Semaglutide for Alcohol Use Disorder: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Semaglutide for Alcohol Use Disorder (NCT05520775), a randomized phase 2 study. The primary outcome is Change in Alcohol Consumed.

2. Clinical Question

3. Trial Design

This completed Phase II trial was registered as a randomized, triple-masked, parallel-group study. The registry lists an enrollment of 48 and the conditions alcohol use disorder and cigarette smoking. Its brief summary describes an early-Phase II human laboratory screening study using a randomized, placebo-controlled, dose-ranging design. The sponsor was the University of North Carolina, Chapel Hill. The registry lists the study start as 2022-09-02 and primary completion as 2024-04-12.

The active group received semaglutide by subcutaneous injection at escalating doses from .25mg to 1.0mg over 9 weeks. The comparator group received sham subcutaneous injections over 9 weeks. The registry identifies the design as parallel, meaning the posted comparison is between separate groups rather than a within-person crossover comparison. The registry record does not report further details about the allocation sequence, masking procedures, or how dose escalation was managed.

The primary endpoint compares change from baseline (Week 0) to post-medication (Week 8) in estimated grams of ethanol consumed. Its stated analysis population includes participants completing both pre- and post-treatment laboratory self-administration. The posted primary group summaries include 13 semaglutide participants and 12 sham/placebo participants. These outcome-specific numbers are not the same as the registry’s overall enrollment figure; the registry record does not explain the difference or report the reasons that some participants are absent from this endpoint analysis.

The registry lists 11 outcome measures and six secondary outcomes, including subjective alcohol effects, alcohol and cigarette demand, and daily use. The registry record does not report the original sample-size justification, a detailed statistical analysis plan, or interim analyses. No sponsor-reported analyses are listed for the posted secondary outcomes.

4. Participant Flow and Accounting

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

Overall Study

Analysis population for the primary outcome, as defined in the registry: Participants who completed pre- and post-treatment laboratory self-administration.

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Change in Alcohol Consumed, measured over Baseline (Week 0) to post-medication (Week 8).

The primary endpoint is change in estimated grams of ethanol consumed during laboratory self-administration, measured from baseline (Week 0) to post-medication (Week 8). It is a continuous outcome reported as a mean and standard deviation. The endpoint description identifies estimated ethanol consumption, while the analysis population is restricted to participants who completed pre- and post-treatment laboratory self-administration.

A change score describes how the measurement at the later assessment differs from the baseline measurement. A negative mean change indicates a decrease in the recorded measure over that interval; it does not, by itself, show why the measure changed or whether the change generalizes beyond the assessment setting. The posted means are -32.72 grams in the semaglutide group and -6.95 grams in the sham/placebo group.

In general, a laboratory self-administration endpoint offers a defined setting for measuring alcohol-related behavior under study conditions. It is distinct from a measure of daily alcohol use in ordinary life. The registry lists change in daily alcohol use separately as a secondary outcome. The record does not report how laboratory consumption was elicited or whether the endpoint was assessed at any other time.

The between-group estimate is the mean change in the semaglutide group minus the mean change in the sham/placebo group. The posted estimate is -25.77 grams. This contrast describes the observed group summaries in the endpoint population; it does not establish a mechanism or a result for every randomized participant.

7. Results Posted in the Registry

• Semaglutide: mean -32.72 versus -6.95 on control; difference -25.77 (95% CI -46.35 to -5.19), standardized effect d = -0.98; z-test p = 0.014.

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 Subjective Stimulation (Biphasic Alcohol Effects Scale)

• 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: mean 0.45 versus -1.28 on control; difference 1.73 (95% CI -6.49 to 9.95), standardized effect d = 0.13; z-test p = 0.680.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Semaglutide and the control. The interval gives the range of effects that remain compatible with the data.

Change in Subjective Sedation (Biphasic Alcohol Effects Scale)

• 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: mean 0.14 versus -3.22 on control; difference 3.36 (95% CI -2.41 to 9.13), standardized effect d = 0.35; z-test p = 0.253.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Semaglutide and the control. The interval gives the range of effects that remain compatible with the data.

Change in Alcohol Demand (Alcohol Purchase Task)

• 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: mean -2.91 versus -2.90 on control; difference -0.01 (95% CI -3.76 to 3.74), standardized effect d = -0.00; z-test p = 0.996.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Semaglutide and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes address related but distinct aspects of alcohol and cigarette use: subjective stimulation and sedation, alcohol demand, cigarette demand, and daily alcohol and cigarette use. The posted numerical comparisons cover subjective stimulation, subjective sedation, and alcohol demand. Their pattern is not uniformly aligned with the primary laboratory self-administration contrast: the secondary estimates include contrasts close to zero and intervals that span zero. These measures are not interchangeable with the primary endpoint, and differences in measurement and outcome-specific participant counts affect their interpretation.

The secondary findings therefore provide context rather than a direct replication of the primary result. The primary endpoint concerns estimated grams consumed in laboratory self-administration among completers; the secondary outcomes assess other experiences or behaviors, some in different settings. A result on one measure need not imply the same pattern for another. The registry record lists daily alcohol use and cigarette-related measures as outcomes, but does not provide posted numerical comparisons for all six secondary outcomes in the results represented in the record.

The secondary comparisons are unadjusted, and the registry record does not report a multiplicity correction, prespecified hierarchy, or sponsor-reported secondary analyses. In general, evaluating many outcomes increases the opportunity for chance findings. For that reason, individual unadjusted secondary p-values carry less weight than a result from a prespecified, appropriately analyzed primary endpoint, and the secondary results are best treated as exploratory descriptions. They neither independently establish the primary pattern nor erase it.

The differing numbers of participants contributing across outcomes also matter. The registry record does not explain why outcome-specific sample sizes vary or report how missing observations were handled. Readers should avoid interpreting the secondary results as if every measure used the same participants or had the same precision. Overall, the secondary outcomes broaden the measurement scope, but the incomplete set of posted analyses and absent multiplicity information limit conclusions across the family of outcomes.

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

• Change in Subjective Stimulation (Biphasic Alcohol Effects Scale)
• Change in Subjective Sedation (Biphasic Alcohol Effects Scale)
• Change in Alcohol Demand (Alcohol Purchase Task)
• Change in Cigarette Demand (Cigarette Purchase Task)
• Change in Daily Alcohol Use
• Change in Daily Cigarette Use

9. Statistical Interpretation

10. Statistical Methods Explained

What does a mean change represent?

The primary endpoint is continuous and summarized by a mean and standard deviation. A mean is the arithmetic average of participants’ change scores. A change score compares a participant’s later measurement with their baseline measurement; the group mean summarizes those individual changes. Here the reported interval is baseline (Week 0) to post-medication (Week 8), and the unit is grams of estimated ethanol consumed. In general, the standard deviation describes how dispersed participant measurements are around a group mean. It describes variability among observations, not the precision of the mean itself.

The primary group means are -32.72 grams for semaglutide and -6.95 grams for sham/placebo. The estimated contrast is -25.77 grams, defined as the semaglutide mean change minus the sham/placebo mean change. A negative contrast indicates a more negative average change in the semaglutide group. This is a summary of the posted outcome population, not a statement that each participant changed by that amount.

How should the mean difference be read?

A mean difference preserves the endpoint’s original units, which makes it interpretable on the scale of estimated grams consumed. It compares group averages rather than comparing the proportion of participants who crossed a threshold. The posted group standard deviations are 27.98 grams and 24.49 grams. The registry also gives a pooled standard deviation of 26.37 and a standardized effect size of -0.977 for the primary comparison. In general, a standardized effect expresses a mean contrast relative to a measure of variability; it has no units and should not be mistaken for the observed mean difference in grams.

The comparison statistics are recalculated from the posted summary statistics. They are not listed as a sponsor-reported analysis. The registry record does not report the statistical test, covariate adjustment, or model used in an original sponsor analysis, so none should be inferred from the recalculation. The comparison is an unadjusted summary-statistic contrast.

What does the confidence interval contribute?

In general, a confidence interval conveys uncertainty around an estimate. It is a range generated by a method that, under its assumptions and repeated use, has a stated coverage property. It is not a range containing a known proportion of individual participant outcomes, and it does not assign a probability to a particular fixed treatment effect after the data have been observed. For the primary comparison, the 95% confidence interval runs from -46.35 to -5.195 grams. The interval gives context for the estimate of -25.77 grams and shows that the estimate is not known with exact precision.

The interval and p-value are related summaries of the recalculated comparison, but they answer different descriptive questions: the interval displays a range of compatible effect estimates, while a p-value measures how unusual data at least this incompatible with a specified null comparison would be under the calculation’s assumptions. The unadjusted p-value is 0.014. It should not be interpreted as the probability that the treatment has no effect or as a measure of the size or importance of the difference.

Why do variability and sample size matter?

In general, uncertainty in a mean comparison depends on the amount of variability in outcomes and the number of observations contributing to the comparison. More variable measurements make a group mean less precise at a given sample size; more observations can improve precision if the design and analysis assumptions are appropriate. The primary endpoint includes 13 semaglutide participants and 12 sham/placebo participants. Its standard deviations are substantial relative to the group means, so the observed mean changes should not be read as predictions for individual participants.

The outcome-specific population is defined by completion of both laboratory assessments. This restriction matters because the posted comparison does not describe participants without both measurements. The registry record does not report a missing-data method, a sensitivity analysis, or a comparison of participants included and not included in the primary endpoint analysis. Consequently, the extent to which missing outcomes could affect the estimate cannot be assessed from the record.

Why can over-dispersion matter?

In general, over-dispersion means that observed variability is greater than a statistical model expects. When a model assumes less variability than the data contain, its standard errors can be too small and its confidence intervals too narrow. This concept is most directly relevant to models for counts or other outcomes with a variance structure specified by the model. The primary endpoint is reported as a continuous mean and standard deviation, and the registry record does not report a model that would allow an assessment of over-dispersion. It would therefore be inappropriate to claim that over-dispersion was present or handled in a particular way.

For planning illustrations, the stated calculation uses a normal approximation and equal allocation. Those assumptions apply to the planning illustration, not necessarily to the trial’s original design or to an unreported sponsor analysis. The record does not report the trial’s original sample-size assumptions, the planned analysis model, or the intended handling of repeated or missing measurements.

What do unadjusted secondary comparisons mean?

Unadjusted secondary comparisons are evaluated without an indicated correction for examining multiple outcomes. In general, testing many outcomes creates more opportunities for apparently noteworthy results by chance. An adjustment can address that issue, but the registry record does not report a multiplicity procedure or a prespecified hierarchy that would indicate which outcomes were confirmatory. The secondary estimates and p-values should therefore be treated as exploratory descriptions rather than as a coordinated set of confirmatory tests.

The record lists no sponsor-reported secondary analyses. The posted secondary comparisons are recalculated from the summary statistics and should be understood accordingly. The registry’s own sponsor analysis would take precedence if a discrepancy were indicated; the discrepancy indicator is false for this record. That does not supply the missing analysis plan or establish that every calculation matches a protocol-specified procedure.

11. Confidence Intervals and Precision

The primary mean-difference estimate is -25.77 grams, and its 95% confidence interval extends from -46.35 to -5.195 grams. The interval represents uncertainty in the estimated group contrast under the calculation’s assumptions. Its width shows that the summary data do not identify a single precise value for the underlying difference. The point estimate is useful as a central summary, but it should not be treated as an exact or guaranteed effect.

In general, a confidence interval describes values compatible with the data and a specified statistical procedure. It is not a prediction interval for individual participants, and it does not show the range of outcomes that every participant might experience. The primary outcome population comprises participants who completed both laboratory assessments, with 13 in the semaglutide group and 12 in the sham/placebo group. The registry does not report how missing primary measurements were handled or whether a different analysis population was used in an original sponsor analysis.

The unadjusted p-value for the recalculated primary comparison is 0.014. It accompanies the estimate and interval but does not express the magnitude or practical importance of the result. The record does not report an adjustment for examining multiple outcomes, so the p-value should not be viewed as multiplicity-adjusted evidence. The outcome-specific sample size and incomplete information about missing data and analysis procedures limit how fully the interval’s assumptions can be checked from the registry record.

Precision is distinct from bias. A narrow interval would not rule out systematic problems in measurement or selection, and an interval alone cannot establish that the participants represented a broader population. The registry record does not report enough detail to evaluate those possibilities. The result is best read as an estimate with measurable uncertainty for the stated laboratory endpoint population, rather than as a precise forecast for other participants or settings.

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 illustrations are planning calculations based on the observed effect, not the trial’s original design assumptions. They use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Each planning scenario uses a stated fraction of the observed effect as the effect to detect. For these continuous outcomes, the figures are participants per arm, not a total across both arms and not total events. The distinction matters: the numbers indicate a prospective planning scale for each group under those assumptions, not the number enrolled in this completed trial.

The 80% power column gives the number of participants per arm estimated to provide an 80% chance of detecting the specified effect if that effect is real and the planning assumptions hold. The 90% power column gives the corresponding planning number for a higher chance of detecting that same specified effect. Power is conditional on the assumed effect, variability, statistical procedure, and design. These figures are not observed power; they do not describe the probability that the completed trial’s result is true or the chance that the trial succeeded.

Rows planning for 100%, 75%, or 50% of the observed effect show how the required sample size changes when the target effect is made smaller. A smaller target effect is harder to distinguish from random variation, so the planning calculation requires more participants. This is especially important when the observed effect comes from a small outcome sample: using that estimate for planning may not reflect the effect that a future study should expect. The registry record does not report the trial’s own original sample-size justification or assumptions, so the illustrations should not be read as evidence about why the trial enrolled its participants.

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 = -25.770; pooled standard deviation σ = 26.369.
2. n = 2 × (1.96 + 0.842)² × 26.369² / -25.770² = 16.4, rounded up to 17 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 <- -25.77                      # observed difference in means
sigma <- 26.3685632162042                     # 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(5520775)
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 = 17 (80% power), 23 (90% power)
 75% of observed effect: n per arm = 30 (80% power), 40 (90% power)
 50% of observed effect: n per arm = 66 (80% power), 89 (90% power)
power.t.test: 17.4 
Simulated power at n = 17 per arm: 0.786 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates several outcomes or makes several statistical comparisons. In general, the more comparisons considered, the greater the chance that at least one result may appear unusual by chance alone. A study can address this through a prespecified testing hierarchy, adjustment procedures, or clear designation of exploratory outcomes. The registry record does not report a multiplicity strategy, adjustment method, or hierarchy for the primary and secondary outcomes. The primary p-value is unadjusted, as are the posted secondary comparisons.

The record lists 11 outcome measures and six secondary outcomes, but does not list sponsor-reported analyses for the secondary outcomes. This does not show which comparisons were prespecified for confirmatory testing or how the outcomes were selected for reporting. The registry record does not report an analysis plan describing how multiple outcomes were to be interpreted. The primary result should therefore be distinguished from the broader set of secondary comparisons, without treating the latter as a single confirmatory body of evidence.

Missing data are another unresolved issue. The stated primary population includes participants completing both pre- and post-treatment laboratory self-administration, while the primary group summaries include 13 semaglutide participants and 12 sham/placebo participants. The overall enrollment was 48. The registry record does not report why the outcome-specific counts differ from overall enrollment, the number missing at each assessment, reasons for missingness, or the method used to handle missing observations. It also does not report sensitivity analyses that would show whether assumptions about missing outcomes change the estimate.

The record does not report whether the analysis used an intention-to-treat population, a per-protocol population, or another analysis population beyond the primary outcome’s stated completion criterion. It does not report imputation, model-based handling of incomplete measurements, covariate adjustment, or interim analyses. These omissions mean that the posted summary-statistic comparison can be described, but its relationship to any planned sponsor analysis cannot be established. The discrepancy indicator is false; nevertheless, the analysis details not reported in the registry remain unknown.

15. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 4% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports serious adverse events for 24 participants at risk in each group. It lists zero participants affected by serious adverse events in the semaglutide group and zero in the sham/placebo group. It also reports zero deaths in both groups. The serious-event terms list is empty. These figures describe what the registry record reports for the stated groups and do not provide event descriptions or timing.

For other adverse events, the registry reports 22 participants affected among 24 at risk in the semaglutide group and 18 among 24 at risk in the sham/placebo group. These are counts of participants affected, not a measure of event severity or a count of every event occurrence. The record does not provide further details in the registry record about the types, duration, or clinical significance of these other events.

In general, zero reported serious events in a group does not establish that the risk is absent; it describes the events recorded within the reported study data. Safety counts should be interpreted in light of the number at risk and the duration and completeness of follow-up, details the registry record does not fully report. These figures alone do not establish a comparative safety conclusion.

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

The primary result describes a difference in average change in estimated grams of ethanol consumed during laboratory self-administration from baseline (Week 0) to post-medication (Week 8). The posted mean changes were -32.72 grams in the semaglutide group and -6.95 grams in the sham/placebo group, producing an estimated mean difference of -25.77 grams. The 95% confidence interval was -46.35 to -5.195 grams, and the unadjusted p-value was 0.014. The comparison is calculated from posted summary statistics and applies to participants who completed both laboratory assessments.

These numbers do not establish what happened to every participant, why the group summaries differed, or whether a similar difference would occur in a different setting. The endpoint is laboratory self-administration; it is not the same measure as daily alcohol use, which the registry lists separately. The registry record does not report numerical results for all listed secondary outcomes or the sponsor’s analysis procedures. It also does not report a multiplicity plan or missing-data strategy that would clarify how the family of outcomes and incomplete assessments were handled.

In general, a p-value is not the probability that a treatment works, nor is it the probability that the null hypothesis is true. A mean difference is a statistical contrast, not a personal forecast or a statement about the clinical importance of a change. The confidence interval communicates uncertainty in the estimated contrast under its assumptions; it does not remove uncertainty about the population, measurement, or analysis choices.

The record supports a careful description of the posted group changes and their uncertainty in this laboratory endpoint population. It does not establish a causal mechanism, generalizability beyond the studied participants and setting, or a result for every randomized participant. It also does not support medical advice or a conclusion about treatment decisions. Those broader interpretations require evidence and details that the registry record does not report.

17. Why This Trial Matters Statistically

This trial illustrates why statistical interpretation should begin with the exact outcome population and measurement. The registry’s overall enrollment is 48, while the primary summaries include 13 semaglutide participants and 12 sham/placebo participants who completed both laboratory assessments. The contrast is therefore an endpoint-specific summary, not a result that can automatically be attributed to every person enrolled or randomized.

It also shows why effect estimates and uncertainty belong together. The mean difference of -25.77 grams is a useful summary in the endpoint’s original units, while its 95% confidence interval, from -46.35 to -5.195 grams, communicates that the estimated contrast is not known exactly. The unadjusted p-value of 0.014 is another summary, but does not replace the estimate, interval, or consideration of the analysis population.

The study includes several related but distinct outcomes, from laboratory consumption to subjective alcohol effects and demand measures. Without a reported multiplicity plan, secondary results need more cautious interpretation than a prespecified primary comparison. Likewise, an outcome-specific sample-size planning illustration is not a record of the trial’s original design rationale. Distinguishing those uses prevents planning numbers from being mistaken for observed power or for a justification of the study size.

Finally, the registry record leaves important methodological details unreported, including missing-data handling and the sponsor’s detailed analysis procedures. Recognizing those limits is part of statistical interpretation, not a reason to discard the posted results. The key is to describe what the estimates address, how precisely they are estimated, and which questions remain unresolved.

18. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The primary endpoint is based on participants who completed pre- and post-treatment laboratory self-administration. Its posted sample sizes are smaller than the overall enrollment, and the registry record does not report the reasons for this difference, the number missing at each assessment, or how missing observations were handled. The result may therefore describe a selected subset of enrolled participants; the record does not provide enough information to assess the effect of that selection.

The endpoint is a laboratory measure of estimated ethanol consumption, not the separately listed measure of daily alcohol use. The registry record does not report details of the laboratory task, the assessment procedures, or whether the endpoint was measured at other time points. This limits interpretation of how closely the endpoint reflects behavior outside the laboratory and how durable any change might be.

The posted primary comparison is recalculated from summary statistics, and the registry does not list a sponsor-reported analysis. Detailed information about the intended model, covariate adjustment, missing-data methods, and analysis population is not reported. Nor is a multiplicity strategy reported for the set of outcome measures. The secondary findings should consequently be read as unadjusted and exploratory rather than as a set of confirmatory tests.

The registry record also does not report the original sample-size justification or the detailed rationale for the outcome-specific sample sizes. The separate planning illustrations use the observed effect and stated assumptions, so they cannot answer why the trial enrolled its participants. Finally, the record does not provide enough detail about the participant characteristics beyond the listed conditions and primary outcome population to assess how applicable the findings may be to other groups.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Semaglutide for Alcohol Use Disorder — NCT05520775.
• Registry record last updated 2025-04-02; status last verified 2024-05.
• Results first posted 2025-03-24.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

22. Record Summary

The registry describes a completed, randomized, triple-masked, parallel Phase II human laboratory trial comparing semaglutide with sham/placebo. It lists an enrollment of 48 and a primary endpoint of change in estimated grams of ethanol consumed from baseline (Week 0) to post-medication (Week 8), among participants completing both laboratory self-administration assessments.

The posted primary group means were -32.72 grams for 13 semaglutide participants and -6.95 grams for 12 sham/placebo participants. The recalculated mean difference was -25.77 grams, with a 95% confidence interval from -46.35 to -5.195 grams and an unadjusted p-value of 0.014. The registry does not list a sponsor-reported analysis for this outcome.

Six secondary outcomes are listed, while sponsor-reported secondary analyses and a multiplicity plan are not reported. The registry also does not report the trial’s original sample-size justification or its missing-data methods. Safety records list zero serious adverse events and zero deaths in either group, with other adverse events affecting 22 of 24 participants in the semaglutide group and 18 of 24 in the sham/placebo group.