Educational-Medical-Behavioral Treatment of Fecal Incontinence: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Educational-Medical-Behavioral Treatment of Fecal Incontinence (NCT01717456), a randomized na study. The primary outcome is Fecal Incontinence Severity Index (FISI) at End of Treatment.

2. Clinical Question

The trial asked whether an educational, medical, and behavioral program for fecal incontinence could be delivered by home health care nurses to frail elderly patients, and how end-of-treatment fecal incontinence severity compared with standard care. The registry describes this as a community-based effectiveness trial. The primary endpoint was the Fecal Incontinence Severity Index (FISI) at the end of treatment, identified as Week 6.

3. Trial Design

The registry describes a randomized, double-masked, parallel-group trial. It lists an enrollment of 31 and a status of terminated. The start is recorded as 2013-01, and primary completion as 2015-03. The registry record does not report why the study was terminated, or give further details about the timing or process of termination.

The two groups were Educational-Medical-Behavioral and Standard Care. The more comprehensive intervention combined education and medical management of diarrhea and constipation with behavioral training. The listed components include fiber supplements, laxatives or anti-diarrheals, pelvic floor muscle exercises, tips on preventing fecal incontinence, a daily diary, and protective pads or garments. Standard care included fiber supplements, a daily diary, and protective pads or garments as needed. The record does not fully describe the delivery procedures for either group beyond these components and the intended home health care nurse delivery of the intervention.

The primary outcome was assessed at end of treatment, specified as Week 6. The reported primary endpoint population was limited to participants who provided end-of-treatment data during a home visit. There were 10 observations in the Educational-Medical-Behavioral group and 5 in Standard Care for the reported FISI outcome. These are outcome-specific counts and should not be treated as a statement of total enrollment or of the number assigned to each group.

The registry also lists 32 outcome measures, including secondary outcomes addressing adequate relief, severity, caregiver burden, fecal incontinence frequency, and urinary incontinence status. It reports 23 secondary outcome results and one primary analysis. The registry record does not report the allocation procedure, the reasons for the enrollment target, or additional details of masking. Phase is listed as not applicable.

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: Baseline data collection and written consent was obtained at a home visit prior to referring the patient to HHC for randomization and initiation of treatment. Only 19/31 who gave consent to the research assistant were randomized. 3 others were judged ineligible by HHC, and 9 dropped out while awaiting treatment.

End of Treatment

Reasons for not completing this period:

Follow-Up 6 Months After End of Tx

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Analysis population includes all participants who provided end of treatment data to research assistants during a home visit. One subject from the EMB treatment did not provide data, and 1 subject from the SC group did not provide these 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.

Population: The baseline analysis population is limited to patients who were randomized after referral to Home Health Care.

6. Primary Endpoint

The registry lists the primary outcome as Fecal Incontinence Severity Index (FISI) at End of Treatment, measured over End of Treatment (Week 6).

The primary endpoint was the Fecal Incontinence Severity Index at the end of treatment, identified as Week 6. The FISI asks participants about the frequency of four types of fecal incontinence during the past month: solid, liquid, mucus, and gas. The four responses are multiplied by empirically derived patient weights and then added. The score ranges from 0-61, with higher scores indicating more severe fecal incontinence.

This measure is used to summarize both the types of symptoms and their reported frequency in a single continuous score. A group mean therefore describes average reported severity, while the standard deviation describes how much individual scores vary around that mean. The measure is based on participant reports about the past month, so it represents reported symptoms over that period rather than a direct count of events observed by a researcher.

The registry reports mean FISI scores and standard deviations at end of treatment. It does not provide baseline FISI values in the posted primary result, so the posted comparison is a comparison of final values, not a reported change-from-baseline estimate. The registry does not report an interpretation threshold for a meaningful difference on this scale. The score's direction is clear—higher means more severe—but the clinical importance of a particular difference is not established by the information in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry reports group means and standard deviations for a continuous outcome, followed by a two-sided t-test comparing final values. The mean is a measure of the center of the observed scores. The standard deviation describes the dispersion of scores around that center. These summaries are useful together: equal means can conceal differing variability, while the same mean difference can be more or less precisely estimated depending on the spread of scores and the amount of available data.

What does a t-test compare?

In general, a t-test assesses whether the observed difference between group means is compatible with a null hypothesis of no difference, under the assumptions of the test. A two-sided test considers departures in either direction. The registry reports a two-sided test and a p-value of .05. A p-value is a measure of how unusual the observed data, or data more extreme under the test, would be if the null model and test assumptions held. It is not the probability that the null hypothesis is true, and it does not measure the probability that the result is due to chance.

For a mean comparison, the assumptions concern how observations are generated and how their variation is represented by the test. The registry record does not report diagnostic checks, an equal-variance choice, or other details of the t-test implementation. With small outcome-specific groups, estimates of means and variability can be sensitive to individual observations. The record does not provide participant-level data, so the influence of individual values cannot be evaluated from the posted summaries.

Why does the confidence interval matter?

A confidence interval gives a range of effect estimates compatible with the data and the interval procedure. It communicates uncertainty about the estimated contrast in a way a p-value alone does not. Although the result lists a 95% confidence level, the lower and upper interval limits are absent. Consequently, the record does not show the width of the interval or the range of differences it would contain. The p-value and confidence level should not be mistaken for the missing interval itself.

The reported result is a comparison of final values, as indicated by the analysis description. It is not described as an adjusted comparison, and the registry record does not report an adjustment for baseline FISI or other covariates. In general, an adjusted analysis can account for specified baseline variables, while an unadjusted comparison uses the group outcome summaries without such adjustment. Without a reported adjustment model, no adjusted effect can be inferred.

How should the spread be read?

The standard deviations of 10.3 and 9.17 describe variation in the FISI values within the two outcome groups. They are not standard errors or confidence intervals. A standard deviation describes participant-level spread; a standard error describes uncertainty in an estimated quantity. The latter depends on both variability and the amount of information used in the estimate. The standard deviations alone therefore do not give the uncertainty around the mean difference.

In general, over-dispersion means that observed variation is greater than a statistical model expects. It can make model-based standard errors too small and tests too optimistic if the model does not account for the extra variability. The primary outcome is a continuous score analyzed with a t-test, and the registry does not report a separate over-dispersion assessment. The concept is relevant to count or rate outcomes among the listed secondary measures, but no count-model analysis is described in the primary result.

What are the planning calculations?

Any sample-size illustrations associated with this record are planning exercises, not observed power. Their stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is defined as a stated fraction of the observed effect, and the non-time-to-event quantities are expressed as participants per arm for 80% power or another listed planning target. Such calculations answer a hypothetical design question under their assumptions; they do not change the evidence from the completed trial or show the probability that the trial's result is correct. The registry record does not report the trial's own sample-size justification, so the planning illustrations should not be read as its original design rationale.

Random allocation can support a causal comparison when the trial is implemented and analyzed as planned, but missing outcome data and the small available outcome groups can limit that interpretation. The record identifies only participants who posted end-of-treatment data as the primary analysis population. It does not report an intention-to-treat analysis or a missing-data model. Statistical tests cannot repair uncertainty created by unobserved outcomes unless assumptions and methods for doing so are specified and justified.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Educational-Medical-Behavioral", "Standard Care")
n   <- c(10, 5)
m   <- c(18, 22)
sp  <- c(10.3, 9.17)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Educational-Medical-Behavioral  10  18.000  10.300  10.632  25.368
CARM  Standard Care  5  22.000  9.170  10.614  33.386

11. Analyses Reported by the Sponsor

The registry's own analysis is a two-sided t-test comparing final FISI values. It reports a mean difference of 4.0 and p = .05, with the confidence level listed as 95% but no confidence-interval limits. The group means are 18.0 for Educational-Medical-Behavioral and 22.0 for Standard Care. The record does not specify the subtraction order for the reported mean difference, so the direction is clearest from the separate group means.

The record does not flag a discrepancy between the sponsor's reported analysis and a recalculation. Where a recalculation is available, it is an unadjusted calculation from posted summary statistics and is not a replacement for the sponsor's analysis. The sponsor's own analysis takes precedence if a discrepancy is present. Here, the record does not provide interval limits, and the sponsor's reported result remains the main inferential result to interpret. It should be read with the outcome-specific sample sizes, the missing end-of-treatment data, and the absence of reported adjustment details in mind.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists 32 outcome measures and reports 23 secondary outcome results. It also lists one primary analysis. With several outcomes and assessment times, repeated statistical testing can increase the chance of at least one apparently notable result even when no corresponding effect exists. That is a general multiplicity concern; it does not establish that the reported result is false. The registry record does not report a multiplicity adjustment, a hierarchy for secondary outcomes, or a statistical analysis plan specifying which tests were confirmatory.

The primary analysis population is defined as participants who provided end-of-treatment data to research assistants during a home visit. The record states that one subject from the Educational-Medical-Behavioral group did not provide data and one subject from the Standard Care group did not provide these data. The analyzed outcome counts are 10 and 5, respectively. These available-case counts and the listed missing observations make clear that the reported comparison is not a complete-outcome result for every participant enrolled.

The registry record does not report why these data were missing, whether missingness differed in its causes between groups, or whether missing values were imputed. It does not describe sensitivity analyses, an intention-to-treat analysis, or methods for handling missing outcomes. In general, an available-case analysis can be unbiased under particular assumptions about missingness, but those assumptions cannot be checked from the summaries. If missingness is related to symptom severity or treatment experience, the observed group means may not represent the outcomes that would have been observed for all participants.

The study is listed as terminated, but the reason is not reported in the registry record. The record also does not explain whether termination affected outcome collection or analysis. That absence limits evaluation of possible selective reporting or changes to the planned analyses. The registry's primary result can be described as posted, but the details needed to assess the full analysis population and the handling of missing data are not reported.

13. 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 serious adverse event terms

Serious events with the highest arm-level rate: disability (12.5%).

The safety record lists serious adverse events among 11 participants at risk in the Educational-Medical-Behavioral group and 8 in Standard Care. It reports zero serious adverse events for the intervention group and one for Standard Care. The listed serious adverse event term is Disability, reported as 12.5%. The record lists zero other adverse events in each group, using the respective at-risk counts shown in the safety information.

These figures should be read as registry-reported counts and a reported term, not as a complete account of all possible harms. The record does not provide a narrative description of the serious event, its timing, severity details beyond its serious classification, or its relationship to treatment. Death counts are not reported in the registry record. The adverse-event at-risk counts differ from the outcome-specific FISI counts, so they should not be substituted for the primary endpoint analysis population.

With the small numbers recorded, a single event can have a substantial influence on the percentage reported. The safety information does not establish comparative risk with precision, and the absence of reported events in a group does not show that no risk exists. These data describe what was posted for this trial and do not support broader conclusions about safety.

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

The posted primary result describes average FISI scores at the end of treatment. The intervention group's mean was 18.0, compared with 22.0 in Standard Care, and higher scores indicate more severe fecal incontinence. The sponsor's two-sided t-test reported a mean difference of 4.0 and p = .05. The confidence level is given as 95%, but interval limits are not reported. These registry entries describe a numerical contrast and its reported test result; they do not by themselves establish how important the contrast is to patients.

The result does not show that every participant in the intervention group had lower severity than every participant in Standard Care. Group means summarize distributions, and the reported standard deviations indicate variation among participants. Nor does this endpoint establish effects on all the secondary outcomes, caregiver burden, urinary incontinence, or longer-term symptoms. Although follow-up outcomes appear among the listed measures, the primary comparison is at Week 6.

The registry describes randomized allocation, but the primary result uses available end-of-treatment data, with one subject in each group not providing those data. The outcome counts are limited, and the record does not report a missing-data strategy, adjustment for baseline severity, or the reasons for termination. The listed result therefore cannot resolve uncertainty about missing outcomes, precision, or how well these findings would apply beyond the participants represented in the analysis.

Clinical importance is also not specified. The FISI has a 0-61 range and a clear direction, but the registry does not state a threshold for a meaningful change or difference. The result should not be translated into a treatment recommendation. It is a report of an observed end-of-treatment group comparison in this trial, with inferential and interpretive limitations described by the information available in the registry record.

15. Why This Trial Matters Statistically

This trial is statistically informative because it distinguishes a community-delivery question from the earlier university referral-center studies described in the study summary. The research question concerned whether a multicomponent conservative program could be delivered by home health care nurses to frail elderly patients. That context matters when interpreting what the trial was designed to address, but the record does not establish whether the intervention's delivery in this setting achieved a particular clinical result.

The endpoint combines reports about solid, liquid, mucus, and gas incontinence into a weighted severity score. Reporting the means and standard deviations gives readers both a measure of average severity and an indication of variation. The result also illustrates why an inferential test should not be read alone: the group summaries, outcome-specific counts, missing data, and absent interval limits all affect how much can be concluded from p = .05.

The record highlights challenges common to small clinical trials. Available outcome counts can be much more limited than the enrollment figure, making estimates vulnerable to individual observations and leaving uncertainty about participants without data. Multiple listed outcomes also make it important to know which analyses were prespecified and whether adjustments or a hierarchy were used. Those details are not reported.

Finally, the registry's termination status and lack of a stated reason create questions that cannot be resolved from the posted information. The study remains useful for understanding how a complex intervention and a patient-reported severity endpoint were represented in the registry, while also showing why reported estimates need to be read alongside reporting gaps and limits on precision.

16. 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 primary result is based on end-of-treatment observations from 10 participants in the Educational-Medical-Behavioral group and 5 in Standard Care. These counts are limited for estimating group means and variability, and the record does not provide individual-level data for checking the influence of unusual observations. The enrollment figure of 31 does not explain how participants were distributed across groups or why the primary endpoint counts were lower.

The primary analysis population includes participants who provided end-of-treatment data during a home visit. One subject in each group did not provide these data. The reasons for missingness and the methods, if any, used to address it are not reported in the registry record. The reported comparison therefore cannot be assumed to represent all enrolled participants.

The analysis is described as a t-test of final values. The registry does not report baseline FISI values in the primary result, an adjusted model, or details such as test diagnostics and variance handling. It gives a 95% confidence level but not the interval limits. Consequently, the precision of the contrast cannot be assessed from the inferential result as posted.

The study is terminated, with no reason reported. The record does not give the trial's sample-size justification, statistical analysis plan, multiplicity strategy, or explanation of how termination related to recruitment, follow-up, or analyses. It lists multiple outcomes but does not identify a confirmatory hierarchy. These omissions limit assessment of prespecification and selective reporting.

Finally, the record describes the intended population and intervention but does not provide enough detail to evaluate all aspects of eligibility, delivery fidelity, or generalizability. The listed follow-up outcomes do not replace the primary end-of-treatment result, and the primary endpoint alone cannot establish longer-term patterns. These limitations qualify interpretation; they do not determine the direction or clinical importance of the observed group means.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Educational-Medical-Behavioral Treatment of Fecal Incontinence — NCT01717456.
• Registry record last updated 2017-02-17; status last verified 2017-02.
• Results first posted 2017-02-17.
• 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.

20. Record Summary

NCT01717456 is a randomized, double-masked, parallel-group trial listed as terminated. It compared an Educational-Medical-Behavioral program with Standard Care for fecal incontinence. The study summary describes a community-based effectiveness question about delivery of conservative treatment by home health care nurses to frail elderly patients. Enrollment is listed as 31; the registry records the start as 2013-01 and primary completion as 2015-03.

The primary outcome was mean FISI score at end of treatment, Week 6. Reported means were 18.0 for the intervention and 22.0 for Standard Care, with standard deviations of 10.3 and 9.17. The sponsor reported a two-sided t-test, mean difference 4.0, and p = .05; confidence-interval limits are not reported. The endpoint counts were 10 and 5, with one subject in each group not providing end-of-treatment data.

The record lists 32 outcome measures and 23 posted secondary results. The reason for termination, the sample-size justification, multiplicity plan, and missing-data methods are not reported in the registry record.