A Global Phase 3 Study to Evaluate the Safety and Efficacy of Elagolix in Subjects With Moderate to Severe Endometriosis-Associated Pain: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Global Phase 3 Study to Evaluate the Safety and Efficacy of Elagolix in Subjects With Moderate to Severe Endometriosis-Associated Pain (NCT01931670), a randomized phase 3 study. The primary outcome is Percentage of Responders at Month 3 Based on Daily Assessment of Dysmenorrhea (DYS).

2. Clinical Question

The primary endpoint combines a pain-score criterion with a restriction on rescue analgesic use. This makes the endpoint a binary classification: a participant either met the full responder definition or did not. It therefore captures the proportion meeting a prespecified composite rule rather than the average change in pain score alone. The registry record also lists secondary outcomes relating to pain scales, analgesic use, and responder status at other time points. Those outcomes provide context but do not replace the Month 3 primary question.

3. Trial Design

The registry record describes NCT01931670 as a completed Phase 3 randomized, quadruple-masked, parallel-group study of elagolix in subjects with moderate to severe endometriosis-associated pain. The official title identifies the study as double-blind and placebo-controlled. The listed condition is endometriosis, and the brief description specifies adult premenopausal female subjects. AbbVie is listed as the sponsor.

There were three treatment groups: placebo twice daily, elagolix 150 mg once daily, and elagolix 200 mg twice daily. Each regimen was planned for the 6-month Treatment Period. The registry enrollment is 815. The arm-level primary outcome results include 353 participants for placebo, 221 for elagolix 150 mg QD, and 225 for elagolix 200 mg BID. These outcome-specific counts should not be treated as a complete account of randomization or follow-up for every analysis.

The study start date is 2013-09-09, the primary completion date is 2016-01-06, and its status is completed. The primary endpoint was the percentage of responders at Month 3 based on daily assessment of dysmenorrhea. The endpoint description says the dysmenorrhea scale ranged from 0, meaning none, to 3, meaning severe, and was recorded in a daily electronic diary. The study also registered outcomes at Month 3 and Month 6 involving pain ratings, dyspareunia, analgesic use, and responder status.

The allocation ratio, details of the randomization sequence, and the identities of the parties covered by quadruple masking are not reported in the registry record. Neither are the original sample-size justification, interim-analysis plan, or full statistical analysis plan. The treatment-group outcome counts and the overall enrollment are distinct registry figures with different roles; they should not be combined to infer additional participant totals.

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: The study consisted of 4 periods: a Washout Period (if applicable); a Screening Period of ≤ 100 days prior to first dose; a 6-month Treatment Period; and a Post-Treatment Follow-up Period of ≤ 12 months (if applicable). Participants were randomized into the study in a 3:2:2 ratio to placebo, elagolix 150 mg QD, or elagolix 200 mg BID, respectively.

Treatment Period

Reasons for not completing this period:

Post-Treatment Follow-Up (PTFU) Period

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The modified intent-to-treat (mITT) analysis set; all randomized participants who took at least 1 dose of randomized, double-blind study drug. Population included mITT participants who either had data during the Month 3 35-day window or who prematurely discontinued prior to or at Month 3 and met the rules for last observation carried forward.

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 Percentage of Responders at Month 3 Based on Daily Assessment of Dysmenorrhea (DYS), measured over At Month 3 of the Treatment Period.

The primary endpoint is the percentage of participants classified as responders at Month 3 based on daily assessment of dysmenorrhea, abbreviated DYS in the registry record. DYS was recorded in an electronic diary on a scale from 0 (none) to 3 (severe). To qualify as a responder, a participant had to have a reduction of -0.85 or greater from baseline in DYS pain and no increased rescue analgesic use for endometriosis-associated pain. Both conditions were part of the definition.

This endpoint is useful for asking how many participants met a specified combined threshold, rather than describing only an average change. It incorporates both the reported pain score and the use of rescue analgesics, which helps keep the responder classification tied to the study's stated rule. Because it is binary, the main descriptive result is a proportion in each treatment group, and the comparison can be expressed as a difference in responder proportions.

The responder definition depends on the chosen threshold and on the rule concerning analgesic use. It does not describe the full distribution of pain experiences, the size of each individual participant's change, or outcomes beyond the defined assessment period. A responder percentage is therefore one focused summary of the Month 3 result, not a complete account of all pain-related outcomes or the treatment period.

7. Results Posted in the Registry

• Elagolix 150 mg QD: 43.4% (96/221) versus 22.7% (80/353) on control; risk difference 20.8 percentage points (95% CI 12.9 to 28.6), risk ratio 1.92 (1.50–2.45); unadjusted two-proportion z-test p = <0.001.
• Elagolix 200 mg BID: 72.4% (163/225) versus 22.7% (80/353) on control; risk difference 49.8 percentage points (95% CI 42.5 to 57.1), risk ratio 3.20 (2.59–3.94); unadjusted two-proportion z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change From Baseline to Month 3 in Numeric Rating Scale (NRS) Scores

• 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:
  • Elagolix 150 mg QD: mean -1.90 versus -1.33 on control; difference -0.57 (95% CI -0.88 to -0.26), standardized effect d = -0.33; z-test p = <0.001.
  • Elagolix 200 mg BID: mean -2.55 versus -1.33 on control; difference -1.22 (95% CI -1.53 to -0.91), standardized effect d = -0.70; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Elagolix 150 mg QD than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Elagolix 200 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Month 6 in DYS

• 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:
  • Elagolix 150 mg QD: mean -1.06 versus -0.52 on control; difference -0.54 (95% CI -0.68 to -0.40), standardized effect d = -0.70; z-test p = <0.001.
  • Elagolix 200 mg BID: mean -1.65 versus -0.52 on control; difference -1.13 (95% CI -1.27 to -0.99), standardized effect d = -1.45; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Elagolix 150 mg QD than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Elagolix 200 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Month 6 in NMPP

• 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:
  • Elagolix 150 mg QD: mean -0.63 versus -0.48 on control; difference -0.15 (95% CI -0.26 to -0.04), standardized effect d = -0.26; z-test p = 0.008.
  • Elagolix 200 mg BID: mean -0.80 versus -0.48 on control; difference -0.32 (95% CI -0.43 to -0.21), standardized effect d = -0.54; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Elagolix 150 mg QD than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Elagolix 200 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary outcomes cover additional pain ratings, analgesic use, dyspareunia, and responder assessments at other times. The available continuous-outcome summaries include change in NRS scores at Month 3, change in DYS at Month 6, and change in NMPP at Month 6. Across these outcomes, the reported group estimates generally show larger decreases from baseline in the elagolix groups than in the placebo group, with differences between the two elagolix regimens also visible in the posted estimates. These summaries add context to the primary Month 3 responder result but measure different outcomes or use different scales and time points.

The registry lists 31 outcome measures and 218 analyses, and 29 secondary outcomes are posted. This breadth means that findings should be considered as a pattern across related measures rather than as a collection of isolated p values. The secondary measures can provide corroborating context when their direction is coherent with the primary endpoint, but they do not independently redefine the primary responder result. Some outcomes measure average change, others concern analgesic use or symptoms, and their scales and analysis populations are not interchangeable.

Multiplicity arises when many hypotheses are tested. Even if each test uses a conventional significance threshold, conducting many tests increases the chance that some results appear statistically notable by chance. The registry record does not report whether the secondary analyses were adjusted for multiplicity, how any testing hierarchy was defined, or which secondary outcomes were intended to support confirmatory claims. Consequently, unadjusted secondary p values carry less evidential weight than a prespecified primary comparison interpreted within its stated analysis plan. The exact study plan is not reported in the registry record.

The secondary findings should also be interpreted with attention to different analysis counts, model methods, and time points. Recalculated comparisons from aggregate summaries are approximate and do not reproduce the reported mixed-effects models. A broad directional pattern can be described, but it does not establish that every secondary outcome has the same certainty or importance as the primary result.

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

• Change From Baseline to Month 3 in Numeric Rating Scale (NRS) Scores
• Change From Baseline to Month 6 in DYS
• Change From Baseline to Month 6 in NMPP
• Change From Baseline to Month 3 in Analgesic Use Across Both Classes of Rescue Analgesics
• Change From Baseline to Month 6 in Analgesic Use Across Both Classes of Rescue Analgesics
• Change From Baseline to Month 3 in Dyspareunia (DYSP)
• Change From Baseline to Month 3 in Use of Narcotic Class of Medication (Opioids)
• Percentage of Responders for Each Month, Except Month 3, in DYS

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is binary because each participant is classified as either meeting or not meeting the Month 3 responder definition. For each group, the reported percentage describes the fraction classified as responders. A comparison of two such proportions can be expressed in several ways. The recalculated comparison used is a risk difference: the absolute difference between the two group proportions on the calculation scale. It retains the direction of the contrast and is directly connected to the question of how much the proportion differs between groups.

The unadjusted risk-difference calculation uses the posted responder counts and outcome denominators. It does not incorporate covariate adjustment or reproduce the model-based sponsor analysis. For the 150 mg QD comparison, the posted data used in the recalculation are 80 responders among 353 placebo participants and 96 among 221 elagolix participants. For the 200 mg BID comparison, they are 80 among 353 and 163 among 225. The corresponding recalculated risk differences and intervals are stated with the primary results. These are simple summary-statistic recalculations, not replacements for the sponsor's prespecified or adjusted analysis.

The registry record reports logistic regression for each primary comparison and labels both as superiority analyses. Logistic regression models the relationship between treatment group and a binary outcome on a log-odds scale. A model-based analysis can differ from a crude comparison of proportions, particularly when model terms or analysis-population handling differ. The registry record does not give the full model specification, covariates, or detailed treatment of missing observations. The sponsor's reported p values should therefore be distinguished from recalculated p values based directly on summary counts.

What does a confidence interval describe?

A confidence interval is an uncertainty range around an estimate, constructed using a specified statistical procedure. In repeated use of that procedure under its assumptions, intervals are intended to reflect the uncertainty associated with sampling variation. A narrower interval indicates greater precision on the stated scale; a wider interval indicates less precision. An interval does not show the distribution of individual participant outcomes and does not guarantee that the true effect lies within its particular bounds.

The recalculated intervals for the primary risk differences are based on the unadjusted summaries. The registry record does not state the confidence level for those recalculated intervals, and the sponsor's posted primary analyses do not include interval bounds. The estimates and intervals should be interpreted on the risk-difference scale, not as odds ratios or relative risks. Those other scales can give different numerical descriptions of the same binary-outcome comparison.

Why do analysis populations matter?

The primary endpoint description names a modified intent-to-treat population. It includes randomized participants who took at least one dose of randomized, double-blind study drug and either had data during the Month 3 35-day window or prematurely discontinued prior to or at Month 3 and met the stated criteria. The registry record cuts off before the full criteria are given, so the complete definition is not reported in the registry record. This is not identical, by definition, to every randomized participant. The outcome counts for the endpoint also differ from the overall enrollment and should be understood as analysis-specific.

Missing data can affect a binary responder endpoint because a participant without an evaluable assessment cannot automatically be classified in the same way as someone with a recorded outcome. The registry record does not report the full missing-data method, assumptions about missing outcomes, or sensitivity analyses. It is therefore not possible to assess from the registry entry alone how alternative missing-data assumptions might affect the result.

What do the p values say?

A p value describes how incompatible the observed data are with a specified null hypothesis under the statistical model and its assumptions. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of an effect. The sponsor's primary analyses report p < 0.001 for each comparison. The recalculated unadjusted p values are also <0.001. The stated statistical methods and the populations being analyzed remain important to interpretation.

For continuous secondary outcomes, the registry reports least-squares mean changes and standard errors, with comparisons from mixed-effects models. A least-squares mean is a model-based mean, and a standard error describes the estimated uncertainty in that mean. The recalculated secondary contrasts use the posted summary values and are approximate unadjusted comparisons. They do not reproduce the mixed-effects models, which may account for the study's repeated measurement structure in ways the summary-statistic recalculations cannot capture.

General statistical principle: over-dispersion arises when observed variability is greater than a model's assumed variability. For binary data, a model that fails to accommodate extra variation may produce uncertainty estimates that are too small. The registry record does not state that over-dispersion was assessed or that it was present in this trial. This general point is not a claim about the trial's analysis.

11. Confidence Intervals and Precision

The recalculated primary comparisons include interval estimates around the unadjusted risk differences. For elagolix 150 mg QD versus placebo, the estimate is 0.208 and the interval extends from 0.129 to 0.286. For elagolix 200 mg BID versus placebo, the estimate is 0.498 and the interval extends from 0.425 to 0.571. The registry record does not state the confidence level for these recalculated intervals. The sponsor's logistic-regression results report p values but do not give interval bounds in the registry entry.

An interval communicates precision on the scale of the estimate. Its bounds describe values compatible with the recalculation procedure and its assumptions, rather than a range containing individual participant outcomes. The placement and width of an interval should be considered alongside the point estimate and the analysis method. These unadjusted intervals cannot be treated as intervals from the sponsor's logistic-regression model.

The observed outcome counts differ between the placebo and elagolix groups, and the analyzed population varies across endpoints. In general, the amount of information and the variability in the outcome contribute to precision. The posted primary interval estimates are relatively separated from zero on the risk-difference scale, but that statistical feature does not by itself establish the clinical importance of the contrast or resolve limitations in the analysis population and missing-data description.

The registry record does not report interval bounds for the sponsor's primary comparisons, nor does it provide the full model details needed to reconstruct them. It also does not report a multiplicity-adjusted confidence procedure for the many registered analyses. The interval estimates should therefore be regarded as unadjusted recalculations for the specified binary comparisons, with their scope kept distinct from the full registry analysis.

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 use the observed effect as a starting point and show planning figures for detecting the full observed effect, 75% of the observed effect, or 50% of the observed effect. For the outcomes in this study, the figures are participants per arm, not total events. They are not the trial's original design calculations. The registry record does not report the original sample-size justification or the assumptions used to plan enrollment.

The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The target effect is the stated fraction of the observed effect. Under these assumptions, the 80% power column gives the illustrative number of participants per arm for an 80% chance of detecting the specified effect if that effect and the assumptions apply. The 90% power column gives the corresponding number per arm for a 90% chance. These are design-planning concepts, not guarantees about results in a future study.

Smaller effects require more participants to detect under otherwise unchanged assumptions. Thus, planning for 75% or 50% of an observed effect generally gives larger participant requirements than planning for the full observed effect. The full observed effect may be an optimistic planning target because an estimate from one trial is subject to sampling variation. The figures are illustrations derived from the posted results, not evidence that the original trial was designed using these calculations.

This is not observed power. Observed power is not an appropriate substitute for interpreting the estimated effect and its uncertainty after a study has been completed. The planning figures instead answer a hypothetical design question: what group size would be indicated under the listed assumptions for a chosen effect size and target power? They do not alter the interpretation of the posted outcome data.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.227; treatment proportion p₁ = 0.434; average p̄ = 0.331.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6652 = 1.3038.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6488 = 0.5461.
4. n = (1.3038 + 0.5461)² / (0.2078)² = 79.3, rounded up to 80 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
p0 <- 0.226628895184136                          # control proportion
p1 <- 0.434389140271493                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1931670)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 80 (80% power), 106 (90% power)
 75% of observed effect: n per arm = 136 (80% power), 182 (90% power)
 50% of observed effect: n per arm = 292 (80% power), 390 (90% power)
power.prop.test: 79.3 
Simulated power at n = 80 per arm: 0.809 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The registry record reports superiority analyses for both primary comparisons using logistic regression. The sponsor-reported p value is < 0.001 for elagolix 150 mg QD versus placebo and < 0.001 for elagolix 200 mg BID versus placebo. The recalculated unadjusted binary comparisons also give p values of <0.001 for both contrasts. The unadjusted estimates and intervals are based on posted group-level counts and are not the same as model-based results.

The registry record does not provide the full logistic-regression specification or interval estimates for the sponsor analyses. The recalculation therefore serves as a transparent, simple comparison of the posted proportions; it cannot establish what the sponsor's adjusted model would produce under a different specification. For the primary endpoint, the two approaches point in the same broad direction and have the same displayed significance threshold, while their methods and reporting detail differ.

For continuous secondary outcomes, sponsor analyses use mixed-effects models, whereas the recalculations use posted least-squares means and standard errors to form approximate, unadjusted contrasts. The reported and recalculated p values are not identical for every endpoint. For example, the NMPP comparison for elagolix 150 mg QD has a recalculated p value of 0.008 and a sponsor-reported p value of 0.009. The sponsor's model-based results are the study's reported analyses; recalculated values provide supplementary context rather than a replacement.

15. Multiplicity, Missing Data and Analysis Populations

The registry record contains many outcomes and analyses: 31 outcome measures, 218 analyses, and 29 posted secondary outcomes. The primary endpoint is identified separately, but the record does not report a detailed multiplicity strategy, a testing hierarchy, or whether secondary p values were adjusted. Without those details, secondary statistical findings should be interpreted cautiously. A set of tests can yield apparently notable results by chance even when each analysis is considered separately.

The primary analysis population is described as modified intent-to-treat. It includes randomized participants who took at least one dose of randomized, double-blind study drug and either had data in the Month 3 35-day window or prematurely discontinued prior to or at Month 3 and met the stated criteria. The registry description ends before the full criteria are given. The exact remaining eligibility conditions for this population are not reported in the registry record.

The record does not report how missing Month 3 data were handled, whether any imputation was used, or what assumptions were made for participants without evaluable outcomes. It also does not report sensitivity analyses exploring other missing-data assumptions. Those omissions matter because the primary endpoint requires a responder classification based on assessment data and rescue analgesic use. The published group counts and percentages alone cannot reveal the impact of unobserved outcomes.

Analysis counts vary across endpoints. For example, the primary outcome counts and the continuous secondary outcome counts are not identical, reflecting endpoint-specific available data or populations. The registry record does not explain every difference in those counts. No inference about reasons for missingness, protocol deviations, or exclusions should be made without the full report. The original sample-size rationale, interim-analysis plan, and complete statistical analysis plan are also not reported in the registry record.

16. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: abdominal pain (0.9%), back pain (0.9%), endometriosis (0.9%), uterine polyp (0.9%), appendicitis (0.9%).

The registry safety summary lists serious adverse events for groups with 360 participants at risk in placebo, 226 in elagolix 150 mg QD, and 229 in elagolix 200 mg BID. The numbers affected were 12, 12, and 5, respectively. Deaths listed were 0 for placebo, 1 for elagolix 150 mg QD, and 0 for elagolix 200 mg BID. These are group-level counts in the registry safety record; they do not describe the cause, timing, duration, or individual circumstances of events.

The most frequent serious-event terms listed include abdominal pain, back pain, endometriosis, and uterine polyp, each at 0.9%, followed by appendicitis at 0.9% and abortion spontaneous complete at 0.6%. These terms are registry-coded event descriptions. The record does not provide enough detail in this summary to attribute any event to treatment or to determine clinical relatedness.

Serious adverse event counts should be read separately from the other adverse-event counts and from the primary efficacy result. Differences in counts alone do not establish comparative safety, and small counts can be imprecise. A complete safety interpretation would require fuller information about event definitions, follow-up, exposure, severity, relatedness, and statistical comparisons; those details are not reported in the registry record summary.

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

The posted primary result describes the proportion of participants meeting a particular Month 3 dysmenorrhea responder rule in each group. The percentages are 22.7 for placebo, 43.4 for elagolix 150 mg QD, and 72.4 for elagolix 200 mg BID. The sponsor's logistic-regression analyses report superiority for both elagolix comparisons against placebo, with p < 0.001. The unadjusted recalculations also yield p values below 0.001 and provide risk-difference estimates with interval bounds.

This finding does not mean that every participant in an elagolix group was a responder, or that every participant experienced the same change. Nor does it describe outcomes outside the definition, such as all dimensions of pain, long-term outcomes, or effects beyond the 6-month Treatment Period. A group-level responder proportion is not a prediction of an individual's outcome.

The primary endpoint depends on its operational threshold: a reduction of -0.85 or greater from baseline and no increased rescue analgesic use. Different responder definitions could classify participants differently. The endpoint also focuses on Month 3; it should not be conflated with the registered Month 6 DYS outcome or with other pain measures.

Statistical significance does not by itself establish the magnitude of benefit that matters to patients, nor does it resolve the limitations of the registry's incomplete reporting of the analysis plan, missing-data methods, or interval confidence level. The primary result is evidence about the study's defined comparisons under the reported analyses, not proof of a universal effect in every population or setting. The record alone also does not provide a full benefit-risk assessment. Interpretation of safety requires more detail than the listed counts, and no treatment recommendation follows from these statistics.

18. Why This Trial Matters Statistically

This trial illustrates how a clinical endpoint can combine a symptom score with a treatment-use condition. The primary result is not simply a change in a pain scale: responder status requires both the stated DYS reduction and no increase in rescue analgesic use. That distinction affects what the percentages mean and which participants are classified as responders.

It also shows why analysts should distinguish a model-based sponsor analysis from a recalculation using aggregate results. The registry reports logistic regression for the primary binary outcome, while the recalculated risk differences offer an accessible absolute-scale description. These analyses can be informative together, but they are not interchangeable. The model specification, analysis population, and handling of missing data remain important for interpreting the reported evidence.

The primary outcome sits within a broader registry record with many outcomes and analyses. Secondary measures can help assess whether the overall pattern is coherent, but multiplicity and incomplete reporting of adjustment plans limit how much weight should be placed on individual secondary p values. Statistical interpretation depends not only on whether a p value crosses a threshold, but also on the precision, scale, endpoint definition, and context of the comparison.

Finally, the planning illustrations demonstrate the sensitivity of sample-size requirements to the effect size chosen for design. Planning around a smaller fraction of an observed effect requires more participants per arm under the stated assumptions. These calculations are hypothetical illustrations and are not evidence of the trial's original design rationale or observed power. Together, these features make the study a useful example of separating endpoint definition, primary inference, supplementary analyses, and planning assumptions.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The registry entry does not include the full statistical analysis plan, original sample-size justification, randomization details, allocation ratio, or a detailed description of the parties included in quadruple masking. The model specification for the sponsor's primary logistic-regression analyses is not reported. The exact confidence level for the recalculated intervals is also not stated in the registry record.

The modified intent-to-treat population definition is incomplete in the registry description, which ends before the full Month 3 conditions are given. Missing-data handling, imputation, sensitivity analyses, and assumptions about participants without evaluable outcomes are not reported. These omissions limit assessment of how analysis-population choices and missing observations might affect the primary results.

The registry lists many outcomes and analyses, but does not report a multiplicity plan or whether secondary tests were adjusted. The posted secondary outcomes cover different measures, time points, and analysis counts. Their results should not be treated as equivalent in evidential status or as a single confirmatory test family without additional information.

The safety summary gives group counts and selected event terms, but the record excerpt does not provide the full event narratives, timing, severity, treatment relatedness, exposure-adjusted rates, or comparative safety analyses. Counts should not be used alone to establish causal attribution. Finally, the results relate to the study population, regimens, and 6-month Treatment Period recorded in the registry; the entry does not establish how results generalize beyond those conditions.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Global Phase 3 Study to Evaluate the Safety and Efficacy of Elagolix in Subjects With Moderate to Severe Endometriosis-Associated Pain — NCT01931670.
• Registry record last updated 2018-09-07; status last verified 2018-03.
• Results first posted 2018-09-07.
• 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

NCT01931670 is a completed randomized, quadruple-masked, parallel-group Phase 3 study sponsored by AbbVie. It compared placebo with elagolix 150 mg QD and elagolix 200 mg BID over the 6-month Treatment Period in subjects with moderate to severe endometriosis-associated pain. The primary endpoint was the Month 3 percentage meeting a combined dysmenorrhea and rescue-analgesic responder definition.

The posted primary responder percentages were 22.7 for placebo, 43.4 for elagolix 150 mg QD, and 72.4 for elagolix 200 mg BID. The sponsor reported logistic-regression superiority analyses with p < 0.001 for both comparisons. Recalculated unadjusted risk differences provide additional absolute-scale estimates, but do not replace the sponsor analyses. The registry also reports secondary pain and analgesic outcomes and a safety summary. Multiplicity procedures, complete missing-data methods, the full analysis plan, and the original sample-size rationale are not reported in the registry record.