Test A | Test B/ SenSura/ Test C | Test C/ Test B/ SenSura | Test C/ SenSura/ Test A |
|---|---|---|---|---|---|---|
| STARTED | 3 | 3 | 3 | 2 | 4 | 4 |
| COMPLETED | 3 | 3 | 3 | 2 | 4 | 4 |
| NOT COMPLETED | 0 | 0 | 0 | 0 | 0 | 0 |
Test Period 3
| Stage | Test A/ Test B/ SenSura | Test A/ Test C/ SenSura | Test B/ SenSura/ Test A | Test B/ SenSura/ Test C | Test C/ Test B/ SenSura | Test C/ SenSura/ Test A |
|---|---|---|---|---|---|---|
| STARTED | 3 | 3 | 3 | 2 | 4 | 4 |
| COMPLETED | 3 | 3 | 3 | 2 | 4 | 4 |
| NOT COMPLETED | 0 | 0 | 0 | 0 | 0 | 0 |
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: Only includes the ITT population. The two screen failures and the subject who did not complete the Test B period as planned are not included. The subject that did not complete the test B period was also a screen failure, however it was first discovered after applying a product. Thus, no endpoint data has been recorded for this subject.
| Characteristic | Unit | Overall Study Population |
|---|---|---|
| Participants analysed | 28 | |
| Age, Continuous | years | 61.7 (SD 8.6) |
| Sex: Female, Male: Female | Participants | 5 |
| Sex: Female, Male: Male | Participants | 23 |
6. Primary Endpoint
The registry lists the primary outcome as Degree of Leakage, measured over 10 days.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | units on a scale |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is degree of leakage, a continuous summary in the registry results, reported as a mean and standard deviation for each product. The underlying assessment uses a four-point leakage scale developed by Coloplast A/S. Its response choices are no leakage, starting to leakage, leakage, and sudden leakage. The assessment was made at every baseplate change during the 10-day timeframe.
The scale is intended to record the degree of leakage rather than simply whether any leakage occurred. A mean provides a compact description of the average recorded rating, while the standard deviation describes how much ratings varied around that average. Lower values correspond to less severe categories on the listed scale, and higher values correspond to more severe categories. The registry does not provide a separate clinical threshold for interpreting the size of a mean difference.
Using a mean treats the ordered scale as though distances between adjacent categories can be summarized numerically. That can be useful for comparing average scores, but the score is still based on ordered categories, not a direct physical measurement with guaranteed equal spacing between every response. The posted results do not give category-specific counts, distributions, or the number of leakage assessments contributing to each mean.
The endpoint is relevant to product performance because leakage is the experience being rated during product use. It does not by itself describe other aspects of safety, comfort, usability, or preference. Those outcomes are not reported as secondary results in the registry record.
7. Results Posted in the Registry
- Coloplast Test Product B: mean 1.80 versus 1.80 on control; difference 0.00 (95% CI -0.45 to 0.45), standardized effect d = 0.00; z-test p = 1.000.
- Coloplast Test Product C: mean 1.90 versus 1.80 on control; difference 0.10 (95% CI -0.42 to 0.62), standardized effect d = 0.12; z-test p = 0.707.
- SenSura: mean 1.70 versus 1.80 on control; difference -0.10 (95% CI -0.54 to 0.34), standardized effect d = -0.13; z-test p = 0.653.
Mean difference: Coloplast Test Product B
95% CI: -0.45 to 0.45
Recalculated from the posted summary statistics
8. Statistical Interpretation
The reported mean leakage score was 1.8 for Coloplast Test Product A, 1.8 for Product B, 1.9 for Product C, and 1.7 for SenSura. The corresponding standard deviations were 0.7, 0.7, 0.9, and 0.8. These values describe the posted product-level summaries; they do not show how scores changed within each participant across products.
The unadjusted comparison of Product B with Product A has a reported mean difference of 0.0, with p = 1.0. The comparison of Product C with Product A has a reported mean difference of 0.1, with p = 0.707. The comparison of SenSura with Product A has a reported mean difference of -0.1, with p = 0.653. These p-values are unadjusted and do not account for multiple comparisons. They should not be read as proof that products are identical or that any difference is absent.
The confidence intervals for each of these comparisons include zero. This means the posted estimates are compatible with no difference as well as with differences in either direction within the intervals. The intervals are relatively broad compared with the small observed mean differences, so the results do not pin down the size or direction of a potential difference precisely. A confidence interval that includes zero is not an equivalence result; equivalence requires a prespecified margin and an analysis designed to assess whether the interval falls within that margin. Neither is reported in the registry record.
Interpretation also needs to account for the crossover design. Because participants tested products in sequences, product ratings may be related within a participant. A comparison that uses only separate group summary statistics cannot use the within-person covariance that a paired analysis could use, and it does not account for sequence or period effects. The posted recalculated comparisons are simple unadjusted comparisons of summaries, not a reported crossover model. The registry record does not report an adjusted analysis of the randomized sequences.
The sample-size illustrations use observed effects and are planning examples, not evidence about the power of this completed investigation. For comparisons where planning figures are listed, the required number per arm becomes larger when planning for 75% or 50% of the observed effect rather than the full observed effect. Those figures assume equal allocation and a normal approximation, as described in the record, and do not reflect the crossover structure. They should not be used as observed power or as proof that the study was adequately or inadequately sized.
Overall, the posted summaries show similar average scores across the products, with modest differences in the reported means. The available results are too limited to establish a definitive comparative conclusion: the record does not report a crossover-adjusted treatment effect, a clinically important difference, or an equivalence or non-inferiority framework. The evidence should therefore be described as a set of product-level summaries and unadjusted comparisons rather than a conclusive test of comparable performance.
9. Statistical Methods Explained
The registry reports a mean and standard deviation for the primary leakage score. It also gives unadjusted mean differences, confidence intervals, and p-values for comparisons against Product A. Understanding what these summaries describe helps separate the observed data from the strength of the statistical evidence.
What does a mean describe?
A mean is an average of the recorded ratings. In the posted results, Product A and Product B each have a mean of 1.8, Product C has a mean of 1.9, and SenSura has a mean of 1.7. The scale categories are ordered from less leakage to more leakage. A mean gives one summary of that ordered score, but it can conceal different patterns in the underlying responses. For example, the same average could arise from a tightly clustered set of ratings or from a wider mix of low and high ratings. The registry does not report category-level distributions, so that detail cannot be assessed.
The standard deviation describes spread around the group mean. The reported values are 0.7 for Product A, 0.7 for Product B, 0.9 for Product C, and 0.8 for SenSura. A larger standard deviation indicates more variation in the recorded scores within that product summary. It is not the uncertainty in the mean itself; uncertainty in an estimated mean is commonly described using a standard error or a confidence interval.
What does a mean difference describe?
A mean difference is the average score in one product summary minus the average score in the reference summary, according to the comparison as reported. For Product B compared with Product A, the reported difference is 0.0. For Product C compared with Product A, it is 0.1, and for SenSura compared with Product A, it is -0.1. A positive difference indicates a higher average score for the compared product, while a negative difference indicates a lower average score. Given the direction of the scale, a higher score corresponds to a more severe leakage category on average; this is a descriptive interpretation, not a statement about treatment benefit.
These comparisons are marked as recalculated and are simple unadjusted calculations from posted summary statistics. They are not a replacement for a sponsor-reported analysis. The record does not report a sponsor analysis that adjusts for the crossover design. Because the investigation assigned product sequences and participants tested more than one product, a paired or repeated-measures analysis could use the relationship between a participant’s ratings under different products. Comparisons reconstructed from separate means and standard deviations do not use that within-person relationship.
How should a p-value be read?
A p-value describes how incompatible the observed result is with a specified null model, assuming that model and its assumptions are correct. It is not the probability that the null hypothesis is true, nor is it a measure of the clinical importance of the difference. The reported unadjusted p-values are 1.0 for Product B versus Product A, 0.707 for Product C versus Product A, and 0.653 for SenSura versus Product A. These values do not provide evidence of a statistically clear difference under the simple comparisons reported. They do not establish that the products have equal performance.
There are multiple product comparisons against Product A. When several hypotheses are tested, the chance of at least one apparently unusual result can increase. The registry record does not report a multiplicity adjustment, a hierarchy of comparisons, or a prespecified strategy for handling multiple tests. Accordingly, the p-values should be treated as unadjusted and interpreted with that limitation in mind.
Why does the crossover design matter?
In a crossover investigation, participants receive or test different products in a sequence, so observations from the same participant can be correlated. General statistical principle: a paired analysis can account for that correlation and may be more efficient than treating product observations as independent, provided the design and data support the model. Period or sequence effects may also matter if ratings change over time or depend on the order of product use. The registry record does not report whether these effects were assessed, how repeated observations were modeled, or how many assessments contributed to each summary.
The posted comparisons use product-level summaries and are described as unadjusted. They do not convey the treatment contrast from a model that explicitly accounts for participant, period, and sequence. The degree to which this changes uncertainty cannot be determined without the underlying data and a documented analysis.
Why can over-dispersion matter?
General statistical principle: over-dispersion occurs when observed variability is greater than a model expects. If a model assumes that observations are more independent or less variable than they really are, its standard errors can be too small and its confidence intervals too narrow. Repeated leakage ratings within a person could be correlated, and ratings collected at multiple baseplate changes may not behave like independent observations. The registry does not report a model for these repeated assessments, so it is not possible to determine how dependence or over-dispersion was handled.
The outcome is also an ordered scale summarized as a mean. General statistical principle: treating an ordinal score as continuous can be a useful simplification, but it relies on treating steps on the scale as sufficiently comparable for averaging. Alternative analyses may focus on the distribution across categories. The registry does not report such an analysis.
What do the planning illustrations mean?
The sample-size illustrations are based on the observed effect and are explicitly described as planning illustrations, not the trial’s own design calculation. The assumptions listed are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The calculations show participants per arm for 80% and 90% power when planning for 100%, 75%, or 50% of the observed effect. For example, the posted figures for the Product C comparison give 1,014 participants per arm for 80% power when planning for 100% of the observed effect, and 4,053 participants per arm when planning for 50% of that effect. For the SenSura comparison, the corresponding figures are 909 and 3,634 participants per arm. These are hypothetical planning quantities under the stated assumptions, not observed enrollment targets, actual power, or proof of the performance of the completed crossover investigation.
10. Confidence Intervals and Precision
Confidence intervals describe the range of effect estimates that are compatible with the data under the analysis and its assumptions. They are useful for assessing precision: a narrow interval indicates that the estimate is more tightly constrained, while a wide interval allows a broader range of plausible differences. They are not guarantees that the true effect lies inside the interval.
For Product B versus Product A, the reported mean difference is 0.0; for Product C versus Product A, it is 0.1; and for SenSura versus Product A, it is -0.1. Each reported confidence interval includes zero. Thus, the estimates do not rule out no average difference, but they also allow differences in either direction. The posted intervals do not support a claim of equivalence because the registry record does not specify an equivalence margin or report an equivalence analysis.
The interval estimates are based on unadjusted summary comparisons rather than a reported model for the crossover sequences. Precision may differ if within-person correlations, period effects, or sequence effects are incorporated. The registry record does not report such an adjusted analysis, and the summary information cannot recover the paired uncertainty.
Group means and standard deviations provide descriptive information, but they do not show the full distribution of ratings or the number of repeated assessments underlying each summary. The product-level participant counts are not all the same, and the registry does not describe missing outcome data or its handling. These factors limit how completely the precision of the primary endpoint can be judged from the posted summaries alone.
11. Multiplicity, Missing Data and Analysis Populations
The registry lists one primary outcome measure, degree of leakage, and no posted secondary outcome measures. It reports three unadjusted comparisons against Product A: Product B, Product C, and SenSura. The registry record does not report whether these comparisons were all prespecified, whether one was considered primary among the comparisons, or whether any adjustment for multiple testing was planned or used. The reported p-values should therefore be understood as unadjusted results, not as multiplicity-controlled evidence.
The record does not report a statistical analysis plan, an analysis population definition, or a method for handling repeated measures in the crossover design. It does not specify whether analyses were based on all randomized participants, participants who completed each product period, or another group. The product summaries list participant counts, but these counts alone do not establish which participants contributed to every comparison or how incomplete data were handled.
Missing outcome data and reasons for missingness are not reported in the registry record. Nor does the record describe imputation, sensitivity analyses, or exclusions from the primary endpoint analysis. In a crossover design, missing observations during one product period can affect within-person comparisons; the posted aggregate summaries cannot show whether this occurred or how it was addressed.
The record also does not report an adjusted analysis accounting for participant, sequence, or period. Consequently, the available comparisons should not be treated as a complete account of the statistical analysis of the randomized crossover investigation. No inference about unreported interim analyses or sample-size justification is possible from the registry record.
12. 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 |
|---|---|---|---|
| Coloplast Test Product A | 0 | 19 | 0.0% |
| Coloplast Test Product B | 0 | 19 | 0.0% |
| Coloplast Test Product C | 0 | 19 | 0.0% |
| SenSura | 1 | 28 | 3.6% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Coloplast Test Product A | 6 of 19 |
| Coloplast Test Product B | 8 of 19 |
| Coloplast Test Product C | 4 of 19 |
| SenSura | 6 of 28 |
Most frequent serious adverse event terms
| Event term | Organ system | Coloplast Test Product A | Coloplast Test Product B | Coloplast Test Product C | SenSura |
|---|---|---|---|---|---|
| stenosis of catherter in the right kidney | Renal and urinary disorders | 0 of 19 | 0 of 19 | 0 of 19 | 1 of 28 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Coloplast Test Product A | Coloplast Test Product B | Coloplast Test Product C | SenSura |
|---|---|---|---|---|---|
| peristomal skin irritation | Skin and subcutaneous tissue disorders | 5 of 19 | 5 of 19 | 4 of 19 | 4 of 28 |
| stinging skin by fistel | Skin and subcutaneous tissue disorders | 0 of 19 | 0 of 19 | 1 of 19 | 0 of 28 |
| cramps in the right kidney with sever pain | Renal and urinary disorders | 1 of 19 | 0 of 19 | 0 of 19 | 0 of 28 |
| influenza | Infections and infestations | 0 of 19 | 1 of 19 | 0 of 19 | 0 of 28 |
| cold | Infections and infestations | 0 of 19 | 1 of 19 | 0 of 19 | 0 of 28 |
| back pain | Musculoskeletal and connective tissue disorders | 0 of 19 | 1 of 19 | 0 of 19 | 0 of 28 |
| bladder infection | Renal and urinary disorders | 0 of 19 | 0 of 19 | 0 of 19 | 1 of 28 |
| peristomal skin irritaion | Skin and subcutaneous tissue disorders | 0 of 19 | 0 of 19 | 0 of 19 | 1 of 28 |
| diarre due to food intolerance | Gastrointestinal disorders | 0 of 19 | 0 of 19 | 1 of 19 | 0 of 28 |
Serious events with the highest arm-level rate: stenosis of catherter in the right kidney (3.6%).
The safety summaries report serious adverse events by product. For Product A, 0 serious adverse events were reported among 19 at risk; for Product B, 0 among 19; for Product C, 0 among 19; and for SenSura, 1 among 28. The registry also identifies “stenosis of catherter in the right kidney” as a serious adverse event term and reports 3.6% for that term. The registry record does not provide further detail about the event or its attribution.
These counts are descriptive. They do not by themselves establish whether an event was caused by a product, and the record does not report a causal assessment. The at-risk counts are product-specific and should not be added to infer a number of separate participants, particularly given the crossover design. The safety denominators also differ from some of the participant counts in the outcome summaries; the registry record does not explain why.
Deaths are not reported in the registry record. The summaries also list other, non-serious adverse events affecting 6 participants for Product A, 8 for Product B, 4 for Product C, and 6 for SenSura. The registry record does not provide enough detail to compare event types, severity, duration, or exposure time across products. The small counts and limited context call for a descriptive reading rather than a firm comparative safety conclusion.
13. What the Result Does, and Does Not, Mean
The results describe average leakage ratings during use of the tested products and give simple unadjusted comparisons with Product A. The reported means are close together, and the estimated differences are small in scale units. The confidence intervals include zero, so these summaries do not establish a clear difference between any of the compared products under the unadjusted calculations.
That interpretation is not the same as showing that products are equivalent. Equivalence requires a prespecified range of differences considered unimportant and an analysis that tests whether the uncertainty lies within that range. The registry record does not report either. Similarly, the absence of a statistically clear difference is not evidence that the products have exactly the same effect.
The posted summaries also do not establish a causal comparison that accounts for all features of the randomized crossover design. Participants tested products in assigned sequences, but the reported comparisons are based on group summaries rather than a model that accounts for within-participant correlation, period, or sequence. The results cannot show whether individual participants tended to rate one product differently from another.
The primary endpoint is a four-category scale summarized as a mean. It does not provide category frequencies, the number of assessments, or a direct description of how often leakage occurred at a particular severity. The registry does not report results for other product attributes or posted secondary outcomes. Conclusions should therefore be limited to the reported leakage-score summaries and the serious adverse event counts.
The planning illustrations do not change what the completed study observed. They are hypothetical sample-size calculations under stated assumptions, not observed power and not a retrospective demonstration that the study was or was not adequately powered. In short, the registry presents descriptive and unadjusted evidence, with important uncertainty and design details not reported.
14. Why This Trial Matters Statistically
This investigation illustrates why trial structure matters when interpreting a simple comparison of averages. In a parallel-group trial, each participant is generally summarized under one assigned condition. In a crossover trial, participants test more than one product, and their observations can be related. An analysis that accounts for this relationship may answer a different statistical question and yield different uncertainty from a comparison based only on separate group summaries.
The record also shows the distinction between a nonsignificant comparison and evidence of equivalence. The p-values are unadjusted, and the confidence intervals include zero, but that does not demonstrate that differences are small enough to be clinically unimportant. A specific equivalence or non-inferiority margin and an analysis built around that question would be needed to support such a conclusion. Neither is reported in the registry record.
There is a further measurement issue: leakage is recorded on an ordered four-point scale and summarized by means. Means are familiar and concise, but they do not reveal the category distribution. Reporting category counts or a suitable model for ordered outcomes could provide complementary information. Those details are not present in the registry record.
Finally, the planning illustrations depend on the effect size selected for planning. Illustrations based on smaller fractions of an observed effect require more participants per arm under their stated assumptions. They are useful for considering future planning scenarios, but they cannot be mistaken for the study’s own sample-size rationale or for observed power. The registry record does not report a sample-size justification.
15. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
The main limitation for interpretation is that the registry record does not report an analysis that accounts for the randomized crossover design. Participants tested different products in randomized orders, so observations can be correlated within participant and may depend on period or sequence. The available mean comparisons are unadjusted summaries and do not make those design features explicit.
The outcome is an ordered four-point scale, but the results report means and standard deviations rather than category-specific distributions. The record does not report how many leakage assessments contributed to each mean or whether repeated assessments were modeled. Without those details, it is difficult to assess the distribution of scores and the uncertainty associated with repeated measurements.
Product-level outcome counts differ, and safety at-risk counts differ from some outcome counts. The registry record does not explain these differences, describe participant flow, or report missing data and its handling. It also does not define the analysis population or state whether all randomized participants contributed to the endpoint summaries.
The comparisons are unadjusted, and no multiplicity strategy is reported despite several comparisons against Product A. The registry does not report a clinically important difference, equivalence margin, non-inferiority framework, or sponsor-reported adjusted treatment effect. The sample-size illustrations are planning calculations from observed effects rather than the trial’s own design rationale. Safety reporting is limited to counts and a serious event term; the record does not provide further causal or clinical context. These limitations constrain conclusions to the descriptive results posted in the registry.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: Safety and Performance of New 2-piece Ostomy Product Concept Compared With SenSura Click in Subjects With Ileostomy — NCT01800890.
- Registry record last updated 2014-08-06; status last verified 2014-07.
- Results first posted 2014-08-06.
- 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.
19. Record Summary
This completed randomized, unmasked crossover investigation evaluated three Coloplast test products and SenSura Click in people with an ileostomy. The registry reports an enrollment of 31 and describes three randomized product sequences. Its primary endpoint was degree of leakage, assessed at every baseplate change on a four-point scale during a 10-day timeframe.
Mean scores were 1.8 for Product A, 1.8 for Product B, 1.9 for Product C, and 1.7 for SenSura. The unadjusted comparisons against Product A had p-values of 1.0, 0.707, and 0.653, respectively. Each confidence interval included zero. The registry does not report a crossover-adjusted analysis, a multiplicity strategy, missing-data handling, or an equivalence framework.
Serious adverse event counts were 0 for Product A, 0 for Product B, 0 for Product C, and 1 for SenSura. The record gives limited context for safety interpretation. Planning figures are illustrative calculations, not observed power or the trial’s reported sample-size justification.