Study Evaluating a New Ostomy Appliance With Regard to Leakage, Handling and Comfort: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study Evaluating a New Ostomy Appliance With Regard to Leakage, Handling and Comfort (NCT01243294), a randomized phase 2, phase 3 study. The primary outcome is Leakage (Percent of All Base Plates With Leakage).

2. Clinical Question

The study asked whether leakage and participant assessments differed between a new ostomy appliance, called SS in the registry, and SenSura. It enrolled people with colostomy and used each appliance in turn, so participants could assess both products. The primary outcome concerned leakage across base plates; secondary outcomes included participants’ assessments of security, handling, and comfort, as well as wear time and adverse events.

This is a product-comparison question within a particular study population and observation period. It is not a comparison of long-term outcomes: each product was evaluated over a test period of 10 (±2) days, and base plates were changed 1-6 times a day. The registry does not report a primary inferential analysis that accounts for the crossover structure. Consequently, the reported summaries can describe the observed leakage values, but the record does not establish a statistically adjusted estimate of the difference between appliances.

3. Trial Design

The registry describes a randomized, open-label crossover study of two devices. Participants used both the new appliance SS and SenSura, with one product used first and the other afterward. The record says 26 participants started at SS and crossed over to SenSura, while 28 started at SenSura and crossed to SS. It reports that 54 participants evaluated each device. The enrollment was 56.

The study was open label, meaning masking was not used. A crossover design can let each participant contribute observations under both products, which may reduce the influence of stable differences between participants when a suitable paired analysis is used. It also makes the order of product use relevant: period effects, learning, and carryover from the first product may affect later observations. The registry record does not report whether these effects were assessed or how they were handled analytically.

The primary outcome was measured after each base-plate change over a period of 10 +/- 2 days. The registry says base plates were changed 1-6 times a day. The participant-assessment outcomes were recorded after each test period, described as 10 (±2) days with one product and then 10 (±2) days with the other. The study is marked completed, and its recorded start and primary-completion dates are 2010-08 and 2010-11.

Randomization method and allocation concealment are not reported in the registry record. Nor are details of sequence generation, washout between products, protocol deviations, participant flow, or handling of incomplete observations. These details matter when interpreting a crossover study because the summaries for two products may be correlated within participants, while an analysis that treats the two sets as independent may not represent that design.

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: 56 subject where enrolled, however two subjects did not comply to the in- and exclusion criteria and was hence terminated before testing any devices

First Intervention (10 Days +/- 2 Days)

Second Intervention (10 Days +/- 2 Days)

Analysis population for the primary outcome, as defined in the registry: Intention to treat. As this is a cross-over investigation 26 started at SS and crossed over to SenSura, and 28 started at SenSura and crossed to SS leading to a total population of 54 evaluating each medical device

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 Leakage (Percent of All Base Plates With Leakage), measured over After each base plate change measured over a period of 10 +/- 2 days. Base plates are changed 1-6 times a day.

The primary outcome is leakage, described as the percent of all base plates with leakage. At each base-plate change, leakage was assessed on a four-point scale: no leakage, leakage on the base plate, leakage soiling clothing, and sudden leakage. The latter three categories counted as leakage; no leakage was the preferred endpoint.

This outcome addresses a practical feature of appliance use: whether leakage occurred during the period of wear. Recording observations after each base-plate change also captures repeated experiences rather than relying on a single end-of-study recollection. However, those repeated observations arise from participants who used both products, and observations within a participant may be related. A statistical comparison therefore needs to respect the crossover and repeated-measure structure if it is to quantify uncertainty appropriately.

The registry reports values of 27.0 and 30.0 percent for the two appliances, with n=54 for each. It does not provide an uncertainty interval or a primary comparison estimate. It also states that the posted values were missing or not estimable for a two-arm comparison for this count-type endpoint. Thus, the summaries describe the recorded outcome values, but the registry record does not give a formal estimate of how precisely the appliance contrast is determined.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation depends on how an outcome was measured, how observations are related, and what comparison was planned. The registry describes a randomized crossover study, reports summaries for both devices, and lists no registered analyses. The methods needed to connect the design to a formal primary comparison are therefore not reported in the registry record.

What does a crossover design change?

In a parallel-group study, participants are generally assigned to one product and contribute observations to that product’s group. In a crossover study, each participant uses more than one product. This can be useful because each person can serve as a reference for their own response, reducing the impact of stable participant characteristics on a product comparison. The observations are paired, however: the values from one participant under each product may be related. Analyses that account for that pairing can differ from analyses that treat the product groups as independent.

The order in which products are used can matter. Outcomes may change over time regardless of product, participants may become more familiar with the appliance, or effects of the first period may persist into the next. These possibilities are often described as period, learning, and carryover effects. They are general concerns in crossover designs, not claims that such effects occurred in this study. Whether the protocol included a washout period, whether order effects were assessed, and how any such effects were modeled are not reported in the registry record.

What is an unadjusted comparison?

An unadjusted comparison summarizes an outcome contrast without accounting for other features of the design or additional variables. The posted secondary risk-difference comparisons are unadjusted. Their estimates and intervals can convey the direction and uncertainty of the reported contrasts under the calculation used, but they do not show that the crossover dependence or other design features were modeled. The registry lists no reported analyses, so the record does not identify a sponsor analysis that can be used to resolve that limitation.

For the primary leakage endpoint, the registry supplies values for each device but says the values are missing or not estimable for a two-arm comparison for this count-type outcome. It does not give an inferential estimate or interval for the contrast. A comparison of the reported values alone cannot supply an appropriate uncertainty estimate. In particular, it would not be sound to infer statistical significance from the direction or apparent closeness of two descriptive values.

How should an interval be read?

In general, a confidence interval is a range of values compatible with the observed data under a specified statistical method and its assumptions. Its width reflects statistical precision: wider intervals indicate greater uncertainty about the estimate than narrower intervals. An interval containing the no-difference value does not demonstrate that the products are equivalent; it means the data and method do not rule out that value at the interval’s stated confidence level. Conversely, an interval that excludes no difference does not establish clinical importance or remove concerns about bias, multiplicity, or whether the analysis matches the design.

The secondary outcome comparisons include risk differences, with intervals and unadjusted p-values. A p-value is a measure of how unusual data at least as inconsistent with a null hypothesis would be if that hypothesis and the analysis assumptions held. It is not the probability that the null hypothesis is true, nor a measure of the size or importance of an effect. Because the registry does not report a crossover-adjusted analysis, these statistical summaries should be interpreted as unadjusted comparisons rather than as a complete analysis of the trial design.

Why does over-dispersion matter?

In general, over-dispersion occurs when count data vary more than a statistical model expects. If a model assumes less variability than is present, standard errors may be too small and intervals may be too narrow. Repeated leakage observations can also be correlated within a participant, which is a distinct but related reason that a simple model may understate uncertainty. The record does not report the distribution of leakage counts or a model for repeated observations, so it is not possible to determine whether over-dispersion was assessed or how dependence was handled.

What do the planning illustrations mean?

The planning illustrations use the observed effect as a reference and show participants per arm under stated assumptions: a two-sided significance level of 0.05, equal allocation, and a normal approximation. The rows describe planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. For example, the comfort comparison lists 37 participants per arm for 80% power when planning for 100% of the observed effect, and 111 participants per arm for 80% power when planning for 50% of the observed effect.

These are planning illustrations, not observed power and not evidence that the trial was designed around those assumptions. Smaller target effects require larger sample sizes under the same general planning approach. The registry does not report the trial’s own sample-size justification, assumptions, or intended power. It also does not say that the illustrations account for crossover pairing, so they should not be interpreted as a design-specific sample-size recommendation.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists several secondary outcomes, including adverse events, security, handling, comfort, and wear time. It posts results for security, handling, and comfort, but the record does not provide posted numerical results for every listed secondary outcome. A missing result is not evidence that no outcome occurred or that the products were equivalent on that measure.

When a study examines multiple outcomes, each test creates an opportunity for a result to appear statistically notable by chance. In general, a multiplicity plan may prioritize outcomes, adjust significance thresholds, or otherwise account for the number of comparisons. Whether such a plan was used, which outcomes were treated as confirmatory, and whether any adjustment was made are not reported in the registry record. The posted secondary p-values are unadjusted and should not be interpreted as controlling the overall error rate across all outcomes.

The registry describes the primary population as intention-to-treat and says 26 participants began with SS and crossed to SenSura, while 28 began with SenSura and crossed to SS. It also reports 54 participants evaluating each device, compared with enrollment of 56. The disposition of the other enrolled participants, reasons for any missing observations, and methods for handling missing data are not reported in the registry record. It is therefore not possible to assess whether missingness could have affected the estimates.

The record does not describe how intention-to-treat was operationalized for this crossover study, including whether all randomized participants were analyzed according to assigned sequence or how incomplete periods were handled. The planned analysis, primary statistical model, treatment of repeated observations, and sensitivity analyses are also not reported. These omissions limit assessment of bias and uncertainty. The absence of those details does not show that no such methods were used; it means they cannot be evaluated from the registry record.

11. 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 non-serious adverse event terms

The registry lists zero serious adverse events among 54 participants at risk for SenSura and zero among 54 participants at risk for SS. It lists 2 other adverse events for SenSura and 1 for SS, with 54 at risk in each group. These are descriptive counts during the study’s observation periods.

The serious-event figures should not be read as proof that serious events cannot occur or that the products have identical safety profiles. A small study and short product-use periods may provide limited information about uncommon or delayed events. The registry does not report serious adverse-event terms, and deaths are not reported in the registry record. The listed other adverse events are not described by type in these figures, so their clinical nature cannot be assessed from the counts alone.

Because participants used both appliances, the event counts also need context about exposure periods and attribution. The registry provides group counts but does not explain how events in the crossover periods were assigned, whether any events were judged related to an appliance, or how safety comparisons were analyzed. These counts are useful as a concise record of what was reported, but they do not establish a comparative safety difference.

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

The results describe a randomized, open-label crossover evaluation of SS and SenSura in people with colostomy. For the primary leakage endpoint, the registry posts values of 27.0 and 30.0 percent, respectively, with n=54 for each device. It does not post a primary comparison estimate, interval, or p-value. The primary summaries therefore describe the observed values but do not establish the precision of a difference between appliances.

Secondary participant assessments show a mixed pattern, with some posted comparisons favoring SS descriptively and the handling comparison close between products. Those comparisons are unadjusted, and the registry does not report a crossover-adjusted analysis. Their p-values and intervals do not establish whether a difference is important to participants, and they do not settle the primary leakage question. The record also does not report a multiplicity plan, so the secondary findings carry additional uncertainty when considered as a group.

The findings do not establish equivalence. A lack of a reported primary significance test is not evidence that the devices perform the same, just as a secondary p-value below a conventional threshold is not proof of a clinically important benefit. The record also cannot show how representative the participants were beyond the stated colostomy condition, or how outcomes might differ over longer use, because such information is not reported.

In general, statistical results describe uncertainty under the assumptions and methods used; they do not by themselves determine practical importance or answer every question about a product. Here, the missing primary inferential result, the paired crossover design, the open-label assessments, and unreported analysis details all constrain interpretation. The posted data are best treated as descriptive evidence from a short comparison, not as a definitive estimate of the relative effects of the two appliances.

13. Why This Trial Matters Statistically

This trial illustrates why design and analysis must be read together. A crossover study gives each participant experience with both products, which can make within-person comparison informative. But that advantage depends on analysis that respects the pairing and considers order, period, and possible carryover. The registry reports the crossover sequences but does not report whether the posted comparisons accounted for those features.

The primary endpoint also demonstrates the difference between a descriptive summary and an inferential result. The registry gives leakage values for both products, yet does not provide an uncertainty interval or formal primary comparison. Without that information, readers cannot determine the precision of the contrast from the registry record. Reporting outcome values alone does not answer whether an apparent difference is robust to sampling variability.

The secondary outcomes show why multiplicity matters. Several participant assessments were listed, with unadjusted comparisons for some outcomes and different patterns across them. A single p-value can be easy to overemphasize when many outcomes are examined. Without a reported hierarchy or adjustment plan, individual secondary results are better treated as exploratory rather than as a unified confirmatory conclusion.

Finally, the planning illustrations underscore that sample-size calculations depend on assumptions about the effect to detect and the analysis. They are not observed power, and the registry does not report that they were used to design this study. Together, these features make the record useful for understanding the questions and observed summaries, while also showing why transparent analysis plans and complete reporting are essential for interpreting crossover trials.

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.

Several limitations specific to this study constrain interpretation. The trial was open label, so participants knew which appliance they were using when making subjective assessments. Expectations could influence reported security, handling, or comfort; the registry does not report any method to address such influence. The primary leakage assessment also involves repeated observations after base-plate changes, which may be correlated within participants.

The crossover structure requires attention to paired observations, sequence, and time period. The record gives the sequence counts but does not report a model, period-effect assessment, carryover assessment, or washout details. It is therefore not possible to determine whether these design features were addressed in the analysis. The registry also does not report the primary comparison estimate or uncertainty interval, limiting interpretation of the main endpoint.

The enrollment was 56, while the record describes 54 participants evaluating each device. Participant flow, reasons for missing observations, and missing-data methods are not reported. The numerical summaries for the primary outcome are not accompanied by an inferential comparison, and the listed secondary comparisons are unadjusted. Multiplicity handling is not reported, as are the trial’s own sample-size justification and analysis plan.

The test periods were 10 (±2) days per product, and the registry describes base-plate changes 1-6 times a day. These summaries therefore concern a limited observation period; longer-term use and outcomes beyond those recorded are not established by this study. The record identifies colostomy as the condition but does not provide further participant characteristics in the information summarized. These limitations do not demonstrate that bias occurred, but they restrict how confidently readers can interpret the results and apply them beyond the recorded study setting.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Study Evaluating a New Ostomy Appliance With Regard to Leakage, Handling and Comfort — NCT01243294.
• Registry record last updated 2011-10-07; status last verified 2011-10.
• Results first posted 2011-06-22.
• 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.

18. Record Summary

NCT01243294 is a completed randomized, open-label crossover study sponsored by Coloplast A/S. It evaluated a new ostomy appliance, SS, against SenSura in people with colostomy. The registry lists enrollment of 56 and describes 54 participants as evaluating each device, with 26 beginning at SS and 28 beginning at SenSura.

The primary outcome was the percent of base plates with leakage, assessed after each change over a period of 10 +/- 2 days. The registry posts values of 27.0 percent for New Adhesive SS and 30.0 percent for SenSura, but does not provide an inferential primary comparison. Secondary participant assessments include security, handling, and comfort; their posted comparisons are unadjusted. The record lists no reported analyses, does not describe multiplicity handling or missing-data methods, and does not provide the trial’s own sample-size justification.