EndoRings Colonoscopy vs Standard Colonoscopy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for EndoRings Colonoscopy vs Standard Colonoscopy (NCT03418662), a randomized na study. The primary outcome is Adenoma Detection Rates.

2. Clinical Question

3. Trial Design

The registry describes a randomized, parallel-group trial comparing EndoRings Colonoscopy with standard colonoscopy. Allocation was randomized, and masking is listed as none. In a parallel design, each participant is assigned to one group and receives that group's approach; this differs from a design in which each participant receives both approaches. The registry does not provide further detail about the randomization procedure or how assignment was concealed.

The recorded enrollment is 592. The primary outcome entries give 284 participants for EndoRings Colonoscopy and 278 for the standard-colonoscopy control arm. The registry status is completed. The recorded study start is 2018-01-19, and the primary completion date is 2018-09-13. These dates describe the registry record, not the timing of each participant's procedure.

The intervention was colonoscopy with an EndoRings device attached to the distal end of the scope. The control procedure was standard colonoscopy without a device attachment. The primary outcome timeframe is during the colonoscopy procedure. Other outcomes listed in the registry concern polyp detection, detections per colonoscopy, cecal intubation, time, patient comfort, and equipment problems. Some secondary outcome results are posted, but analyses for all listed outcomes are not reported in the registry record.

Additional details that would help characterize the trial design, including eligibility criteria, study setting, the randomization method, and the original sample-size justification, are not reported in the registry record. The registry record also does not describe a masking procedure beyond listing masking as none.

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

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 Adenoma Detection Rates, measured over During colonoscopy procedure.

The primary endpoint counts participants with at least one adenoma detected during the colonoscopy procedure. It is a binary outcome at the participant level: each participant either had at least one adenoma detected or did not. The posted counts are 143 of 284 participants in the EndoRings Colonoscopy arm and 124 of 278 in the standard-colonoscopy arm.

This kind of endpoint is used to describe whether an examination detected any adenoma in a participant. It does not measure the total number of adenomas, the number of all polyps, or the size or location of detected lesions. Those are distinct questions. A participant with one detected adenoma and a participant with more than one both contribute to the primary outcome as participants with at least one adenoma.

Counting participants can make the outcome straightforward to interpret as a detection rate, while retaining an important limitation: it does not capture every difference in the number of detections. The registry lists the timeframe as during the colonoscopy procedure. It does not report further details about how adenomas were defined or classified, or about procedures for adjudicating the endpoint.

7. Results Posted in the Registry

• EndoRings Colonoscopy: 50.4% (143/284) versus 44.6% (124/278) on control; risk difference 5.7 percentage points (95% CI -2.5 to 14.0), risk ratio 1.13 (0.95–1.34); unadjusted two-proportion z-test p = 0.172.

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.

Polyp Detection Rate

• 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:
  • EndoRings Colonoscopy: 70.1% (199/284) versus 67.6% (188/278) on control; risk difference 2.4 percentage points (95% CI -5.2 to 10.1), risk ratio 1.04 (0.93–1.16); unadjusted two-proportion z-test p = 0.532.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EndoRings Colonoscopy and the control. The interval gives the range of effects that remain compatible with the data.

Number of Detections Per Colonoscopy

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • EndoRings Colonoscopy: mean 2.29 versus 1.82 on control; difference 0.47 (95% CI 0.03 to 0.91), standardized effect d = 0.18; z-test p = 0.037.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for EndoRings Colonoscopy than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Cecal Intubation Rate

• 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:
  • EndoRings Colonoscopy: 98.9% (281/284) versus 99.6% (277/278) on control; risk difference -0.7 percentage points (95% CI -2.1 to 0.7), risk ratio 0.99 (0.98–1.01); unadjusted two-proportion z-test p = 0.326.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EndoRings Colonoscopy and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists secondary outcomes that cover detection, procedure completion, procedure timing, comfort, and equipment problems. Numerical comparisons are posted for polyp detection rate, number of detections per colonoscopy, and cecal intubation rate. The registry does not report numerical analyses for every secondary outcome it lists, so the posted secondary results are only part of the broader set of outcomes named in the record.

Across the posted secondary results, the directions and the strength of evidence are not uniform. The binary polyp-detection and cecal-intubation comparisons have unadjusted intervals that include their respective no-difference values. The mean number of detections per colonoscopy has a reported unadjusted interval that does not include zero. This is a pattern across different outcome types, not one single overall treatment effect. Each secondary endpoint answers a distinct question and has its own scale and uncertainty.

The secondary outcomes give context for the primary endpoint but do not replace it. Polyp detection is related to adenoma detection, but the registry defines the primary question specifically as participants with at least one adenoma. Counts of detections per colonoscopy measure a different feature again. Cecal intubation concerns completion of the examination to the cecum, rather than whether an adenoma was found.

Unadjusted secondary findings carry less weight when several outcomes are examined because multiple comparisons increase the chance that at least one result appears notable by chance. The record does not report a multiplicity plan, a hierarchy among secondary outcomes, or adjusted secondary analyses. The secondary results are therefore best treated as exploratory context rather than as a collection of independent confirmatory conclusions. Missing descriptions of the analyses and populations also limit how fully these findings can be assessed.

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

• Polyp Detection Rate
• Number of Detections Per Colonoscopy
• Total Number of Detections
• Cecal Intubation Rate
• Time Comparison for Each Method
• Patient Comfort Score
• Problems Encountered With Equipment

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary because each participant is categorized according to whether at least one adenoma was detected. For a binary outcome, a risk is the proportion of participants in an arm who meet the outcome definition. A risk difference expresses the difference between those arm-specific risks. A risk ratio compares the risks as a ratio, while an odds ratio compares the odds. These measures use distinct scales and can have different numerical values even when they describe the same underlying outcome.

What does the confidence interval describe?

In general, a confidence interval describes uncertainty around an estimate under the statistical procedure used to construct it. It is not a range that guarantees where the true effect lies, and it does not describe the range of individual participant outcomes. For the primary risk difference, the reported interval runs from -0.025 to 0.140. Since this interval crosses zero, it includes no difference and also includes values on either side. The registry record does not describe the interval construction method, so the particular assumptions behind it are not reported in the registry record.

What does the p-value add?

In general, a p-value measures how unusual the observed data, or data more extreme, would be under a specified null model and its assumptions. It does not provide the probability that the null model is correct. The primary comparison has an unadjusted p-value of 0.172. The term unadjusted matters: it indicates that the posted value is not presented as adjusted for multiple outcome comparisons. The registry does not describe a prespecified multiplicity strategy or the full analysis plan.

For a binary endpoint, the arm counts and participant totals are central to interpretation. Here, 143 of 284 participants in the EndoRings arm and 124 of 278 participants in the control arm had at least one adenoma detected. The risk difference, risk ratio, and odds ratio provide alternative summaries of the contrast between these groups. They are not independent confirmations: they re-express the same outcome data using different scales.

How should the secondary continuous outcome be read?

The number of detections per colonoscopy is reported as a mean with a standard deviation for each arm. A mean summarizes the average number of detections, while the standard deviation describes the spread of observations around that mean. The reported means are 2.29 with a standard deviation of 3.09 for EndoRings Colonoscopy and 1.82 with a standard deviation of 2.19 for standard colonoscopy. The posted mean difference is 0.47, with a confidence interval from 0.028 to 0.912 and an unadjusted p-value of 0.037.

In general, count outcomes can be unevenly distributed, with many participants having relatively few detections and some having more. When variation is greater than a model assumes, standard errors and tests that rely on that model may not represent uncertainty well; this is often called over-dispersion. The registry posts means and standard deviations for detections per colonoscopy, but it does not report a distributional model or an analysis method for this outcome. It is therefore not possible to determine from the registry record whether over-dispersion was assessed or addressed.

What can be said about the analysis procedures?

The record posts estimates, confidence intervals, and unadjusted p-values for the reported comparisons. It does not report the statistical test, model specification, covariates, handling of missing observations, or whether analyses followed an intention-to-treat approach. Those details are not reported in the registry record. The values can be interpreted descriptively as posted, but the analysis cannot be independently characterized as adjusted or unadjusted beyond the stated unadjusted p-values.

The reported planning illustrations use a two-sided significance level of 0.05, equal allocation, and a normal approximation, with effects set to stated fractions of the observed effect. These are assumptions for the illustrations, not descriptions of the trial's original design. The original sample-size assumptions and justification are not reported in the registry record.

11. Confidence Intervals and Precision

Precision concerns how narrowly or broadly an estimate is bounded by its confidence interval. The primary risk-difference estimate has a reported interval from -0.025 to 0.140. The interval crosses zero and covers both a possible negative difference and a possible positive difference. This breadth means the posted data do not pin down the size or direction of the underlying difference precisely.

For another view of the same binary comparison, the risk-ratio interval runs from 0.948 to 1.344, and the odds-ratio interval runs from 0.904 to 1.755. Each interval includes the value corresponding to no difference on its respective scale. The intervals are not interchangeable because a risk difference, risk ratio, and odds ratio have different meanings and units. Their shared feature is that they leave uncertainty about whether there is a difference and, if so, how large it may be.

Confidence intervals should not be interpreted as a range containing most individual outcomes. They describe uncertainty about an estimated group contrast. Nor does an interval crossing the no-difference value prove that the groups are identical. It indicates that the observed data, under the interval's method and assumptions, do not rule out that value.

The registry does not report the method used to construct these intervals, and it does not provide an analysis plan with which to assess model assumptions. Precision should therefore be interpreted from the posted interval bounds rather than from assumptions about an unreported procedure. The sample-size illustrations address hypothetical future planning under stated assumptions; they do not narrow the uncertainty in the observed trial estimate.

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 sample-size figures are planning illustrations based on the observed effect, not the trial's original design justification. For these non-time-to-event outcomes, the figures are participants per arm. The 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 set to the stated fraction of the observed effect. The trial's own original design assumptions are not reported in the registry record.

The 80% power column gives the number of participants per arm that the planning calculation indicates would be needed to have an 80% chance of detecting the stated effect under those assumptions, if that effect and the assumptions were correct. The 90% column describes the corresponding planning target for a 90% chance. For the primary outcome, planning for 100% of the observed effect gives 1,184 participants per arm for 80% power and 1,585 participants per arm for 90% power. Planning for 75% of the observed effect gives 2,102 participants per arm for 80% power and 2,814 participants per arm for 90% power. Planning for 50% of the observed effect gives 4,721 participants per arm for 80% power and 6,320 participants per arm for 90% power.

The pattern is expected: smaller effects are harder to distinguish from random variation, so they require more participants under the same planning assumptions. The listed figures are not observed power. They are hypothetical planning values and should not be read as a retrospective score of whether the completed trial was adequately powered.

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 = 0.446; treatment proportion p₁ = 0.504; average p̄ = 0.475.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.7062 = 1.3841.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.7050 = 0.5934.
4. n = (1.3841 + 0.5934)² / (0.0575)² = 1,183.7, rounded up to 1,184 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 <- 0.446043165467626                          # control proportion
p1 <- 0.503521126760563                          # 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(3418662)
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 = 1,184 (80% power), 1,585 (90% power)
 75% of observed effect: n per arm = 2,102 (80% power), 2,814 (90% power)
 50% of observed effect: n per arm = 4,721 (80% power), 6,320 (90% power)
power.prop.test: 1183.7 
Simulated power at n = 1,184 per arm: 0.798 (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 reports unadjusted p-values for the comparisons that have posted numerical results. It does not report whether the primary endpoint was formally designated as the sole confirmatory test, whether secondary outcomes were arranged in a testing hierarchy, or whether any adjustment for multiple comparisons was planned. Those multiplicity details are not reported in the registry record.

Multiplicity matters because examining several outcomes creates more opportunities for chance patterns to appear noteworthy. This does not make the outcomes uninformative, but it affects how strongly an isolated unadjusted result should be interpreted. In particular, the secondary results should be read with the recognition that no adjustment strategy is described. The record also does not explain whether the reported p-values were selected from a larger set of analyses.

Missing-data handling is not reported in the registry record. The record does not state how participants with incomplete procedures, missing outcome information, or other unavailable measurements were handled. It does not provide a missingness count or describe any imputation or sensitivity analysis. The arm sizes in the outcome entries are available, but the relationship between those entries and the full analysis population is not described.

The analysis populations are also not reported in the registry record. It is not stated whether the analysis used all randomized participants, only participants who received the assigned procedure, or another defined group. Nor is an intention-to-treat analysis explicitly reported. Randomized allocation is recorded, but without the analysis-population definition, readers cannot verify how assignment was reflected in the reported outcome comparisons.

These omissions do not alter the arithmetic of the posted counts, but they limit evaluation of the inferential analysis. A registry record can communicate outcome summaries without documenting every statistical decision; where those decisions are absent, they should not be inferred.

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 5% reporting threshold.

The registry reports serious adverse events for 284 participants at risk in the EndoRings Colonoscopy arm and 278 in the standard-colonoscopy arm. It reports zero serious adverse events in each arm. The record also reports zero other adverse events in each arm and zero deaths in each arm.

These figures describe the adverse-event counts recorded in the registry. A zero posted count means that no events of that category are listed for the participants at risk in the record; it does not establish that an event is impossible or that no unrecorded event occurred. The registry does not list serious adverse-event terms for either group, and it does not provide further details about event definitions, surveillance, timing, or attribution.

Adverse-event counts should be interpreted alongside the scope and completeness of reporting. The record does not report additional safety analyses or a detailed method for collecting events. These registry entries therefore describe what is recorded, without supporting broader conclusions beyond the listed counts.

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

The primary result describes a randomized comparison of participant-level adenoma detection during colonoscopy. More participants in the EndoRings arm than in the standard-colonoscopy arm are recorded as having at least one adenoma detected, and the estimated risk difference is positive. The confidence interval is broad and includes zero, while the unadjusted p-value is 0.172. Together, these features indicate that the point estimate has a direction, but the data leave meaningful uncertainty about the size and direction of the underlying difference.

The result does not show that the groups are exactly the same. An interval that includes no difference can also include nonzero values. Conversely, a positive point estimate does not establish that the intervention caused a higher detection rate in the broader population. The estimate is based on the participants and procedures represented in the posted outcome data, and the registry does not report enough analysis detail to assess every assumption behind the comparison.

The endpoint is limited to whether at least one adenoma was detected per participant. It does not by itself describe the total number of adenomas, the clinical significance of findings, or other outcomes such as procedure time, comfort, or equipment problems. The registry lists several such secondary outcomes, but numerical results are not posted for all of them.

The findings should not be treated as medical advice or as a stand-alone basis for choosing a procedure. They are statistical summaries from a completed randomized trial record. Interpretation depends on the endpoint definition, uncertainty, analysis methods, population, and completeness of reporting. Several of those details are not reported in the registry record, so conclusions should remain limited to the posted comparisons.

17. Why This Trial Matters Statistically

This trial illustrates why a randomized comparison should be read through both its estimate and its uncertainty. The primary outcome counts participants with at least one adenoma detected, and the estimated comparison points toward a higher detection rate in the EndoRings arm. Yet the confidence interval includes zero and the unadjusted p-value is 0.172. Reporting the direction alone would overstate what the data establish; reporting only a threshold judgment would obscure the estimated range of plausible differences.

It also demonstrates the value of distinguishing endpoints that may sound similar. Adenoma detection rate counts participants with at least one adenoma. Polyp detection rate concerns participants with at least one polyp, while detections per colonoscopy summarizes a number of detections. Cecal intubation rate addresses completion of the examination. These endpoints describe related aspects of colonoscopy but are not substitutes for one another.

The secondary results show why multiplicity and analysis plans matter. Several outcomes are listed, and the record gives unadjusted comparisons for some of them. Without a reported testing hierarchy or multiplicity strategy, isolated secondary findings require caution. The registry also illustrates the limits of interpreting results when details about missing data, analysis populations, and methods are not reported.

Finally, planning illustrations based on an observed effect can help readers understand how sample-size needs change when targeting smaller effects or higher power. They are distinct from the trial's original design justification and from evidence about the observed result. Keeping those roles separate prevents planning calculations from being mistaken for an assessment of the completed trial.

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 registry record leaves several trial-specific details unavailable. Eligibility criteria and a fuller description of the enrolled population are not reported in the registry record. The record identifies randomized allocation and no masking, but does not describe the randomization method, allocation concealment, or implementation procedures. The original sample-size justification and design assumptions are also not reported.

The statistical analysis plan is not reported in the registry record. In particular, the record does not specify the test or model used for the primary comparison, the construction method for its confidence interval, covariate adjustment, handling of missing outcomes, or analysis-population definition. It also does not report whether an intention-to-treat approach was used. These gaps limit assessment of how the posted estimates were obtained and whether the assumptions of the analyses were appropriate.

The registry lists multiple secondary outcomes, but only some have numerical comparisons posted. Analyses for all listed outcomes are not reported in the registry record. A multiplicity strategy is not reported, which makes unadjusted secondary findings more difficult to interpret as confirmatory evidence. The record does not provide additional information on endpoint adjudication or detailed definitions for adenomas and polyps.

Safety reporting is limited to the posted counts. Detailed event definitions, collection methods, timing, and attribution are not reported in the registry record. These limitations concern what can be learned from the record; they do not imply that the missing procedures or analyses were absent from the trial itself.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: EndoRings Colonoscopy vs Standard Colonoscopy — NCT03418662.
• Registry record last updated 2019-09-20; status last verified 2019-09.
• Results first posted 2019-09-20.
• 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 describes a completed, randomized, parallel-group comparison of EndoRings Colonoscopy and standard colonoscopy, with no masking. Recorded enrollment is 592. The primary outcome is the number of participants with at least one adenoma detected during colonoscopy. The posted counts are 143 of 284 in the EndoRings arm and 124 of 278 in the standard-colonoscopy arm.

The primary risk-difference interval includes zero, and the unadjusted p-value is 0.172. The registry also posts secondary comparisons for polyp detection, detections per colonoscopy, and cecal intubation. Serious adverse events, other adverse events, and deaths are recorded as zero in both arms. Details of the analysis plan, missing-data handling, and analysis populations are not reported in the registry record.