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 Investigation of a New 2-piece Ostomy Product in People With an Ileostomy or Colostomy (NCT02362360), a randomized na study. The primary outcome is Fit to the Peristomal Area, Measured by a 5-point Scale Ranging From "Very Poor" to "Very Good"..
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT02362360 |
| Phase | NA |
| Condition | Ileostomy, Colostomy |
| Allocation | Randomized |
| Design model | Crossover |
| Masking | None (open label) |
| Enrollment | 52 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Coloplast A/S |
| Results posted | Yes |
2. Clinical Question
Population
People with an ileostomy or colostomy were eligible for the question studied. The registry record reports enrollment of 52, but does not provide further details about participant characteristics or a separate analysis population for the primary outcome.
Intervention
The intervention was the Coloplast Test Product, a new 2-piece ostomy product. The planned assessment concerned how well its baseplate fit the body contours around the stoma.
Comparator
The comparator was a Hollister product. Participants were assigned to a product order: the Coloplast test product followed by the comparator, or the comparator followed by the Coloplast test product.
Primary question
The primary question was how participants rated fit to the peristomal area for each product on a five-point scale from very poor to very good. The registry record does not report the ratings or a statistical comparison, so it does not establish which product received higher ratings.
3. Trial Design
The registry record describes a randomized, unmasked crossover study. Participants tested both the Coloplast Test Product and the Comparator (Hollister), with the sequence randomized between testing the Coloplast product first and testing the comparator first. In a crossover design, each participant can contribute information under both product conditions. That structure can make a within-participant comparison useful because a participant’s own ratings may be less affected by stable personal differences than comparisons between separate groups.
The crossover structure also means that product order and the experience of the first test period may matter. The registry record does not report whether there was a washout period, how long each product was used, or how the analysis handled possible period, order, or carryover effects. Those details should not be inferred from the design label alone.
The study is listed as completed, with enrollment of 52. The start is recorded as 2015-02 and primary completion as 2015-05. The registry record names Coloplast A/S as sponsor. It lists the condition areas as ileostomy and colostomy. No masking was used, so participants and those assessing the products were not described as blinded to the product assignment.
The stated primary assessment timeframe is 21 +/- 3 days. The outcome is a participant evaluation of the baseplate’s ability to fit body contours around the stoma. Although the registry record lists one primary outcome measure, it does not report analysis entries or results for the planned rating. The enrollment figure and completion status do not by themselves show how many participants posted usable ratings for either product.
4. Participant Flow and Accounting
The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.
Before assignment: One subject was a screen failure and was not exposed to any of the test products. This subject was excluded from the safety population, which therefore included 52 subjects.
Period 1
| Stage | Coloplast Test Product Then Comparator | Comparator Then Coloplast Test Product |
|---|---|---|
| STARTED | 26 | 26 |
| COMPLETED | 23 | 25 |
| NOT COMPLETED | 3 | 1 |
Reasons for not completing this period:
| Reason | Coloplast Test Product Then Comparator | Comparator Then Coloplast Test Product |
|---|---|---|
| Lack of Efficacy | 1 | 0 |
| Withdrawal by Subject | 2 | 1 |
Period 2
| Stage | Coloplast Test Product Then Comparator | Comparator Then Coloplast Test Product |
|---|---|---|
| STARTED | 23 | 25 |
| COMPLETED | 23 | 25 |
| NOT COMPLETED | 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.
| Characteristic | Unit | Overall Study Population |
|---|---|---|
| Participants analysed | 52 | |
| Age, Continuous | years | 70.9 (SD 9.5) |
| Sex: Female, Male: Female | Participants | 11 |
| Sex: Female, Male: Male | Participants | 41 |
6. Primary Endpoint
The registry lists the primary outcome as Fit to the Peristomal Area, Measured by a 5-point Scale Ranging From "Very Poor" to "Very Good"., measured over 21 +/- 3 days.
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | not applicable |
| Unit | percentage of subjects answering |
| Endpoint classification | not reduced to a single comparison |
The primary endpoint is a participant rating of how well each product’s baseplate fits the body contours in the area around the stoma. Responses use a five-point scale, with categories ranging from very poor to very good. The stated timeframe is 21 +/- 3 days, and the outcome is described as a percentage of subjects answering.
This endpoint captures perceived fit, a practical feature of an ostomy product that may differ between individuals and across body contours. Asking participants directly can measure their experience rather than relying only on an external observer’s judgment. The ordered response categories also preserve distinctions between poorer and better reported fit, rather than reducing the experience to a simple yes-or-no response.
However, the scale is ordinal: its categories have an order, but the distance between adjacent categories is not necessarily equal. A category distribution can therefore be informative in ways that a single average or a combined favorable-versus-unfavorable result may not be. The registry record does not report how responses would be summarized or how missing answers would be treated. It also does not give the observed category counts or percentages. Without those results, the planned endpoint identifies what the study intended to assess, but not the direction or precision of any product difference.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record identifies a clinically specific comparison: ratings of peristomal fit with the Coloplast Test Product and the Hollister comparator. It reports the design and the planned rating scale, but not the primary outcome results. In particular, no response-category counts, percentages, effect estimate, confidence interval, or statistical test for the primary endpoint is reported in the registry record. The effect and its precision therefore cannot be interpreted from this record.
The endpoint has several ordered categories. The registry record notes that this primary outcome has several categories or time points and is not reduced to one comparison. That matters for interpretation: a single contrast would depend on how categories or time points were selected or combined. Because no such reduction or analysis is reported, there is no basis to describe a direction, magnitude, or statistical significance for the primary question. The record’s count of zero analysis entries is consistent with the absence of a reported primary analysis.
The randomized crossover design is relevant to how an eventual estimate could be understood. A comparison that uses each participant’s ratings under both products can account for stable differences between participants. But a crossover analysis also needs to consider sequence and period, and possibly carryover. The registry record does not state how these features were handled, so the design alone cannot establish whether a particular analysis would have accounted for them.
The enrollment figure is not a substitute for the number with complete paired outcome data. The registry record does not report how many participants completed both product assessments, how many posted each rating, or whether participants were excluded from an analysis. It consequently does not establish the amount of information underlying the primary outcome.
The adverse-event entries describe counts for the product groups, but they do not answer the fit question. They should be read as descriptive safety reporting, not as evidence of a primary-endpoint effect. The registry record does not provide an inferential comparison for those entries either. Overall, the posted record supports a description of the trial’s intent, structure, and listed adverse-event counts. It does not support a conclusion about comparative fit or a precise estimate of the difference in ratings.
9. Statistical Methods Explained
The main statistical issue is that the primary endpoint is a set of ordered response categories rather than a single continuous measurement. A response of very good is more favorable than a response of good, but the scale does not establish that the gap between very poor and poor is the same as the gap between good and very good. Methods should respect both the ordering and the categorical nature of the responses. The registry record does not report which method was planned or used.
What does a crossover comparison use?
In a crossover study, a participant receives or tests each condition in sequence. The comparison can use the within-participant difference in response, rather than treating all observations under one product as unrelated to all observations under the other. This can be efficient when each participant serves as their own comparator, because characteristics that remain stable across periods are shared by both observations. This is a general explanation of the design, not a claim about the analysis used in this trial.
A valid crossover interpretation also depends on the timing and sequence of assessments. Ratings may vary with period, experience, or the order in which products are used. A previous product could potentially influence a later assessment, which is generally called carryover. Statistical approaches can account for some design features, but the registry record does not report a washout arrangement, period-specific results, or the method for handling order and carryover. It is therefore not possible to assess those aspects of the analysis from the record.
How should an ordinal endpoint be analyzed?
For an ordered scale, one approach is to retain and report the distribution across categories. This makes clear whether responses are concentrated in favorable, unfavorable, or intermediate categories. Other methods can model the ordering while making assumptions about how category probabilities relate to product and participant. A simpler analysis might combine categories or select a particular contrast, but that changes the question and can discard information. The registry record does not report a chosen approach, so no particular model or contrast should be attributed to the investigators.
When responses are reported as percentages, the denominator and handling of missing answers are important. The registry record describes the outcome unit as a percentage of subjects answering, but does not state the analysis denominators, whether every participant answered for both products, or how incomplete paired observations were treated. Percentages alone would not convey the precision of a comparison; uncertainty estimates would also be needed to show how compatible the data are with different underlying differences.
What does a confidence interval tell the reader?
In general, a confidence interval expresses uncertainty around an estimated effect under the assumptions of the analysis. A narrow interval indicates greater precision than a wide interval, while an interval spanning values that imply different conclusions may leave the size or direction uncertain. A confidence interval is not a guarantee that the true value lies in the displayed range, and its interpretation depends on the analysis being appropriate. No confidence interval for the primary outcome is reported in the registry record.
What can be said about significance testing?
A significance test addresses compatibility between data and a specified null hypothesis under a statistical model. A small p-value is not a measure of the size or practical importance of an effect, and a larger p-value does not establish equivalence. Interpretation requires the estimate, its uncertainty, the hypotheses tested, and the analysis choices. The registry record reports no primary-outcome test, p-value, or analysis plan, so significance cannot be assessed.
The registry record also gives general assumptions for planning illustrations: a two-sided significance level of 0.05, equal allocation, and a normal approximation, with effects expressed as fractions of an observed effect. These are planning assumptions, not evidence that the original trial was designed using them. The illustrations are not observed power. Since no primary effect estimate or analysis is reported in the registry record, the illustrations should not be taken as a post hoc demonstration of what the trial could detect.
Finally, the registry record’s count of zero analyses means that statistical claims about the primary outcome are not available in this record. The methods explain choices an analysis could face; they do not identify the method used in the trial or replace a reported analysis.
10. Multiplicity, Missing Data and Analysis Populations
The primary endpoint is recorded as having several response categories, and the registry record states that it was not reduced to one comparison. It also identifies a timeframe of 21 +/- 3 days. When an outcome includes multiple categories or assessment occasions, multiple possible comparisons can arise. General statistical practice is to specify which contrasts are primary, or to account for the interpretive consequences of examining many contrasts. The registry record does not report a multiplicity strategy, a selected contrast, or whether any adjustment was planned or used.
That omission does not establish that the investigators performed multiple tests. It means the record does not explain how the range of possible comparisons was handled. Without reported category-level results and a defined inferential analysis, a reader cannot determine whether any reported finding would reflect a prespecified comparison or a selection among alternatives.
Missing data are also important in a crossover study because interpreting a paired comparison generally requires information for both product assessments. The registry record does not report missing primary ratings, completion by period, reasons for missingness, imputation, or a sensitivity analysis. Enrollment of 52 does not establish the number of complete pairs or the outcome denominators.
The analysis population is not reported in the registry record. It is therefore unclear whether the primary analysis was intended to include all randomized participants, participants who used both products, or another defined group. No conclusions about exclusions or the handling of incomplete records should be inferred. These gaps limit assessment of both bias and precision, independently of the rating scale itself.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Coloplast Test Product | 0 | 51 | 0.0% |
| Comparator | 3 | 49 | 6.1% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Coloplast Test Product | 9 of 51 |
| Comparator | 17 of 49 |
Most frequent serious adverse event terms
| Event term | Organ system | Coloplast Test Product | Comparator |
|---|---|---|---|
| Lung infection | Respiratory, thoracic and mediastinal disorders | 0 of 51 | 1 of 49 |
| Compartment syndrome in left lower leg | Musculoskeletal and connective tissue disorders | 0 of 51 | 1 of 49 |
| Acute renal failure | Renal and urinary disorders | 0 of 51 | 1 of 49 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Coloplast Test Product | Comparator |
|---|---|---|---|
| Skin irritation | Skin and subcutaneous tissue disorders | 9 of 51 | 17 of 49 |
Serious events with the highest arm-level rate: lung infection (2.0%), compartment syndrome in left lower leg (2.0%), acute renal failure (2.0%).
The registry record lists serious adverse events for 0 of 51 at risk in the Coloplast Test Product group and 3 of 49 at risk in the Comparator group. It lists other adverse events for 9 of 51 at risk in the Coloplast group and 17 of 49 at risk in the Comparator group. These are descriptive counts as recorded, not a reported statistical comparison between products.
The record lists lung infection, compartment syndrome in left lower leg, and acute renal failure among the top serious terms, each recorded as 2.0%. The entries do not establish whether an event was caused by a product. The registry record does not report deaths, so death counts cannot be inferred from the blank entries.
In a crossover study, product exposure and the period in which an event occurred can affect how safety counts should be interpreted. The registry record does not explain event attribution, timing, overlap, or whether a person could contribute to reporting under more than one product. It also does not give a statistical safety analysis or uncertainty estimates. The counts should therefore be read as the adverse-event information entered in the registry, not as proof of a comparative risk difference or a causal relationship.
12. What the Result Does, and Does Not, Mean
The record establishes that the trial was designed to compare participant ratings of peristomal fit for a Coloplast test product and a Hollister comparator. Randomized product order and a crossover structure define the intended comparison, while the five-point scale describes the planned assessment. The record also reports enrollment and descriptive adverse-event counts.
It does not report the primary outcome ratings or an analysis of those ratings. As a result, it does not show whether ratings favored either product, how large any difference might have been, or how precise an estimate would be. It also cannot establish that the products performed similarly: absence of a reported comparison is not evidence of equivalence or no difference.
The design description alone cannot fill the results gap. A crossover can support within-participant comparisons, but interpretation depends on the actual data, the number of complete assessments, and the handling of order and period. Those details are not reported in the registry record. The five-point outcome also allows multiple ways to summarize the responses, and the record does not identify a statistical analysis or a single comparison.
The listed safety counts provide additional descriptive information, but they do not answer the primary fit question and do not by themselves establish causation. Overall, the registry record communicates what was intended to be assessed and how the study was structured, but it does not provide the primary results needed to estimate comparative fit. Any conclusion about the relative ratings would require results and an analysis that are not reported in the registry record.
13. Why This Trial Matters Statistically
This trial raises statistical questions that are common in evaluations of user-facing devices. The measured outcome is a participant’s ordered judgment of fit, not a direct continuous measurement. Its interpretation depends on preserving the category information and being clear about how responses are summarized. The registry record’s description of the five-point scale makes the target assessment understandable, while the lack of outcome results leaves the statistical comparison unresolved.
The crossover design is another useful feature to consider. When the same participant assesses both products, stable personal characteristics can be controlled through within-participant comparison. At the same time, sequence and period may matter, so the design requires an analysis that matches its structure. The record does not report whether or how these features were handled. This distinction illustrates why knowing a design label is not the same as knowing the analysis.
The endpoint also demonstrates the importance of specifying a primary contrast when several categories or time points are possible. The registry record says the outcome was not reduced to one comparison. That prevents a reader from treating a single summary as the definitive primary result. A complete report would need to connect the planned question, category-level data, analysis method, and uncertainty estimate.
Finally, enrollment and adverse-event counts do not substitute for a primary outcome analysis. The record is useful for identifying the trial’s structure and planned measurement, but its statistical contribution remains limited without reported ratings, denominators, and analysis results. That is a distinction between a completed study record and an interpretable estimate of comparative effect.
14. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
The most direct limitation for interpretation is that the registry record does not report the primary outcome results. It gives the intended rating scale and timeframe, but not category counts, percentages, an effect estimate, or an uncertainty measure. Comparative fit therefore cannot be assessed from the record.
The record does not specify the analysis population or the number of participants with ratings for both products. Although enrollment is reported as 52, the record does not establish how many contributed complete crossover observations. Missingness, exclusions, and reasons for incomplete assessments are not reported in the registry record.
Important crossover details are also absent. The record does not report a washout period, period-specific results, or methods for addressing order and carryover. It gives no statistical analysis plan or explanation of how the multiple response categories or timeframe were handled. These omissions make it difficult to assess whether an eventual comparison would align with the design and the planned question.
The study was unmasked, as recorded, and the primary endpoint is a participant evaluation. That combination means expectations could potentially influence subjective ratings; the record does not report procedures to assess or mitigate this possibility. The registry also provides no participant characteristics that would allow assessment of the population represented beyond the listed ileostomy and colostomy conditions.
For safety, the record gives event counts but does not report causal attribution, timing, inferential comparisons, or death counts. These limits mean the entries should remain descriptive. The registry record is therefore insufficient for estimating primary comparative fit or making a detailed assessment of the safety analysis.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Investigation of a New 2-piece Ostomy Product in People With an Ileostomy or Colostomy — NCT02362360.
- Registry record last updated 2016-10-11; status last verified 2016-08.
- Results first posted 2016-10-11.
- Data retrieved from ClinicalTrials.gov on 2026-11-09.
- Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
NCT02362360 is a completed randomized, unmasked crossover study of the Coloplast Test Product and a Hollister comparator in people with an ileostomy or colostomy. Participants tested both products in randomized order. The registry record reports enrollment of 52 and a primary timeframe of 21 +/- 3 days.
The primary outcome was participant-rated fit of the baseplate to body contours around the stoma, using a five-point scale from very poor to very good. The registry record does not report primary outcome results or an analysis. It lists serious adverse events for 0 of 51 at risk in the Coloplast group and 3 of 49 at risk in the Comparator group, and other adverse events for 9 of 51 and 17 of 49, respectively. These counts are descriptive and do not establish causation or a comparative effect.