Removal of the Evolution® Esophageal Stent - Fully Covered: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Removal of the Evolution® Esophageal Stent - Fully Covered (NCT01900691), a na na study. The primary outcome is Number of Patients With Successful Removal of Study Stent.

2. Clinical Question

3. Trial Design

The registry record describes the CLARITY study as a clinical investigation approved by US FDA to study removal of the Evolution® Esophageal Stent - Fully Covered in malignant and benign indications. Cook Group Incorporated is listed as the sponsor. The study is marked completed, with a recorded start of 2013-09 and primary completion on 2018-12-10. The listed enrollment is 130.

The design is single-group, with allocation marked NA and masking listed as none. These entries describe a study without a separate randomized control group and without masking. The record does not describe a comparative treatment assignment. Consequently, the primary outcome is a count of participants meeting a removal-success definition, not an estimate of a difference between study arms.

The outcome description says the design allowed 130 patients to be enrolled to ensure that 58 patients had an attempted endoscopic stent removal between 7 days and 6 months for assessment of the primary measure. It specifies that the first 58 patients, whether they had malignant or benign lesions, with submitted data about an attempted removal are included in that outcome measure. This is a description of the planned outcome population; it does not establish how many participants actually had an attempt, had data submitted, or were included in an observed analysis.

The registry record lists a secondary outcome concerning the number of patients with benign indications who achieved clinical success. It does not report the results for that outcome. The rationale and detailed design of the study beyond these entries, including a fuller statistical analysis plan and eligibility criteria, are not reported in the registry record.

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:

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 Number of Patients With Successful Removal of Study Stent, measured over 7 days to 6 months.

The primary endpoint is the number of participants with successful removal of the study stent. It is a count outcome: the endpoint concerns how many participants meet the stated definition, rather than the amount of time to removal or a continuous measurement. The timeframe is 7 days to 6 months.

Success requires complete removal during a single endoscopic procedure, with the wire mesh integrity maintained so that the stent can be removed in one contiguous piece. The definition also excludes removal accompanied by tissue damage or hemorrhage visible during retrieval that is related to the removal and requires immediate treatment. This makes the endpoint a procedural success measure incorporating both completion and specified immediate complications.

In general, a prespecified endpoint makes clear which event is being counted and which observations qualify. A count can be useful for describing how often the defined outcome was recorded in the analyzed group. To interpret such a count as a rate or proportion, the number of participants assessed and the handling of missing observations also matter. Those observed outcome details are not reported in the registry record. The planned inclusion of the first 58 patients with submitted attempt data does not itself provide the observed count or establish the analyzed denominator.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

In general, an endpoint is the outcome chosen to address a study question. Here, the stated primary endpoint is a count of participants meeting a defined removal-success criterion. A count is directly interpretable as the number meeting the criterion only when its analysis population and observed value are known. A proportion additionally requires a clear denominator. The registry record describes the planned outcome population but does not report the observed count or analyzed denominator.

What does a single-group count show?

For a single-group study, a count can describe what was observed among participants assessed under the study conditions. It does not by itself establish what would have happened under a different device, procedure, or care strategy. A control group helps make a comparative estimate possible, but the record lists a single-group model and no comparator. Accordingly, there is no randomized between-group contrast to interpret.

For a binary outcome, each assessed participant is classified according to whether the specified event occurred. In general, a proportion is the number meeting the definition divided by the number assessed. The denominator must be defined carefully: participants enrolled, participants undergoing an attempt, and participants with outcome data need not be interchangeable analysis populations. The endpoint description identifies the first 58 patients with submitted attempted-removal data as the planned population, but the observed denominator and missing-data handling are not reported in the registry record.

How should uncertainty be understood?

A confidence interval is a range of values compatible with the observed data under the statistical model and its assumptions. It communicates precision: wider intervals generally indicate less precision, while narrower intervals indicate more. An interval cannot be interpreted without an observed estimate and a stated method. No primary confidence interval or observed estimate is reported in the registry record, so precision cannot be evaluated for the primary endpoint.

In general, standard methods for binary outcomes rely on assumptions about how observations arise, including that the analyzed participant outcomes are appropriately represented by the model. Repeated observations from the same participant, or dependence among participants, can affect uncertainty estimates. The registry entries do not describe repeated outcome measurements or a model for dependence. It would therefore be inappropriate to attribute a particular inferential method to the study.

Over-dispersion is a general concern when observed variation exceeds what a chosen model expects. For a count model, this can make model-based standard errors too small if not addressed. It is not possible to determine whether over-dispersion is relevant to the reported primary outcome from the registry record: the endpoint is described as a count of participants, but no fitted model, event data, or dispersion estimate is reported. A participant count should not be treated as though it were a modeled event-rate analysis without supporting details.

What do planning assumptions mean?

Sample-size calculations are planning exercises that estimate the information needed for a specified design and target effect under stated assumptions. They are not results and do not measure the power achieved after a study. The registry description says enrollment of 130 was intended to ensure 58 attempted removals with submitted data for the primary measure, referring to a sample-size calculation. The calculation details beyond that description are not reported in the registry record.

Any planning illustrations based on an observed effect should be interpreted as hypothetical design scenarios, not observed power. The stated illustration assumptions use a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and effects expressed as fractions of the observed effect. Those assumptions do not describe the listed single-group trial design. Without the displayed scenario results and an observed effect estimate, no sample-size target or power conclusion can be derived for this study.

How should a significance test be read?

In general, a p-value measures how unusual data at least as incompatible with a specified null model would be if that model and the test assumptions were true. It does not measure the probability that a treatment works, nor does it describe the size or practical meaning of an effect. Interpretation also depends on the prespecified hypothesis and analysis plan. The registry record lists 0 analyses and reports no primary p-value or hypothesis-testing procedure. There is therefore no significance test result to interpret.

Statistical methods should follow the design and endpoint, with the analysis population, missing-data approach, and uncertainty method described clearly. The registry record does not report those details for the primary endpoint. General concepts can explain what such methods would address, but they cannot fill gaps in the reported study analysis.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Evolution® Esophageal Stent")
n      <- c(58)
events <- c(57)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Evolution® Esophageal Stent  58  57  98.3  90.8  100.0  90.9  99.7  90.9  99.6

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 2 outcome measures, including the primary outcome of successful study-stent removal and a secondary outcome concerning clinical success among patients with benign indications. It lists 0 analyses. The observed results for these outcomes, and any analysis connecting them, are not reported in the registry record.

Multiplicity arises when several outcomes, time points, or statistical tests are examined. In general, testing multiple hypotheses can increase the chance of obtaining at least one apparently notable result by chance. A study may address this through a prespecified hierarchy, adjustment procedure, or other strategy, but the registry record does not report a multiplicity plan. With no posted analyses or outcome estimates, it is not possible to assess whether or how multiplicity was handled.

The record describes the first 58 patients with submitted data about attempted removal as the planned primary-outcome population. It does not report how many had outcome data, whether any records were incomplete, how missing observations were handled, or whether the outcome analysis followed a different population definition. These details matter because excluding participants without recorded outcomes can affect both the denominator and the interpretation of the estimate.

The analysis population is also not fully specified beyond the endpoint description. The registry record does not report whether all enrolled participants, only those undergoing an attempted removal, or another defined set contributed to any completed primary analysis. The planned population description should not be mistaken for confirmation of the population actually analyzed. Without reported outcome counts, analysis populations, and missing-data methods, neither the completeness nor the robustness of the outcome analysis can be assessed.

12. 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: device dislocation (7.7%), chest pain (5.4%), dysphagia (4.6%), pneumonia (4.6%), abdominal pain (3.8%).

The registry safety entries report 130 participants at risk for serious adverse events and 46 affected. For other adverse events, the record reports 130 at risk and 94 affected. It also reports 10 deaths. These are descriptive registry counts; the record does not provide a comparative safety estimate in the registry record reported.

The serious-event terms listed with percentages are device dislocation at 7.7%, chest pain at 5.4%, dysphagia at 4.6%, pneumonia at 4.6%, abdominal pain at 3.8%, and vomiting at 3.8%. These percentages are reported as listed. The registry entries do not give corresponding participant counts for each term, clarify whether participants could contribute more than one event term, or state how the percentages were calculated. They should not be used to infer unreported counts.

Adverse-event summaries do not by themselves establish causality. The registry record does not report whether each event was judged related to the stent, its placement, removal, or another cause. The event categories and terms are also not a substitute for a complete clinical assessment. In general, interpretation requires context about event definitions, timing, follow-up, and attribution; those details are not reported in the registry record.

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

The record establishes that the study was designed to evaluate removal of the Evolution® Esophageal Stent - Fully Covered in malignant and benign indications, and it supplies a specific definition of successful removal. It also describes a planned primary-outcome population: the first 58 patients with submitted data about an attempted removal during the 7 days to 6 months timeframe. These details clarify what the primary question was intended to measure.

The record does not report the observed number of successful removals, the denominator evaluated, or an uncertainty estimate. It therefore does not allow readers to quantify the primary outcome or assess how precisely it was estimated. The listed enrollment of 130 cannot stand in for the number of participants with an attempted removal or complete endpoint data.

The single-group design does not include a like-for-like control comparison in the registry record. Thus, even an observed count would describe outcomes in the study group rather than establish a difference relative to an alternative. The record also does not report the analysis plan, missing-data handling, or results for the listed secondary outcome. Those gaps restrict interpretation of both outcome completeness and statistical uncertainty.

The safety information reports adverse-event counts, deaths, and selected serious-event terms with percentages. These summaries do not establish that the device caused the events, and the registry entries do not provide comparative safety estimates or detailed attribution. Overall, the posted information supports an account of the study purpose, design, endpoint definition, and recorded safety summaries. It does not support a quantitative conclusion about the primary removal-success outcome or a causal conclusion about benefits or harms.

14. Why This Trial Matters Statistically

This trial illustrates a basic distinction between defining an endpoint and reporting its result. The registry record gives a detailed operational definition of successful removal, including complete removal during a single endoscopic procedure, maintained wire-mesh integrity, and the absence of specified visible tissue damage or hemorrhage requiring immediate treatment. Such a definition helps determine what qualifies as success. Without the observed count and denominator, however, the definition alone cannot tell readers how often success was recorded.

The design also matters for the kind of inference available. A single-group study can describe the experience of its participants, but it does not provide a randomized comparison with another approach. The design label and absence of a comparator therefore set limits on causal and comparative interpretation regardless of the endpoint definition.

The distinction between enrollment and endpoint population is another important statistical point. The listed enrollment is 130, while the primary-outcome description identifies the first 58 patients with submitted attempted-removal data as the planned group for assessment. These figures refer to different aspects of the study record; enrollment should not be substituted for the outcome denominator.

Finally, safety counts and listed event percentages need context about definitions, follow-up, and causal assessment. When analysis results, missing-data methods, and uncertainty estimates are not reported, readers cannot judge precision or the robustness of an outcome estimate. This record is therefore a useful example of why study design, endpoint definition, analysis population, and reported results must be considered together.

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.

A central limitation for interpretation is that the registry record does not report the observed primary outcome value or its evaluated denominator. The endpoint definition and planned population are available, but they do not reveal the observed number of successful removals or the completeness of outcome data.

The study is listed as single-group, with allocation marked NA and masking listed as none. No separate comparator group is described, limiting comparative interpretation. The registry entries do not report a detailed eligibility framework, the actual number of attempted removals, or the number of participants with complete primary-outcome information.

The registry record does not report a statistical analysis plan, the method used to estimate uncertainty, missing-data handling, or a multiplicity strategy. It lists 0 analyses, so no primary estimate, interval, or test result is available to assess. The secondary outcome is named, but its observed result is not reported.

Safety information is also limited in detail. The record lists affected-participant counts, deaths, and selected serious-event terms with percentages, but the registry entries do not describe event attribution, timing, calculation of the listed percentages, or whether individuals may appear under multiple terms. These limitations mean that the safety entries are descriptive and cannot be interpreted as causal comparisons.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Removal of the Evolution® Esophageal Stent - Fully Covered — NCT01900691.
• Registry record last updated 2022-09-13; status last verified 2022-08.
• Results first posted 2022-02-23.
• 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.

19. Record Summary

The registry record describes the completed CLARITY study, sponsored by Cook Group Incorporated, as a single-group clinical investigation of removal of the Evolution® Esophageal Stent - Fully Covered in malignant and benign indications. The listed enrollment is 130, and the recorded dates are 2013-09 for study start and 2018-12-10 for primary completion.

The primary endpoint counts participants with successful removal under a definition involving complete removal during a single endoscopic procedure, intact wire mesh, and no specified visible damage or hemorrhage requiring immediate treatment. The planned primary-outcome population is the first 58 patients with submitted data about attempted removal in the 7 days to 6 months timeframe. The observed primary result and analyzed denominator are not reported in the registry record.

The record lists a secondary clinical-success outcome for benign indications, 0 analyses, and safety counts of 46 participants affected by serious adverse events, 94 affected by other adverse events, and 10 deaths. These entries do not supply a comparative estimate or causal assessment.