Study of ALXN2050 in Adult Participants With Generalized Myasthenia Gravis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of ALXN2050 in Adult Participants With Generalized Myasthenia Gravis (NCT05218096), a randomized phase 2 study. The primary outcome is Percentage Of Participants With a Myasthenia Gravis Activities of Daily Living (MG-ADL) Total Score Reduction Of ≥ 2 Points In Any 4 Consecutive Weeks During The First 8 Weeks And Who Did Not Receive Rescue Therapy.

2. Clinical Question

The question is about reaching a prespecified symptom-score threshold over a sustained run of weeks, while also accounting for rescue therapy. It is not simply a comparison of average score change at a single visit. The endpoint therefore classifies participants according to whether they met the threshold-and-duration condition and avoided rescue therapy during the relevant period.

The registry lists an enrollment of 70 and identifies the study as Phase 2, randomized, double-blind, placebo-controlled, and multicenter. The record marks the study as terminated. The reason for termination is not reported in the registry record. The posted outcome counts and analyzed participant numbers vary by outcome, so enrollment should not be treated as the denominator for each comparison.

3. Trial Design

The registry describes a Phase 2, randomized, double-blind, placebo-controlled, multicenter study with a parallel-group model and triple masking. The study evaluated ALXN2050 in adults with generalized myasthenia gravis. The three groups were ALXN2050 180 mg twice daily, ALXN2050 120 mg twice daily, and placebo. According to the arm description, participants assigned to placebo later received ALXN2050; the timing and transition details are not reported in the registry record.

The registry lists an enrollment of 70. For the primary outcome, the posted analyzed counts are 16 in the 180 mg group, 8 in the 120 mg group, and 18 in the placebo group. These are outcome-specific counts, rather than a complete account of everyone enrolled or treated. Other outcome counts differ, and the record defines the primary-outcome population as participants who received at least one dose and were evaluable for that measure.

The primary outcome covers baseline through Week 8. The registry reports the percentage meeting the MG-ADL response definition and not receiving rescue therapy, along with 90% confidence intervals. Three secondary outcomes are posted at Week 8: change in QMG total score, change in MG-ADL total score, and change in Neuro-QoL Fatigue score. The reported continuous summaries are least-squares means with standard errors.

The study start date is 2022-04-27, and the primary completion date is 2023-11-30. The status is terminated. Allocation concealment, the randomization sequence, the exact masking roles, the reason for termination, and the original statistical and sample-size design details are not reported in the registry record. The primary-outcome analysis population is described, but comparable population and missing-data details for every posted secondary analysis are not reported.

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.

Primary Evaluation

Reasons for not completing this period:

Extended Treatment

Reasons for not completing this period:

Open-label Extension

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set: all participants who received at least 1 dose of study intervention. Here, "Overall Number of Participants Analyzed" signifies those participants who were evaluable for this outcome measure

5. Baseline Characteristics

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

Population: Full Analysis Set: all participants who received at least 1 dose of study intervention.

6. Primary Endpoint

The registry lists the primary outcome as Percentage Of Participants With a Myasthenia Gravis Activities of Daily Living (MG-ADL) Total Score Reduction Of ≥ 2 Points In Any 4 Consecutive Weeks During The First 8 Weeks And Who Did Not Receive Rescue Therapy, measured over Baseline through Week 8.

The primary endpoint is the percentage of participants whose MG-ADL total score fell by at least 2 points in any 4 consecutive weeks during the first 8 weeks and who did not receive rescue therapy. It is a responder measure: each participant either meets the full criterion or does not, and the group result is expressed as a percentage.

The MG-ADL is an 8-item participant-reported scale covering symptoms and functional performance in activities of daily living. Its items address ocular, bulbar, respiratory, and gross motor or limb impairment associated with myasthenia gravis. Each item is graded from 0, normal, to 3, most severe. The total is the sum of the item scores and ranges from 0 to 24, with higher scores indicating worse function.

A threshold-based endpoint can be useful because it asks how many participants attained a specified amount of improvement over consecutive weeks, rather than relying only on a group average. The additional condition concerning rescue therapy is part of the endpoint definition and must be retained when interpreting the response percentages. The registry does not report a separate rationale for choosing the 2-point threshold, the consecutive-week condition, or the rescue-therapy rule; those rationales are not reported in the registry record.

The primary endpoint is distinct from the secondary MG-ADL outcome, which is a mean change from baseline at Week 8. The responder percentage and the mean score change address related but different summaries of participant outcomes.

7. Results Posted in the Registry

• Group 1: ALXN2050 180 mg BID: 56.2% (9/16) versus 66.7% (12/18) on control; risk difference -10.4 percentage points (95% CI -43.1 to 22.2), risk ratio 0.84 (0.49–1.45); unadjusted two-proportion z-test p = 0.533.

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 In Quantitative Myasthenia Gravis (QMG) Total Score At Week 8

• 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:
  • Group 1: ALXN2050 180 mg BID: mean -1.10 versus -1.40 on control; difference 0.30 (95% CI -1.57 to 2.17), standardized effect d = 0.08; z-test p = 0.753.
  • Group 2: ALXN2050 120 mg BID: mean -3.00 versus -1.40 on control; difference -1.60 (95% CI -3.94 to 0.74), standardized effect d = -0.45; z-test p = 0.180.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group 1: ALXN2050 180 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group 2: ALXN2050 120 mg BID and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline In MG-ADL Total Score At Week 8

• 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:
  • Group 1: ALXN2050 180 mg BID: mean -2.50 versus -3.20 on control; difference 0.70 (95% CI -0.70 to 2.10), standardized effect d = 0.27; z-test p = 0.327.
  • Group 2: ALXN2050 120 mg BID: mean -3.70 versus -3.20 on control; difference -0.50 (95% CI -2.20 to 1.20), standardized effect d = -0.19; z-test p = 0.564.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group 1: ALXN2050 180 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group 2: ALXN2050 120 mg BID and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline In Quality Of Life In Neurological Disorders (Neuro-QoL) Fatigue Score At Week 8

• 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:
  • Group 1: ALXN2050 180 mg BID: mean -8.70 versus -8.30 on control; difference -0.40 (95% CI -7.86 to 7.06), standardized effect d = -0.03; z-test p = 0.916.
  • Group 2: ALXN2050 120 mg BID: mean -10.10 versus -8.30 on control; difference -1.80 (95% CI -10.92 to 7.32), standardized effect d = -0.13; z-test p = 0.699.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group 1: ALXN2050 180 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group 2: ALXN2050 120 mg BID and the control. The interval gives the range of effects that remain compatible with the data.

The three posted secondary outcomes cover clinician-oriented disease severity scoring, daily-activity function, and fatigue-related quality of life. Together, they broaden the outcome picture beyond the primary responder definition, which is based on an MG-ADL threshold over consecutive weeks with no rescue therapy. The secondary measures instead report least-squares mean change from baseline at Week 8.

Across the secondary comparisons, the estimates do not show a consistent pattern of separation from placebo. The unadjusted confidence intervals include zero for each posted dose-versus-placebo contrast. This overall pattern does not provide clear supporting evidence of a common difference across the secondary measures, but it also does not demonstrate that the groups are equivalent. The estimates remain imprecise, and model and missing-data details are not reported in the registry record.

The secondary outcomes are relevant context for the primary finding because they assess related aspects of gMG symptoms and functioning. They are not interchangeable with the primary endpoint: an average change at Week 8 can differ in meaning from the proportion meeting a threshold across consecutive weeks. Agreement across distinct measures can sometimes strengthen interpretation, while disagreement can raise questions about how effects vary by outcome; in this record, the posted comparisons do not establish a consistent treatment-placebo separation.

Unadjusted secondary results carry less inferential weight when several outcomes and comparisons are examined. In general, multiple testing increases the chance that at least one apparently notable result arises by chance if no adjustment or prespecified hierarchy is used. The registry does not report a multiplicity plan or sponsor analyses for these secondary measures. Their results should therefore be treated as descriptive and exploratory rather than as confirmatory evidence independent of the primary endpoint.

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

• Change From Baseline In Quantitative Myasthenia Gravis (QMG) Total Score At Week 8
• Change From Baseline In MG-ADL Total Score At Week 8
• Change From Baseline In Quality Of Life In Neurological Disorders (Neuro-QoL) Fatigue Score At Week 8

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is binary at the participant level. A participant is counted as a responder only if the MG-ADL reduction reached at least 2 points in any 4 consecutive weeks during the first 8 weeks and the participant did not receive rescue therapy. The reported group percentages summarize the fraction meeting this combined condition. This is different from comparing mean score changes, because the responder analysis focuses on crossing a specified threshold and satisfying the timing and rescue-therapy conditions.

What does the exact test compare?

The registry reports Barnard's Unconditional Exact Test for each ALXN2050 dose compared with placebo. In general, an exact test evaluates how compatible the observed allocation of binary outcomes is with a null comparison, using a probability calculation suited to categorical data. The unconditional form does not condition on the total number of responders in the two groups in the same way as some other exact tests. The registry reports the resulting group difference, 90% confidence interval, and p-value. Details of any additional adjustments or test implementation choices are not reported in the registry record.

A confidence interval describes a range of values compatible with the data under the method's assumptions; it is not a statement that the true difference has a specified probability of lying in that particular realized interval. When an interval includes zero, the data do not rule out no difference under that interval procedure. The interval may also include differences in either direction, as in these primary comparisons. The width is important: a wide interval leaves substantial uncertainty about the size and direction of the underlying difference.

How should the recalculation be understood?

The posted recalculation is a simple unadjusted comparison based on the displayed summary statistics. For the primary binary outcome, it gives a risk-difference estimate and an unadjusted p-value. It does not reproduce the registry's Barnard exact-test procedure, and it does not incorporate any unreported covariate adjustment, stratification, or analysis-plan provisions. The recalculation is therefore a descriptive cross-check, not a substitute for the sponsor's reported analysis.

The continuous secondary outcomes are posted as least-squares mean changes with standard errors. A least-squares mean is an adjusted model-based mean in general statistical usage, but the model specification and covariates used for these particular registry estimates are not reported in the registry record. The accompanying simple comparisons use differences between the posted group summaries. Their confidence intervals and p-values are unadjusted recalculations, not sponsor-reported secondary analyses. The standard errors describe the uncertainty around the posted means under the analysis that generated them; they are not the spread of individual participant scores.

Why does dispersion matter?

For a continuous outcome, a group mean can conceal substantial variation among participants. Standard errors communicate uncertainty about the estimated mean, while standard deviations describe variation among individual observations. They are not interchangeable. The recalculations use an approximate pooled standard deviation inferred from the posted standard errors and analyzed counts. That is a calculation aid, not a directly reported participant-level standard deviation, and the approximation should not be mistaken for a fitted sponsor analysis.

For binary outcomes, the observed percentage is also subject to sampling variability, especially when the analyzed groups are small. Exact procedures are one way to address inference for proportions without relying solely on a large-sample normal approximation. General statistical practice also recognizes that the precision of an estimate depends on the number of observed outcomes and the total analyzed, not just on the percentage itself.

What do the p-values say?

A p-value measures how unusual the observed data, or more extreme data, would be under a specified null model and test procedure. It is not the probability that the null hypothesis is true, and it does not measure the clinical importance of an observed difference. The registry's primary p-values are from its stated exact test; the recalculated and secondary p-values are unadjusted and should be read as exploratory descriptions of the posted summaries.

The registry does not report the original statistical analysis plan, the planned significance level for the primary outcome, a multiplicity adjustment, interim analyses, or model details. Those design and analysis features are not reported in the registry record, so they cannot be inferred from the posted p-values or from general conventions.

11. Confidence Intervals and Precision

The primary outcome confidence intervals are reported at the 90% level. For the 180 mg group, the response percentage is 57.1%, with a 90% confidence interval from 40.0% to 73.1%. For the 120 mg group, it is 57.1%, with a 90% confidence interval from 32.5% to 79.4%. For placebo, it is 64.3%, with a 90% confidence interval from 47.0% to 79.2%. Each interval covers a wide span of possible response percentages, particularly for the 120 mg group.

The registry's primary between-group intervals are also broad: -28.8 to 15.0 for 180 mg versus placebo, and -34.8 to 19.3 for 120 mg versus placebo. Both include zero and allow for differences in either direction. The intervals therefore do not pinpoint a precise between-group effect. Their breadth is consistent with the relatively small outcome-specific analyzed groups, although precision also depends on the event proportions and the interval method.

For the secondary continuous outcomes, the posted recalculated confidence intervals likewise include zero for each dose-versus-placebo comparison. This means the estimates do not precisely distinguish a nonzero difference from no difference using those unadjusted intervals. The registry reports standard errors for the least-squares means, but does not post sponsor-reported secondary comparison intervals or p-values.

Confidence intervals should be considered alongside the point estimates and analysis methods. They describe statistical uncertainty, not all sources of uncertainty: registry reporting, outcome evaluability, unreported missing-data handling, and the lack of a reported multiplicity plan also constrain interpretation. A wide interval is not evidence that the groups are equivalent; it indicates that the data are compatible with a range of effects.

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 assumptions. For these non-time-to-event outcomes, the figures represent participants per arm, not 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 the stated fraction of the observed effect. The original trial's sample-size justification and design assumptions are not reported in the registry record.

The 80% power column gives an illustrative per-arm sample size for a design that would have an 80% chance of detecting the specified effect under the planning assumptions, if that effect and those assumptions were correct. The 90% power column describes the corresponding planning target for a higher chance of detection. These are design calculations, not properties observed after the trial. This is not observed power.

The rows that use 100% of the observed effect take the observed effect as the planning target. Rows using 75% or 50% of that effect represent smaller effects to detect. Smaller effects generally require more participants to distinguish them from random variation, which is why the planning numbers rise as the target effect becomes smaller.

The values can be very large when the observed effect is small relative to the variability, as in some continuous-outcome comparisons. Such figures are sensitive to the estimated effect and variability from a small study, so they should be read as conditional illustrations rather than forecasts or recommendations. The sample-size calculations do not establish what the study was designed to detect, explain its enrollment, or provide evidence that any result was adequately powered.

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 = 0.667; treatment proportion p₁ = 0.562; average p̄ = 0.615.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6883 = 1.3490.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6843 = 0.5760.
4. n = (1.3490 + 0.5760)² / (-0.1042)² = 341.5, rounded up to 342 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 <- 0.666666666666667                          # control proportion
p1 <- 0.5625                          # 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(5218096)
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 = 342 (80% power), 457 (90% power)
 75% of observed effect: n per arm = 600 (80% power), 803 (90% power)
 50% of observed effect: n per arm = 1,332 (80% power), 1,782 (90% power)
power.prop.test: 341.5 
Simulated power at n = 342 per arm: 0.800 (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 reports the sponsor's primary comparisons using Barnard's Unconditional Exact Test. For ALXN2050 180 mg versus placebo, the reported difference is -7.1, with a 90% confidence interval from -28.8 to 15.0 and p = 0.680. For ALXN2050 120 mg versus placebo, the difference is -7.1, with a 90% confidence interval from -34.8 to 19.3 and p = 0.734.

The simple recalculation from the posted summary counts uses a different, unadjusted method. For 180 mg versus placebo, its p-value is 0.533. The recalculation is useful as a transparent descriptive check, but it is not the sponsor's exact-test analysis and should not be substituted for it. The methods do not produce identical inference, so differences between their results are not, by themselves, evidence of a data error.

The registry record does not flag a discrepancy between the posted results and recalculation. The sponsor's stated analysis remains the primary registry-reported analysis, while the recalculation is supplementary. No sponsor-reported comparisons are posted for the secondary outcomes; the secondary contrasts described in the statistical summaries are unadjusted recalculations.

The rationale for selecting Barnard's test, the full primary analysis specification, and any analysis-plan provisions beyond the reported method are not reported in the registry record. Interpretation should therefore remain tied to the results and method explicitly posted.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary endpoint and posts three secondary outcomes, but a multiplicity strategy is not reported in the registry record. It is therefore unclear whether the original plan used a testing hierarchy, adjusted significance levels, or another procedure to control the interpretation of several outcomes and dose comparisons. The posted secondary recalculations are explicitly unadjusted and should not be read as if they accounted for the number of comparisons.

The full statistical analysis plan, details of the primary model beyond the reported exact test, and any interim analyses are not reported in the registry record. The original sample-size justification is also not reported. These omissions prevent a review of whether the posted analyses correspond to prespecified choices or whether other planned analyses were conducted.

For the primary outcome, the registry describes the Full Analysis Set as participants who received at least one dose, with the analyzed number referring to those evaluable for that outcome. The record does not provide a fuller account of missing primary outcomes, reasons for non-evaluability, imputation, or sensitivity analyses. It also does not report missing-data handling for the secondary outcomes. The analyzed participant counts differ across measures, but the reasons for those differences are not reported in the registry record.

Randomization and masking are stated, but the sequence-generation method, allocation concealment, identity of masked parties, and procedures for maintaining masking are not reported. These details matter for assessing potential bias, but their absence from the registry record does not establish that the procedures were inadequate. The registry status is terminated; the reason for termination and its relationship, if any, to the posted analyses are not reported. These missing details limit evaluation of analysis choices and completeness without changing the numerical results that are posted.

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: cervical dysplasia (25.0%), myocardial infarction (7.7%), sinus arrest (7.7%), hepatic failure (7.7%), femur fracture (7.7%).

For the primary evaluation period, the registry lists serious adverse events in 1 of 28 participants in the ALXN2050 180 mg group, 1 of 14 in the 120 mg group, and 3 of 28 in the placebo group. The corresponding counts for other, non-serious adverse events are 17 of 28, 7 of 14, and 15 of 28. No deaths are listed in these primary-evaluation groups.

The registry also reports extended-treatment and open-label-extension groups separately. Serious adverse events are listed for 4 of 27 in the 180 mg group, 4 of 14 in the 120 mg group, 3 of 13 in the placebo/180 mg group, and 2 of 13 in the placebo/120 mg group. The death count is 1 in the placebo/180 mg extension group and 0 in the other listed extension groups. These groups represent different treatment periods and should not be combined into a single comparison.

These are descriptive counts, not proof that an intervention caused or prevented an event. Exposure duration, event-level details, and statistical comparisons for safety are not reported in the registry record. Serious adverse event counts should also be distinguished from all adverse events; they do not summarize the overall tolerability profile.

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

The primary result describes the proportion of analyzed participants who met a particular MG-ADL response rule during the first 8 weeks and did not receive rescue therapy. The observed percentages were 57.1% in each ALXN2050 group and 64.3% in the placebo group. The sponsor-reported comparisons have confidence intervals that include zero, and the intervals span substantial differences in both directions. The posted data therefore do not identify a precise between-group effect.

That uncertainty does not prove that the treatments have the same effect, nor does it demonstrate that either dose is beneficial or ineffective. A nonsignificant result is not an equivalence finding. Equivalence or non-inferiority would require an appropriate design, margin, and analysis; those are not reported in the registry record.

The secondary outcomes also do not resolve the uncertainty. Their unadjusted comparisons have intervals that include zero, and there is no reported multiplicity strategy. Their role is contextual rather than confirmatory. The safety counts are descriptive and should not be interpreted as causal comparisons, especially across distinct primary and extension treatment periods.

The record reports that the study was terminated, but the reason is not reported in the registry record. The posted enrollment, outcome-specific analyzed counts, and missing-data details do not provide a full account of participant flow or outcome availability. Accordingly, the results should be understood as estimates from the reported evaluable groups, with limitations in precision and reporting detail. They do not establish a treatment recommendation or settle the broader clinical question for adults with generalized myasthenia gravis.

18. Why This Trial Matters Statistically

This trial is statistically informative because it illustrates the distinction between an observed response percentage and a precise treatment-placebo comparison. The percentages alone may appear straightforward, but their confidence intervals and the between-group intervals show substantial uncertainty. Estimating a responder proportion in relatively small analyzed groups can leave a wide range of plausible values.

The endpoint also combines several requirements: a score reduction threshold, a consecutive-week condition, and no rescue therapy. That makes the endpoint clinically interpretable as a sustained response criterion, while also making the result dependent on the exact definition and outcome evaluability. It differs from the mean change outcome, so the primary and secondary measures need not tell precisely the same statistical story.

The record offers a useful contrast between sponsor-reported exact testing and simple unadjusted recalculation. Such recalculations can help readers understand the posted summary data, but they cannot recreate an unreported full analysis plan or replace the named registry analysis. The secondary outcomes further demonstrate why the number of outcomes considered matters: without a reported multiplicity strategy, secondary p-values have limited confirmatory force.

Finally, termination status and incomplete reporting of design, missing-data, and analysis details make precision and transparency central to interpretation. Those limits do not erase the reported observations, but they help define what can responsibly be concluded from them.

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 outcome-specific analyzed groups are smaller than the registry's enrollment figure, and the primary outcome analysis population is restricted to participants who received at least one dose and were evaluable. Reasons for non-evaluability and details of participant flow are not reported in the registry record. This limits assessment of whether missing outcome data could affect the comparisons.

The study is marked terminated, but the reason is not reported. The record does not report the original sample-size justification, the planned detectable effect, or the complete analysis plan. Thus, the illustrative planning figures based on observed effects should not be used to infer the study's original power or design objectives.

The primary comparisons are reported with 90% confidence intervals, and the observed intervals are broad. The secondary comparisons are unadjusted recalculations, with no sponsor-reported analysis details posted for those outcomes. A multiplicity strategy, model specifications for the least-squares means, and secondary-outcome missing-data methods are not reported.

The registry gives broad design labels, including triple masking and randomization, but does not report the random sequence method, allocation concealment, which parties were masked, or how masking was maintained. Safety summaries separate primary evaluation and extension groups, and the record does not provide exposure-adjusted comparisons. The available counts therefore should not be interpreted as comparative rates or causal effects.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study of ALXN2050 in Adult Participants With Generalized Myasthenia Gravis — NCT05218096.
• Registry record last updated 2025-01-09; status last verified 2025-01.
• Results first posted 2025-01-09.
• 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

The registry describes a randomized, double-blind, placebo-controlled, multicenter Phase 2 parallel-group study of ALXN2050 in adults with generalized myasthenia gravis. The groups received ALXN2050 180 mg twice daily, ALXN2050 120 mg twice daily, or placebo, with the placebo arm later receiving ALXN2050 according to the arm description.

The primary endpoint was the percentage meeting an MG-ADL reduction criterion during the first 8 weeks without rescue therapy. The posted response percentages were 57.1%, 57.1%, and 64.3% for the 180 mg, 120 mg, and placebo groups. The sponsor-reported comparisons had broad 90% confidence intervals that included zero. Three Week 8 secondary outcomes are also posted, but their unadjusted comparisons do not show a consistent separation from placebo.

The registry lists enrollment of 70, study status terminated, and primary completion date 2023-11-30. The reason for termination, original sample-size rationale, multiplicity plan, and detailed missing-data methods are not reported in the registry record.