LowCostomy: Dedicated Toward Creating a High-quality, Low-cost Colostomy Appliance for Those in Sub-Saharan Africa: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for LowCostomy: Dedicated Toward Creating a High-quality, Low-cost Colostomy Appliance for Those in Sub-Saharan Africa (NCT05824351), a non-randomized na study. The primary outcome is Skin Irritation as Measured by Draize Score for Erythema and Edema.

2. Clinical Question

3. Trial Design

The registry identifies this as a completed, nonrandomized study with no masking and a parallel model. It lists an enrollment of 50, Duke University as the sponsor, and a phase of NA. The recorded start date is 2023-06-10, and the primary completion date is 2023-06-23. These are registry entries; they do not by themselves describe how the study was conducted at each visit.

There is an important feature to keep in view when interpreting the design: the primary endpoint description says each participant received all three adhesive types. The registry also lists three intervention descriptions, one for each adhesive. Although the model is listed as parallel, the statement that each participant was tested with all three formulations describes repeated exposure within participants. The registry does not explain this apparent design tension or give a fuller account of the allocation structure. It does not report the order in which adhesives were applied, whether application order varied, or whether any interval separated applications.

Because allocation was nonrandomized, differences between adhesive results cannot automatically be interpreted as effects caused by the adhesive itself. The record does not describe a random allocation procedure, and its own design note cautions that the arms are not a like-for-like control comparison. When each participant receives each adhesive, comparisons may also depend on how repeated measurements and their relationship within a participant were handled. The registry does not report that analysis detail.

The stated purpose was to examine the safety of the beeswax-pine resin peristomal adhesive interface. The primary endpoint was skin irritation measured by Draize scores for erythema and edema. The record also lists adverse side effects and overall well-being measured by daily survey among secondary outcomes. It gives 14 outcome measures and 2 analyses, but does not report a full protocol, analysis plan, or numerical primary endpoint findings. The results available in the registry therefore support description of the design and outcome definitions, but not a quantitative assessment of comparative irritation.

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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Each participant received all three types of adhesive. Data not collected on 9 participants.

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 Skin Irritation as Measured by Draize Score for Erythema and Edema, measured over Assessed daily up to 7 days, day 7 reported.

The primary endpoint is skin irritation measured by Draize scores for erythema and edema. The registry describes each score as ranging from 0 to 4, with higher values indicating greater irritation. It says individual scores below 3 were classified as not severe. This threshold characterizes individual scores; it should not be mistaken for a group-level result or for evidence that a particular adhesive was safe.

The registry specifies a mean as the summary measure and standard deviation as the measure of dispersion. A mean describes the average score in a group or condition, while a standard deviation describes how spread out individual scores are around that average. Reporting both can give a broad account of the observed scores, although neither alone describes every feature of their distribution.

The endpoint was assessed daily up to 7 days, with day 7 reported. Skin findings such as erythema and edema are relevant to the stated purpose of examining irritation at the adhesive interface. However, the registry record does not report the actual day 7 means or standard deviations, nor does it report a numerical comparison between the adhesive types. The endpoint definition explains what the study intended to measure, not what its numerical findings were.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the mean describe?

The primary outcome is a continuous score summarized by its mean, with a standard deviation. In general, a mean is the arithmetic average of the values included in an analysis. It offers a compact description of the typical score, but it does not show how scores are distributed, whether there are clusters at particular values, or whether a small number of observations influence the average. The standard deviation gives a description of the spread of values around the mean. A small spread indicates scores are closer to the mean than a large spread does, in general; neither spread nor mean reveals the individual observations.

Here, the underlying Draize scores are bounded from 0 to 4, and the registry defines higher scores as greater irritation. The bounded scale matters when interpreting a mean: the mean is a summary of scores on that scale, not a direct count of participants with irritation. The record says individual scores below 3 were classified as not severe. That classification applies to individual scores, and it does not tell readers the mean score, the number of scores at or above a threshold, or the proportion of participants with any particular degree of irritation.

Why does the repeated assessment matter?

The primary endpoint description states that each participant received all three adhesive types. If outcomes from the same participant are compared across those types, the observations may be correlated: a participant's measurements under one condition may be more similar to that participant's other measurements than to measurements from another participant. As a general statistical principle, an analysis should reflect the structure of the observations. A paired or repeated-measures approach can account for within-participant relationships, whereas an analysis that treats all observations as independent may misstate uncertainty. The registry record does not report which approach was used, so it is not possible to evaluate that aspect of the analysis.

The registry lists a parallel model while also stating that each participant received all three types. These descriptions do not, on their own, explain the full measurement and allocation structure. The order of application, any interval between applications, and any handling of potential order effects are not reported in the registry record. These details matter because the interpretation of repeated exposure depends on how the assessments were organized and analyzed. No particular procedure should be assumed.

What does uncertainty mean?

In general, an estimate is more useful when accompanied by a measure of its uncertainty. A confidence interval communicates the range of estimates compatible with the observed data under the interval's assumptions. A standard error can describe uncertainty in an estimate, while a standard deviation describes variation among observations; these are different quantities. The registry identifies a standard deviation for the primary endpoint but does not report numerical endpoint summaries or a confidence interval for a comparison. The precision of a difference between adhesives is therefore not available in the registry record.

A hypothesis test, when used, evaluates how compatible data are with a specified statistical model and null hypothesis. A p-value does not measure the size or importance of an effect, nor does it establish that the null hypothesis is true or false. The registry record does not report a primary endpoint p-value, the testing procedure, or the hypothesis being tested. No significance conclusion can be drawn from the endpoint description alone.

How should design affect the comparison?

Nonrandomized allocation means that assignment is not described as random. In general, randomization helps balance measured and unmeasured participant characteristics across treatment groups, while nonrandomized comparisons may be affected by differences in who receives or is assessed under each condition. The registry itself cautions that the arms are not a like-for-like control comparison. The description that each participant received all three adhesives may allow within-participant comparisons, but it does not resolve every design concern. The record does not report the application sequence or the statistical method used to compare scores.

Masking is listed as none. Masking can, in general, reduce the influence of knowledge of the assigned condition on assessment or reporting. Its absence does not establish that assessments were biased, but it leaves open the possibility that expectations could influence subjective scoring. The record does not describe assessor training, independent review, or other procedures for standardizing the Draize assessments, so those features should not be presumed.

What can be learned from planning assumptions?

The registry includes a description of a planning illustration based on the observed effect. It specifies a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect described as a fraction of the observed effect. It also distinguishes between participants per arm for most outcomes and total events for time-to-event calculations. These are planning assumptions, not a report of the trial's observed power. The resulting sample-size values are not reported in the registry record, and the registry does not say that these assumptions formed the original study design.

A sample-size illustration is conditional on its assumptions, including the effect size chosen for planning and the model used. It is not evidence that a study was adequately powered, and it cannot substitute for observed estimates and their uncertainty. In this record, no numerical observed effect for the primary endpoint is reported, so readers cannot independently judge the planning illustration against the endpoint results.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 14 outcome measures and 2 analyses. It includes adverse side effects and overall well-being measured by daily survey among the secondary outcomes; the overall well-being outcome appears three times in the listed descriptions. The record does not explain whether these entries represent distinct time points, analyses, or repeated listings. It does not report which outcomes were designated as confirmatory, how many comparisons were tested, or whether any multiplicity adjustment was used.

Multiplicity is a general statistical concern when many outcomes or comparisons are examined. The more questions assessed, the greater the chance that some results may appear unusual just by chance. Adjustments or a prespecified hierarchy can help address that concern, but the registry does not report whether such procedures were used. Without the analysis plan and full numerical results, the handling of multiple outcomes cannot be evaluated.

For missing data, the primary outcome description states that data were not collected on 9 participants. The record does not say why those data were unavailable, whether the missingness affected all three adhesive assessments or particular measurements, or how missing observations were handled. It does not report whether the analysis used complete observations only, imputation, or another method. These are not details that can be inferred from the enrollment or endpoint description.

In general, missingness can affect an estimate if the observations that are absent differ systematically from those that are available. The amount and likely effect depend on the reasons for missing data and on the analysis method. Since those reasons and methods are not reported, the potential direction or magnitude of missing-data bias cannot be determined. The registry also does not define a separate analysis population for the primary endpoint. It is therefore unclear which observations contributed to any analysis, and the numerical outcome results needed to assess this are not reported in the registry record.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

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 records 0 serious adverse events and 6 other adverse events in a single combined group covering the Tanzanian beeswax-pine adhesive, the domestic beeswax-pine adhesive, and the control. The group lists 50 at risk. It also records 0 deaths. These are the safety figures as entered for the combined group; they are not broken down by adhesive type in the registry record.

Because the safety counts combine all three adhesives, they cannot show which formulation, if any, was associated with an event. The figures also do not establish the nature or severity of each of the 6 other events beyond the category shown. The registry lists no serious adverse event terms, so it does not provide descriptions of serious events. This should be read as a report of the registry's recorded counts, not as proof that no event occurred outside what was captured or reported.

These adverse-event counts are distinct from the primary Draize endpoint, which measures erythema and edema using scores from 0 to 4. An event count and an irritation score answer different questions. The registry record does not provide numerical Draize results or event-specific attribution, so neither the safety counts nor the endpoint definition can establish comparative safety between the adhesives.

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

The record establishes that a completed study examined a beeswax-pine resin adhesive interface and a control adhesive in participants with a colostomy. It specifies the primary measurement, the timing, and the scale: Draize scores for erythema and edema, assessed daily up to 7 days, with day 7 reported; scores range from 0 to 4, and higher scores indicate greater irritation. It also describes individual scores below 3 as not severe. These details make the intended outcome interpretable, but they are not numerical findings.

The registry does not report the day 7 means, standard deviations, or a comparative estimate for the adhesives. It therefore does not show whether scores were higher or lower for one formulation, how large any difference might have been, or how precisely a difference was estimated. No p-value or confidence interval for the primary comparison is reported. A conclusion about the direction or statistical significance of the primary result cannot be drawn from the outcome definition.

The safety figures provide a limited additional description: the combined adhesive group has 0 serious adverse events, 6 other adverse events, and 0 deaths recorded, with 50 listed at risk. Since the count is not separated by adhesive, it cannot identify which product was associated with the events. The registry does not provide the event details needed to interpret the 6 other events further.

The nonrandomized design and the registry's caution that the arms are not a like-for-like control comparison also matter. Each participant is described as receiving all three adhesive types, but the record does not explain the order of application or how repeated measurements were analyzed. The record reports missing data for 9 participants without explaining the reasons or handling. These gaps constrain interpretation of any comparison.

Accordingly, the record supports a description of what was assessed and how the study was organized, but not a quantitative claim about whether the adhesives differed in irritation or safety. It does not establish that a formulation works, does not work, or is safer than another. Those conclusions would require numerical results and analysis details not reported in the registry record.

13. Why This Trial Matters Statistically

This study raises a useful statistical issue: the description combines three adhesive conditions with a statement that every participant received each one, while the registered model is parallel. That makes clarity about the observation structure especially important. When measurements are repeated within participants, the analysis may need to account for their dependence. A clear account of allocation, application order, and analysis would help readers understand what comparisons were actually made and how uncertainty was estimated.

The endpoint also illustrates the distinction between defining a measure and reporting a result. The registry gives the Draize score range, the direction of interpretation, a threshold for classifying individual scores as not severe, and a day 7 reporting time. These make the outcome definition more transparent. But the mean and standard deviation values are absent, so readers cannot assess observed irritation or the precision of any comparison. A carefully defined outcome is necessary for interpretation, but it cannot replace the result itself.

Missingness is another important feature. The record notes data were not collected on 9 participants, but does not explain why or how the analyses handled the unavailable observations. General statistical reasoning shows why these details matter: if observations are missing for reasons related to the outcome, the available data may not represent the full study population. The record does not permit an assessment of whether that concern applies.

Finally, the combined safety counts illustrate why aggregation needs context. The registry records 6 other adverse events for a group containing all three adhesive types, with no attribution by type. Those counts describe the combined record, not comparative event rates. This trial is therefore statistically informative as an example of why design structure, endpoint reporting, missing-data handling, and outcome-specific safety summaries are essential to interpreting clinical research. Its numerical primary findings and several analysis details are not reported in the registry record.

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 registry does not report numerical results for the primary endpoint. In particular, the day 7 means and standard deviations for erythema and edema are absent, as are a comparative estimate, confidence interval, and test result. This prevents assessment of the observed scores, the size of a difference, or its precision.

The design description has an unresolved ambiguity: the model is listed as parallel, while the endpoint description says each participant received all three adhesives. The registry does not clarify the allocation structure, application sequence, or how repeated observations were analyzed. It also identifies the allocation as nonrandomized and warns that the arms are not a like-for-like control comparison. These features limit causal interpretation and make the analysis method particularly relevant.

The record states that data were not collected on 9 participants, but gives no reasons, outcome-specific missingness details, or method for handling missing observations. It does not identify the analysis population for the primary endpoint. The potential influence of missing data therefore cannot be assessed.

The registry lists 14 outcome measures and 2 analyses, but does not report a complete statistical analysis plan, a multiplicity strategy, or which results were considered primary beyond the named endpoint. The overall well-being daily survey appears three times among the secondary outcomes, with no explanation of whether the entries refer to different time points or analyses.

Safety reporting is aggregated across the two beeswax-pine adhesives and the control. The record therefore does not allow event attribution by adhesive. It lists no serious-event terms and gives no detail about the 6 other events. The registry also does not describe masking beyond listing none, or report procedures for standardizing outcome assessment. These limitations are specific to the information recorded and should not be filled in by assumption.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: LowCostomy: Dedicated Toward Creating a High-quality, Low-cost Colostomy Appliance for Those in Sub-Saharan Africa — NCT05824351.
• Registry record last updated 2024-09-26; status last verified 2024-08.
• Results first posted 2024-09-26.
• 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

NCT05824351 is a completed, nonrandomized study sponsored by Duke University. Its stated purpose was to examine the safety of a peristomal adhesive interface made from beeswax and pine resin. The record lists an enrollment of 50, no masking, a parallel model, and phase NA. It records a start date of 2023-06-10 and a primary completion date of 2023-06-23.

The primary endpoint was skin irritation measured by Draize scores for erythema and edema, assessed daily up to 7 days, with day 7 reported. Scores range from 0 to 4, and higher scores indicate greater irritation; individual scores below 3 were classified as not severe. Each participant is described as receiving the Tanzanian beeswax-pine adhesive, the domestic beeswax-pine adhesive, and Hollister's AdaptTM Barrier Rings. Data were not collected on 9 participants.

The registry records 0 serious adverse events, 6 other adverse events, and 0 deaths in a combined group with 50 at risk. Numerical primary endpoint results, event attribution by adhesive, and key details of the statistical analysis are not reported in the registry record.