A Research Study to See How Well Semaglutide Helps People Who Have a Body Weight Above the Healthy Weight Range: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Research Study to See How Well Semaglutide Helps People Who Have a Body Weight Above the Healthy Weight Range (NCT06041217), a randomized phase 3 study. The primary outcome is Change in Body Weight (%).

2. Clinical Question

3. Trial Design

This was a phase 3 randomized, parallel-group study sponsored by Novo Nordisk A/S. The registry record lists the study as completed, with 242 participants enrolled. It records a start date of 2023-09-15 and a primary completion date of 2025-04-02. These administrative details describe the trial record, not the timing of every participant’s treatment or follow-up.

Participants were allocated to semaglutide 2.4 mg or placebo. Both groups received once-weekly subcutaneous injections for 44 weeks. The design is classified as quadruple-masked. The registry record does not identify the individual roles covered by that classification, so it is not possible from this record to say precisely who was masked. The parallel-group structure means that the two assigned groups are compared over the same treatment period rather than participants crossing between treatments.

The brief summary describes a study lasting about 1 year, with 12 clinic visits and 3 remote visits by phone with study staff. The primary endpoint was percentage change in body weight from baseline, week 0, to the end of treatment, week 44. The registry describes the primary outcome population as the full analysis set, including all randomized participants, and states that the number analyzed for this outcome was the number with available data.

The posted primary outcome summaries contain results for 159 participants assigned to semaglutide and 78 assigned to placebo. The registry’s total enrollment and these outcome-specific analyzed counts describe different aspects of the record; the record does not give a complete account of why some enrolled or randomized participants are not represented in the primary outcome summaries. Details such as the randomization procedure, allocation ratio, original sample-size justification, and any interim analyses are not reported in the registry record.

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.

Before assignment: Participants were randomised in 2:1 ratio to receive once weekly subcutaneous (s.c.) injection of either semaglutide 2.4 mg or semaglutide matching placebo as an adjunct to a reduced-calorie diet and increased physical activity. The trial has a 44-week treatment period (16 weeks of dose escalation period and 28 weeks of maintenance period), followed by a 5-week follow-up period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: FAS included all randomised participants. Overall number of participants analyzed = participants with available data for this outcome measure.

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) included all randomised participants.

6. Primary Endpoint

The registry lists the primary outcome as Change in Body Weight (%), measured over Baseline (week 0), end of treatment (week 44).

The primary endpoint is change in body weight expressed as a percentage of baseline weight. It compares body weight at week 44 with body weight at week 0, then summarizes that change as a group mean. A negative mean indicates that the group’s average body weight was lower at the end of treatment than at baseline. The posted means are −12.2% for semaglutide and −2.2% for placebo.

Using a percentage rather than only an absolute weight change expresses the change relative to each participant’s starting weight. This can make a group-level comparison easier to interpret across participants who may begin at different body weights. That is a general property of percentage outcomes; the registry record does not give a separate rationale for choosing this endpoint.

The endpoint is relevant to the stated study question because the brief summary describes comparing weight loss between the two groups. It is a continuous measure, and the record reports a mean and standard deviation for each group. The endpoint is assessed at a specified treatment time point, the end of treatment at week 44, rather than being a measure of the timing of an event.

A group mean condenses the observed results and does not show the full distribution of individual changes. The standard deviations in the posted summaries describe variability among participants, while the confidence interval for the treatment difference describes uncertainty about the group comparison. Neither alone provides a complete account of individual responses. The record does not state whether the endpoint was transformed or how any missing week-44 measurements were handled.

7. Results Posted in the Registry

• Semaglutide 2.4 mg: mean -12.20 versus -2.20 on control; difference -10.00 (95% CI -11.75 to -8.25), standardized effect d = -1.35; 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 Waist Circumference

• 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 -9.10 versus -2.40 on control; difference -6.70 (95% CI -8.17 to -5.23), standardized effect d = -1.15; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Semaglutide 2.4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change in Body Weight (kg)

• 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 -9.30 versus -1.70 on control; difference -7.60 (95% CI -8.95 to -6.25), standardized effect d = -1.36; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Semaglutide 2.4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change in Body Mass Index

• 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 -3.40 versus -0.60 on control; difference -2.80 (95% CI -3.29 to -2.31), standardized effect d = -1.35; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Semaglutide 2.4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary outcomes cover other measures, including waist circumference, body weight in kilograms, body mass index, waist-height ratio, blood pressure, cholesterol, and the number of participants achieving a stated body-weight reduction threshold. The record lists 22 secondary outcomes as posted and 24 outcome measures overall. This breadth can show whether the primary result sits alongside changes in related measurements, but it also means that the secondary results address multiple questions rather than one single confirmatory endpoint.

For the continuous secondary outcomes with group summaries shown, the mean changes are numerically more negative in the semaglutide group than in the placebo group. These measures relate to the primary result because they describe other dimensions of body size or related health measurements over the same baseline-to-week-44 period. They should be interpreted as complementary outcomes, not as substitutes for the primary percentage-change endpoint. The tables present the individual summaries and should be consulted for the exact values and intervals.

The registry record does not provide a multiplicity adjustment for the secondary analyses. In general, when many outcomes are tested, the chance of at least one apparently notable result arising by chance can increase. This is why unadjusted secondary results generally carry less confirmatory weight than a prespecified primary analysis with a clearly reported method. The record does not state whether the secondary outcomes were arranged in a testing hierarchy or whether any formal family-wise error procedure was used.

Not every listed secondary outcome has the same kind of data or analysis. Some are continuous changes; another is framed as whether participants achieved a threshold. The record’s summary results should therefore be read outcome by outcome, with attention to each measure’s definition and analysis population. The overall pattern can offer context, but it does not establish that every secondary outcome was analyzed or interpreted under a single shared inferential plan.

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

• Number of Participants Who Achieved Body Weight Reduction ≥ 10% (Yes/No)
• Change in Waist Circumference
• Change in Body Weight (kg)
• Change in Body Mass Index
• Change in Waist-height Ratio (WtHR)
• Change in Systolic Blood Pressure
• Change in Diastolic Blood Pressure
• Change in Total Cholesterol (mmol/L) - Ratio to Baseline

9. Statistical Interpretation

10. Statistical Methods Explained

The registry reports an ANCOVA analysis for the primary endpoint and also makes it possible to compare the posted group summaries using a simple unadjusted calculation. These are related but not interchangeable approaches. The ANCOVA result is the sponsor-reported analysis. The recalculation uses only the posted group means, standard deviations, and analyzed group counts; it does not reproduce an adjusted model.

What does a mean summarize?

The mean is the arithmetic average of the participants’ endpoint values in a group. For this outcome, the values are percentage changes in body weight from baseline to week 44. A mean provides a compact group summary, but it does not show whether individual results are tightly clustered or widely spread. The standard deviation describes the spread of values around the mean. Here, the posted standard deviations are 8.2 for semaglutide and 5.4 for placebo.

In general, a standard deviation is not the same thing as uncertainty in the estimated mean. The uncertainty of a mean also depends on how many observations contribute to it. The outcome-specific analyzed counts are 159 and 78. The record defines the analyzed population for the primary outcome as participants with available data, within a full analysis set that includes all randomized participants.

What does the unadjusted comparison do?

The simple comparison contrasts the posted means for semaglutide and placebo without adjustment for other variables. It gives a mean difference of −10.0. Its interval, from −11.75 to −8.251, represents uncertainty around that unadjusted contrast under the calculation used for the displayed summary. The corresponding unadjusted p-value is <0.001. This recalculation is useful as a transparent check on the group summaries, but it is not the same as the trial’s model-based analysis.

In general, an unadjusted comparison does not account for any baseline covariates or other model terms. An adjusted model can account for variables specified in its analysis, potentially improving precision or accounting for chance differences. The registry identifies the sponsor’s method as ANCOVA but does not report the covariates or the full model specification in this record. It would therefore be inappropriate to infer which adjustments were made.

How should the ANCOVA result be read?

The sponsor reports a treatment difference of −9.87, a 95% confidence interval from −11.78 to −7.96, and p < 0.001. ANCOVA is a model-based method for comparing a continuous outcome between groups while accounting for covariates. That is a general description of the method, not a claim about which covariates this trial used. The registry’s reported result is the available account of the sponsor’s primary analysis; the details needed to reconstruct it are not reported in the registry record.

The sponsor’s estimate is a treatment difference on the percentage-change scale. The negative sign indicates the direction of the reported contrast as coded in the record. Interpreting the sign depends on the order in which groups are compared, so the group means are useful context. The posted group means show decreases in both groups and a more negative mean in the semaglutide group.

What do confidence intervals and p-values contribute?

In general, a confidence interval gives a range of values compatible with the data and the statistical method, under its assumptions. A narrower interval indicates greater precision than a wider interval on the same scale. A p-value describes how unusual data at least as discrepant as those observed would be under a specified null hypothesis and model assumptions. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of an effect. The reported p-values are small, but interpretation should also consider the estimate, its interval, the design, and the outcome’s context.

The recalculated interval and the sponsor’s ANCOVA interval are not expected to match exactly because one uses a simple unadjusted summary-statistic comparison and the other is model-based. The record marks no discrepancy between the posted and recalculated results. That does not make the calculations identical; it means the record does not flag a discrepancy requiring a different reading of the reported analysis.

Why can over-dispersion matter?

For a continuous outcome, variability is represented by the spread of measurements around a mean. In other statistical settings, over-dispersion means that observed variability is greater than a model assumes. In general, if a model understates variability, its standard errors may be too small and its intervals may be too narrow. This is a general statistical concern, not a finding that over-dispersion occurred in this trial. The record provides standard deviations for the primary outcome but does not report a specific assessment of over-dispersion.

The primary endpoint is continuous, so the posted mean-and-standard-deviation summaries are appropriate descriptive quantities for the scale as reported. They do not determine whether all model assumptions were met. The record does not provide model diagnostics, residual checks, or a full statistical analysis plan. Those items are not reported in the registry record and cannot be assessed from the summary results alone.

11. Confidence Intervals and Precision

The sponsor-reported 95% confidence interval for the primary treatment difference runs from −11.78 to −7.96. The point estimate is −9.87. In general, a confidence interval communicates both the direction and the precision of an estimated comparison: it gives a range of values compatible with the data under the model and its assumptions. Here, the interval lies on the negative side of zero, in the direction consistent with a larger mean decrease in the semaglutide group when read alongside the posted group means.

The recalculated unadjusted interval runs from −11.75 to −8.251 around a mean difference of −10.0. It is based on the group summaries rather than the sponsor’s ANCOVA model. The two intervals are similar in their overall location and span, but they should not be combined or treated as if they were estimates from one analysis. Their methods differ, and the sponsor’s interval belongs to the reported primary analysis.

Precision is not the same as certainty about every aspect of the result. A confidence interval does not show the range of individual participant outcomes, and it does not address unreported design or analysis details. The primary outcome has standard deviations of 8.2 and 5.4 in the two groups, which describe observed variation around their means. That variation is distinct from the uncertainty in the estimated treatment difference.

The reported interval is conditional on the analysis and data included. The registry says the primary outcome analysis used participants with available data, but it does not report the missing-data method or a sensitivity analysis. The confidence interval therefore should be read as the uncertainty reported for the analysis, not as a resolution of possible uncertainty from missing outcomes or other unreported modeling choices.

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 table is a planning illustration based on the observed primary outcome effect, not the trial’s original design calculation. Its rows consider planning for 100%, 75%, and 50% of the observed effect. The columns give participants per arm for 80% power and participants per arm for 90% power. For example, planning for 75% of the observed effect gives 16 participants per arm for 80% power and 21 participants per arm for 90% power. The table’s figures are per arm, not total participants or total events.

The stated illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It uses the stated fraction of the observed effect as the effect to detect. The sample-size assumptions for the trial’s own original design are not reported in the registry record. These calculations should not be read as a reconstruction of that original design.

In general, power is the chance that a study using a specified design and analysis will detect an effect of a specified size when that effect is present. The 80% and 90% columns represent different planning targets under the illustration’s assumptions. A higher target generally requires more participants for the same target effect. The table also shows the basic planning relationship that smaller effects need more participants to detect than larger effects, holding the stated assumptions fixed.

These are planning illustrations, not observed power. They do not describe the probability that the trial’s result is true, and they do not revise the results from the completed study. The plotted curve, where shown, visualizes the same planning relationship rather than supplying a separate trial finding. Its values should be read alongside the table and its assumptions.

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 = -10.000; pooled standard deviation σ = 7.400.
2. n = 2 × (1.96 + 0.842)² × 7.400² / -10.000² = 8.6, rounded up to 9 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 <- -10                      # observed difference in means
sigma <- 7.40018401151318                     # 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(6041217)
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 = 9 (80% power), 12 (90% power)
 75% of observed effect: n per arm = 16 (80% power), 21 (90% power)
 50% of observed effect: n per arm = 35 (80% power), 47 (90% power)
power.t.test: 9.7 
Simulated power at n = 9 per arm: 0.765 (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 sponsor’s reported primary analysis is an ANCOVA treatment difference of −9.87, with a 95% confidence interval from −11.78 to −7.96 and p < 0.001. This is the inferential result reported for the trial. It should be kept distinct from the simple unadjusted recalculation based on the posted group means, standard deviations, and analyzed counts.

The recalculation gives a mean difference of −10.0, with a confidence interval from −11.75 to −8.251 and an unadjusted p-value of <0.001. It offers a check on the direction and approximate scale of the group contrast using summary statistics. It cannot reproduce the ANCOVA estimate because it does not include the model-based adjustment described by the sponsor.

The registry record does not flag a discrepancy between these results. That means the record does not identify a conflict requiring the recalculation to supersede the sponsor’s analysis. The two estimates remain products of different methods, and the sponsor’s ANCOVA result is the trial-reported analysis to use when describing the sponsor’s inferential finding. The covariates and detailed model specification are not reported in the registry record, so the adjustment itself cannot be independently reconstructed from these summaries.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates more than one outcome, comparison, or time point. In general, repeated statistical testing can increase the chance of at least one result appearing notable by chance, even when each individual test uses a conventional threshold. This trial record lists 24 outcome measures and 22 posted secondary outcomes. The registry record does not report a multiplicity adjustment, a testing hierarchy, or a detailed plan describing how inference across outcomes was controlled.

The primary result is reported as an ANCOVA treatment difference with a 95% confidence interval and p < 0.001. The registry identifies this as a superiority analysis. The record does not give enough detail to determine whether the primary result was part of a broader prespecified procedure for controlling error across analyses. The unadjusted recalculated p-value is a summary-statistic calculation, and it is not a multiplicity-adjusted result. Secondary findings should therefore be treated as supportive or exploratory in the absence of reported adjustment details.

For the primary outcome population, the record states that the full analysis set included all randomized participants and that the overall number analyzed was participants with available data for this outcome. The group summaries show outcome-specific analyzed counts of 159 and 78. The registry record does not explain all differences between enrollment, randomization, and those analyzed counts, nor does it report a detailed participant flow in the information.

The method used to handle missing body-weight measurements is not reported in the registry record. In particular, the record does not state whether missing values were imputed, whether a particular missing-data assumption was used, or whether sensitivity analyses examined alternative assumptions. In general, missing-data methods matter because conclusions may depend on why measurements are absent and on how the analysis represents those unobserved outcomes. That is a general methodological concern; the record does not establish that any specific missing-data bias occurred.

The original sample-size justification, interim-analysis plan, covariates in the ANCOVA model, and full statistical analysis plan are also not reported in the registry record. These omissions limit independent assessment of the planned inference and analysis decisions. They do not alter the numerical result posted, but they constrain how completely the result can be audited from this registry information alone.

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: angina unstable (1.2%), patellofemoral pain syndrome (1.2%), pyelonephritis acute (1.2%), abdominal pain (0.6%), cholecystitis (0.6%).

The registry’s safety summary reports serious adverse events for 13 of 161 participants at risk in the semaglutide group and 3 of 81 at risk in the placebo group. For other adverse events, the corresponding figures are 113 of 161 and 26 of 81. The record reports zero deaths in each group. These are counts and denominators from the posted safety summary; they are separate from the primary outcome analyzed counts.

The record lists serious adverse-event terms with percentages, including unstable angina, patellofemoral pain syndrome, acute pyelonephritis, abdominal pain, cholecystitis, and cholelithiasis. The listed percentages are 1.2% for the first three terms and 0.6% for the next three. These terms describe reported events; the registry summary alone does not establish whether an event was caused by treatment.

In general, adverse-event counts are useful for describing what was observed during a trial, but interpretation depends on definitions, ascertainment, follow-up, and participant context. The summary does not provide a full account of event severity, timing, relatedness assessments, or the comparative uncertainty around these safety counts. The figures should therefore be read as posted safety observations, not as a complete safety profile or a causal conclusion.

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

The posted results describe a randomized comparison of semaglutide 2.4 mg and placebo over 44 weeks in adults with overweight or obesity. For the primary endpoint, the group means show decreases in percentage body weight from baseline in both groups, with a more negative mean in the semaglutide group. The sponsor-reported ANCOVA comparison is −9.87 percentage points, with a 95% confidence interval from −11.78 to −7.96 and p < 0.001. This is the statistical finding reported in the registry record.

That result does not describe what happened to every participant. Group means summarize average changes, while the standard deviations show that individual values varied around those averages. A participant’s outcome may differ from the group mean. The interval around the treatment difference describes uncertainty in the group comparison under the reported analysis; it is not an interval containing a specified proportion of individual responses.

The finding is also limited to the participants and treatment period represented in the record. The study’s population is described as adults with overweight and obesity, and the endpoint is assessed at week 44. The record does not establish what the comparison would be over a different duration, in a different population, or under different conditions. It also does not provide all details needed to independently reconstruct the adjusted model or missing-data handling.

The result should not be taken as a guarantee of an individual outcome, a complete account of benefits and harms, or evidence about outcomes not reported. Secondary measures and adverse-event summaries add information, but the registry does not report enough about multiplicity or analysis plans to treat every secondary result as equally confirmatory. Statistical significance is not the same as clinical importance, and the record does not provide a separate clinical-importance threshold for the primary endpoint.

In general, a trial estimate is strongest as a description of the comparison it actually made, under its design and analysis. Here, the primary result is a group-level comparison at the end of treatment, supported by an adjusted sponsor analysis and accompanied by an unadjusted recalculation. The interpretation should preserve that scope rather than extending the result beyond what the posted data establish.

18. Why This Trial Matters Statistically

This trial illustrates why statistical reading should separate a group summary from an adjusted treatment comparison. The posted means describe the observed average percentage changes, whereas the sponsor’s ANCOVA estimate is the reported inferential comparison. A simple recalculation from summary statistics can help readers understand the scale and direction of the contrast, but it is not a substitute for the trial’s model-based analysis.

It also demonstrates the role of precision. The sponsor’s estimate is accompanied by a 95% confidence interval, allowing the reader to see a range of estimates compatible with the reported analysis rather than relying on a point estimate alone. The group standard deviations add a different kind of information: they describe variation among observed participant outcomes. Keeping these concepts distinct helps avoid treating variability, uncertainty, and individual prediction as if they were the same.

The record also highlights how analysis populations and missing data affect interpretation. The primary outcome population is described as a full analysis set, but the outcome count is defined by available data. Without a reported missing-data method or full participant flow, readers cannot fully assess how unavailable measurements were handled. Similarly, a list of many outcome measures makes multiplicity relevant, yet adjustment details are not reported.

Finally, the planning illustration shows how sample-size requirements depend on the effect targeted and the assumptions used. It is not evidence of the trial’s original design rationale or a retrospective measure of power. Together, these features make the study useful for understanding the distinction between posted results, analysis choices, uncertainty, and planning calculations—questions that arise in the interpretation of clinical trials more broadly.

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.

Several limitations specific to this registry record affect how completely the trial can be assessed. The primary endpoint summaries include available-data counts, but the record does not explain the full participant flow from enrollment and randomization to analysis. It also does not report how missing week-44 measurements were handled or whether sensitivity analyses assessed the effects of missing data. The posted estimates therefore cannot, on their own, show how robust the result is to alternative missing-data assumptions.

The sponsor reports ANCOVA, but the covariates and full model specification are not reported in the registry record. This prevents independent reconstruction of the adjusted estimate from the information shown. The simple recalculation is useful as a descriptive comparison, but it is unadjusted and should not be mistaken for the sponsor’s model.

The record does not report the original sample-size justification, the trial’s design assumptions, or any interim-analysis plan. The sample-size figures shown elsewhere are planning illustrations based on the observed effect, not documentation of the original design. The registry also does not report multiplicity procedures for the secondary outcomes. This limits the strength of confirmatory interpretation across the many posted measures.

The safety summary provides event counts and selected serious-event terms, but not a complete account of timing, severity, treatment relatedness, or uncertainty for each event. Nor does this summary alone establish a causal link between treatment and an event. The record classifies the study as quadruple-masked but does not specify the roles covered by that term in the available information.

These limitations concern what can be concluded from the registry record and do not demonstrate that a particular bias or analysis problem occurred. They mark areas where the record lacks detail for independent evaluation.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Research Study to See How Well Semaglutide Helps People Who Have a Body Weight Above the Healthy Weight Range — NCT06041217.
• Registry record last updated 2026-05-18; status last verified 2026-04.
• Results first posted 2026-05-18.
• 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

This completed phase 3 study randomized adults with overweight or obesity to once-weekly semaglutide 2.4 mg or placebo for 44 weeks. It was a parallel-group, quadruple-masked trial sponsored by Novo Nordisk A/S, with 242 participants enrolled.

The primary endpoint was percentage change in body weight from baseline at week 0 to the end of treatment at week 44. The posted group means were −12.2% for semaglutide and −2.2% for placebo. The sponsor-reported ANCOVA treatment difference was −9.87, with a 95% confidence interval from −11.78 to −7.96 and p < 0.001.

The registry also posts secondary outcome and safety summaries. Details of the original sample-size justification, missing-data handling, multiplicity procedures, and full ANCOVA specification are not reported in the registry record.