Efficacy and Safety Study of Elagolix Versus Placebo or Leuprorelin Acetate in Endometriosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety Study of Elagolix Versus Placebo or Leuprorelin Acetate in Endometriosis (NCT00797225), a randomized phase 2 study. The primary outcome is Change From Baseline in the Monthly Mean Numerical Rating Score (NRS) for Endometriosis Pain.

2. Clinical Question

The central outcome is a participant-reported measure of endometriosis pain. Participants used an electronic diary to rate their worst endometriosis pain over the past day on a scale from 0, meaning no pain, to 10, meaning worst pain ever. The monthly mean is the average of daily ratings during the 4 weeks before a visit.

The study was designed to compare elagolix with both placebo and an active-control treatment during the initial treatment period. The later period has a different structure: the placebo and leuprorelin groups were re-randomized to elagolix, while the original elagolix groups continued their assigned dose. The available registry entries therefore describe both an initial comparative period and subsequent treatment with elagolix, but do not report numerical outcome results for either period.

The registry lists additional measures of pelvic pain, dysmenorrhea, analgesic use, and dyspareunia. These outcomes provide other ways to describe symptoms or medication use, but their estimates are not reported in the record.

3. Trial Design

This was a randomized, quadruple-masked, parallel-group Phase II study of elagolix, placebo, and leuprorelin acetate in endometriosis. The registry lists enrollment of 174. The study is recorded as completed, with a start date of 2008-11-26 and a primary completion date of 2010-02-24. The registry record does not report further details about the randomization procedure or the meaning of each masking designation.

During the first 12 weeks, the elagolix 150 mg group received 150 mg tablets once a day and a placebo intramuscular injection once a month. The elagolix 250 mg group received 250 mg tablets once a day and a placebo intramuscular injection once a month. The placebo group received placebo tablets once a day and a placebo injection once a month. The leuprorelin group received placebo tablets once a day and leuprorelin acetate 1-month depot 3.75 mg by intramuscular injection once a month.

After the initial 12 weeks, participants in the placebo and leuprorelin groups were re-randomized to receive one of the two elagolix doses for an additional 12 weeks. Participants originally assigned to either elagolix dose continued that same dose for the additional 12 weeks. Consequently, the initial treatment assignments support the planned comparison with placebo and leuprorelin over the first period, while the later treatment structure is not a continuation of those same comparator assignments.

The primary outcome was assessed at baseline and Weeks 4, 8, and 12. The registry describes the measure as change from baseline in the monthly mean Numerical Rating Score for endometriosis pain. It also lists 24 outcome measures and 45 analyses. Those counts indicate a broad set of recorded outcomes and analyses; they do not reveal which analyses were prespecified as primary or how statistical multiplicity was handled.

The registry record does not report the sample-size justification, planned effect size, detailed analysis model, covariates, interim analyses, or stopping rules. It describes a planning illustration based on the observed effect and specified general assumptions, but no numerical planning estimates are available in the record. These planning assumptions should not be mistaken for a report of the trial's original design rationale or observed statistical power.

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: Patients were randomized equally to oral elagolix 150 mg or 250 mg once daily, placebo or leuprorelin acetate (LA) 1-month depot 3.75 mg injection for 12 weeks. Thereafter, patients originally randomized to placebo or LA were re-randomized to 1 of the elagolix doses and patients randomized to elagolix continued their assigned dose for 12 weeks.

Only the first 6 of 8 groups are shown.

Weeks 1 to 12

Reasons for not completing this period:

Weeks 13 to 24

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All randomized participants who received at least 1 dose of study drug and had at least 1 evaluable e-Diary report following randomization (intent-to-treat population). The analysis includes participants with non-missing data at each time point.

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 From Baseline in the Monthly Mean Numerical Rating Score (NRS) for Endometriosis Pain, measured over Baseline and Weeks 4, 8, and 12.

The primary endpoint is change from baseline in the monthly mean Numerical Rating Score for endometriosis pain. The score uses an 11-point scale: participants selected one number from 0, no pain, to 10, worst pain ever, to represent their worst endometriosis pain over the past day. They entered the rating at approximately the same time each day using an electronic diary. The monthly mean is the average of daily ratings during the 4 weeks before each visit.

In general, a daily rating captures a participant's experience close to the time it occurs, while averaging ratings across a period describes pain over more than one day. A change-from-baseline endpoint expresses how the measured score differs from the participant's starting value, rather than describing only a follow-up score. The rating scale is a continuous numerical measure for the registry's analysis, although the individual response is selected from ordered scale points.

The endpoint is relevant to the stated study question because it directly records the symptom being evaluated: endometriosis pain. The registry specifies least-squares means as the summary measure and standard errors as the dispersion measure. In general, a least-squares mean is a model-based estimate of a group mean; the model details needed to interpret any adjustment are not reported in the registry record. A standard error describes the precision of an estimated mean, not the spread of individual participants' scores.

The outcome was scheduled at baseline and Weeks 4, 8, and 12. The registry record does not report the group estimates, standard errors, confidence intervals, or comparison tests for these assessments. Thus, the endpoint's definition is available, but the magnitude and precision of observed changes are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary summary as a least-squares mean and its dispersion as a standard error. The specific statistical model, included covariates, assumptions, and method for comparing groups are not reported in the registry record. The endpoint description therefore supports an explanation of the reported statistical terminology, but not a reconstruction of the trial's analysis.

What does a least-squares mean represent?

In general, a least-squares mean is an estimated mean produced by a statistical model. Depending on the model, it may account for variables or structure included in that model. It is not necessarily identical to the simple arithmetic average of the observed scores. Since the registry record does not specify the model or its covariates, it is not possible to determine what adjustments were made or how they affect the estimate.

The endpoint is a change from baseline in a monthly average score. A model for repeated measurements could, in general, use data from multiple visits and account for within-participant relationships. That is a general possibility, not a description of the model used in this trial. The analysis method for repeated observations is not reported in the registry record.

What does the standard error tell the reader?

In general, a standard error describes the precision of an estimated quantity. A smaller standard error indicates less sampling uncertainty under the assumptions of the analysis; it does not mean that individual participants' scores varied less. The standard deviation, by contrast, describes variation among observed values. The registry identifies standard errors for the least-squares means, but no actual estimates or standard errors are reported in the information.

A confidence interval is generally formed from an estimate and its uncertainty, with a method that also depends on the analysis. It provides a range of values compatible with the data and model at a stated confidence level. Without an estimate, standard error, interval, or stated interval method, there is no basis for describing the precision of the trial's primary comparison.

Why do repeated time points matter?

The primary endpoint was measured at baseline and Weeks 4, 8, and 12. In general, data at more than one follow-up visit can distinguish an early pattern from a later one, but they also create choices about which time point or overall trajectory answers the main question. Testing multiple time points can increase the chance of finding at least one apparently notable result by chance if each is considered separately. Statistical approaches can address this issue, but the chosen approach and multiplicity plan are not reported in the registry record.

The registry notes that the primary outcome has several categories or time points and is not reduced to one comparison. That means there is no single primary contrast available in the record to summarize. A full interpretation would require the group estimates at the relevant visits, the comparison definitions, and the analysis plan, including how repeated measurements and multiple comparisons were handled.

What is the role of the analysis population?

The primary population is described as all randomized participants who received at least one dose of study drug and had at least one evaluable electronic-diary report after randomization. For each time point, the analysis includes participants with non-missing data. This is the registry's stated operational definition; it is not a complete description of every analysis population used in the trial.

In general, restricting a time-point analysis to participants with non-missing outcome data means the estimate at that visit depends on who contributed data. If missingness is related to outcome values, treatment experience, or other factors, the observed participants may not fully represent the randomized group. Methods such as likelihood-based analyses, imputation, or sensitivity analyses can address some missing-data concerns, but the registry record does not report whether such methods were used.

How should planning calculations be distinguished from results?

The registry describes a sample-size planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect. These are described as planning assumptions, not as a report of observed statistical power. No numerical planning estimates or observed effect values are reported in the registry record.

In general, a sample-size illustration asks how many participants might be needed under assumed conditions to detect a specified effect with a chosen power. It is conditional on the assumptions, including the effect size and analysis method. Such a calculation is not evidence that a trial had a particular probability of detecting an effect after its results were observed. The registry record does not report the original sample-size justification, so the planning illustration should not be treated as the trial's documented design rationale.

Finally, statistical significance and clinical importance are distinct concepts. A test result, even if reported, would need to be considered alongside the size and uncertainty of the effect and the interpretation of the pain scale. Since the primary-outcome estimates and tests are not reported in the registry record, none of those judgments can be made from the available information.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 24 outcome measures and 45 analyses. The primary pain outcome is assessed at baseline and Weeks 4, 8, and 12, and the record indicates that it is not reduced to one comparison. It also lists secondary outcomes involving pain, dysmenorrhea, analgesic use, and dyspareunia. With multiple outcomes, visits, and potential group contrasts, multiplicity is an important interpretive issue in general: considering many statistical tests can increase the chance of at least one apparently positive result arising by chance. The registry record does not report a multiplicity adjustment, hierarchy of outcomes, or prespecified testing sequence.

For the primary outcome, the registry defines an analysis population as randomized participants who received at least one dose and had at least one evaluable electronic-diary report following randomization. The analysis includes those with non-missing data at each time point. This describes the population used for the stated endpoint but does not establish how missing observations were handled statistically or whether other analysis populations were used.

In general, missing outcome data can affect estimates if the probability of missingness is related to the outcome or to participant characteristics. Complete-case analyses may be vulnerable to bias under some missing-data patterns, while other methods rely on their own assumptions. The registry record does not report the amount or pattern of missing primary-outcome data, imputation, sensitivity analyses, or assumptions about missingness.

The detailed statistical analysis plan, rules for selecting comparisons, and any interim analyses are not reported in the registry record. Consequently, the number of analyses alone cannot establish whether the reported analysis plan controlled false-positive risk or how results were selected for reporting.

11. 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: diabetes mellitus non-insulin-dependent (1.2%), appendicitis (1.1%), paranasal sinus benign neoplasm (1.1%).

The registry reports serious adverse events, other adverse events, and deaths by study group. For serious adverse events, the listed at-risk and affected counts are: placebo, 43 and 0; elagolix 150 mg, 85 and 1; elagolix 250 mg, 87 and 2; and leuprorelin acetate, 44 and 0. These are descriptive counts, not estimates of a treatment effect. The registry reports zero deaths in each group.

For other adverse events, the at-risk and affected counts are: placebo, 43 and 3; elagolix 150 mg, 85 and 25; elagolix 250 mg, 87 and 21; and leuprorelin acetate, 44 and 6. The record does not provide a statistical comparison of these counts. It also does not establish from these figures whether an event was caused by, or related to, study treatment.

The registry lists the serious-event terms diabetes mellitus non-insulin-dependent at 1.2%, appendicitis at 1.1%, and paranasal sinus benign neoplasm at 1.1%. The denominators or calculation details for these percentages are not reported in the registry record, so they should be read as listed rather than recalculated.

In general, safety counts need context about event definitions, observation time, severity, and attribution. The registry record does not report those details in the information. Small counts can also be imprecise; the listed numbers should not be interpreted as proof of a difference between groups.

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

The record describes a randomized Phase II study that compared elagolix with placebo and leuprorelin acetate during an initial treatment period, with follow-up treatment involving elagolix after Week 12. It defines a patient-reported pain endpoint and gives descriptive safety counts. These details clarify what the study was designed to examine and how the primary outcome was measured.

The record does not report the primary outcome estimates or a single comparison result. Therefore, it does not allow a reader to quantify the change in pain in any group, compare the groups, assess the precision of an estimated difference, or determine whether a result was statistically significant. The absence of those results in the registry record is not evidence that the treatments had equal outcomes, nor is it evidence of a benefit or lack of benefit.

In general, an observed difference is not automatically clinically important. Interpreting one requires the estimated magnitude, uncertainty, outcome context, and a suitable basis for judging what size of change matters. Those primary-outcome details are not reported in the registry record. The endpoint's numerical range alone does not establish a threshold for meaningful change.

The safety counts describe recorded events but do not establish causation. Without event definitions, attribution, detailed follow-up information, and statistical comparisons, the counts cannot support a definitive comparison of safety between groups. Zero deaths are recorded in each group, but that observation alone does not characterize the full safety profile.

The trial's enrollment, masking, treatment assignments, and outcome definitions provide design context, not a substitute for results. Any conclusion about comparative effects would require the missing outcome estimates and their analysis context. The record also does not report the statistical plan needed to assess how multiple outcomes and time points were handled.

13. Why This Trial Matters Statistically

This trial is statistically interesting because its primary outcome is a repeated, participant-reported measure rather than a single measurement at one follow-up visit. Daily electronic-diary scores were averaged over the 4 weeks before each assessment, and the primary outcome was scheduled at baseline and Weeks 4, 8, and 12. That structure raises general questions about summarizing repeated observations, defining the main comparison, and accounting for multiple time points.

The endpoint is described as a least-squares mean with standard error. These terms distinguish a model-based estimate from a simple raw average and describe the precision of that estimate. However, the model itself and the numerical estimates are not reported in the registry record. This makes the distinction between a well-defined outcome and an interpretable result especially important: a measure can be clearly specified even when the evidence needed to assess its observed effect is unavailable.

The study also includes placebo and active-control groups during the initial period, followed by re-randomization of the placebo and leuprorelin groups to elagolix. That change in treatment structure matters when considering what comparisons the later follow-up can support. The registry record does not provide later-period outcome estimates or a detailed analysis plan.

Finally, the record lists many outcomes and analyses but does not report how multiplicity was addressed. In general, prespecifying a primary comparison and explaining how related tests are handled helps readers distinguish confirmatory evidence from exploratory analyses. Here, the registry states that the primary outcome has multiple time points and is not reduced to one comparison, while the detailed statistical plan is not reported. These omissions limit the strength of any statistical interpretation, regardless of the study's design features.

14. 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 principal limitation for interpreting efficacy is that numerical primary-outcome results are not reported in the registry record. Group changes, least-squares means, standard errors, confidence intervals, and comparison tests are unavailable. Without those results, neither the direction nor the magnitude or precision of the primary contrast can be assessed.

The registry describes assessments at multiple time points but does not identify a single primary comparison in the information available. It also does not report the statistical model, covariates, repeated-measures approach, multiplicity strategy, interim analyses, or detailed analysis plan. The listed counts of outcomes and analyses cannot substitute for those methodological details.

The primary analysis population is defined using treatment receipt and availability of at least one evaluable diary report after randomization, with non-missing data required at each time point. The record does not report the number or pattern of missing observations, how missing data were handled, or whether sensitivity analyses were conducted. This limits assessment of potential bias from incomplete outcome data.

The treatment structure changes after the first 12 weeks: the placebo and leuprorelin groups are re-randomized to elagolix, while the original elagolix groups continue treatment. The later period therefore differs from the initial comparison period, and numerical results or analysis details for the later period are not reported.

Safety information is limited to group-level counts and listed serious-event terms. Definitions, attribution to treatment, event timing, and statistical comparisons are not reported in the registry record. The planning illustration is described through assumptions, but its numerical estimates and the original sample-size justification are not reported.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Efficacy and Safety Study of Elagolix Versus Placebo or Leuprorelin Acetate in Endometriosis — NCT00797225.
• Registry record last updated 2018-09-10; status last verified 2018-04.
• Results first posted 2018-09-10.
• 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.

18. Record Summary

NCT00797225 is a completed, randomized, quadruple-masked, parallel-group Phase II study of elagolix, placebo, and leuprorelin acetate for endometriosis. The registry lists enrollment of 174, a start date of 2008-11-26, and a primary completion date of 2010-02-24.

The primary outcome is change from baseline in monthly mean Numerical Rating Score for endometriosis pain, assessed at baseline and Weeks 4, 8, and 12. The registry defines the diary scale and analysis population but does not report the primary-outcome estimates or a single comparison result.

The record lists 24 outcome measures and 45 analyses. It includes descriptive serious and other adverse-event counts and reports zero deaths in each group. Detailed statistical methods, multiplicity handling, missing-data methods, and the original sample-size justification are not reported in the registry record.