Research Study to Investigate How Well Semaglutide Tablets Taken Once Daily Work in East Asian People Who Are Overweight or Living With Obesity: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Research Study to Investigate How Well Semaglutide Tablets Taken Once Daily Work in East Asian People Who Are Overweight or Living With Obesity (NCT05132088), a randomized phase 3 study. The primary outcome is Percent Change From Baseline in Body Weight.

2. Clinical Question

3. Trial Design

This completed phase 3 study used randomized allocation, a parallel-group design, and quadruple masking, as recorded in the registry. Its stated enrollment was 201. The study compared oral semaglutide 50 mg once daily with oral semaglutide placebo once daily in East Asian participants with overweight or obesity. The registry record identifies Novo Nordisk A/S as the sponsor.

The study description says participants were assigned to a group at random by computer and took one tablet each morning for 68 weeks. Both groups also received discussions with study staff about healthy food choices, becoming more physically active, and what participants could do to lose weight. Thus the comparison concerns assignment to the study medicine or placebo in the context of those shared lifestyle discussions; it is not a comparison of tablets without any other study support.

The primary outcome was percent change in body weight from baseline to week 68. The analysis description uses the in-trial observation period, defined as the uninterrupted period from randomization at week 0 until the date of last contact with the study site. The Full Analysis Set comprised all randomized participants, while the number analyzed for this outcome was the number with available outcome data. The posted outcome counts were 127 in the semaglutide group and 64 in the placebo group.

The study description mentions 14 clinic visits, 7 phone calls, and blood samples at 12 visits. It also describes pregnancy-related restrictions and urine pregnancy testing for women able to become pregnant. Further protocol details, including eligibility criteria beyond the broad population description, are not reported in the registry record. The registry record also does not report the original sample-size justification or the study’s planned interim analyses.

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 50 milligram (mg) oral semaglutide or semaglutide matching placebo once weekly. The trial had a 68-week treatment period (16 weeks of dose escalation period and 52 weeks of maintenance period) followed by a 7-week follow-up period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set (FAS) comprised 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 Percent Change From Baseline in Body Weight, measured over Baseline (week 0), week 68.

The primary endpoint is percent change in body weight from baseline, at week 0, to week 68. It expresses the change relative to each participant’s starting body weight, rather than reporting an absolute change in kilograms. The registry describes the outcome as a mean with standard deviation and specifies that the estimate uses data from the in-trial observation period, which runs from randomization to the last contact with the study site.

Body weight is a continuous measure: each participant can have a value along a scale rather than only being classified into a yes-or-no category. A group mean gives a concise description of the average change, while the standard deviation describes how spread out individual changes were around that average. Comparing the group means therefore addresses the average difference between randomized groups, but does not by itself describe every participant’s experience.

The endpoint is useful for this study because the stated research question concerns change in body weight during treatment. The registry also lists secondary outcomes that capture other aspects of weight change and its impact, but those do not replace the primary endpoint. The primary endpoint description identifies the analysis population as the Full Analysis Set, comprised of all randomized participants, and clarifies that only participants with available data for this outcome contributed to its reported analysis. The registry record does not report additional details about how missing week 68 measurements were handled.

7. Results Posted in the Registry

• Oral Semaglutide 50 mg: mean -14.90 versus -1.50 on control; difference -13.40 (95% CI -15.46 to -11.34), standardized effect d = -1.62; 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 From Baseline in Impact of Weight on Quality of Life-Lite for Clinical Trials (IWQOL-Lite for CT) - Physical Function Domain (5-items) Score

• 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:
  • Oral Semaglutide 50 mg: mean 7.60 versus 1.90 on control; difference 5.70 (95% CI 0.64 to 10.76), standardized effect d = 0.31; z-test p = 0.027.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Oral Semaglutide 50 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in Body Mass Index (BMI)

• 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:
  • Oral Semaglutide 50 mg: mean -4.89 versus -0.47 on control; difference -4.42 (95% CI -5.11 to -3.73), standardized effect d = -1.59; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Oral Semaglutide 50 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in Waist Circumference Measured According to the JASSO (Japan Society for the Study of Obesity) Guideline

• 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:
  • Oral Semaglutide 50 mg: mean -11.20 versus -1.40 on control; difference -9.80 (95% CI -11.59 to -8.01), standardized effect d = -1.37; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Oral Semaglutide 50 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary outcomes cover several related dimensions: body-weight reduction thresholds, body mass index, waist circumference, visceral fat area in a subset of the Japanese study population, and a physical-function domain of a weight-related quality-of-life measure. This range offers different views of weight change and its potential correlates, rather than simply repeating the primary continuous body-weight endpoint.

Across the continuous secondary outcomes with posted group summaries, the mean changes generally point in the same direction as the primary comparison: the semaglutide group means are more negative for body mass index and waist circumference, while its mean change in the physical-function score is higher. The listed categorical weight-reduction thresholds and visceral fat outcomes are additional measures, but this narrative does not infer their numerical findings from outcome titles alone. Their detailed results should be read on their own scales and with attention to the available data for each measure.

These outcomes relate to the primary result by examining other measures of body size, weight-related function, or the proportion crossing specified weight-change cutoffs. They are not independent confirmations simply because they are distinct endpoints. Outcomes can be correlated, and multiple statistical tests create more opportunities for apparently notable results to occur by chance.

The recalculated secondary comparisons are unadjusted, and the registry record does not report a multiplicity adjustment or a hierarchy of secondary hypotheses. For that reason, unadjusted secondary p-values carry less weight than a prespecified primary analysis: they are best treated as supporting or exploratory evidence rather than definitive standalone findings. The overall pattern can add context, but it does not change the definition or interpretation of the primary endpoint. Further details on secondary endpoint missingness and analysis populations are not reported in the registry record.

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

• Number of Participants Who Achieved Body Weight Reduction Greater Than or Equal (>=) to 10% (Yes/No)
• Change From Baseline in Impact of Weight on Quality of Life-Lite for Clinical Trials (IWQOL-Lite for CT) - Physical Function Domain (5-items) Score
• Number of Participants Who Achieved Body Weight Reduction Greater Than or Equal (>=) to 15% (Yes/No)
• Number of Participants Who Achieved Body Weight Reduction Greater Than or Equal (>=) to 20% (Yes/No)
• Change From Baseline in Body Mass Index (BMI)
• Change From Baseline in Waist Circumference Measured According to the JASSO (Japan Society for the Study of Obesity) Guideline
• Change From Baseline in Visceral Fat Area (VFA) Measured by CT Scan in a Subset of the Japanese Study Population (%)
• Change From Baseline in Visceral Fat Area (VFA) Measured by CT Scan in a Subset of the Japanese Study Population (Centimeter Square [cm^2])

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, so the posted group summaries use means and standard deviations. The mean is the arithmetic average of the outcome values among participants with available data. The standard deviation describes the dispersion of those values around the mean; it is not the uncertainty in the mean itself. The primary outcome counts were 127 for oral semaglutide 50 mg and 64 for placebo. Their reported mean changes were -14.9 and -1.5, with standard deviations of 9.5 and 5.0, respectively.

What does the unadjusted comparison represent?

The recalculated comparison subtracts the placebo mean from the semaglutide mean. Its estimate of -13.4 is therefore an unadjusted difference in average percent change, expressed in percentage points. Because the outcome values are changes from baseline, a negative group mean represents a decrease relative to baseline. The difference is negative because the semaglutide group mean was more negative than the placebo group mean. This straightforward calculation does not adjust for baseline characteristics or other covariates.

A standard error describes the estimated sampling uncertainty of an estimate. In general, a standard error tends to be smaller when the estimate is based on more observations or when individual measurements are less variable. It is used to construct a confidence interval and test a null hypothesis. It is not a description of the spread of participant-level outcomes; that role belongs to the standard deviation.

What is a confidence interval?

In general, a confidence interval is a range produced by a statistical procedure that, under its assumptions, has a specified long-run coverage rate for the quantity being estimated. The reported recalculated interval for the primary difference is -15.46 to -11.34 at the 95% confidence level. The sponsor’s adjusted ANCOVA interval is -15.61 to -10.52, also at the 95% level. The endpoints and widths depend on the analysis method and its assumptions. A confidence interval is not a guarantee that the true effect lies within that particular interval, and it does not describe the range of individual participant outcomes.

Why can adjusted and unadjusted results differ?

The registry reports an ANCOVA treatment difference of -13.07. ANCOVA is a general analysis-of-covariance approach that estimates a group difference while accounting for selected covariates in a model. In general, covariate adjustment can change the estimate and its precision compared with a simple comparison of group means. The registry does not report the covariates or full model specification, so the exact reasons for the difference between -13.07 and the recalculated -13.4 are not reported in the registry record. Since the discrepancy indicator is false, there is no flagged conflict requiring the sponsor result to take precedence; both estimates should be described according to their distinct methods.

What does a p-value convey?

In general, a p-value measures how surprising data at least as incompatible with a specified null hypothesis would be if that hypothesis and the statistical model were correct. The recalculated unadjusted result has p < 0.001, while the sponsor’s reported ANCOVA result has p < 0.001. These values are not the probability that the null hypothesis is true, nor do they measure the size or practical importance of the difference. Interpretation should consider the estimated difference, its confidence interval, the design, and the analysis population rather than relying on a threshold alone.

Why can over-dispersion matter?

General statistical note: over-dispersion arises when the variability in data is greater than a model assumes. If a model underestimates variability, standard errors may be too small and confidence intervals too narrow. This issue is especially relevant to count or binary outcomes analyzed with models that make specific variance assumptions. The primary endpoint is reported as a continuous measure with means and standard deviations; the registry does not report an over-dispersion assessment or a model for the primary endpoint beyond identifying the sponsor analysis as ANCOVA. The general concept is not evidence that over-dispersion occurred in this trial.

The posted outcome description uses the Full Analysis Set, defined as all randomized participants, and states that the analyzed number is the number with available data for the outcome. General statistical practice distinguishes the population definition from the observed records available for a particular endpoint. The registry record does not report the detailed missing-data procedure, assumptions about missingness, or sensitivity analyses. Without those details, it is not possible to judge whether the reported estimates would be robust to different ways of handling unavailable measurements.

11. Confidence Intervals and Precision

The recalculated unadjusted mean difference for the primary endpoint is -13.4, with a 95% confidence interval from -15.46 to -11.34. The interval indicates that the data are compatible with a range of negative differences under the unadjusted method and its assumptions. Its limits are relatively close to one another compared with the scale of the estimate, so the estimate is more informative than a direction-only statement. The interval does not mean that individual participant changes were confined to those values.

The sponsor’s adjusted ANCOVA estimate is -13.07, with a 95% confidence interval from -15.61 to -10.52. This interval also lies below zero. It is an interval for the adjusted treatment difference, not for either group’s mean on its own. Because the analyses differ, their confidence intervals should be read separately rather than combined or treated as duplicate results.

Precision depends on factors such as the amount of observed data and variation in the outcome. In general, larger samples and less variability can yield narrower intervals, though the exact result also depends on the analysis. The primary outcome analysis included 127 participants in the semaglutide group and 64 in the placebo group, and the group standard deviations were 9.5 and 5.0. The registry does not report the full reasons for the difference between randomized enrollment and the outcome-specific analysis counts.

A confidence interval addresses sampling uncertainty under a model; it does not account for every possible source of uncertainty. It cannot by itself resolve concerns about missing data, outcome measurement, generalizability, or the choice of analysis. Those issues depend on design and reporting details that are not all reported in the registry record.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size figures are planning illustrations based on the observed effect, not the trial’s original design assumptions. The registry record does not report the original sample-size justification. The calculations use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They show participants per arm for 80% power and participants per arm for 90% power, using the stated proportion of the observed effect as the effect to detect. These are participant counts per arm, not total event counts.

In general, power is the probability that a statistical test will reject its null hypothesis under a specified effect and analysis setup. The 80% power column gives the estimated number of participants per arm for a design with an 80% chance of detecting the specified effect under those assumptions. The 90% power column gives the corresponding number per arm for a 90% chance. Higher target power usually requires a larger planned sample when other assumptions are held fixed.

The primary endpoint illustrations use effects set at 100%, 75%, and 50% of the observed difference. For 100% of the observed effect, the figures are 6 participants per arm for 80% power and 9 for 90% power. For 75% of the observed effect, they are 11 and 15. For 50% of the observed effect, they are 24 and 33. Smaller effects need more participants because they are harder to distinguish from random variation under the stated assumptions.

These figures are not observed power and do not establish what the trial was originally designed to detect. They are conditional illustrations that depend on the observed effect and the calculation assumptions. In particular, the normal approximation and equal allocation assumptions may not reproduce the original design process, which is not reported 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 = -13.400; pooled standard deviation σ = 8.276.
2. n = 2 × (1.96 + 0.842)² × 8.276² / -13.400² = 6.0, rounded up to 6 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -13.4                      # observed difference in means
sigma <- 8.27647267862342                     # 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(5132088)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 6 (80% power), 9 (90% power)
 75% of observed effect: n per arm = 11 (80% power), 15 (90% power)
 50% of observed effect: n per arm = 24 (80% power), 33 (90% power)
power.t.test: 7.1 
Simulated power at n = 6 per arm: 0.718 (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 own primary analysis as an ANCOVA treatment difference of -13.07, with a 95% confidence interval from -15.61 to -10.52 and p < 0.001. The recalculated unadjusted difference from the posted group means is -13.4, with a 95% confidence interval from -15.46 to -11.34 and p < 0.001. Both estimates are negative, but they come from different methods and should not be presented as if they were the same calculation.

The sponsor’s estimate is adjusted using ANCOVA; the recalculation is a simple comparison of the posted means and standard deviations. In general, adjustment for covariates can affect an estimated difference and its uncertainty. The registry record does not report which covariates were included, the full model specification, or other details needed to reconstruct the sponsor’s result. Therefore, the numerical difference between the estimates cannot be attributed to a particular modeling choice based on the registry record alone.

The recalculation is useful as a transparent check on the group summaries, while the sponsor’s analysis is the result reported by the trial sponsor. The registry does not flag a discrepancy between the analyses. Neither estimate should be substituted for the other: each needs to be interpreted with its own method and confidence interval. The sponsor’s adjusted result is the trial’s reported analysis; the unadjusted calculation is supplementary context, not a replacement for it.

15. Multiplicity, Missing Data and Analysis Populations

The record identifies a primary endpoint and lists multiple secondary outcomes, but the statistical plan for controlling the chance of false-positive findings across multiple tests is not reported in the registry record. Multiplicity arises when many hypotheses are tested: even if none of the underlying effects were present, testing many outcomes can increase the chance that at least one result appears statistically notable by chance. General approaches include adjusting significance thresholds, setting a test hierarchy, or clearly treating secondary analyses as exploratory. The registry does not state which approach, if any, was planned for this study.

The primary endpoint has a reported sponsor ANCOVA analysis and a separately recalculated unadjusted comparison. The available information does not establish how the sponsor’s primary test fit into any broader testing strategy, or whether secondary outcomes were ordered or adjusted. The unadjusted secondary comparisons therefore need cautious interpretation. Their p-values, where calculated, do not account for the number of outcomes considered unless an adjustment is explicitly reported.

The primary outcome population is described as the Full Analysis Set, comprising all randomized participants, with the number analyzed defined as participants with available data for the endpoint. This distinction matters because endpoint data can be unavailable for some randomized participants. The registry record does not report how missing primary outcome measurements were handled, whether imputation was used, what assumptions were made about why data were missing, or whether sensitivity analyses examined alternatives.

General statistical note: missing-data methods rely on assumptions about the relationship between observed data and unavailable outcomes. Different plausible assumptions can lead to different estimates. Reporting the number analyzed is useful, but it is not enough by itself to establish that missingness could not affect the result. Similarly, the record does not report the missing-data approach for the secondary outcomes or detailed endpoint-specific population counts beyond those posted for the outcomes.

The registry also does not report interim analyses, stopping rules, or the original sample-size justification. These details should not be inferred from the final results or from the planning illustrations. Their absence limits what can be concluded about the study’s prespecified statistical procedures.

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: appendicitis (1.5%), atrial fibrillation (1.5%), carpal tunnel syndrome (1.5%), cataract (1.5%), hepatic enzyme increased (1.5%).

The registry lists serious adverse events among 134 participants at risk in the oral semaglutide 50 mg group and 66 participants at risk in the placebo group. It reports 8 participants with serious adverse events in the semaglutide group and 6 in the placebo group. It also lists other adverse events among 134 and 66 participants at risk, with 106 and 47 participants affected, respectively. No deaths were reported in either group.

These figures describe the reported counts during the study; they do not by themselves establish why an event occurred or whether it was caused by the assigned treatment. The numbers at risk differ from the primary outcome analysis counts, and the adverse-event figures should be read using their own denominators rather than substituted for the outcome populations.

The registry lists several serious-event terms at 1.5% each: appendicitis, atrial fibrillation, carpal tunnel syndrome, cataract, hepatic enzyme increased, and myofascial pain syndrome. These entries are event categories reported in the record; they do not provide a full account of event timing, severity beyond the serious-event classification, or individual clinical circumstances. The registry record does not report further detail in the safety summary. Group counts alone are descriptive and are not a basis for individual medical decisions.

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

The primary result describes an average difference in percent change in body weight from baseline to week 68 between randomized groups. In the posted data, the semaglutide group had a mean change of -14.9 and the placebo group had a mean change of -1.5. The recalculated unadjusted difference is -13.4 percentage points, while the sponsor’s adjusted ANCOVA analysis reports -13.07. These statistics describe group-level outcomes during the in-trial observation period.

The estimates do not imply that each participant had the same change as the group mean. Standard deviations indicate that participant outcomes varied, and the group summaries cannot convey every individual trajectory. The analyses also concern participants with available outcome data, rather than necessarily every randomized participant for whom a week 68 measurement might have been expected. The registry record does not report the detailed method used for missing measurements.

The findings are specific to the studied population, comparison, and observation period: East Asian participants with overweight or obesity assigned to oral semaglutide 50 mg once daily or placebo, with study staff discussions about food choices and physical activity, and an outcome assessed through week 68. They do not by themselves establish how the results apply to other populations, different doses, other treatment settings, or longer periods. Those questions are not answered by this comparison.

A statistical result is not a treatment recommendation. The confidence intervals describe uncertainty around group differences under the analyses used; they do not prove an effect for any individual or resolve every source of uncertainty. Likewise, a small p-value does not measure the importance of a change for an individual. The safety counts are descriptive and should be interpreted separately from the primary weight outcome.

Overall, the registry supports describing a negative average between-group difference in the primary outcome, with confidence intervals that do not cross zero in either reported analysis. Broader conclusions require attention to the trial’s design, analysis assumptions, missing-data reporting, secondary-outcome multiplicity, and the limits of applying one study’s findings beyond its stated setting.

18. Why This Trial Matters Statistically

This trial illustrates why the distinction between an outcome’s scale and its statistical contrast matters. The primary measure is percent change from baseline, while the reported treatment comparison is a difference between group means. A negative mean in each group describes a decrease from baseline; the between-group estimate addresses how those average changes differ. Keeping those quantities separate avoids interpreting a group’s change as if it were itself the treatment contrast.

It also illustrates the value of reading adjusted and unadjusted estimates together without conflating them. The sponsor’s ANCOVA treatment difference and the simple recalculation are close in direction and scale, but they are not the same analysis. The adjusted estimate is the sponsor-reported result, while the recalculation makes explicit how the posted means compare. Knowing that the methods differ—and that key model details are not reported—helps readers avoid attributing differences to unexplained causes.

Precision is another central statistical issue. Confidence intervals communicate a range of estimates compatible with the analysis, rather than offering only a binary conclusion from a significance test. The primary intervals remain on the negative side of zero, while their numerical limits still reflect uncertainty. This supports a more informative reading than a p-value alone.

The study also shows why outcome availability, multiplicity, and design assumptions matter. The Full Analysis Set is defined broadly, but the primary analysis counts include participants with available data. The handling of missing outcomes and control of multiple secondary tests are not reported in the registry record. Finally, sample-size illustrations based on an observed effect cannot be mistaken for original design planning or observed power. Together, these distinctions help readers interpret the posted evidence in context rather than treating one estimate as a complete account of the trial.

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 enough detail to reconstruct the sponsor’s ANCOVA model. In particular, the covariates and full model specification are not reported in the registry record. This limits interpretation of why the adjusted estimate differs from the unadjusted recalculation, even though both estimates are negative and have confidence intervals below zero.

The primary analysis uses available outcome data, with 127 participants in the semaglutide group and 64 in the placebo group. The registry record does not report the detailed reasons for outcome data being unavailable, how missing measurements were handled, or sensitivity analyses using alternative missing-data assumptions. The randomized enrollment was 201, but that overall figure does not replace the endpoint-specific analysis counts.

The record lists a range of secondary outcomes, but does not report a multiplicity-control procedure or a testing hierarchy. Secondary comparisons should therefore be interpreted cautiously, particularly when their results are unadjusted. For some outcomes, including visceral fat area, the registry describes measurement in a subset of the Japanese study population; findings from such a subset may not represent all participants in the trial.

The study description identifies an East Asian population, but the registry summary does not provide further detail in the primary outcome description about the population’s composition or eligibility criteria. Generalizability beyond the studied population and the 68-week treatment period cannot be determined from the reported comparison alone. The registry record also does not report the original sample-size justification or interim-analysis plan, so the planning illustrations should not be treated as evidence about the study’s original statistical design.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Research Study to Investigate How Well Semaglutide Tablets Taken Once Daily Work in East Asian People Who Are Overweight or Living With Obesity — NCT05132088.
• Registry record last updated 2026-08-14; status last verified 2026-08.
• Results first posted 2026-08-14.
• 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

NCT05132088 is a completed phase 3, randomized, quadruple-masked, parallel-group study sponsored by Novo Nordisk A/S, with enrollment of 201. It compared oral semaglutide 50 mg once daily with oral semaglutide placebo once daily in East Asian participants with overweight or obesity. The study description includes shared discussions with study staff about food choices and physical activity.

The primary outcome was percent change in body weight from baseline at week 0 to week 68, using the in-trial observation period. The posted means were -14.9 for semaglutide and -1.5 for placebo. The recalculated unadjusted mean difference was -13.4, with a 95% confidence interval from -15.46 to -11.34; the sponsor’s ANCOVA result was -13.07, with a 95% confidence interval from -15.61 to -10.52.

The registry also posts secondary outcomes and descriptive safety counts. Important details—including missing-data methods, multiplicity procedures, full adjusted-model specifications, and the original sample-size justification—are not reported in the registry record.