Sacral Nerve Stimulation Therapy for the Treatment of Chronic Fecal Incontinence: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Sacral Nerve Stimulation Therapy for the Treatment of Chronic Fecal Incontinence (NCT00200057), a non-randomized na study. The primary outcome is Proportion of Subjects With at Least 50% Reduction in Number of Incontinent Episodes Per Week.

2. Clinical Question

3. Trial Design

NCT00200057, titled “Sacral Nerve Stimulation Therapy for the Treatment of Chronic Fecal Incontinence,” was a completed, non-randomized, single-group device study. The official title identifies Medtronic InterStim sacral nerve stimulation therapy for bowel control. The sponsor is MedtronicNeuro. The registry lists no applicable phase, no masking, and an enrollment of 285.

The study began in 2002-01, and primary completion is listed as 2007-08. These registry dates describe the study record; they do not establish when any individual participant was followed or whether every participant completed the planned follow-up. The brief summary describes 120 patients as being implanted and followed closely for twelve months, with follow-up once a year thereafter until the study closed. It also describes up to 20 centers in the United States. The primary analysis population is described as successfully implanted subjects. The registry record does not explain how enrollment of 285 relates to the 120 implanted subjects or to the analysis population.

With no randomized comparator, changes from baseline are within-subject observations rather than randomized treatment contrasts. The design can describe outcomes among implanted subjects, but it cannot by itself separate a treatment effect from other explanations for change over time. Masking is listed as none. Details of a comparator, protocol deviations, and a fuller account of the study procedures 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.

Before assignment: All patients who signed an informed consent were considered enrolled in the study. Of the 285 subjects who enrolled in the study, 132 subjects underwent acute test stimulation with 129 proceeding to the sub-chronic test stimulation phase. Of these, 120 subjects qualified for permanent implant. All 120 patients were successfully implanted.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All subjects who were successfully implanted were included in the analysis. A modified worst-case analysis was used for missing data, where all subjects who were missing 12-month data were classified as failures, unless there was a subsequent diary available, in which case the subsequent diary was substituted for the missing 12-month data.

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 Proportion of Subjects With at Least 50% Reduction in Number of Incontinent Episodes Per Week, measured over Baseline and 12 months.

The primary endpoint is the proportion of implanted subjects who achieved at least a 50% reduction in fecal incontinent episodes per week at 12 months compared with baseline. The endpoint converts each subject’s change into a binary classification: a reduction meeting the threshold is a success; a reduction that does not meet it is not. The primary objective was that at least 50% of subjects would be successes.

A threshold-based endpoint can make a clinically interpretable target explicit and gives a direct summary of how many subjects meet that target. It also discards information about the size of changes within each category: subjects just meeting the threshold and subjects with larger reductions both count as successes. The observed success rate therefore answers a specific question about threshold attainment, rather than describing the full distribution of episode changes.

The registry lists baseline and 12 months as the timeframe and defines the observed therapeutic success rate using implanted subjects. It also describes a modified worst-case approach to missing 12-month data, classifying subjects without such data as failures unless a subsequent diary was available. The registry record’s description of what happens when a subsequent diary is available is incomplete. The actual success proportion and its 95% confidence interval are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a proportion estimate?

The primary endpoint is a proportion: the share of subjects classified as successes under the registry’s threshold rule. Each subject is classified according to whether the number of fecal incontinent episodes per week fell by at least 50% from baseline to the 12-month assessment. The resulting estimate is a summary of the frequency of threshold attainment in the analyzed group. It is not the average reduction in episodes, and it does not show how far each subject’s result was above or below the threshold.

A confidence interval communicates sampling uncertainty around an estimate. In general, it gives a range of values compatible with the data under the method’s assumptions. It does not guarantee that a particular range contains the true value, and its interpretation depends on the analysis and data quality. Although the primary endpoint is described with a 95% confidence interval, the estimate and interval themselves are not reported in the registry record. Their width, location, and relationship to the objective therefore cannot be assessed.

What does the single-group design allow?

The allocation is non-randomized and the model is single-group. There is no randomized comparator against which to interpret the change from baseline. A within-subject comparison uses each subject’s baseline as a reference, but baseline is not a concurrent control condition. In general, that means the observed change can be described, while a causal contrast with an alternative treatment or no intervention cannot be isolated from other changes occurring over time. This is a design limitation, not evidence for or against a particular outcome.

Randomization is useful because it can balance measured and unmeasured factors between groups on average. Without random assignment and a comparison group, differences between the observed follow-up and baseline may reflect influences besides the intervention. The registry record does not report a control group, masking, or a randomized allocation process. The record also does not report an adjusted causal analysis that would alter the basic single-group interpretation.

How should the threshold be understood?

A threshold-based endpoint provides a clear rule for classifying success. Here, the rule requires at least a 50% reduction in weekly episodes at 12 months compared with baseline. It is possible for two subjects with different magnitudes of change to receive the same success classification if both meet the threshold. Conversely, subjects with similar reductions near the boundary can be assigned different classifications. These are general properties of dichotomizing a continuous change measure.

Thresholds can aid interpretation when the question is whether a specified degree of change was achieved. They do not replace examination of the underlying outcome distribution. The registry record does not provide the individual or group-level episode data needed to describe that distribution. Nor does it report the actual proportion crossing the threshold.

What does the missing-data approach imply?

The primary analysis description says that all subjects missing 12-month data were classified as failures, unless a subsequent diary was available. Treating missing outcomes as failures is a conservative classification for an endpoint where success requires meeting a reduction threshold, but it does not eliminate uncertainty about missing outcomes. It makes an assumption about how subjects without the specified observation are counted. A later diary may be used differently, but the registry record’s description of that rule is truncated after saying a subsequent diary was available. The remaining rule is not reported in the registry record.

In general, missing-data assumptions can influence the estimated proportion, particularly when the amount or pattern of missingness is substantial. The number missing at 12 months, reasons for missingness, and sensitivity analyses are not reported in the registry record. It is therefore not possible to assess how robust the primary estimate would be to alternative missing-data assumptions.

What do planning calculations represent?

Planning illustrations are distinct from observed results and from the study’s original design justification. The assumptions described for planning illustrations are a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. Such calculations are hypothetical planning exercises; they do not show the power actually achieved by this single-group study. The record does not report the trial’s own sample-size justification. The specific effect fractions and resulting sample-size values are not reported in the registry record.

For time-to-event planning, the stated convention is to report total events; for other planning outputs, it is participants per arm. No time-to-event primary endpoint is described in the registry record. These conventions should not be confused with the observed enrollment or implanted population.

What can be said about multiple outcomes?

The record lists seven outcome measures and seven analyses. When several outcomes are examined, the chance of at least one apparently notable result can increase if each is interpreted independently. Statistical methods can address this issue through prespecified outcome hierarchies or multiplicity adjustments, but the registry record does not report such a procedure. It also does not provide sufficient results to assess how multiple testing was handled in practice. The primary efficacy finding cannot be reconstructed from the stated objective alone.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists seven outcome measures and seven analyses. These include the primary proportion achieving at least a 50% reduction in weekly fecal incontinent episodes, a proportion for urgent incontinent episodes, and changes on four quality-of-life scales. The listed outcomes represent multiple opportunities to examine different aspects of the study. In general, when multiple outcomes or tests are considered, the interpretation of isolated findings can be affected by multiplicity. A prespecified testing hierarchy or adjustment can help define how evidence across outcomes is evaluated, but such a procedure is not reported in the registry record.

The primary endpoint’s missing-data rule is described as a modified worst-case analysis. Subjects missing 12-month data were classified as failures unless a subsequent diary was available. The registry record’s description of how a subsequent diary changes the classification ends mid-sentence; the remainder of that rule is not reported in the registry record. Counts of missing 12-month outcomes, reasons for missingness, and sensitivity analyses using alternative assumptions are also not reported in the registry record.

The primary analysis population is described as all subjects who were successfully implanted. The record reports enrollment of 285 and describes 120 implanted subjects, but it does not give a complete accounting of participants from enrollment through the endpoint analysis. It does not report the number contributing primary endpoint data or a detailed flow through analysis populations. The stated analysis population and missing-data rule are therefore important context, but they do not supply the absent efficacy estimate or resolve uncertainty about missing outcomes.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: implant site infection (4.2%), rectal prolapse (4.2%), implant site pain (3.3%), transient ischaemic attack (1.7%), deep vein thrombosis (1.7%).

Among the 120 implanted subjects, 41 were recorded as having serious adverse events, and 88 were recorded as having other adverse events. These are counts of affected subjects in the registry’s implanted-subject group, not a comparison between treatment groups. The record does not report a randomized control group, so the figures do not establish how event occurrence compares with another treatment or with no intervention.

The registry lists the following serious adverse event terms with their posted percentages: implant site infection, 4.2%; rectal prolapse, 4.2%; implant site pain, 3.3%; transient ischaemic attack, 1.7%; deep vein thrombosis, 1.7%; and pancreatitis, 1.7%. These are the listed terms and percentages; the registry record does not provide additional detail about event timing, duration, severity beyond the serious classification, or attribution to the device. The terms should not be interpreted as evidence that the intervention caused the events.

Deaths are not reported in the registry record. The overall counts and listed terms can describe the recorded safety experience in the implanted group, but they do not by themselves establish comparative safety or quantify risks beyond the study’s recorded follow-up and reporting.

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

The record establishes what the primary endpoint was intended to measure: the proportion of successfully implanted subjects with at least a 50% reduction in weekly fecal incontinent episodes at 12 months compared with baseline. It also sets out the target that at least 50% of subjects would meet that threshold. This defines the question, but it is not itself evidence that the target was achieved.

The numerical primary result and its 95% confidence interval are not reported in the registry record. As a result, the observed frequency of success, the precision of that estimate, and whether the result met the stated objective cannot be determined from the recorded primary outcome information. No conclusion about the size or certainty of the primary efficacy result follows from the objective alone.

Even if a before-and-after result were available, the single-group non-randomized design would limit causal interpretation. A change among implanted subjects would not, on its own, show how outcomes would have differed under a comparator condition. It could describe the course of the measured outcome in this group, but it could not isolate the intervention’s contribution from other influences over time.

The safety information records adverse events among implanted subjects, including the listed serious event terms and percentages. These observations do not supply a comparative safety estimate, and the registry does not report deaths. More detailed information about the circumstances and attribution of events is not reported in the registry record.

Accordingly, the record supports a description of the intended efficacy question, study structure, missing-data approach as far as recorded, and some safety counts. It does not support a numerical conclusion about primary efficacy or a randomized comparison of benefit or harm. Those distinctions separate a study objective and observed event reporting from evidence about comparative effects.

13. Why This Trial Matters Statistically

This study illustrates why endpoint definitions, analysis populations, and design structure need to be read together. The primary question uses a specific threshold: at least a 50% reduction in weekly fecal incontinent episodes by 12 months. The endpoint is therefore a proportion of subjects crossing a defined boundary, not an average change in episodes. That distinction determines what the result would mean and what information it leaves out.

The study is described as non-randomized and single-group. This design can organize follow-up around baseline and later observations, but it does not create a randomized contrast. Statistical interpretation must therefore distinguish a change observed in the implanted group from an effect attributable to the intervention. A precise estimate, if reported, would not by itself remove that design limitation.

The missing-data rule is another important statistical feature. Classifying subjects with missing 12-month data as failures directly affects how the success proportion is defined. The exception for a subsequent diary is incompletely described in the registry record, and the extent of missingness is not reported. Without those details and the primary estimate, readers cannot evaluate the influence of the rule on the reported endpoint.

Finally, the record lists multiple outcomes but does not report a multiplicity procedure. That makes it important to distinguish the primary objective from secondary measures and to avoid treating every outcome as if it answered the same question. The absence of the primary numerical result is itself consequential: a stated endpoint and analysis approach are not substitutes for the estimate and uncertainty needed to judge what the data show.

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 of the registry record for statistical interpretation is that it does not report the primary success proportion or its 95% confidence interval. Without those values, the primary objective cannot be evaluated against an observed efficacy estimate, and the precision of the estimate cannot be described. The record also does not report a p-value or other numerical primary test result.

The study has a single-group, non-randomized design with no reported comparator and no masking. Any change from baseline would be a within-group observation rather than a randomized treatment contrast. The design cannot, by itself, distinguish intervention-related change from other influences that may occur over time.

The enrollment figure is 285, while the brief summary describes 120 implanted subjects and the primary population is defined as successfully implanted subjects. The registry record does not explain the relationship among these numbers or provide a complete participant flow through the primary analysis. The number included in the endpoint analysis is not reported in the registry record.

The missing-data description is incomplete: it states that subjects missing 12-month data were classified as failures unless a subsequent diary was available, but does not finish explaining the subsequent-diary rule. Missing-data counts, reasons, and sensitivity analyses are not reported. The record lists multiple outcomes but does not report how multiplicity was handled. Further protocol details, the trial’s own sample-size justification, and additional information about adverse-event attribution are not reported in the registry record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Sacral Nerve Stimulation Therapy for the Treatment of Chronic Fecal Incontinence — NCT00200057.
• Registry record last updated 2013-01-24; status last verified 2013-01.
• Results first posted 2011-08-30.
• 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

NCT00200057 is a completed, non-randomized, single-group device study of InterStim sacral nerve stimulation therapy for chronic fecal incontinence. The registry lists enrollment of 285 and describes 120 implanted subjects. The primary endpoint was the proportion of implanted subjects achieving at least a 50% reduction in weekly fecal incontinent episodes at 12 months compared with baseline.

The primary efficacy result and its 95% confidence interval are not reported in the registry record. The record describes a modified worst-case approach for missing 12-month data, but the exception involving a subsequent diary is incompletely recorded. Safety figures include 41 implanted subjects with serious adverse events and 88 with other adverse events; deaths are not reported in the registry record. The single-group design does not provide a randomized comparison.