Liraglutide 3mg (Saxenda) on Weight, Body Composition, Hormonal and Metabolic Parameters in Obese Women With PCOS: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Liraglutide 3mg (Saxenda) on Weight, Body Composition, Hormonal and Metabolic Parameters in Obese Women With PCOS (NCT03480022), a randomized phase 3 study. The primary outcome is Absolute Body Weight (BW).

2. Clinical Question

3. Trial Design

The registry identifies this as a phase 3, randomized, parallel-group trial with placebo control. Its official title describes a double-blind trial, while the registry masking field says quadruple masking. The parties covered by that masking designation are not reported in the registry record. The listed sponsor is Woman's, and the record status is completed.

Enrollment is listed as 88. The start date is 2018-09-26, and primary completion is listed as 2021-02-22. The primary outcome results give group sizes of 44 for liraglutide and 23 for placebo; the registry does not explain the relationship between those outcome group sizes and total enrollment. The adverse-event results use different at-risk group sizes, also without an explanation of the analysis populations.

Participants were assigned to liraglutide or placebo. Both arm descriptions specify a stepwise dose escalation, with the active arm reaching 3.0 mg liraglutide subcutaneously once daily. The registry does not report further details about allocation concealment, how randomization was generated, adherence, concomitant care, or visit schedules. It also does not report whether lifestyle interventions were part of the trial treatment, despite the background summary discussing lifestyle changes as an area of interest.

The primary outcome was absolute body weight, with secondary outcomes including body mass index, percent body-weight change, threshold weight loss, measures of abdominal adiposity, and total fat mass. The record lists 29 outcome measures and 29 analyses. Further information about the analysis populations and handling of missing results is 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.

Overall Study

Reasons for not completing this period:

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 Absolute Body Weight (BW), measured over 32 weeks of treatment.

The primary endpoint is absolute body weight, measured in kilograms at 32 weeks of treatment. The record describes the aim as assessing treatment impact on change in body weight after that period, but the posted arm summaries give mean absolute body weight at the endpoint: 104.7 kg for liraglutide and 117.9 kg for placebo. Each arm summary includes a standard error, which describes the estimated uncertainty around that arm's mean, not the spread of individual participants' weights.

General statistical context: body weight is a direct, continuous measure. Comparing group means can describe an average difference between randomized groups, while retaining the original measurement scale. A result at a defined follow-up point also gives a clear time reference for the comparison. The endpoint is relevant to the trial's stated focus on weight reduction in women with PCOS and obesity. However, an endpoint mean is not itself a change-from-baseline estimate. The registry's primary outcome description refers to change, but baseline values and an explicit baseline-adjusted estimate are not reported in the registry record.

The difference and confidence interval discussed in the statistical interpretation are recalculated from posted summary statistics; they are not the sponsor's reported ANOVA estimate. The registry reports a sponsor-analysis p-value but does not report its corresponding effect estimate or confidence interval.

7. Results Posted in the Registry

• Liraglutide Pen Injector (Saxenda): mean 104.70 versus 117.90 on control; difference -13.20 (95% CI -24.53 to -1.87), standardized effect d = -0.63; z-test p = 0.022.

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.

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 errors.
• Result:
  • Liraglutide Pen Injector (Saxenda): mean 39.10 versus 43.40 on control; difference -4.30 (95% CI -8.43 to -0.17), standardized effect d = -0.55; z-test p = 0.042.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Liraglutide Pen Injector (Saxenda) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change in Percent Body Weight

• 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 errors.
• Result:
  • Liraglutide Pen Injector (Saxenda): mean 5.70 versus 1.40 on control; difference 4.30 (95% CI 1.71 to 6.89), standardized effect d = 0.85; z-test p = 0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Liraglutide Pen Injector (Saxenda) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

5% Weight Loss From Baseline

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Liraglutide Pen Injector (Saxenda): 56.8% (25/44) versus 21.7% (5/23) on control; risk difference 35.1 percentage points (95% CI 12.8 to 57.4), risk ratio 2.61 (1.15–5.92); unadjusted two-proportion z-test p = 0.006.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Liraglutide Pen Injector (Saxenda) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary weight-related results generally align in direction with the primary weight comparison. The liraglutide group has a lower posted BMI mean, greater percent body-weight loss, and more participants recorded as reaching the 5% weight-loss threshold. These measures provide complementary descriptions of weight outcomes: a related body-size measure, a change expressed relative to baseline, and a threshold-based participant count.

They are not independent evidence in the same way that outcomes from unrelated domains might be. BMI and body weight are closely related measurements, and percent change and threshold weight loss are also derived from weight. A consistent direction across such outcomes can describe the pattern, but it does not multiply the strength of evidence as if each result were an unrelated replication.

The secondary outcome list also includes abdominal adiposity measures and total fat mass. The record lists 29 outcome measures and analyses and states that 27 secondary outcomes are posted. The information in the registry record does not support a complete account of results across all hormonal, metabolic, or body-composition measures. In particular, a directional pattern among the weight-related results should not be generalized to every outcome domain.

The posted secondary p-values are unadjusted in the recalculations, and the registry does not report a multiplicity correction. General statistical context: testing many outcomes increases the opportunity to observe nominally notable p-values by chance, especially when outcomes are related or when the analysis plan is unclear. For that reason, secondary findings usually carry less confirmatory weight than the primary endpoint, particularly when the record does not identify which secondary analyses were prespecified or how the family of tests was handled.

The secondary results can therefore be read as supportive descriptions of the measured weight pattern, while recognizing that their inferential strength is limited by multiplicity and incomplete reporting. They do not resolve the discrepancy in the primary analysis and do not establish outcomes that are not reported in the registry record.

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

• Body Mass Index (BMI)
• Change in Percent Body Weight
• 5% Weight Loss From Baseline
• 10% Body Weight Loss From Baseline
• Abdominal Adiposity (Waist Circumference [WC]
• Waist-to-Hip Ratio
• Waist-to Height Ratio [WHtR])
• Total Fat Mass Evaluated by DEXA

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, and the registry summarizes each arm with a mean and standard error. A mean describes the center of a group on the measurement scale. A standard error describes the precision of the estimated mean; it is not the standard deviation of participant values and does not by itself show how much individual weights varied.

The posted summaries can be used for a simple, unadjusted comparison of the two means. For the primary outcome, that recalculation gives a mean difference of -13.2 kg and a 95% confidence interval from -24.53 to -1.871. The recalculated p-value is 0.022. The calculation uses only the posted arm-level summaries and is not adjusted for other variables. The registry's own analysis is an ANOVA superiority analysis, reported with p <0.002. Because the record flags a discrepancy, the sponsor's analysis takes precedence. The registry does not give enough detail to reconstruct the sponsor's model or determine why the results differ.

General statistical context: analysis of variance, or ANOVA, evaluates differences in means across groups under a specified model. The name alone does not reveal which covariates or assumptions were used. Those details are not reported in the registry record. A superiority test evaluates evidence against a null hypothesis of no group difference in the modeled outcome; its p-value is not an estimate of the size or practical importance of the difference. A p-value also does not state the probability that the null hypothesis is true.

A confidence interval gives a range of values compatible with the estimate under the method's assumptions. It conveys uncertainty about the estimated difference, whereas the standard errors in the arm summaries describe uncertainty in each arm mean. General statistical context: wider intervals indicate less precision, and interval width depends on variability, sample size, and the analysis method. The sponsor's primary confidence interval is not reported, so the recalculated interval should not be attributed to the sponsor's ANOVA.

For BMI and percent body-weight change, the record also reports means and standard errors by arm and sponsor ANOVA p-values. The simple recalculations use those posted summaries and are unadjusted. The threshold outcome, 5% weight loss from baseline, is binary: a participant either meets the recorded threshold or does not. The posted counts are 25 in the liraglutide group and 5 in the placebo group. The registry gives a Wilcoxon (Mann-Whitney) superiority analysis for this outcome. General statistical context: the Wilcoxon rank-sum procedure compares ranks of observations between groups and is commonly used for ordered or continuous measurements. The registry does not explain its use for this binary endpoint, and no additional details about that analysis are reported.

The recalculated risk difference for the threshold outcome is 0.351, with a 95% confidence interval from 0.128 to 0.574, and an unadjusted p-value of 0.006. A risk difference expresses the contrast between the groups' observed proportions on an absolute scale. The sponsor reports p <0.007 for its Wilcoxon analysis. These results use different approaches and should not be conflated. The sponsor's reported test remains the registry's own analysis; the recalculation is descriptive and unadjusted.

General statistical context: over-dispersion occurs when observed variability exceeds what a model assumes. It matters because a model that understates variability can make uncertainty look smaller than it is. The registry does not report whether over-dispersion was assessed or relevant to the analyses, so no conclusion can be drawn about it in this trial. Similarly, assumptions about distributional shape, baseline adjustment, repeated measurements, and treatment of influential observations are not reported.

The record identifies 29 outcome measures and 29 analyses, but does not report a complete statistical analysis plan, the original sample-size calculation, analysis-population definitions, or missing-data procedures. It also does not state whether the reported p-values are adjusted for the number of outcomes. Those omissions limit independent assessment of the analysis choices and the risk of selective emphasis. General statistical context: a well-specified analysis plan helps readers distinguish primary confirmatory tests from exploratory comparisons, and makes it easier to understand how deviations, missing values, and multiple outcomes were handled.

11. Confidence Intervals and Precision

Precision is best assessed using an interval around an estimated group difference, rather than a p-value alone. For absolute body weight, the recalculated mean difference is -13.2 kg, with a 95% confidence interval from -24.53 to -1.871. The interval lies below zero, indicating that the recalculated difference is negative across the reported interval. Its span also shows that the estimate is not exact: a range of effect sizes remains compatible with the summary data and calculation method.

This interval is an unadjusted recalculation, not the sponsor's ANOVA interval. The sponsor's confidence interval and effect estimate are not reported in the registry record. The discrepancy between the sponsor's p-value, p <0.002, and the recalculated p-value, 0.022, reinforces the need not to treat the recalculated interval as a reconstruction of the sponsor's analysis.

The posted BMI and percent body-weight change comparisons also have recalculated intervals. For BMI, the mean difference is -4.3 kilogram/meter squared, with a 95% confidence interval from -8.435 to -0.166. For percent body-weight change, the mean difference is 4.3 percentage points as recorded in the measure's units, with a 95% confidence interval from 1.707 to 6.893. The binary threshold comparison has a recalculated risk difference of 0.351, with a 95% confidence interval from 0.128 to 0.574. These intervals derive from the posted summaries and are unadjusted.

General statistical context: confidence intervals reflect sampling uncertainty under the calculation's assumptions; they do not incorporate every possible source of uncertainty, such as missing-data bias, measurement issues, or limitations in trial conduct. The registry's lack of analysis-population and missing-data details therefore matters when judging how fully these intervals capture uncertainty. Intervals also do not establish whether an effect is clinically important; that judgment would require criteria not 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 planning figures are illustrations based on the observed effect, not the trial's original design calculation. For these non-time-to-event outcomes, the figures are participants per arm, rather than total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The trial's own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm under those assumptions for a design with an 80% chance of detecting the specified effect if that effect is present and the model assumptions hold. The 90% power column gives the corresponding number for a design with a 90% chance under the same conditions. These are prospective planning concepts; neither column says what power the completed trial had.

The rows based on 100%, 75%, and 50% of the observed effect show how the planning count changes when the target effect is made smaller. For example, the primary outcome illustration lists 40 participants per arm for 80% power at 100% of the observed effect, 71 for 75%, and 159 for 50%. The corresponding 90% figures are 53, 95, and 212. Smaller effects generally require more participants to detect, because they are harder to distinguish from random variation.

These calculations are not observed power. They are planning illustrations that reuse an effect estimated from the trial, so they should not be taken as evidence about the adequacy of the original design or as a post-trial measure of how convincing the result is. Their assumptions may not match the sponsor's analysis, whose full specification is not reported. They are most useful for illustrating how sample-size requirements depend on the target effect and desired power, not for replacing an original protocol justification.

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 = -13.200; pooled standard deviation σ = 20.962.
2. n = 2 × (1.96 + 0.842)² × 20.962² / -13.200² = 39.6, rounded up to 40 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 <- -13.2                      # observed difference in means
sigma <- 20.9621343599138                     # 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(3480022)
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 = 40 (80% power), 53 (90% power)
 75% of observed effect: n per arm = 71 (80% power), 95 (90% power)
 50% of observed effect: n per arm = 159 (80% power), 212 (90% power)
power.t.test: 40.6 
Simulated power at n = 40 per arm: 0.796 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor's primary analysis is reported as an ANOVA superiority test with p <0.002. No sponsor-reported mean difference or confidence interval is included in the registry record. The recalculated comparison uses the posted group means and standard errors and gives a mean difference of -13.2 kg, a 95% confidence interval from -24.53 to -1.871, and p = 0.022. This is a simple unadjusted recalculation, not a reproduction of the sponsor's model.

The record flags a discrepancy between the recalculation and the sponsor's result. Accordingly, the sponsor's own analysis takes precedence when describing the trial's reported inferential result. The recalculation can still help readers understand the scale and uncertainty implied by the posted summaries, but it cannot explain the sponsor's result or establish what analytical choices produced it.

The same distinction applies to the secondary outcomes. The registry reports sponsor analyses using ANOVA for BMI and percent body-weight change, and a Wilcoxon (Mann-Whitney) analysis for the 5% weight-loss threshold. Recalculated estimates and intervals are based on summary statistics and unadjusted comparisons. The registry does not provide enough detail to determine whether the sponsor used additional covariates or other model features, or whether its tests handled multiplicity.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists 29 outcome measures and 29 analyses, and the posted results include 27 secondary outcomes. It does not report whether the analyses were prespecified in a protocol or statistical analysis plan, which secondary outcomes were confirmatory, or whether any adjustment for multiple testing was used. The sponsor's primary and secondary test results are reported, but a comprehensive account of the analysis hierarchy is not available in the registry record.

General statistical context: when several hypotheses are tested, the chance of at least one apparently positive result can increase if each test is judged separately at the same threshold. Multiplicity procedures can control that risk, but they can also affect the interpretation and precision of individual estimates. Without a reported plan, the posted secondary p-values should be treated as unadjusted evidence rather than as definitive tests across all outcomes.

Missing-data methods are not reported in the registry record. The primary outcome group sizes are 44 and 23, while the safety at-risk group sizes are 55 and 27. The record does not explain these differing denominators, identify how many randomized participants contributed to each outcome, or state whether all randomized participants were included in the analyses. It also does not describe withdrawals, missing visits, imputation, or sensitivity analyses. These details matter because missing outcomes can affect estimates if the participants with observed results differ systematically from those without them.

The record does not state whether analyses followed an intention-to-treat population, a per-protocol population, or another definition. Baseline adjustment, covariate selection, handling of adherence, and the treatment of protocol deviations are also not reported. The sponsor's ANOVA results cannot be fully evaluated without those details, and the summary-based recalculations cannot fill that gap.

These reporting omissions do not establish that a particular method was or was not used. They mean only that the registry record does not describe it. Consequently, readers can identify the posted group summaries and tests, but cannot fully assess analysis populations, missingness assumptions, or the handling of multiple outcomes.

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 0% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports zero serious adverse events among 55 participants at risk in the liraglutide group and among 27 participants at risk in the placebo group. It also reports zero deaths in each group. No serious adverse-event terms are listed in the record. These are counts recorded during the trial; they do not establish that no unreported or unrecorded events occurred.

Other adverse events are reported for 40 participants in the liraglutide group and 8 in the placebo group, with the same respective at-risk denominators. The registry labels these as other adverse events but does not provide event descriptions in the posted record excerpt. These counts should be distinguished from serious adverse events: the record reports no serious events in either group, while reporting other adverse events in both.

General statistical context: a count of zero observed serious events does not show that the underlying risk is zero, especially when the number of participants observed is limited. The record does not report detailed severity, timing, duration, treatment discontinuations due to adverse events, or attribution methods. The registry counts alone therefore provide a limited description of safety experience and should not be interpreted as a complete safety assessment.

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

The posted results describe a randomized comparison of liraglutide and placebo in a trial focused on women with obesity and PCOS. At 32 weeks, the recorded mean absolute body weight was lower in the liraglutide group than in the placebo group. Recalculated secondary weight measures point in a similar direction. The registry's own primary analysis reports an ANOVA superiority result with p <0.002, while the simple unadjusted recalculation differs; the sponsor's result takes precedence because the record flags a discrepancy.

This does not establish that the treatment works or does not work in a broader clinical sense. The registry record does not provide the sponsor's primary effect estimate and confidence interval, the full analysis plan, or the missing-data methods needed for a complete assessment of the reported result. It also does not justify extending the findings to populations, treatment schedules, or follow-up periods beyond those described.

The numerical outcomes are group summaries, not predictions for an individual participant. A group mean does not show the full range of individual responses, and the binary threshold result does not describe how far each participant's weight changed. The recalculated confidence intervals express uncertainty under the calculation used; they do not capture every uncertainty arising from trial conduct, outcome reporting, or analysis choices.

The record also gives limited information about outcomes beyond weight-related measures. While the trial's title and summary mention hormonal and metabolic parameters, the posted details do not support broad conclusions about those domains. The presence of secondary outcomes in a registry does not establish that each was measured, analyzed, or reported in a way that permits interpretation.

Overall, the record supports a description of the observed weight-related group pattern and the reported sponsor test, alongside important uncertainties about analytical detail and reporting completeness. It is not a substitute for a full trial report or a complete account of benefits and harms.

18. Why This Trial Matters Statistically

This trial is statistically informative because it brings together a randomized, placebo-controlled design and a population described as women with obesity and PCOS, while recording a direct weight endpoint and related secondary measures. The primary outcome provides a clear scale-based comparison after 32 weeks, and the secondary weight outcomes offer different ways to characterize the same broad domain.

The record also illustrates why effect estimates, uncertainty intervals, and p-values answer different questions. The recalculated mean difference describes the scale and direction of the posted summary contrast, its confidence interval conveys uncertainty under that recalculation, and the sponsor's ANOVA p-value reports the result of a different analysis. The discrepancy makes transparent reporting of analysis methods especially important: without the sponsor's estimate, interval, and model details, readers cannot fully reconcile the inferential results.

Planning illustrations based on observed effects also show a general design principle: smaller effects require larger sample sizes to detect under otherwise stated assumptions. Those figures are not the original design justification and do not establish the trial's observed power. Keeping planning calculations distinct from the study's actual design protects against interpreting a post hoc illustration as evidence that a trial was adequately or inadequately powered.

Finally, the number of registered outcomes and the absence of reported multiplicity and missing-data methods matter for interpretation. A coherent direction among related weight outcomes is useful descriptive context, but it does not replace a prespecified analysis plan or a clear account of all outcome results. This record is therefore a case in how statistical interpretation depends not only on the numerical result, but also on transparent reporting of populations, methods, and uncertainty.

19. Limitations

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

Several limitations are specific to the information in this trial record. The primary arm summaries have different group sizes, and the registry does not explain why the primary outcome denominators differ from total enrollment or from the safety at-risk counts. The analysis populations and participant flow are not reported, so the completeness and comparability of outcome follow-up cannot be assessed from the record.

The trial is described as quadruple masked in the registry field, while the official title calls it double blind. The record does not identify which participants or study personnel were masked or explain the difference between these descriptions. Randomization is reported, but generation and concealment procedures are not described.

The sponsor reports an ANOVA p-value for the primary outcome but not its effect estimate or confidence interval. The unadjusted recalculation differs from the sponsor result, and the registry flags that discrepancy. The model specification, baseline handling, analysis population, and missing-data procedures are not reported, limiting independent evaluation of the sponsor analysis.

The registry lists many outcomes but does not report a multiplicity strategy or a full analysis plan. Although the title and summary refer to hormonal and metabolic parameters, the posted outcome details do not permit a complete interpretation of those domains. Follow-up for the primary endpoint is 32 weeks; longer-term outcomes are not reported in the record. Detailed adverse-event descriptions, seriousness criteria, and reasons for discontinuation are also not reported.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Liraglutide 3mg (Saxenda) on Weight, Body Composition, Hormonal and Metabolic Parameters in Obese Women With PCOS — NCT03480022.
• Registry record last updated 2021-06-07; status last verified 2021-06.
• Results first posted 2021-06-07.
• 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

NCT03480022 is a completed, randomized, parallel-group, placebo-controlled phase 3 trial of liraglutide in women with obesity and PCOS. The primary endpoint was absolute body weight after 32 weeks. Enrollment is listed as 88, and the primary outcome summaries report 44 participants in the liraglutide group and 23 in the placebo group.

The registry reports an ANOVA superiority result for the primary outcome with p <0.002. A simple unadjusted recalculation from the posted summaries gives a mean difference of -13.2 kg, with a 95% confidence interval from -24.53 to -1.871 and p = 0.022. The record flags a discrepancy, so the sponsor's own analysis takes precedence. Secondary weight-related results generally point in the same direction, but the registry does not report the full analysis plan, multiplicity approach, analysis populations, or missing-data methods.

The safety record lists zero serious adverse events and zero deaths in both groups, alongside other adverse events in each group. These counts and the incomplete methodological detail provide a limited account of the trial's results and safety experience.