A Research Study to Compare a New Medicine Oral Semaglutide to a Dummy Medicine in Children and Teenagers With Type 2 Diabetes: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Research Study to Compare a New Medicine Oral Semaglutide to a Dummy Medicine in Children and Teenagers With Type 2 Diabetes (NCT04596631), a randomized phase 3 study. The primary outcome is Change From Baseline (Week 0) to Week 26 in Glycosylated Haemoglobin (HbA1c)- Percentage Point.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group, Phase 3 study sponsored by Novo Nordisk A/S. The registry lists the study as completed and records enrollment of 132. The study began on 2020-11-02, and the primary completion date was 2025-04-29. Participants were assigned by chance to oral semaglutide or placebo, with both groups continuing background treatment with metformin, basal insulin, or both, alongside diet and exercise.

The registry identifies quadruple masking. Masking is intended to limit the influence of treatment knowledge on participants’ experiences, clinical decisions, and outcome assessment. The precise identities of every masked role are not reported in the registry record. The parallel design means participants were assigned to one study group rather than crossing between the study treatments.

The study description says participants took a tablet each morning on an empty stomach and waited 30 minutes before eating, drinking, or taking another oral medication. The planned study duration is described as about 1 year and 3 months, or 66 weeks. The registry summary describes 12 clinic visits and 8 phone calls with the study doctor, with blood samples at clinic visits and questions asked of participants.

The primary outcome was change from baseline, defined as Week 0, to Week 26 in HbA1c percentage points. Secondary outcomes include glucose, body mass index, body weight, waist circumference, and HbA1c at later follow-up, including Week 52. The registry lists 51 outcome measures and 2 analyses. Details such as the original sample-size justification, the intended handling of treatment discontinuation, and the full statistical analysis plan 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: A total of 132 eligible participants were randomized (1:1) to treatment with oral semaglutide or placebo. The study included a treatment period (up to 52 weeks) and a follow-up period (12 weeks).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: FAS included all randomized participants. Overall number of participants analyzed = Participants with available data for the 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: Baseline analysis was performed on FAS that included all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline (Week 0) to Week 26 in Glycosylated Haemoglobin (HbA1c)- Percentage Point, measured over Baseline (Week 0), Week 26.

The primary endpoint measures the change in HbA1c from baseline at Week 0 to Week 26, expressed in percentage points. HbA1c is a continuous measure of glycemic control: a change summarizes how the measure moved over the specified period. The posted group summaries are mean changes, accompanied by standard deviations. A negative mean change indicates that the measured HbA1c value decreased from baseline on average within that group.

Comparing change between randomized groups addresses whether the average change differed between those assigned oral semaglutide and those assigned placebo, while both groups received background treatment. The reported endpoint is not simply a measurement at Week 26; it is a change relative to each participant’s baseline measurement. This can make the comparison informative about the course of the measure during follow-up, though the registry record does not report all details of how baseline values and missing follow-up observations were handled in the sponsor’s analysis.

HbA1c is used in diabetes studies because it provides a measure of glycemic status over time, rather than representing only a momentary glucose reading. A between-group difference in its change is therefore a way to compare average glycemic change during the study period. The endpoint alone does not describe every aspect of diabetes, participant experience, or safety, and its interpretation depends on the analysis method and the precision of the estimate.

7. Results Posted in the Registry

• Oral Semaglutide: mean -1.00 versus -0.30 on control; difference -0.70 (95% CI -1.19 to -0.21), standardized effect d = -0.50; z-test p = 0.005.

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 (Week 0) in Fasting Plasma Glucose (FPG) to Week 26

• 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: mean -28.20 versus -8.10 on control; difference -20.10 (95% CI -40.28 to 0.08), standardized effect d = -0.35; z-test p = 0.051.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Oral Semaglutide and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline (Week 0) in Body Mass Index (BMI) Standard Deviation Score (SDS) to Week 26

• 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: mean -0.10 versus -0.10 on control; difference 0.00 (95% CI -0.10 to 0.10), standardized effect d = 0.00; z-test p = 1.000.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Oral Semaglutide and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in HbA1c at Week 52 (Percentage Point)

• 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: mean -0.80 versus 0.20 on control; difference -1.00 (95% CI -1.49 to -0.51), standardized effect d = -0.71; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Oral Semaglutide than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes extend the primary HbA1c comparison to other measures and follow-up times. They include fasting plasma glucose and body mass index standard deviation score at Week 26, HbA1c and fasting plasma glucose at Week 52, and changes in body weight and waist circumference at Week 26 and Week 52. The registry lists 49 secondary outcomes as posted, so the available secondary findings form a broad set rather than a single confirmatory comparison.

Across the posted continuous results described in the recalculations, the pattern is not uniform. The Week 26 fasting plasma glucose estimate is negative, with a confidence interval that reaches across zero; the Week 26 BMI standard deviation score estimate is 0.0, with an interval spanning negative and positive values. At Week 52, the posted HbA1c recalculation is negative and its interval excludes zero. These results provide context about other measures and time points, but they do not replace the primary Week 26 HbA1c analysis or establish a single overall effect across all outcomes.

Secondary results usually carry less weight when many outcomes are examined, particularly when no multiplicity adjustment or hierarchy is documented. Testing many outcomes increases the chance that some comparisons appear statistically notable by chance. The registry record does not report the multiplicity strategy for these outcomes, so individual unadjusted p-values should be treated as exploratory rather than interpreted as independent confirmatory evidence. The record also does not provide sponsor analyses for the secondary comparisons described by the recalculations.

Secondary outcomes can still be informative: they can show whether the primary pattern is accompanied by changes in related measures and whether observations at a later follow-up are consistent with earlier ones. Their interpretation depends on outcome definitions, data availability, analysis methods, and multiplicity handling. The breadth of posted outcomes means that isolated results should be considered within the full set, while avoiding claims that the registry record does not support.

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

• Change From Baseline (Week 0) in Fasting Plasma Glucose (FPG) to Week 26
• Change From Baseline (Week 0) in Body Mass Index (BMI) Standard Deviation Score (SDS) to Week 26
• Change From Baseline in HbA1c at Week 52 (Percentage Point)
• Change From Baseline in HbA1c at Week 52 (mmol/Mol)
• Change From Baseline in Fasting Plasma Glucose at Week 52 (mg/dL)
• Change From Baseline in Body Weight to Week 26 and Week 52 (Kilograms [kg])
• Relative Change From Baseline in Body Weight to Week 26 and Week 52
• Change From Baseline in Waist Circumference to Week 26 and Week 52

9. Statistical Interpretation

10. Statistical Methods Explained

For a continuous endpoint such as HbA1c change, the mean summarizes the average observed change in a group. The standard deviation describes how dispersed participant-level changes are around that group mean. It is not the standard error and is not itself a confidence interval. A group can have a noticeable standard deviation while its average is estimated with more precision, because the uncertainty in a mean also depends on the number of observations and the analysis assumptions.

What does the unadjusted recalculation represent?

The simple recalculation compares the posted group means directly. For the primary endpoint, it gives a mean difference of -0.7 percentage points and a 95% confidence interval from -1.185 to -0.214. This calculation is unadjusted: it does not incorporate covariate adjustment from the sponsor’s model. It is useful as a transparent check based on the posted summary statistics, but it is not a substitute for the sponsor’s prespecified or otherwise official analysis. Because the record flags a discrepancy, the sponsor’s own analysis takes precedence.

In general, an unadjusted comparison and an ANCOVA estimate can differ because they use information differently. ANCOVA is a regression-based method that can adjust for baseline measurements and other included covariates. Adjustment may improve precision or account for chance imbalances, depending on the analysis and data. The specific covariates, model specification, and missing-data procedures for this trial are not reported in the registry record, so a more detailed explanation of the difference between the estimates cannot be established from the posted information.

How should the confidence interval and p-value be read?

A confidence interval gives a range of values compatible with the observed data under the method’s assumptions. It conveys uncertainty in the estimated treatment difference rather than the distribution of individual participant outcomes. In general, a narrower interval indicates greater precision, while a wider interval leaves more uncertainty about the size of the difference. A p-value measures how incompatible the data are with a specified null hypothesis under a statistical model; it is not the probability that the null hypothesis is true, nor does it measure clinical importance.

The sponsor reports an ANCOVA treatment difference of -0.83, a 95% confidence interval from -1.25 to -0.40, and p < 0.001. The recalculated unadjusted result is also posted, but it should not displace the sponsor’s result. A statistical finding does not establish that all participants experienced the group average change, and neither the confidence interval nor the p-value describes every dimension of benefit or harm.

What do the standardized effect and planning illustrations mean?

The recalculation includes a standardized effect, d = -0.498, based on the mean difference relative to a pooled standard deviation. Standardization expresses the observed difference relative to the endpoint’s variability, which can help describe magnitude on a scale independent of the original measurement units. It should not be treated as a direct clinical threshold, and it does not replace interpretation of the difference in percentage points.

The planning figures use the observed effect as a starting point and show illustrations for detecting stated fractions of that effect. They are not the trial’s original design calculations. The original sample-size justification and design assumptions are not reported in the registry record. Planning calculations based on an observed effect are sensitive to that estimate and should be understood as hypothetical future-study illustrations, not as evidence about the adequacy of the completed trial.

What is the role of randomization and masking?

In general, random assignment is intended to make comparison groups similar on average in factors that are measured and unmeasured, reducing systematic selection differences. It does not ensure exact balance in every characteristic, especially in a finite study. Masking can reduce the possibility that knowledge of assignment influences behavior, care, reporting, or assessment. The registry identifies randomized allocation and quadruple masking, but does not report every operational detail of assignment concealment or which roles correspond to the masking designation.

The registry describes the primary population as the full analysis set, including all randomized participants, while noting that the number analyzed for this measure is the number with available data. This distinction matters: a population definition can include all randomized participants, yet an endpoint-specific analysis may use only those with an observed outcome, depending on the approach. The exact analysis population and missing-data handling used in the sponsor’s ANCOVA are not reported in the registry record.

11. Confidence Intervals and Precision

The sponsor’s ANCOVA estimate is -0.83 percentage points, with a 95% confidence interval from -1.25 to -0.40. This interval conveys uncertainty about the estimated average treatment difference under the reported analysis. Its values are below zero, consistent with a greater mean decrease in the semaglutide group according to the direction used for the treatment difference. The interval does not mean that 95% of individual participants had changes within those limits.

The unadjusted recalculation gives a difference of -0.7 percentage points, with a 95% confidence interval from -1.185 to -0.214. Its bounds also exclude zero, but the calculation is not the sponsor’s ANCOVA analysis. The estimates and intervals should therefore be distinguished rather than combined or treated as interchangeable. Since the record flags a discrepancy, interpretation should prioritize the sponsor’s reported analysis.

In general, confidence intervals help assess both direction and precision. They show a range of estimates compatible with the data and model, but do not account for every possible source of uncertainty, such as limitations in outcome measurement, missing-data assumptions, or analyses not reported in the registry record. The interval’s exclusion of zero is not a measure of clinical importance; that judgment would require context not established by the endpoint estimate alone.

The group standard deviations, 1.5 for semaglutide and 1.3 for placebo, describe variation in individual changes. They do not imply that every participant followed the average pattern. The analysis counts are 66 for semaglutide and 62 for placebo, with the registry defining the analyzed number as participants with available outcome data. The record does not report the extent or reasons for unavailable measurements, so the precision interval should be read alongside this limitation.

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 for this continuous endpoint are participants per arm, not a total across both arms and not total events. They use a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is expressed as a stated fraction of the observed effect. For the primary endpoint, planning for 100% of the observed effect gives 64 participants per arm for 80% power and 85 participants per arm for 90% power. Planning for 75% of the observed effect gives 113 participants per arm for 80% power and 151 participants per arm for 90% power. Planning for 50% of the observed effect gives 254 participants per arm for 80% power and 340 participants per arm for 90% power.

In plain terms, 80% power means that, if the assumed effect and statistical assumptions were correct, a study of the stated size would have an 80% chance of producing a statistically significant result under the planning model. The 90% column describes the corresponding chance under that model for a study designed to have 90% power. These are prospective planning concepts, not probabilities that the observed result is correct. Smaller target effects require more participants because a smaller difference is harder to distinguish from random variation.

These figures are illustrations calculated from the observed effect, rather than the trial’s original design assumptions, which are not reported in the registry record. This is not observed power. The trial’s actual enrollment and analyzed group counts should not be judged by comparing them mechanically with these hypothetical calculations: the calculations depend on assumed effect size, allocation, significance level, and approximation, and they do not document the original protocol rationale.

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 = -0.700; pooled standard deviation σ = 1.407.
2. n = 2 × (1.96 + 0.842)² × 1.407² / -0.700² = 63.4, rounded up to 64 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 <- -0.7                      # observed difference in means
sigma <- 1.40672985640061                     # 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(4596631)
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 = 64 (80% power), 85 (90% power)
 75% of observed effect: n per arm = 113 (80% power), 151 (90% power)
 50% of observed effect: n per arm = 254 (80% power), 340 (90% power)
power.t.test: 64.4 
Simulated power at n = 64 per arm: 0.797 (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 ANCOVA, with a treatment difference of -0.83 percentage points, a 95% confidence interval from -1.25 to -0.40, and p < 0.001. This is the official reported analysis for the primary comparison and takes precedence over the unadjusted recalculation from posted group means and standard deviations.

The recalculation estimates a difference of -0.7 percentage points, with a 95% confidence interval from -1.185 to -0.214 and p = 0.005. Its purpose is to provide a straightforward comparison based on the group summaries. It does not reproduce ANCOVA and does not incorporate the sponsor model’s adjustment. The difference between the estimates may reflect differences in adjustment or analysis details, but the registry record does not report enough information to determine the specific reason.

Both estimates point in the same direction, but they are distinct analyses and should not be pooled or presented as if one confirms the exact numeric value of the other. The registry flags a discrepancy; accordingly, the sponsor’s reported analysis is the result to prioritize when describing the trial’s primary statistical finding. The recalculation remains an unadjusted check, not a replacement for the sponsor’s method.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when statistical tests are conducted for multiple outcomes, time points, or comparisons. Even if each test uses a conventional threshold, examining many tests can increase the chance of at least one apparently notable result arising by chance. Common approaches include defining one primary endpoint, prespecifying an order for secondary tests, or adjusting significance criteria. Which approach was planned and used for this study is not reported in the registry record. The primary result should therefore be distinguished from the broader collection of secondary findings, and unadjusted secondary results should be interpreted cautiously.

The registry identifies the full analysis set as including all randomized participants and states that the number analyzed for an outcome is the number with available data. It does not report the number missing for each endpoint, reasons for missingness, or whether missingness differed between groups. It also does not report the method used to handle missing outcome data in the sponsor’s analysis, assumptions about missingness, or sensitivity analyses. These details matter because an analysis limited to available observations can be affected if missingness is related to treatment assignment, outcome values, or participant characteristics.

The registry record does not report whether interim analyses were planned or conducted, how the original sample size was justified, or the full statistical analysis plan. Those omissions limit assessment of whether analysis choices were prespecified and how they relate to the reported results. They do not, by themselves, establish that an analysis was inappropriate; they identify information that cannot be evaluated from the registry record.

In general, a complete interpretation considers the outcome hierarchy, analysis population, missing-data strategy, and multiplicity plan together. For this study, the sponsor’s ANCOVA result is reported for the primary endpoint, but the registry does not expose sufficient methodological detail to independently reproduce it. The available information supports a description of the reported estimate and its uncertainty, while leaving those broader analysis questions unresolved.

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: aggression (1.5%), anaphylactic reaction (1.5%), arthritis (1.5%), cerebral venous sinus thrombosis (1.5%), diabetes mellitus inadequate control (1.5%).

The posted serious adverse event figures report 5 participants affected among 66 at risk in the oral semaglutide group and 2 among 66 at risk in the placebo group. Deaths are reported as 0 in each group. These are counts of participants with a serious adverse event, not counts of all events or a complete description of each participant’s clinical course. The listed serious event terms include Aggression, Anaphylactic reaction, Arthritis, Cerebral venous sinus thrombosis, Diabetes mellitus inadequate control, and Gastroenteritis, each shown as 1.5% in the registry data.

The registry also reports other adverse events affecting 45 participants in the semaglutide group and 40 in the placebo group, among 66 at risk in each group. Serious and other adverse events are different categories and should not be conflated. The posted counts do not establish that treatment caused an event, and they do not by themselves characterize event severity, duration, or relationship to study treatment.

Safety interpretation is limited by the information posted. Detailed event narratives, exposure-adjusted rates, and a complete assessment of causality are not reported in the registry record. Counts from this study describe events observed during the trial and should be read as descriptive findings rather than a complete estimate of risk in other populations or settings.

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

The primary result describes an average difference in change in HbA1c between the randomized groups over the specified follow-up. The sponsor’s ANCOVA estimate is -0.83 percentage points, with a 95% confidence interval from -1.25 to -0.40. The posted group means and the unadjusted recalculation also show a greater mean decrease in the oral semaglutide group, but the sponsor analysis takes precedence because the registry flags a discrepancy.

This statistical result does not mean that every participant had a decrease, or that individual responses matched the group average. Group means summarize the center of the observed changes, while standard deviations describe variability. The confidence interval characterizes uncertainty in the estimated group difference under the reported model; it does not describe the range of individual outcomes or guarantee the same result in another study.

The primary outcome is one measure of glycemic control and does not capture every aspect of health, daily life, or treatment burden. Nor does a statistically notable result alone establish that the magnitude is important to every participant. The registry record does not provide a clinical threshold for interpreting the size of the HbA1c difference, so clinical importance cannot be determined from statistical significance alone.

The comparison was made in children and adolescents with type 2 diabetes receiving background treatment with metformin, basal insulin, or both, alongside diet and exercise. Interpretation is specific to that study context. The study’s results do not establish what would happen in populations or treatment settings not described in the record, or beyond the recorded follow-up.

Finally, the registry’s posted data leave questions about missing outcomes, multiplicity, and analysis details unresolved. The results are therefore best understood as the reported randomized comparison with stated uncertainty, not as a complete account of all possible benefits, harms, or longer-term outcomes.

18. Why This Trial Matters Statistically

This trial illustrates why the analysis method matters when interpreting a randomized comparison. The posted group summaries support a transparent unadjusted recalculation, while the registry’s sponsor-reported primary result comes from ANCOVA. Those approaches answer related but not identical statistical questions, and their estimates are not interchangeable. Recognizing that distinction prevents a simple summary-statistic calculation from being mistaken for the trial’s own analysis.

The example also shows why effect estimates and confidence intervals are more informative than a p-value alone. The estimate describes the direction and size of the average difference in HbA1c change, while its interval communicates uncertainty. The standard deviations describe participant-level variation, a different quantity from uncertainty in the average. Keeping these concepts separate helps readers avoid treating a statistically significant result as proof of uniform individual response or clinical importance.

Planning illustrations based on an observed result offer another useful statistical lesson. Their required group sizes change when the target effect changes, so planning for a smaller effect entails more participants. But such illustrations are not the trial’s original design rationale and cannot be used as observed power. The original design assumptions are not reported in the registry record.

Finally, a primary endpoint sits within a wider collection of outcomes. Secondary findings may add context, but their interpretation depends on multiplicity, missing data, and prespecified analysis plans. The registry record leaves those details unreported. This trial therefore highlights the value of reading estimates in conjunction with their methods and limitations, rather than treating any single number as a complete account.

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 original sample-size justification or the assumptions used to plan the study. The available planning illustrations are based on the observed effect and do not document the trial’s design rationale. The full statistical analysis plan, including ANCOVA covariates and model specification, is also not reported, which limits independent reproduction of the sponsor’s primary result.

For the primary endpoint, the registry defines the full analysis set as including all randomized participants but says the number analyzed is the number with available outcome data. The extent, timing, and reasons for missing primary measurements are not reported. The missing-data method and sensitivity analyses are also not reported in the registry record, so the effect of unavailable outcomes on the estimates cannot be assessed from the posted information.

The registry lists many outcomes, but the multiplicity plan is not reported. This limits the strength of conclusions drawn from individual secondary findings, especially where their analyses are unadjusted. Sponsor-reported analyses are not listed for the secondary results described in the recalculations. The discrepancy between the simple primary recalculation and the sponsor’s ANCOVA estimate is flagged, but the record does not explain its source; the sponsor’s analysis takes precedence.

The safety figures are descriptive counts. The registry record does not provide detailed narratives, event duration, treatment relatedness, or exposure-adjusted analyses alongside these figures. Follow-up is described as 66 weeks, so longer-term outcomes are not established by the information posted. The results are also specific to the population and background-treatment context described in the registry, limiting generalization beyond that setting.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Research Study to Compare a New Medicine Oral Semaglutide to a Dummy Medicine in Children and Teenagers With Type 2 Diabetes — NCT04596631.
• Registry record last updated 2026-08-21; status last verified 2026-07.
• Results first posted 2026-08-21.
• 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

NCT04596631 is a completed randomized, quadruple-masked, parallel-group Phase 3 study sponsored by Novo Nordisk A/S. It compared once-daily oral semaglutide with placebo in children and adolescents with type 2 diabetes, alongside background treatment and diet and exercise. The registry records enrollment of 132 and a study duration of 66 weeks.

The primary endpoint was change from baseline to Week 26 in HbA1c percentage points. The sponsor reported an ANCOVA treatment difference of -0.83, with a 95% confidence interval from -1.25 to -0.40 and p < 0.001. The unadjusted recalculation differs; because the registry flags a discrepancy, the sponsor’s analysis takes precedence.

Secondary outcomes cover glucose, HbA1c, body mass index, body weight, and waist circumference. Serious adverse events affected 5 participants in the semaglutide group and 2 in the placebo group; deaths were reported as 0 in each group. Details on the original sample-size rationale, multiplicity, and missing-data methods are not reported in the registry record.