Standard Colonoscopy Versus Colonoscopy With Endocuff Vision: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Standard Colonoscopy Versus Colonoscopy With Endocuff Vision (NCT03361917), a randomized na study. The primary outcome is Inspection Time Comparisons for Each Method (Standard vs. Endocuff Vision).

2. Clinical Question

The primary comparison concerns procedural duration, not a clinical outcome such as cancer diagnosis or prevention. The registry also lists secondary outcomes involving insertion time, total procedure time, detection rates, polyps per colonoscopy, and bowel preparation score. The posted numerical results include insertion time and total procedure time; results for the other listed secondary outcomes are not reported in the registry record. The trial therefore addresses a focused question about time spent inspecting the colon and provides some additional procedural measurements, but the registry record does not establish what the trial found for every listed outcome.

3. Trial Design

This was a randomized, parallel-group trial comparing standard colonoscopy with colonoscopy using Endocuff Vision. The registry lists the study as completed, with enrollment of 200 participants. It records a start date of 2017-12-11 and a primary completion date of 2018-04-18. The sponsor was Indiana University. The phase is listed as not applicable.

The control arm received standard colonoscopy with no device attachments. The intervention arm received colonoscopy with Endocuff Vision attached to the distal end of the scope. Masking is listed as none. The registry does not describe the randomization sequence, allocation concealment, or whether staff or participants knew the assigned method beyond the stated absence of masking.

The primary endpoint was inspection time during withdrawal, measured in minutes. A study assistant used a stopwatch during colonoscopy. The registry also lists insertion time and total procedure time, as well as detection rates, polyps per colonoscopy, and Boston Bowel Preparation Score. The numerical secondary results posted in the registry cover insertion time and total procedure time. Numerical results for the remaining named secondary outcomes are not reported in the registry record.

The registry record does not report the original sample-size justification, planned statistical model, prespecified covariates, interim analyses, or detailed analysis populations. It lists no reported analyses. The numerical contrasts discussed for continuous outcomes are unadjusted recalculations from the posted arm-level summary statistics, rather than a reported sponsor analysis. The registry does not provide further procedural detail about participant flow, protocol deviations, or missing observations.

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 Inspection Time Comparisons for Each Method (Standard vs. Endocuff Vision), measured over During the withdrawal portion of the colonoscopy procedure.

The primary endpoint is inspection time: the time spent actually examining the colon during the withdrawal portion of colonoscopy. It is measured in minutes. A study assistant measured the time with a stopwatch. The registry defines inspection time by subtracting time spent washing, suctioning, performing polypectomy, and taking biopsies from total withdrawal time.

This measure isolates the examination component from other activities that can occur during withdrawal. That makes it a direct procedural-time outcome for comparing the two colonoscopy methods. It is not the same as insertion time or total procedure time: those measure different portions or the overall duration of the procedure. Nor is inspection time itself a measure of polyp detection, diagnostic accuracy, or a patient's health outcome.

The registry reports the arm-level mean and standard error for this continuous measure. The posted mean was 6.49 minutes in the Endocuff Vision arm and 8.42 minutes in the standard-colonoscopy arm. The unadjusted recalculated difference, defined as Endocuff Vision minus standard colonoscopy, was -1.93 minutes. A negative difference indicates a lower mean in the Endocuff Vision arm for this endpoint. These results describe the measured procedure times in this trial; they do not, on their own, establish why the times differed or what that difference means for other outcomes.

7. Results Posted in the Registry

• Endocuff Vision: mean 6.49 versus 8.42 on control; difference -1.93 (95% CI -2.24 to -1.62), standardized effect d = -1.75; z-test p = <0.001.

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.

Insertion Time Comparisons for Each Method (Standard vs. Endocuff Vision)

• 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 errors.
• Result:
  • Endocuff Vision: mean 4.05 versus 4.42 on control; difference -0.37 (95% CI -0.86 to 0.12), standardized effect d = -0.21; z-test p = 0.136.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Endocuff Vision and the control. The interval gives the range of effects that remain compatible with the data.

Total Procedure Time Comparisons for Each Method (Standard vs. Endocuff Vision)

• 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:
  • Endocuff Vision: mean 21.01 versus 21.24 on control; difference -0.23 (95% CI -2.26 to 1.80), standardized effect d = -0.03; z-test p = 0.824.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Endocuff Vision and the control. The interval gives the range of effects that remain compatible with the data.

The secondary results cover two additional procedural-time measures: insertion time and total procedure time. Their recalculated mean differences are both negative, meaning the observed means were lower in the Endocuff Vision arm under the same subtraction order used for the primary result. However, their intervals include zero, and their unadjusted p-values do not provide clear evidence of differences. This contrasts with the primary inspection-time result, whose interval lies below zero and whose unadjusted p-value is p < 0.001.

The measures are related in that each concerns procedural duration, but they represent different portions or scopes of the colonoscopy. The primary result concerns time spent inspecting the colon during withdrawal. Insertion time concerns the insertion portion, while total procedure time covers the procedure. A difference in one measure does not require a difference in another, and a result for one should not be substituted for the others.

The registry also names detection rates, polyps per colonoscopy, and Boston Bowel Preparation Score as secondary outcomes. Numerical results for these outcomes are not reported in the registry record. They therefore cannot be used to determine whether the procedural-time pattern was accompanied by differences in detection, polyp counts, or preparation scores.

In general, secondary outcomes are often interpreted more cautiously than a primary outcome. Multiple comparisons can increase the chance that at least one result appears notable by chance, particularly when outcomes and analyses are numerous. The registry does not report a multiplicity strategy, so the unadjusted secondary p-values should not be treated as though they account for all comparisons. The secondary findings provide context for the primary result, but they do not independently establish a broad pattern across all the outcomes named in the registry.

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

• Insertion Time Comparisons for Each Method (Standard vs. Endocuff Vision)
• Total Procedure Time Comparisons for Each Method (Standard vs. Endocuff Vision)
• Detection Rates
• Polyps Per Colonoscopy
• Boston Bowel Preparation Score

9. Statistical Interpretation

10. Statistical Methods Explained

The outcomes reported for procedure time are continuous measurements expressed in minutes. For a continuous outcome, the mean is the arithmetic average across participants with a recorded measurement. It describes the center of the observed values, but does not describe their full distribution. The primary endpoint uses the mean as its summary measure, with a standard error as the posted measure of uncertainty around that mean.

What does the mean difference represent?

The comparison is expressed as the mean in the Endocuff Vision arm minus the mean in the standard-colonoscopy arm. For inspection time, this unadjusted recalculation is -1.93 minutes. A negative value means that the observed mean was lower in the Endocuff Vision arm under this subtraction order. The same interpretation applies to the secondary continuous-outcome contrasts. The estimate is a difference between arm averages; it is not a statement that every participant had a shorter procedure or that the same difference would occur in every setting.

The registry's comparison estimates are recalculated directly from posted summary statistics. They are unadjusted and should be distinguished from an analysis based on individual participant data or a prespecified model. The registry record does not report a sponsor analysis for these outcomes, covariate adjustments, or the method used for any original inferential analysis. The record lists no reported analyses. As a result, the recalculated values provide a transparent summary comparison, but cannot establish what analytic choices were made beyond those calculations.

Why do standard errors and standard deviations differ?

A standard deviation describes how spread out individual measurements are around their mean. A standard error describes the uncertainty in an estimated mean, and tends to be smaller when the estimate is based on more observations. These are different quantities and should not be read interchangeably. For inspection time and insertion time, the registry reports standard errors. For total procedure time, it reports standard deviations. This difference in reported spread affects how the arm-level results should be understood, even though all three outcomes are expressed in minutes.

In general, the standard error is useful when considering the precision of an arm mean, while the standard deviation gives information about variability among participant measurements. Neither summary alone reveals the shape of the underlying data, the presence of outliers, or whether the distribution is symmetric. Individual-level distributions are not reported in the registry record.

How should the interval and p-value be read?

A confidence interval gives a range of values compatible with the estimate under the method used to construct it. A narrower interval indicates greater precision than a wider interval, all else equal. For the primary comparison, the recalculated interval is -2.236 to -1.624. For insertion time, it is -0.857 to 0.117, and for total procedure time it is -2.26 to 1.8. The registry does not report the confidence level or the method used to calculate these intervals, so those details should not be inferred.

A p-value describes how unusual the data, or more extreme data, would be under a specified null model. It does not give the probability that the null hypothesis is true, and it does not measure the size or importance of a difference. The primary comparison has p < 0.001; the insertion-time comparison has p = 0.136; and the total-procedure-time comparison has p = 0.824. These are unadjusted values. The registry does not report whether any multiplicity adjustment was planned or performed.

The comparisons also report standardized effect sizes, including d = -1.75 for inspection time, d = -0.211 for insertion time, and d = -0.031 for total procedure time. In general, a standardized effect expresses a difference relative to a measure of variability, rather than in the original unit of minutes. It can help compare effects measured on different scales, but it does not replace the original-unit result or communicate clinical importance by itself. The record does not describe a prespecified threshold for interpreting these standardized values.

Why does outcome definition matter?

Inspection time, insertion time, and total procedure time concern different stages or scopes of the procedure. They are related measurements, but they are not interchangeable endpoints. A result for inspection time should not be paraphrased as a result for the whole procedure. Likewise, a time result cannot stand in for the listed outcomes of detection rates, polyps per colonoscopy, or bowel preparation score. Those other outcomes require their own results and analysis details, which are not reported in the registry record.

In general, over-dispersion matters when the observed variability is greater than a statistical model expects. A model that understates variability can produce overly narrow intervals and overly small p-values. The registry record does not report a model for these outcomes or evidence about over-dispersion; this is a general consideration, not a finding about this trial. More broadly, understanding an analysis requires knowing how its assumptions relate to the data, how missing observations were handled, and which participants were included. Those details are not reported in the registry record.

11. Confidence Intervals and Precision

The primary mean difference is -1.93 minutes, with an interval from -2.236 to -1.624. Because the full interval is below zero, the recalculated estimate is consistent with a lower mean inspection time in the Endocuff Vision arm under the stated subtraction order. The interval also conveys the range of uncertainty around the estimate: it does not establish that the true difference is exactly -1.93 minutes. The confidence level and interval-construction method are not reported in the registry record.

For insertion time, the interval runs from -0.857 to 0.117, spanning zero. For total procedure time, the interval runs from -2.26 to 1.8, also spanning zero. These intervals leave uncertainty about the direction and size of the differences in those secondary measures. Their inclusion of zero is not evidence that the methods are equivalent; an equivalence conclusion would require a prespecified margin and a suitable analysis, neither of which is reported in the registry record.

Precision depends on both the variability of measurements and the amount of information available. The primary arm summaries include 101 participants for Endocuff Vision and 99 for standard colonoscopy. The reported standard errors for inspection time are 0.1 and 0.12, respectively. These figures describe uncertainty around the arm means, not the range of individual inspection times. The registry does not provide individual measurements or a fuller distributional summary.

Intervals and p-values answer related but different questions: the interval emphasizes plausible effect sizes, while the p-value summarizes evidence against a null model. Neither determines whether a difference is important in practice. The registry does not report a threshold for a meaningful change in inspection time or a confidence level for the intervals, so conclusions should remain focused on the posted estimate and its stated uncertainty.

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 illustrations based on the observed effects, not the trial's original design assumptions. They use a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers a target effect stated as a fraction of the observed effect: 100%, 75%, or 50%. The figures for these continuous outcomes are participants per arm, not total events.

The 80% power column gives the estimated number of participants per arm under which the specified planning assumptions would yield an 80% chance of detecting the stated effect, if that effect and the calculation assumptions held. The 90% power column gives the corresponding number for a 90% chance. These are planning quantities, not guarantees about what a future study will find. Smaller effects require more participants to detect under the same assumptions, which is why the participant requirements increase as the target fraction becomes smaller.

For inspection time, the planning figures use the observed difference as their starting point; the listed requirements are 6 participants per arm for 80% power and 7 per arm for 90% power at 100% of the observed effect. At 75%, they are 10 and 13 per arm; at 50%, they are 21 and 28 per arm. These calculations are illustrations and do not show the power achieved by the completed trial. They are not observed power.

The original sample-size justification, the effect assumed when the trial was designed, and the trial's own planned significance and power assumptions are not reported in the registry record. The planning exercise should therefore not be used to infer what the investigators anticipated or whether the trial met an original design target.

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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -1.930; pooled standard deviation σ = 1.103.
2. n = 2 × (1.96 + 0.842)² × 1.103² / -1.930² = 5.1, rounded up to 6 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
delta <- -1.93                      # observed difference in means
sigma <- 1.10258832303857                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(3361917)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 6 (80% power), 7 (90% power)
 75% of observed effect: n per arm = 10 (80% power), 13 (90% power)
 50% of observed effect: n per arm = 21 (80% power), 28 (90% power)
power.t.test: 6.2 
Simulated power at n = 6 per arm: 0.781 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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

Multiplicity arises when several outcomes or comparisons are examined. In general, the more statistical tests conducted, the greater the possibility of finding an apparently notable result by chance if each test is judged separately. A prespecified primary outcome can help distinguish the main question from secondary questions, while an adjustment or other stated strategy can clarify how multiple tests are to be interpreted.

The registry identifies inspection time as the primary outcome and lists secondary outcomes that include insertion time, total procedure time, detection rates, polyps per colonoscopy, and Boston Bowel Preparation Score. It does not report a multiplicity adjustment or explain how the secondary comparisons were intended to be interpreted. The p-values associated with the recalculated comparisons are unadjusted. The registry record does not report whether the investigators planned a hierarchy of tests or another approach to multiplicity.

The registry lists no reported analyses. The contrasts and intervals discussed in the statistical interpretation are unadjusted recalculations from the posted summary statistics; they are not a substitute for a complete analysis plan or participant-level analysis. The original statistical analysis plan, including details of model selection, covariate adjustment, and interim analyses, is not reported in the registry record.

Missing-data handling and analysis populations are also not reported in the registry record. The record does not explain whether all randomized participants were included in each outcome analysis, how unavailable measurements were treated, or whether exclusions occurred. The listed arm counts describe the posted outcome summaries, but do not by themselves explain participant flow or the relationship between enrollment and each analysis.

These omissions limit the ability to assess how closely the posted results follow a prespecified plan and how sensitive they might be to analytic choices. They do not establish that any particular method was or was not used; they mean that the method is not documented in the registry record. The recalculated summaries should therefore be read with appropriate attention to the distinction between what is posted and what is not reported.

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 and other adverse events separately for the two arms. For standard colonoscopy, 99 participants were listed as at risk, with 0 serious adverse events and 0 other adverse events reported; deaths were 0. For Endocuff Vision, 101 participants were listed as at risk, with 0 serious adverse events and 0 other adverse events reported; deaths were 0.

These counts describe the adverse-event information recorded in the registry. They do not show that risk is absent, and zero reported events do not establish that the methods have identical safety profiles. The registry record does not provide event definitions beyond the serious-versus-other grouping, further safety follow-up details, or information about how events were assessed. No serious adverse-event terms are listed.

The event counts should also be considered in light of the numbers of participants at risk. A small study can provide limited information about uncommon events, even when no events are recorded. These figures are descriptive registry results, not medical advice or a complete assessment of safety.

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

The clearest statistical finding in the posted procedural-time results is the lower mean inspection time in the Endocuff Vision arm than in the standard-colonoscopy arm. The recalculated mean difference is -1.93 minutes, with an interval from -2.236 to -1.624 and p < 0.001. This describes the observed difference in mean inspection time among the participants represented in the posted summaries.

The result does not mean every procedure was shorter, and it does not by itself explain why the observed means differed. It also does not establish that total procedure time differed: that secondary comparison has an interval spanning zero. The insertion-time result likewise has an interval spanning zero. Those findings do not prove equivalence; they leave uncertainty about the size and direction of differences in those measures.

The trial's primary endpoint is a procedural measure rather than a direct measure of polyp detection, cancer outcomes, or other patient outcomes. Although the registry lists detection rates, polyps per colonoscopy, and bowel preparation score, their numerical results are not reported in the registry record. The procedural-time results therefore cannot establish whether the methods differed on those outcomes or whether any time difference had consequences beyond the measured duration.

Statistical evidence and practical importance are distinct. The registry record does not report a threshold for a clinically meaningful change in inspection time, nor does it establish how a difference in this measurement should be weighed against other aspects of the procedure. The result should be interpreted as evidence about a specific measured endpoint in this randomized trial, not as a general conclusion about all potential benefits, harms, or outcomes of either colonoscopy method.

The posted numerical comparisons are unadjusted recalculations from summary statistics, and the registry lists no reported analyses. Details about missing observations, analysis populations, and the original statistical plan are not reported in the registry record. Those limitations leave important aspects of the analysis and its robustness undocumented.

17. Why This Trial Matters Statistically

This trial illustrates why endpoint definitions matter. Inspection time was not defined as total withdrawal time or total procedure time. It was intended to isolate time spent examining the colon by excluding washing, suctioning, polypectomy, and biopsy time from total withdrawal time. That specific definition makes clear what the primary mean difference describes—and what it does not describe.

The results also demonstrate that related procedural outcomes can tell different statistical stories. The primary inspection-time comparison has an interval that lies below zero, while the intervals for insertion time and total procedure time include zero. This distinction is useful when reading a study with several time measures: evidence about one procedural stage should not automatically be generalized to the whole procedure.

The registry makes it possible to distinguish an arm-level mean, a measure of dispersion, a comparison estimate, and an interval. These quantities answer different questions. Means describe the observed averages; standard errors and standard deviations describe different aspects of uncertainty and variability; an interval communicates uncertainty about a contrast; and a p-value summarizes compatibility with a null model under the calculation used. None of these alone establishes practical importance.

The record also highlights the limits of registry results. The listed secondary outcomes extend beyond procedure time, but numerical results for several of them are not reported. The original analysis plan, multiplicity approach, missing-data handling, and analysis populations are also not reported. A careful statistical reading therefore combines attention to the observed result with attention to what the record does not document.

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. It does not describe the eligibility criteria in detail, the randomization procedure, allocation concealment, or participant flow. Although the trial is listed as randomized and masking as none, those labels alone do not provide enough information to assess every aspect of conduct or implementation.

The primary and secondary comparisons are unadjusted recalculations from posted arm-level summaries, and the registry lists no reported analyses. The original analysis plan, any covariate adjustments, any interim analyses, and the method used to construct the reported intervals are not reported in the registry record. The confidence level for those intervals is also not stated. Missing-data handling and analysis populations are not described, so it is not possible to determine from the record whether all enrolled participants contributed to every outcome summary.

The registry lists detection rates, polyps per colonoscopy, and Boston Bowel Preparation Score, but numerical results for these outcomes are not reported. This restricts interpretation to the procedural-time outcomes with posted values and the recorded adverse-event counts. The record also does not specify a threshold for a meaningful difference in inspection time, limiting assessment of practical importance.

The safety figures report zero serious and other adverse events in both arms and zero deaths. The registry record does not provide further event definitions or safety follow-up detail. These counts are descriptive and should not be treated as a complete assessment of uncommon events or as proof of equal safety.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Standard Colonoscopy Versus Colonoscopy With Endocuff Vision — NCT03361917.
• Registry record last updated 2019-08-06; status last verified 2019-07.
• Results first posted 2019-05-22.
• 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

NCT03361917 is a completed randomized, parallel-group trial sponsored by Indiana University. It enrolled 200 participants and compared standard colonoscopy with colonoscopy using Endocuff Vision. Masking is listed as none. The primary outcome was mean inspection time during withdrawal, measured in minutes by a study assistant using a stopwatch.

The posted arm means were 6.49 minutes for Endocuff Vision and 8.42 minutes for standard colonoscopy. The unadjusted recalculated difference was -1.93 minutes, with an interval from -2.236 to -1.624 and p < 0.001. Secondary time results were posted for insertion time and total procedure time; other named secondary outcomes do not have numerical results reported in the registry record. The registry recorded zero serious adverse events, zero other adverse events, and zero deaths in each arm.

The registry lists no reported analyses. Original design assumptions, the statistical analysis plan, multiplicity procedures, missing-data handling, and analysis populations are not reported in the registry record. The recalculated contrasts should be read as unadjusted summaries of the posted outcome statistics.