Research Study to Investigate How Well Semaglutide Works in People Living With Heart Failure and Obesity: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Research Study to Investigate How Well Semaglutide Works in People Living With Heart Failure and Obesity (NCT04788511), a randomized phase 3 study. The primary outcome is Change in Kansas City Cardiomyopathy Questionnaire Clinical Summary Score (KCCQ-CSS).

2. Clinical Question

The central comparison is between the mean change in a patient-reported measure in the two randomized groups. The posted group means are 16.8 for semaglutide and 10.3 for placebo. The registry’s sponsor-reported analysis gives an estimated treatment difference of 7.8, with a 95% confidence interval from 4.8 to 10.9 and p < 0.001. A separate unadjusted re-calculation from the posted summaries gives a mean difference of 6.5, with a confidence interval from 3.351 to 9.649 and p < 0.001.

These estimates address the relative change in the measured score between the randomized groups. They do not, by themselves, establish how an individual participant experienced the change or whether a particular score difference is important to every participant. The registry record does not report the trial’s original sample-size assumptions or a multiplicity strategy for interpreting the full set of outcomes.

3. Trial Design

This was a phase 3, randomized, double-masked, parallel-group trial. The registry record lists enrollment of 529 and a completed status. The study compared semaglutide 2.4 mg once weekly with placebo, with both described as add-ons to standard of care. Treatment allocation was decided by chance, and the arm descriptions specify gradual dose escalation during the first 16 weeks.

The registry describes the treatment period outcome assessment as change from baseline, week 0, to the end of treatment at week 52. The primary outcome was change in the KCCQ Clinical Summary Score. The record describes the KCCQ as a standardized, self-administered instrument covering heart failure symptoms, physical limitation, quality of life, and social limitation. The Clinical Summary Score uses symptom and physical limitation domains.

The brief summary says participants were to receive weekly injections and have discussions with study staff about healthy lifestyle choices, including healthy food and physical activity. It describes a study lasting approximately 59 weeks, with 11 clinic visits and 1 phone call. These are features described in the trial record; the posted primary endpoint timeframe is week 52.

The registry lists 243 analyzed participants in the semaglutide arm and 237 in the placebo arm for the primary outcome. Its population description says the full analysis set included all randomized participants, while the analyzed count for this endpoint signifies those with an observed value at week 52. Enrollment and endpoint analysis counts therefore describe different stages or definitions, and should not be treated as interchangeable.

The registry record does not report the original sample-size justification, the planned statistical analysis details beyond the reported ANCOVA result, interim analyses, or the trial’s full eligibility criteria. Those design details cannot be inferred from the outcome estimates.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: FAS included all the randomized participants for this trial. Here, Overall Number of Participants Analyzed" signifies those participants who had an observed value at week 52.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Population: Full analysis set (FAS) population included all the randomized participants for this trial.

6. Primary Endpoint

The registry lists the primary outcome as Change in Kansas City Cardiomyopathy Questionnaire Clinical Summary Score (KCCQ-CSS), measured over From baseline (week 0) to end of treatment (week 52).

The primary endpoint is change in the Kansas City Cardiomyopathy Questionnaire Clinical Summary Score (KCCQ-CSS) from baseline, week 0, to the end of treatment at week 52. The registry describes the KCCQ as a standardized 23-item, self-administered instrument that assesses heart failure symptoms, physical limitation, quality of life, and social limitation. The Clinical Summary Score uses the symptom and physical limitation domains.

Scores are transformed to a range of 0-100, with higher scores reflecting better health status. A change score focuses on how the measure differs between the start and end of the stated assessment period. Comparing the groups’ mean changes estimates the difference in average change between participants assigned to semaglutide and those assigned to placebo.

Patient-reported measures can capture symptoms and limitations that matter in daily life and may not be represented by a laboratory measurement alone. In general, repeated standardized questions allow researchers to compare health-status reports using a defined scoring system. That general role does not mean that every numerical change has the same importance for every participant.

The registry record says the primary outcome was evaluated using data from the in-trial period, defined as the uninterrupted interval from randomization to the last contact with the trial site. It does not report a threshold for interpreting the primary score difference as clinically meaningful. The endpoint therefore describes the measured score change; a clinical interpretation requires context beyond statistical evidence alone.

7. Results Posted in the Registry

• Semaglutide 2.4 mg: mean 16.80 versus 10.30 on control; difference 6.50 (95% CI 3.35 to 9.65), standardized effect d = 0.37; 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.

Change in Six-minute Walking Distance (6MWD)

• 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:
  • Semaglutide 2.4 mg: mean 23.50 versus 5.80 on control; difference 17.70 (95% CI 6.60 to 28.80), standardized effect d = 0.29; z-test p = 0.002.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Semaglutide 2.4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change in KCCQ Overall Summary Score (KCCQ-OSS)

• 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:
  • Semaglutide 2.4 mg: mean 16.80 versus 10.90 on control; difference 5.90 (95% CI 2.70 to 9.10), standardized effect d = 0.33; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Semaglutide 2.4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Achieving Threshold for Clinically Meaningful Within-participants Change in KCCQ-CSS (PGI-S)

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Semaglutide 2.4 mg: 43.2% (105/243) versus 32.5% (77/237) on control; risk difference 10.7 percentage points (95% CI 2.1 to 19.3), risk ratio 1.33 (1.05–1.68); unadjusted two-proportion z-test p = 0.016.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Semaglutide 2.4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The detailed secondary results have a broadly favorable direction across different kinds of measures: walking distance, another KCCQ score, and a threshold-based KCCQ outcome. Taken together, these results provide context about whether the primary score pattern is accompanied by differences in other functional and health-status measures. They do not replace the primary endpoint, which was designated as the main outcome of interest.

Secondary outcomes can help describe the breadth of a trial’s findings, but multiple comparisons create a statistical interpretation challenge. In general, when many outcomes are examined, the chance of at least one apparently notable result arising by chance can increase. A multiplicity procedure is one approach to controlling that risk. The registry record does not report a multiplicity adjustment or a hierarchy for the secondary analyses.

The posted secondary p-values are unadjusted. They should therefore be read as exploratory or supportive evidence, rather than as equally definitive tests alongside the primary outcome. The broad directional pattern is informative, but it does not establish that every secondary measure provides independent confirmation. Some measures may be related because they assess overlapping aspects of health status or function.

The registry lists additional secondary outcomes, including inflammatory, weight-loss, and other KCCQ threshold measures. Results for those listed measures are not reported in the registry record. Without their results and the analysis plan, the full pattern across all registered secondary outcomes cannot be assessed. The available secondary evidence should be interpreted in light of that incompleteness and the absence of reported multiplicity details.

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

• Change in Six-minute Walking Distance (6MWD)
• The Hierarchical Composite Endpoint: Percentage of Wins of Participant Pairs
• Change in C-Reactive Protein (CRP): Ratio to Baseline
• Percentage of Participants Achieving 10 Percent (%) Weight Loss (Yes/No)
• Percentage of Participants Achieving 15% Weight Loss (Yes/No)
• Percentage of Participants Achieving 20% Weight Loss (Yes/No)
• Percentage of Participants Improving 5 Points or More in KCCQ Clinical Summary Score (Yes/No)
• Percentage of Participants Improving 10 Points or More in KCCQ Clinical Summary Score (Yes/No)

9. Statistical Interpretation

10. Statistical Methods Explained

The registry reports the primary comparison as an ANCOVA analysis with an estimated treatment difference. ANCOVA is a regression-based method that compares groups while accounting for selected covariates. In general, such adjustment can improve precision or account for prognostic baseline information, depending on the variables and model used. The registry record does not report the covariates, model specification, or other details needed to describe exactly how its ANCOVA was implemented.

The sponsor-reported estimate is 7.8, with a 95% confidence interval from 4.8 to 10.9 and p < 0.001. The reported confidence interval expresses uncertainty around the estimated treatment difference under that analysis. It is not a range that is guaranteed to contain the true effect, nor does it describe the spread of individual participant outcomes.

A separate unadjusted re-calculation uses the posted group means, standard deviations, and analyzed counts. The group means are 16.8 and 10.3, and the reported unadjusted mean difference is 6.5. Its confidence interval is 3.351 to 9.649, and its unadjusted p-value is p < 0.001. This calculation is a simple comparison of the posted summaries, not a recreation of the sponsor’s ANCOVA model. Because it does not incorporate the sponsor’s model details, it is best read as a descriptive cross-check rather than a replacement for the sponsor analysis.

The standard deviation describes variability among observed scores within a group. It is distinct from the standard error, which describes the precision of an estimated mean. In general, the standard error depends on both outcome variability and the amount of information available. The standard deviations for the primary outcome are 17.9 and 17.3; these are measures of spread, not confidence limits for the treatment difference.

A confidence interval combines an estimate with a range of values reasonably compatible with the data and analysis assumptions. In general, a narrower interval indicates greater precision, while a wider interval indicates more uncertainty. The interval does not resolve questions about clinical importance, bias, or whether the analysis assumptions are appropriate. Those questions require design and analysis details beyond the interval itself.

The primary outcome is continuous: it is a score on a scale. A mean difference summarizes the average separation between groups, but does not show the full distribution of participant responses. Two groups can have different means while their individual values overlap. In general, reporting means and standard deviations gives a compact description, but it cannot show how many participants improved, stayed similar, or worsened unless those outcomes are separately reported.

One detailed secondary endpoint is binary: whether a participant met a threshold for a clinically meaningful within-participant change in KCCQ-CSS, as described in the endpoint title. For binary outcomes, a risk difference expresses the difference between group proportions, while a risk ratio or odds ratio expresses a relative comparison. The posted unadjusted risk difference is 0.107, with a confidence interval from 0.021 to 0.193, and p = 0.016. These are unadjusted secondary results; they are not equivalent to the continuous primary score comparison.

In general, continuous and binary outcomes answer different questions. A continuous score uses the amount of change across the scale, whereas a threshold outcome classifies participants according to whether a specified criterion was met. Thresholding can make results easier to interpret in some contexts, but it discards information about the degree of change within each category. The registry record does not provide enough detail to assess how the threshold for this secondary outcome was selected.

The record describes the primary population as the full analysis set, which included all randomized participants. It further clarifies that the number analyzed for the primary result signifies participants with an observed value at week 52. These statements should be read together: the endpoint’s analyzed count is limited to participants with an observed endpoint value, even though the named analysis population is based on randomized participants.

For a complete assessment, important details would include the planned model, covariates, missing-data approach, sensitivity analyses, and any multiplicity procedure. The registry record does not report those details. General statistical interpretation should therefore separate what is directly reported—the estimates, intervals, p-values, and endpoint definitions—from assumptions or methods that are not documented.

11. Confidence Intervals and Precision

The unadjusted primary mean difference is 6.5, with a confidence interval from 3.351 to 9.649. This interval gives a range of effect estimates compatible with the observed data under the re-calculation’s assumptions. Its lower and upper limits are both above zero, the value that would represent no difference in mean change. The unadjusted p-value is p < 0.001.

The sponsor-reported ANCOVA estimate is 7.8, with a 95% confidence interval from 4.8 to 10.9. This interval also lies above zero. The two intervals are not identical because the sponsor-reported analysis and the unadjusted re-calculation use different analytical approaches. The record does not provide the ANCOVA model details needed to attribute the difference to specific adjustments.

In general, a confidence interval is useful because it conveys both direction and precision, rather than only a test result. A narrower interval indicates greater precision for the estimate; a wider interval indicates more uncertainty. Neither interval captures every possible source of uncertainty, such as unreported design features or potential bias. Nor does an interval specify whether the estimated difference is important to participants.

The primary standard deviations, 17.9 and 17.3, describe variability among individual observed scores. They should not be confused with the uncertainty interval for the group difference. The registry reports observed endpoint values for 243 semaglutide participants and 237 placebo participants. It does not report enough missing-data detail to determine how the observed-value analysis might differ from an analysis incorporating all randomized participants under a specified missing-data model.

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 illustrative calculations based on the observed effect, not the trial’s original design assumptions. For these non-time-to-event comparisons, the figures are participants per arm, not total events. The calculations assume a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is a stated fraction of the observed effect.

The 80% power column gives the estimated participants per arm for a design with an 80% chance of detecting the specified effect under those planning assumptions, if that effect were the true one. The 90% power column gives the corresponding per-arm estimate for a design with a 90% chance under the same assumptions. These are planning quantities, not guarantees about a future study’s result.

Rows for 100% of the observed effect use the full observed effect as the target. The 75% and 50% rows use smaller target effects. Smaller effects are harder to distinguish from random variation, so the planning estimates require more participants per arm. This relationship is a general feature of power calculations, not evidence that the original trial was designed around the effect observed in its results.

The registry record does not report the trial’s original sample-size justification or the assumptions used for its design. The planning values should not be interpreted as the number originally planned, as a reconstruction of the trial protocol, or as evidence of observed power. This is not observed power.

13. How the Sample Size Is Derived

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

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 6.500; pooled standard deviation σ = 17.606.
2. n = 2 × (1.96 + 0.842)² × 17.606² / 6.500² = 115.2, rounded up to 116 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 <- 6.5                      # observed difference in means
sigma <- 17.6063213733379                     # 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(4788511)
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 = 116 (80% power), 155 (90% power)
 75% of observed effect: n per arm = 205 (80% power), 275 (90% power)
 50% of observed effect: n per arm = 461 (80% power), 617 (90% power)
power.t.test: 116.1 
Simulated power at n = 116 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. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary analysis as ANCOVA, with an estimated treatment difference of 7.8, a 95% confidence interval from 4.8 to 10.9, and p < 0.001. The unadjusted re-calculation from the posted arm summaries gives a mean difference of 6.5, a confidence interval from 3.351 to 9.649, and p < 0.001.

The re-calculation is a simple, unadjusted comparison of posted summary statistics. It does not reproduce the sponsor’s ANCOVA analysis, whose model details are not reported in the registry record. The two estimates are therefore not interchangeable. The sponsor’s own analysis is the appropriate primary result to prioritize when describing the registry’s reported analysis; the re-calculation offers a transparent summary-based comparison.

Both estimates are positive, and both confidence intervals lie above zero. Their numerical difference should not be interpreted as a contradiction without the model specification and analysis details. The record does not report the adjustment variables or enough information to explain precisely why the estimates differ.

15. Multiplicity, Missing Data and Analysis Populations

The registry record identifies a primary endpoint and lists secondary outcomes, but it does not report a multiplicity strategy. Multiplicity refers, in general, to the problem of interpreting multiple statistical tests: as the number of tests grows, the chance of at least one result appearing notable by chance can also grow. Prespecified testing order, adjustment procedures, or other approaches can address this concern, but no such approach is reported in the registry record.

As a result, the primary result has a clearer role than individual secondary p-values. The unadjusted secondary analyses can describe patterns and generate questions, but the record does not establish that they were protected against the risks of multiple testing. Their p-values should not be treated as if they had been adjusted or as if each were a separate confirmatory primary result.

The registry describes the full analysis set as including all randomized participants. For the primary endpoint, it says the analyzed number signifies participants with an observed value at week 52. That clarification means the endpoint result is based on observed week-52 values, rather than a stated imputation procedure for every randomized participant.

The record does not report the extent or reasons for missing primary outcome data, the method used to handle missing values in the sponsor’s ANCOVA, or sensitivity analyses testing alternative assumptions. It also does not report whether missingness differed between groups. These details matter because conclusions from an observed-value analysis may depend on how missing outcomes relate to participants’ underlying scores and treatment assignment.

The record defines the in-trial period as the uninterrupted interval from randomization to the last contact with the trial site. That definition describes the assessment period but does not, by itself, explain the statistical handling of missing endpoint values. The original analysis plan, missing-data assumptions, and any interim analyses are not reported in the registry record.

16. 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.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cardiac failure (4.5%), atrial fibrillation (3.4%), acute kidney injury (1.9%), diarrhoea (1.1%), atrial flutter (1.1%).

The registry reports serious adverse events affecting 35 of 263 participants at risk in the semaglutide group and 71 of 266 in the placebo group. It reports other adverse events affecting 93 of 263 and 57 of 266, respectively. Deaths are reported for 3 semaglutide participants and 4 placebo participants. These are descriptive counts from the registry record; they should not be treated as adjusted comparisons or as estimates of causal effects.

The listed serious adverse event terms include cardiac failure at 4.5%, atrial fibrillation at 3.4%, acute kidney injury at 1.9%, diarrhoea at 1.1%, atrial flutter at 1.1%, and COVID-19 at 1.1%. The record does not provide, in these figures, enough detail to interpret each event’s timing, duration, severity beyond the serious-event classification, or relationship to treatment.

Safety counts require context. In general, raw numbers can be influenced by how long participants were followed, how events were defined and collected, and whether participants had different exposure time. The registry record does not report enough detail to make an adjusted safety comparison. The figures describe reported events and deaths; they do not establish why an event occurred.

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

The primary outcome shows a larger mean improvement in KCCQ-CSS in the semaglutide group than in the placebo group over the stated baseline-to-week-52 period. The sponsor-reported ANCOVA estimate and the unadjusted re-calculation both have confidence intervals above zero. These results describe group averages and the statistical uncertainty around their comparisons.

They do not show that every participant improved, that each participant had the same experience, or that an individual can expect a particular score change. A group mean can conceal variation in individual outcomes. The registry reports standard deviations, but the summary statistics do not provide a complete account of each participant’s trajectory.

The score is a patient-reported measure of symptoms and physical limitation, with higher scores reflecting better health status. The registry record does not report a threshold for interpreting the primary group difference as clinically meaningful. Statistical evidence of a difference and an assessment of its importance are related but distinct questions. The estimate alone cannot answer whether a change is meaningful to every participant or in every context.

The record’s secondary outcomes offer additional context, but their unadjusted nature and the unreported multiplicity strategy limit how strongly they can be interpreted as confirmatory. Results for several registered secondary measures are not reported in the registry record. The record also does not provide the missing-data analyses needed to assess how endpoint availability might affect interpretation.

These findings are specific to the studied population and trial conditions described in the registry. The record identifies obesity-related heart failure with preserved ejection fraction in its official title and describes semaglutide or placebo as add-ons to standard of care. It does not contain enough detail to establish how the results apply to populations or circumstances beyond those studied. The result is evidence about a measured between-group score difference, not a guarantee of an individual outcome or a substitute for clinical judgment.

18. Why This Trial Matters Statistically

This trial illustrates why a primary endpoint, a reported model-based analysis, and a summary-statistic re-calculation should be kept distinct. The registry’s primary outcome is a patient-reported score, and the sponsor’s ANCOVA result is the reported primary analysis. The unadjusted estimate is useful as a transparent comparison of posted group summaries, but it is not a reconstruction of the sponsor’s model.

The distinction matters because statistical conclusions depend not only on the numerical means but also on the analysis method, assumptions, and population used. Here, the two primary estimates point in the same direction but differ in magnitude. Since the registry record does not report the ANCOVA specification, readers should avoid assigning the difference to an unreported adjustment or treating the estimates as identical.

The trial also shows the value and limits of patient-reported outcomes. A standardized instrument can quantify changes in symptoms and physical limitation using a defined scale. At the same time, a mean difference does not convey the full distribution of experiences or settle the question of clinical importance. Interpretation benefits from the endpoint definition, uncertainty interval, analysis population, and missing-data context considered together.

Finally, the secondary outcomes demonstrate why multiplicity and completeness of reporting matter. Secondary measures can support a broader view of function and health status, but unadjusted tests have less confirmatory weight when many outcomes are considered. Unreported results and undocumented analysis choices leave important uncertainty. Statistical interpretation depends on both the observed estimates and the transparency of the methods used to obtain them.

19. 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 does not report the detailed eligibility criteria, so the population cannot be characterized beyond the description of obesity-related heart failure with preserved ejection fraction and the condition listing. This limits assessment of how closely the analyzed participants match other populations. The record also does not report the original sample-size justification, making it impossible to evaluate the assumptions behind the trial’s planned enrollment from this information.

For the primary outcome, the sponsor’s ANCOVA result is reported, but its model specification and covariates are not. The unadjusted re-calculation is based on posted group summaries and cannot reproduce or verify the sponsor’s model. The record does not report the approach to missing outcome data, the extent or reasons for missingness, or sensitivity analyses. The primary analyzed counts refer to participants with an observed week-52 value.

The record does not report a multiplicity strategy for the secondary outcomes. Several listed secondary outcomes have no results reported in the registry record, limiting assessment of the complete secondary outcome pattern. The available secondary p-values are unadjusted and should not be given the same confirmatory weight as the primary analysis.

Safety figures are presented as counts, but the registry information summarized for this trial does not provide enough context to account for differences in exposure duration or to make adjusted comparisons. Event counts alone cannot establish causality. The registry also does not report interim analyses or enough detail to assess other elements of the planned statistical strategy.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Research Study to Investigate How Well Semaglutide Works in People Living With Heart Failure and Obesity — NCT04788511.
• Registry record last updated 2025-12-05; status last verified 2025-11.
• Results first posted 2024-06-11.
• 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.

23. Record Summary

The registry record describes a completed phase 3, randomized, double-masked, parallel-group trial with enrollment of 529. Semaglutide 2.4 mg once weekly was compared with placebo, both as add-ons to standard of care. The primary endpoint was change in KCCQ-CSS from baseline to week 52.

The sponsor-reported ANCOVA estimated a treatment difference of 7.8, with a 95% confidence interval from 4.8 to 10.9 and p < 0.001. The unadjusted re-calculation from posted summaries estimated a mean difference of 6.5, with a confidence interval from 3.351 to 9.649 and p < 0.001. Secondary results broadly followed the primary direction, but were unadjusted and the record does not report a multiplicity strategy.

Important details—including the original sample-size assumptions, ANCOVA specification, and missing-data methods—are not reported in the registry record.