COPD: Oral Nutrition Supplements vs. Energy- and Protein Dense in Between Meal Snacks.: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for COPD: Oral Nutrition Supplements vs. Energy- and Protein Dense in Between Meal Snacks. (NCT02251496), a randomized na study. The primary outcome is Weight Changes.

2. Clinical Question

The clinical question is about two ways of adding nutrition to the diet, rather than about nutrition support compared with no additional nutrition. The stated objective was to compare the interventions during hospitalisation and at home. The registry also names health-related quality of life as a secondary outcome. Other outcomes described in the study summary include lung-function measures, walking distance, hand-grip strength, length of hospital stay, intake, readmissions and acute exacerbation, but results for those measures are not posted in the registry record. The focus of the available numerical results is therefore narrower than the full list of outcomes in the study summary.

3. Trial Design

The registry records a randomized, parallel-group trial with no masking. Participants were assigned to oral nutrition supplements or between-meal snacks. The two groups received different forms of additional nutrition, and the registry descriptions indicate that the intervention was intended to continue during hospitalisation and at home after discharge. The study is marked completed. The recorded enrollment is 34, with 19 participants in the oral nutrition supplement group and 15 in the snack group in the primary outcome results.

The registry lists the primary endpoint as weight change from baseline to one year from admission to hospital. The reported group summaries are means with standard deviations. The available primary outcome results are based on the recorded group sizes of 19 and 15. The registry also posts a secondary health-related quality-of-life outcome with the same group sizes and a stated measurement timeframe of baseline and one year from admission to hospital.

The study summary describes an overall objective involving 200 patients, whereas the enrollment field records 34. The registry record does not explain this difference, so it is not possible to determine from the posted information whether the objective was revised, recruitment stopped early, or another explanation applies. The trial's original target sample size and its justification are not reported in the registry record. The registry also does not report the random sequence-generation procedure, allocation concealment, or any stratification factors. Randomized allocation is recorded, but these additional design details should not be assumed.

Although the record gives the intervention descriptions and outcome timeframes, details such as adherence, treatment exposure, and how outcomes were collected are not reported in the registry record. The trial's analysis population and handling of participants with missing measurements are also not reported. These omissions limit what can be inferred about how the posted endpoint summaries relate to the original trial protocol and the full set of randomized participants.

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 Weight Changes, measured over baseline and one year from admission to the hospital.

The primary endpoint is weight change in kilograms from baseline to one year from admission to hospital. Weight change is a continuous measure: each participant's outcome is represented by a numerical amount, and the group summaries report the mean and standard deviation. A mean offers a concise description of the group's average observed change, while the standard deviation describes how widely individual observations vary around that average.

Weight is used in this trial because the stated objective is to compare nutritional interventions in malnourished patients with COPD, and the registry identifies weight change as the primary endpoint. A baseline-to-follow-up change focuses on how the measure shifted over the stated interval, rather than simply comparing endpoint weights without reference to baseline. The registry does not provide further detail about whether the endpoint was calculated from paired measurements for each participant, how incomplete measurements were handled, or whether any covariate adjustment was planned.

The posted mean changes are 2.3 kg for the oral nutrition supplement group and 4.4 kg for the snack group. The unadjusted mean difference, defined as the snack-group mean minus the oral-supplement-group mean, is 2.1 kg. This difference is an estimate from the posted group summaries, not a guarantee of the underlying difference in the wider population. Its uncertainty is described by the confidence interval, which is relatively broad and includes zero. The result therefore supports a range of possible between-group differences rather than a single precise value.

7. Results Posted in the Registry

• In Between Meals Snacks (Snacks-group): mean 4.40 versus 2.30 on control; difference 2.10 (95% CI -1.74 to 5.94), standardized effect d = 0.38; z-test p = 0.284.

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.

Health Related Quality of Life (HRQoL)

• 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:
  • In Between Meals Snacks (Snacks-group): mean 8.90 versus 3.90 on control; difference 5.00 (95% CI -3.71 to 13.71), standardized effect d = 0.40; z-test p = 0.260.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between In Between Meals Snacks (Snacks-group) and the control. The interval gives the range of effects that remain compatible with the data.

The registry posts one secondary endpoint, health-related quality of life, in addition to the primary weight-change outcome. Its group summaries have the same general pattern as the primary comparison in that the snack group has the higher reported mean change. The unadjusted secondary comparison also has a confidence interval that includes zero. The registry describes the measure as a score on a scale, but the scale's scoring range, direction, and interpretation are not reported in the registry record. The numerical difference therefore cannot be assigned a clear practical meaning from the record alone.

The secondary result does not provide a separate, definitive confirmation of the primary result. Both comparisons are based on small groups and have uncertainty that permits more than one interpretation. The secondary endpoint can be considered alongside weight change as part of the overall pattern of posted results, but it should not be used to strengthen the primary conclusion beyond what the primary estimate and its uncertainty support.

Unadjusted secondary results generally carry less weight than a prespecified primary result because the more outcomes and comparisons that are examined, the more opportunities there are for apparently notable results to occur by chance. This is the general statistical concern known as multiplicity. The registry record does not report a multiplicity plan, a hierarchy of outcomes, or an adjustment to the secondary comparison. It also does not report results for several additional outcomes listed in the study summary, so the complete landscape of intended endpoint results is unavailable.

The secondary outcome should therefore be interpreted as exploratory or descriptive in the context of the record, rather than as an independent basis for a strong conclusion. This wording reflects the limited posted information and the unadjusted result; it does not imply that the trial investigators formally designated the endpoint as exploratory. That designation is not reported in the registry record.

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

• Health Related Quality of Life (HRQoL)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous, so the registry reports a group mean and standard deviation for each intervention. A mean summarizes the average outcome among the participants included in that group. A standard deviation describes the spread of individual outcomes around the mean; it is not the same as the uncertainty in the mean or the uncertainty in the difference between groups. The posted primary summaries are 2.3 kg with a standard deviation of 4.6 in the oral nutrition supplement group and 4.4 kg with a standard deviation of 6.4 in the snack group.

What does the mean difference represent?

The reported comparison is the snack-group mean minus the oral-supplement-group mean. The result is an unadjusted mean difference of 2.1 kg. “Unadjusted” means that the comparison is calculated from the group summaries without accounting for other measured characteristics, baseline values, or possible differences in follow-up. The registry record does not report an adjusted model for this endpoint. The sign of the difference follows the stated group order: a positive value indicates that the snack-group mean is numerically higher than the oral-supplement-group mean.

A difference estimate is not the same as a claim that the interventions caused a particular change. Randomization is intended to support a fair comparison between assigned groups, but the interpretation of this particular result also depends on the trial's conduct, the availability of outcome data, and the analysis population. Details about those matters are not reported in the registry record. The mean difference describes the posted comparison; it does not resolve the uncertainties created by the small recorded groups and incomplete methodological information.

How should the p-value be read?

The unadjusted p-value for the primary comparison is 0.284. In general, a p-value describes how compatible the observed data, or data more extreme, are with a statistical model that assumes no group difference. It is not the probability that the null hypothesis is true, nor is it a measure of the size or clinical importance of an effect. A larger p-value does not prove that there is no difference. In this trial, the p-value should be considered alongside the effect estimate and its confidence interval, not as a stand-alone decision rule.

The p-value is labelled unadjusted. No multiplicity adjustment is reported in the registry record. The p-value therefore should not be treated as if it accounts for testing multiple outcomes or comparisons. The registry names several outcomes in its summary, but only a subset has numerical results posted. The number of planned comparisons and any hierarchy among outcomes are not reported in the registry record.

What does a confidence interval add?

In general, a confidence interval gives a range of estimates compatible with the data and the assumptions of the statistical method. The primary difference has a 95% confidence interval from -1.743 to 5.943 kg. The interval includes zero, the value representing no difference between group means. It also includes values below and above zero. Thus the posted result is uncertain about both the direction and the size of the between-group difference. The interval is not a range in which every possible value is equally likely, and it does not guarantee that the true effect lies inside it.

The calculations labelled recalculated are simple, unadjusted recalculations from posted summary statistics. They are not substitutes for a prespecified analysis of participant-level data. They do not account for potentially relevant covariates, repeated measurements, or missing data unless those features are reflected in the posted summary statistics. The registry does not report the original analysis method, so the recalculated result should not be presented as the trial's complete statistical analysis.

Why does variation matter?

General statistical principle: greater variability among individual outcomes makes it harder to estimate a group mean precisely, especially when the groups are small. Here, the standard deviations are 4.6 kg and 6.4 kg, while the group sizes are 19 and 15. The differences among participants' weight changes therefore contribute to uncertainty in the estimated group contrast. The standard error values recorded for the group means are 1.055 and 1.652, but the registry does not provide a full participant-level analysis with which to examine the distribution or any influential observations.

General statistical principle: when data are more variable than a statistical model assumes, uncertainty estimates can be too narrow if that extra variability is ignored. This is often discussed as over-dispersion, particularly for count or categorical outcomes. The posted primary measure is continuous and reported with means and standard deviations; the registry does not report an over-dispersion assessment. It would not be appropriate to infer that over-dispersion was present or that a particular alternative model was used.

What is not documented?

The registry record does not report the trial's original sample-size justification, the planned analysis population, the handling of missing observations, an interim-analysis plan, or the statistical analysis plan. It also does not report whether the endpoint was analyzed using a model that accounts for baseline values. Those details affect how an estimate should be interpreted and whether the posted summary represents the planned primary analysis. Their absence does not prove that no such methods were used; it means they cannot be confirmed from the registry record.

11. Confidence Intervals and Precision

Precision refers to how narrowly an estimate is determined by the available data. For the primary endpoint, the observed unadjusted mean difference is 2.1 kg, with a 95% confidence interval from -1.743 to 5.943 kg. The interval spans zero and includes differences in both directions. This means that the posted data do not pin down a single direction or a narrow range of plausible effects. The interval is wide relative to the point estimate, so the estimate should be interpreted cautiously.

In general, a confidence interval is constructed by a method that would capture the underlying quantity at its stated rate across repeated samples if the model assumptions hold. For one particular interval, it is not correct to say that there is a 95% probability that the true difference lies within its limits. The interval describes statistical uncertainty under its assumptions; it does not incorporate every source of uncertainty, such as incomplete reporting, outcome measurement issues, or deviations from the study plan.

The limited group sizes and the observed variation are relevant to the interval's width. There are 19 participants in the oral nutrition supplement group and 15 in the snack group, and the reported standard deviations are 4.6 kg and 6.4 kg. With fewer observations and substantial variation, estimates commonly have less precision. This is a general statistical explanation, not a claim about why any participant did or did not contribute data.

The registry does not report the number of participants with missing primary outcomes, the analysis population, or the method used to handle missing data. Consequently, the interval's precision cannot be assessed in light of those details. The recorded group sizes in the outcome results should not automatically be interpreted as the number randomized or as evidence that all randomized participants had complete follow-up. The registry record does not provide enough information to establish that relationship.

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, not the trial's original design calculations. They estimate the participants needed in each arm under the stated assumptions: a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is specified as a fraction of the observed effect. The figures are participants per arm, not total events. The registry record does not report the assumptions used for the original trial design or its sample-size justification.

For 80% power, the planning figures describe the number of participants per arm that would give the stated probability of detecting the selected effect under the calculation's assumptions, if that effect and the model assumptions were correct. The 90% power column uses a higher target probability of detecting that same selected effect and therefore calls for more participants per arm. These are design concepts, not guarantees about the outcome of a future study. This is not observed power.

The planning illustration considers 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The associated figures are respectively 107, 189, and 425 participants per arm for 80% power, and 143, 253, and 569 participants per arm for 90% power. The pattern reflects a general principle: smaller effects are harder to distinguish from random variation, so detecting them at the same power generally requires more participants. These figures should not be read as recommendations or as a reconstruction of the trial's intended enrollment. The discrepancy between the study summary's objective involving 200 patients and the recorded enrollment of 34 is not explained in the registry record.

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 = 2.100; pooled standard deviation σ = 5.461.
2. n = 2 × (1.96 + 0.842)² × 5.461² / 2.100² = 106.2, rounded up to 107 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 <- 2.1                      # observed difference in means
sigma <- 5.46099807727489                     # 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(2251496)
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 = 107 (80% power), 143 (90% power)
 75% of observed effect: n per arm = 189 (80% power), 253 (90% power)
 50% of observed effect: n per arm = 425 (80% power), 569 (90% power)
power.t.test: 107.1 
Simulated power at n = 107 per arm: 0.800 (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

The study summary names a range of outcomes, including weight change, lung-function measures, walking distance, hand-grip strength, health-related quality of life, length of hospital stay, intake, readmissions, and acute exacerbation. The registry posts numerical results for weight change and health-related quality of life. Results for the other outcomes are not reported in the registry record. It is not possible to tell whether those outcomes were measured but not posted, were not measured, or were handled in another way.

When a study assesses multiple outcomes, the chance of at least one apparently unusual result can increase. General statistical practice may address this through prespecified outcome hierarchies, multiplicity adjustments, or clear separation of primary and secondary analyses. The record identifies a primary endpoint and a secondary health-related quality-of-life endpoint, but it does not report a statistical plan for controlling multiplicity or the planned number of comparisons. The posted p-values are unadjusted and should be read as such.

Important details about missing data and analysis populations are not reported in the registry record. The posted group sizes for both endpoints are 19 and 15, but the record does not say how many participants were randomized to each arm, whether any participants lacked follow-up measurements, or whether the analysis included all randomized participants. The method for handling missing measurements, withdrawals, or other incomplete records is also not reported. It is therefore not possible to assess whether the endpoint summaries represent an intention-to-treat population, a per-protocol population, or another analysis set.

The registry does not report an interim-analysis plan, stopping rules, or the trial's full statistical analysis plan. These omissions prevent confirmation of whether the posted analyses followed prespecified methods. They do not establish that such methods were absent in the conduct of the trial; they are simply not documented in the registry record. The stated objective involving 200 patients alongside recorded enrollment of 34 adds uncertainty about the relationship between the original plan and the posted results, but the reason for the difference 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 0% reporting threshold.

The registry records zero participants affected by serious adverse events in each group: 0 of 19 in the oral nutrition supplement group and 0 of 15 in the between-meal snack group. It also records zero participants affected by other adverse events in each group: 0 of 19 and 0 of 15, respectively. These figures describe what was recorded in the registry for the stated safety categories; they do not show that no health events of any kind occurred.

Deaths are listed separately: 4 in the oral nutrition supplement group and 3 in the snack group. The registry record does not report the timing, causes, relationship to the interventions, or circumstances of these deaths. It also does not specify the safety follow-up period or provide enough detail to determine how deaths relate to the adverse-event counts. The death figures should therefore be reported descriptively and should not be interpreted as evidence that one intervention caused more or fewer deaths.

With small recorded groups and limited event detail, these safety counts provide little information about uncommon events or differences in risk. The registry's zero counts are not proof that an intervention is free of risk. They are a record of the event counts posted, without the context needed for a fuller safety assessment.

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

The posted primary result is an unadjusted mean weight-change difference of 2.1 kg in favor of the numerically higher mean in the snack group, with a 95% confidence interval from -1.743 to 5.943 kg and an unadjusted p-value of 0.284. This describes the observed data; it does not establish that the interventions differ, nor does it establish that they are equivalent. The interval includes zero and allows for a range of possible differences, including some in the opposite direction.

The result also does not show that either intervention is effective or ineffective. The trial compares two nutrition approaches, and the posted comparison estimates their relative outcomes. There is no untreated comparison group in the record. A comparison between the two interventions cannot, on its own, establish what would have happened without either intervention. No medical advice follows from these summaries.

The trial's recorded enrollment is 34, although the registry summary describes an objective involving 200 patients. The reason is not reported in the registry record. The posted outcome groups are small, and the confidence interval is broad. Those features limit precision. Further uncertainty arises because the analysis population, missing-data handling, and original statistical plan are not reported. The record also posts results for only a subset of the outcomes listed in the study summary.

Health-related quality of life is the only secondary endpoint with posted numerical results. Its unadjusted comparison is also uncertain, and the scoring details are not reported in the registry record. The secondary result should not be treated as decisive confirmation of the primary estimate, particularly because multiplicity procedures are not documented.

The appropriate interpretation is therefore bounded: the registry reports these group means and unadjusted comparisons for the recorded participants. It does not provide enough information to make broad claims about all intended endpoints, the conduct of the original analysis, or outcomes beyond the posted follow-up data. The uncertainty is part of the result, not a reason to replace the estimate with a categorical conclusion.

17. Why This Trial Matters Statistically

This trial illustrates why a point estimate should be read together with its precision. The primary comparison is a positive mean difference of 2.1 kg, but its confidence interval extends from -1.743 to 5.943 kg. The estimated direction alone does not capture the uncertainty: the interval includes no difference and values on either side. A p-value of 0.284 likewise cannot settle the question by itself. The estimate, interval, and study context convey more than a binary significant-or-not label.

The recorded enrollment of 34, compared with the study summary's objective involving 200 patients, highlights the importance of distinguishing a study's stated objective from the number recorded as enrolled. The registry does not explain the difference. For interpretation, neither figure should be silently substituted for the other, and neither should be treated as proof of a particular recruitment or stopping history.

The planning illustrations also demonstrate how sample-size requirements depend on the effect a study aims to detect. Smaller target effects require more participants under the same stated assumptions. These illustrations are not the original trial's sample-size plan, and they are not evidence of the study's observed power. Keeping planning calculations separate from trial results prevents a common misinterpretation of post hoc sample-size reasoning.

Finally, the record shows why completeness of statistical reporting matters. The trial is marked randomized, but details of sequence generation, analysis populations, missing data, multiplicity, and the statistical plan are not reported. The study summary lists outcomes for which numerical results are not posted. Such gaps do not prove that methods were not used or outcomes were not collected, but they constrain reproducibility and the strength of conclusions that can be drawn from the registry record.

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 in interpreting this trial is the small recorded enrollment of 34, divided into groups of 19 and 15 in the primary results. The standard deviations are sizable, and the confidence interval for the primary mean difference is broad. The estimate is consequently imprecise. The registry summary refers to an objective involving 200 patients, but the reason for the contrast with recorded enrollment is not reported in the registry record.

The registry does not report the trial's original target sample size, design assumptions, or sample-size justification. The separate planning illustrations use the observed effect and stated calculation assumptions, so they cannot clarify what enrollment the investigators originally planned or why. The trial's own analysis plan, interim analyses, and any stopping rules are not reported either.

Although randomization is recorded, the method of sequence generation and allocation concealment is not reported. Masking is listed as none. The record does not describe how outcomes were assessed or whether measurement procedures differed between groups. It also does not report adherence to the assigned interventions or the amount of nutrition actually consumed, which limits understanding of exposure to the interventions.

For the posted outcomes, the analysis population and handling of missing measurements are not reported. The outcome group sizes do not establish how many participants were initially randomized or whether all had follow-up data. There is no posted adjusted analysis, and the unadjusted results may not account for baseline differences. The registry also does not report a multiplicity plan, while numerical results are unavailable for several outcomes listed in the study summary.

For health-related quality of life, the scale's range and direction are not reported, limiting interpretation of its score changes. Safety results lack details about event timing, causes, follow-up duration, and the relation between deaths and adverse-event categories. These limitations apply to the information in the registry record; they do not establish what information may be available elsewhere.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: COPD: Oral Nutrition Supplements vs. Energy- and Protein Dense in Between Meal Snacks. — NCT02251496.
• Registry record last updated 2021-01-19; status last verified 2020-12.
• Results first posted 2021-01-19.
• 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 records a completed, randomized, parallel-group trial with no masking, comparing oral nutrition supplements with energy- and protein-dense between-meal snacks in malnourished patients with COPD. Enrollment is recorded as 34. The primary endpoint is weight change from baseline to one year from hospital admission. Mean changes were 2.3 kg in the oral nutrition supplement group and 4.4 kg in the snack group; the unadjusted mean difference was 2.1 kg, with a 95% confidence interval from -1.743 to 5.943 kg and an unadjusted p-value of 0.284.

Health-related quality of life is the only secondary outcome with posted numerical results. The registry summary describes an objective involving 200 patients, but the reason for the difference from recorded enrollment is not reported. The original sample-size justification, analysis population, missing-data methods, multiplicity plan, and full statistical analysis plan are not reported in the registry record. The available results are therefore best understood as limited, unadjusted summaries with substantial uncertainty.