A Pilot Study to Assess the Efficacy and Safety of Various Vibrating Capsule Modes: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Pilot Study to Assess the Efficacy and Safety of Various Vibrating Capsule Modes (NCT03329027), a randomized na study. The primary outcome is CSBM1- an Increase of at Least One Weekly Complete Spontaneous Bowel Movement (CSBM) During at Least 6 of the 8 Weeks of Treatment.

2. Clinical Question

The study asked whether either of two vibrating capsule modes was associated with a higher rate of success on the primary bowel-movement outcome than the other mode or a sham capsule. The primary outcome classified a participant as successful if weekly complete spontaneous bowel movements increased from baseline by at least one during at least 6 of the 8 treatment weeks. The primary analysis included participants who completed at least 6 weeks of treatment.

The registry record identifies the study as a pilot and lists constipation as the condition. The comparisons describe outcomes in the posted analysis population; they do not establish how the results would apply to people outside that population or to other treatment schedules.

3. Trial Design

The registry record describes a prospective, multicenter, randomized, double-blind, sham-controlled pilot study. It lists the allocation as randomized, masking as quadruple, and the model as parallel. The study is marked completed. The recorded enrollment is 67, while the primary outcome is reported for an analysis of 44 subjects who completed at least 6 weeks of treatment. These are different descriptions of the study population and should not be treated as interchangeable.

Participants were assigned to one of three arms: vibrating mode 1, vibrating mode 2, or sham. Each arm description specifies 8 weeks of treatment and 5 capsules per week. The two active modes were described as differing in their vibration sessions. The sham capsule was described as visually similar to the active capsules and without active components. The registry record does not report the randomization procedure, allocation concealment details, or the precise procedures used to maintain masking.

The study began on 2017-11-14, and primary completion is recorded as 2018-03-30. The listed phase is NA. The registry record calls the study adaptive, but does not report how adaptation was implemented, what information could trigger a change, or whether any adaptations occurred. Details about the original design assumptions and the rationale for the enrolled sample size are not reported in the registry record. The posted result therefore needs to be read as a pilot comparison, with attention to its restricted primary analysis population and the uncertainty around its estimates.

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: Analysis of 44 subjects who completed at least 6 weeks of treatment

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 CSBM1- an Increase of at Least One Weekly Complete Spontaneous Bowel Movement (CSBM) During at Least 6 of the 8 Weeks of Treatment, measured over 8 weeks.

The primary endpoint is CSBM1 success: a participant counts as a success when the increase from baseline is at least one weekly complete spontaneous bowel movement during at least 6 of the 8 treatment weeks. The registry record reports the outcome as a count of participants and identifies the outcome timeframe as 8 weeks. A complete spontaneous bowel movement is the specified event; the outcome is not simply a count of all bowel movements.

This threshold-based definition turns each participant’s treatment-period pattern into a binary result: success or not success. That makes it possible to compare the fraction of participants meeting the definition across randomized groups. The threshold also combines a change from baseline with a requirement that the change be sustained across much of the treatment period. This can make the result easier to interpret as a responder outcome, but it discards information about the size and week-to-week pattern of changes that do not meet the success definition.

The primary result applies to the analysis of subjects who completed at least 6 weeks of treatment. It does not describe all enrolled participants under an intention-to-treat analysis, because such an analysis is not reported in the registry record. The record does not report further detail about baseline measurement procedures or how missing weekly outcome information was handled.

7. Results Posted in the Registry

• Active Comparator-Vibrating Mode 2: 41.2% (7/17) versus 63.6% (7/11) on control; risk difference -22.5 percentage points (95% CI -59.3 to 14.4), risk ratio 0.65 (0.31–1.33); unadjusted two-proportion z-test p = 0.246.
• Sham Comparator: 56.2% (9/16) versus 63.6% (7/11) on control; risk difference -7.4 percentage points (95% CI -44.8 to 30.0), risk ratio 0.88 (0.47–1.65); unadjusted two-proportion z-test p = 0.701.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

SBM 1- Success Rate, Defined as as an Increase From the Base Line of at Least One Weekly Spontaneous Bowel Movement (SBM) During at Least 6 of the 8 Weeks of Treatment.

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Vibrant Active Mode 1: 72.7% (8/11) versus 43.8% (7/16) on control; risk difference 29.0 percentage points (95% CI -6.8 to 64.8), risk ratio 1.66 (0.86–3.23); unadjusted two-proportion z-test p = 0.137.
  • Vibrant Active Mode 2: 52.9% (9/17) versus 43.8% (7/16) on control; risk difference 9.2 percentage points (95% CI -24.8 to 43.2), risk ratio 1.21 (0.59–2.47); unadjusted two-proportion z-test p = 0.598.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Vibrant Active Mode 1 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Vibrant Active Mode 2 and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary outcome is SBM success, defined as an increase from baseline of at least one weekly spontaneous bowel movement during at least 6 of the 8 treatment weeks. Its direction is not uniformly aligned with the primary outcome’s pattern: the secondary comparison estimates are positive for each active mode relative to sham, while the primary estimates are negative for mode 2 and sham relative to mode 1. These outcomes use different bowel-movement definitions and different reference groups, so their numerical contrasts are not direct replications of one another.

The secondary comparisons are based on small groups and have wide confidence intervals that include zero. Their unadjusted p-values do not provide strong evidence that the observed differences are distinguishable from sampling variation. The registry record lists one posted secondary outcome and no reported analyses. The reported secondary values are therefore best treated as exploratory descriptions of the observed groups rather than as confirmatory findings.

As a general statistical point, testing multiple outcomes or comparisons increases the chance of obtaining an apparently notable result by chance if each is considered separately. Unadjusted secondary results carry less weight because they do not account for that multiplicity and may not represent prespecified confirmatory tests. The registry record does not report a multiplicity strategy, a hierarchy of endpoints, or a plan for interpreting the secondary outcome alongside the primary one. The secondary pattern can offer context about a related measure, but it does not resolve the uncertainty in the primary comparison or replace it.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• SBM 1- Success Rate, Defined as as an Increase From the Base Line of at Least One Weekly Spontaneous Bowel Movement (SBM) During at Least 6 of the 8 Weeks of Treatment.

9. Statistical Interpretation

10. Statistical Methods Explained

The posted primary comparisons use a risk difference. This is the difference between the proportion meeting the success definition in one group and the proportion meeting it in the reference group. A risk difference of zero corresponds to equal observed proportions; a negative estimate indicates a lower observed proportion in the group named first than in the reference group. The mode 2 comparison uses mode 1 as the reference, and the sham comparison also uses mode 1 as the reference.

What does a risk difference describe?

As a general statistical concept, a risk difference expresses an absolute contrast on the outcome’s probability scale. It is directly tied to the success definition used in the trial. The estimate is not an adjusted effect: the recalculated comparisons use the posted group counts without adjustment for other participant characteristics. This helps keep the comparison transparent, but it does not account for any differences between groups that may remain in a small randomized sample.

The registry record also posts risk ratios and odds ratios for the comparisons. These express contrasts on different scales. A risk ratio compares the success probabilities, whereas an odds ratio compares the odds of success. Neither scale removes uncertainty, and neither should be treated as a substitute for the underlying group counts and confidence intervals. Since the risk difference is the metric used for the primary comparisons, the interpretation above focuses on that absolute contrast.

What does the confidence interval add?

As a general statistical concept, a confidence interval describes the precision of an estimate under the method used to calculate it. It indicates a range of values that remain compatible with the observed data and the calculation’s assumptions. An interval that includes zero for a risk difference does not establish that the groups are equal. It means the data do not rule out zero difference at the corresponding confidence level; values on either side may also remain plausible.

The primary intervals are wide relative to their point estimates. That is consistent with the limited information in the small analysis groups. The uncertainty is important: focusing only on the point estimate would conceal how much the observed contrast could vary. The record does not report a sponsor analysis or a detailed statistical analysis plan against which to compare the recalculations.

Why use a binary success endpoint?

As a general explanation, a responder endpoint can make a clinical outcome easier to communicate by identifying participants who meet a prespecified change threshold. Here the definition requires both an increase from baseline and achievement during at least 6 of the 8 weeks. This gives the outcome a sustained-response component. However, categorizing participants as successful or not successful means that different bowel-movement patterns can lead to the same classification, while small changes around the threshold can put otherwise similar patterns into different categories.

The reported group counts are the information used for the binary comparisons. The registry record does not report individual-level outcome distributions, how baseline values were incorporated beyond the stated definition, or how incomplete weekly data were classified. Those details can affect how readers understand the responder results.

What does an unadjusted p-value mean?

As a general statistical concept, a p-value measures how unusual data at least as inconsistent with a specified no-difference hypothesis would be, if that hypothesis and the calculation’s assumptions held. It is not the probability that the null hypothesis is true, nor does it describe the size or clinical importance of a difference. The posted p-values are unadjusted. They address each comparison without accounting for multiplicity across outcomes or comparisons.

The registry record lists no reported analyses and no analysis plan details. Thus, the recalculated risk differences, intervals, and p-values should be read as descriptive statistical comparisons based on posted summary data. They do not establish that the analyses were prespecified, and the record does not state whether any other analyses were conducted.

11. Confidence Intervals and Precision

The primary estimates are imprecise. For mode 2 compared with mode 1, the risk difference is -0.225 and the 95% confidence interval extends from -0.593 to 0.144. For sham compared with mode 1, the risk difference is -0.074 and the 95% confidence interval extends from -0.448 to 0.300. Each interval includes zero and values on both sides of zero, so the posted data do not pin down the direction of either difference.

As a general statistical explanation, a confidence interval gives a sense of the range of estimates compatible with the data under the calculation used. A narrow interval conveys greater precision than a wide interval, but precision alone does not establish whether a result is clinically important. The wide intervals in these comparisons mean that materially different group contrasts remain compatible with the posted counts. The point estimates are not precise enough to serve as stable estimates of the underlying difference.

The arm counts—7 of 11 for mode 1, 7 of 17 for mode 2, and 9 of 16 for sham—also show why caution is needed when reading differences between observed proportions from small groups. A small change in the observed count could change the estimated contrast appreciably. The registry record does not report confidence intervals for the arm-level proportions themselves, nor does it report a sponsor model with adjusted intervals. The recalculated intervals are unadjusted and should be interpreted as such.

The confidence intervals do not demonstrate equivalence or non-inferiority. Those conclusions require a prespecified margin and an analysis designed for that purpose; such a margin or analysis is not reported in the registry record. The intervals instead communicate uncertainty around the unadjusted comparisons available from the posted summary data.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are expressed as participants per arm for these binary comparisons, not as total events. The stated planning approach uses a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It uses the observed effect as the starting point and considers planning for 100%, 75%, or 50% of that observed effect. The registry record does not report the original trial’s own sample-size assumptions or justification.

The 80% power column gives the planned participants per arm under which the calculation has 80% power to detect the specified effect, given those assumptions. The 90% power column gives the corresponding planning figure for 90% power. In general, power is the chance of detecting an effect of the assumed size under the calculation’s model if that effect is the true effect. It is not a statement about the probability that the effect exists.

The displayed planning figures vary substantially with the comparison and the fraction of the observed effect selected. For example, the mode 2 comparison’s planning illustration for 75% of the observed effect is 136 participants per arm for 80% power and 182 for 90% power. For the sham comparison, the corresponding figures are 1,218 and 1,629 participants per arm. These are illustrations based on the observed effects, not the trial’s own planned enrollment. Smaller effects require more participants to detect under the same assumptions. These figures are not observed power.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.636; treatment proportion p₁ = 0.412; average p̄ = 0.524.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.7063 = 1.3843.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6882 = 0.5792.
4. n = (1.3843 + 0.5792)² / (-0.2246)² = 76.4, rounded up to 77 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
p0 <- 0.636363636363636                          # control proportion
p1 <- 0.411764705882353                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3329027)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 77 (80% power), 102 (90% power)
 75% of observed effect: n per arm = 136 (80% power), 182 (90% power)
 50% of observed effect: n per arm = 302 (80% power), 404 (90% power)
power.prop.test: 76.4 
Simulated power at n = 77 per arm: 0.790 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Multiplicity, Missing Data and Analysis Populations

The registry record identifies a primary CSBM success outcome and a secondary SBM success outcome, and it reports comparisons across treatment groups. It lists zero reported analyses for the primary outcome and an empty reported-analyses list for the secondary outcome. This means the record does not describe a formal sponsor analysis, an analysis hierarchy, or how the reported comparisons were selected. The recalculated comparisons are unadjusted.

Multiplicity arises when several outcomes, groups, or comparisons are examined. As a general statistical concept, considering several tests without adjustment can increase the chance that at least one result appears noteworthy under a no-effect scenario. The record does not report whether a multiplicity adjustment was planned or applied, whether one comparison was designated as the principal contrast, or how the secondary endpoint was intended to affect interpretation. The posted unadjusted p-values should therefore not be treated as if they control the overall chance of a false-positive conclusion across all tests.

The primary population is described as subjects who completed at least 6 weeks of treatment. The registry record does not report the handling of participants who did not complete that period, the treatment of missing weekly outcome data, or whether the primary analysis followed intention-to-treat principles. It does not report imputation methods, sensitivity analyses, or reasons for exclusion from the primary analysis. These omissions matter because an analysis restricted by treatment completion may differ from one that includes all randomized participants.

The record describes the study as adaptive but does not give details about any adaptation, interim analysis, stopping rule, or safeguards for repeated testing. These elements are not reported in the registry record and should not be inferred from the adaptive label alone. Likewise, the original statistical plan and any prespecified analysis decisions are not reported. The available results support descriptive interpretation, with limited information about how the analyses were planned or how missingness and multiplicity were addressed.

15. 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 1% reporting threshold.

Most frequent non-serious adverse event terms

The serious adverse event figures report zero affected participants in each group: the risk sets are 21 for vibrating mode 1, 22 for vibrating mode 2, and 24 for sham. Deaths are also recorded as zero in each group. These figures describe the posted safety counts; they do not by themselves show that the groups have the same safety profile.

As a general statistical point, zero recorded serious events in a study does not establish that an event cannot occur. A small study may have limited ability to detect uncommon events or differences between groups. The registry record does not list serious adverse event terms. It reports other adverse events affecting 4 participants in mode 1, 7 in mode 2, and 5 in sham, with the corresponding groups at risk listed as 21, 22, and 24. Those are separate counts from the serious-event figures.

The safety data should be interpreted as counts observed in this pilot study, with the recorded group sizes and study context in mind. The registry record does not report further detail about event severity, timing, relatedness, or how events were collected. The counts do not establish comparative safety.

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

The posted primary results describe the proportion meeting a defined CSBM success threshold among participants who completed at least 6 weeks of treatment. They show observed successes in all three groups and unadjusted comparisons with mode 1 as the reference. The confidence intervals are broad and include zero for both primary risk differences. The data therefore leave substantial uncertainty about the direction and magnitude of the group differences.

These results do not establish that either vibrating mode is better than the other or than sham. They also do not demonstrate that the groups are equivalent. A non-significant p-value is not proof of no effect, and a point estimate is not proof of a real effect. The design is identified as a pilot, and the small primary analysis groups limit the precision of the comparisons.

The endpoint is a threshold-based measure of complete spontaneous bowel movements sustained during much of the treatment period. It does not capture every possible aspect of constipation or every pattern of response. The secondary SBM success outcome is related but not identical. Neither outcome alone establishes a broader clinical benefit, and the registry record does not report additional measures needed to address other dimensions of the condition.

The safety counts record no serious adverse events or deaths in the posted groups, but such counts do not establish absence of risk or comparative safety. The study’s findings are specific to the recorded treatment modes, schedule, outcome definitions, and analysis population. The registry record does not report enough detail about missing data, analysis planning, or adaptation to resolve those uncertainties. The most defensible reading is that this pilot provides imprecise descriptive comparisons that require cautious interpretation, not a definitive treatment conclusion.

17. Why This Trial Matters Statistically

This study illustrates how a randomized design can provide a structured comparison among active modes and a sham, while a pilot sample may still leave substantial uncertainty. Randomization helps define the intended group comparison, but it does not guarantee that estimates from small groups will be precise. The primary confidence intervals show the practical importance of considering uncertainty alongside observed counts and point estimates.

The endpoint also demonstrates a common statistical trade-off. A responder definition can give a clear threshold for classifying participants, but it compresses a varied outcome into success or non-success. That makes the result easier to compare across groups while losing information about the size and pattern of changes. Reading the threshold definition carefully is essential to understanding what the comparison actually represents.

The registry record also shows why analysis populations and reporting details matter. The primary result is restricted to participants who completed at least 6 weeks of treatment, while the record does not explain the handling of missing outcomes or participants outside that population. It describes the study as adaptive without reporting implementation details, and it lists no formal analyses. These gaps limit the ability to assess prespecification and the influence of analysis choices.

Finally, the sample-size illustrations show how planning estimates depend on the assumed effect and target power. They are not evidence that the pilot had adequate power for its observed findings. Together, these features make the study useful for understanding estimation, precision, endpoint construction, and reporting limits in clinical research.

18. 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 main limitation is the limited precision of the primary comparisons. The analysis groups are small, and both primary risk-difference intervals include zero while spanning substantial differences in either direction. The point estimates should not be treated as stable measurements of the underlying effects.

The primary analysis population is described as subjects who completed at least 6 weeks of treatment, rather than all enrolled participants. The registry record does not report how many participants were excluded from that analysis, why they were not included, or how missing outcome data were handled. It also does not report whether the analysis was intention-to-treat or whether sensitivity analyses were performed. These omissions prevent assessment of possible effects of incomplete follow-up or analysis-population selection.

The registry record describes the study as adaptive but does not explain what was adapted or whether interim analyses or changes to the plan occurred. It does not provide the original sample-size justification, detailed randomization procedures, or a statistical analysis plan. The record lists no reported analyses, so the recalculated comparisons cannot be checked against a documented sponsor model or prespecified analysis strategy.

Multiplicity is another limitation: the record does not state how the primary and secondary outcomes or the multiple group comparisons were prioritized or adjusted. The secondary results are unadjusted and exploratory in the absence of such detail. Safety reporting is also limited; information on event severity, timing, relatedness, and collection methods is not reported in the registry record. These limitations restrict what can be concluded from the posted results.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Pilot Study to Assess the Efficacy and Safety of Various Vibrating Capsule Modes — NCT03329027.
• Registry record last updated 2024-07-03; status last verified 2024-06.
• Results first posted 2024-07-03.
• 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.

22. Record Summary

The registry record describes a completed, randomized, quadruple-masked, parallel pilot study of vibrating capsule modes and sham for constipation. The primary endpoint was CSBM success during 8 weeks, defined by an increase from baseline of at least one weekly complete spontaneous bowel movement during at least 6 of the 8 treatment weeks. The primary analysis included subjects who completed at least 6 weeks of treatment.

Observed primary success counts were 7 of 11 for mode 1, 7 of 17 for mode 2, and 9 of 16 for sham. The unadjusted risk-difference estimates have wide confidence intervals that include zero. The record also posts an SBM success outcome and safety counts, including zero serious adverse events and zero deaths in each group. Details of the original sample-size rationale, missing-data methods, multiplicity strategy, and formal analysis plan are not reported in the registry record.