Safety and Efficacy Study of RA101495 in Subjects With Generalized Myasthenia Gravis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy Study of RA101495 in Subjects With Generalized Myasthenia Gravis (NCT03315130), a randomized phase 2 study. The primary outcome is Main Portion: Change From Baseline to Week 12 in Quantitative Myasthenia Gravis (QMG) Score.

2. Clinical Question

3. Trial Design

This was a phase 2, multicenter, randomized, double-blind, placebo-controlled, parallel-group study. The registry record lists an enrollment of 45 and describes daily subcutaneous doses of RA101495 at 0.1 mg/kg or 0.3 mg/kg, or matching placebo, for 12 weeks. The planned allocation was 1:1:1. The study status is completed. The registry record lists a start date of 2017-10-11 and primary completion on 2018-12-10.

The primary outcome was change from baseline to Week 12 in the QMG score. The primary analysis population was the modified intention-to-treat population: participants in the intention-to-treat population who received at least one dose of study drug. The posted group sizes for this outcome were 15 in the 0.1 mg/kg group, 14 in the 0.3 mg/kg group, and 15 in the placebo group. These outcome-specific counts need not equal the overall enrollment because they describe the participants included in the posted analysis.

The registry record lists 13 outcome measures and 12 posted analyses. The listed secondary outcomes include changes in MG-ADL, MG-QOL15r, and MG Composite Scale scores; the proportion with at least a 3-point reduction in QMG score; rescue therapy; adverse and serious adverse events; and laboratory measures. The details of all those outcomes are not reported in the registry record. The exact randomization method, allocation concealment procedures, study-site count, treatment adherence, and details of the blinding process are also not reported in the registry record. The original design's sample-size justification and planned analysis details beyond the posted descriptions are not reported in the registry record.

4. Participant Flow and Accounting

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

Before assignment: The Participant flow refers to the Intent-to-treat Set for the main portion and Safety Set for the extension portion.

Main Portion (12 Weeks)

Reasons for not completing this period:

EP:Before Switch to 0.3 mg/kg(Week13-48)

Reasons for not completing this period:

EP:After Switch to 0.3 mg/kg(Week48-122)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The modified ITT (mITT) population included all participants in the ITT population who had received at least 1 dose of study drug.

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: Intent-to-Treat (ITT) population included all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Main Portion: Change From Baseline to Week 12 in Quantitative Myasthenia Gravis (QMG) Score, measured over From Baseline to Week 12.

The primary endpoint is change from baseline to Week 12 in the Quantitative Myasthenia Gravis score. The registry record describes QMG as a standardized and validated quantitative strength scoring system developed specifically for myasthenia gravis. It consists of 13 individual assessments, each scored from 0 to 3, with 0 representing none and 3 representing severe. The total is the sum of those assessments and ranges from 0 to 39. Higher scores represent more severe impairment.

Change from baseline describes how the score at the follow-up point differs from the participant's starting score. A negative change represents a lower score at Week 12 than at baseline. Comparing the mean changes between each dose group and placebo provides a way to describe the difference in average change during the study period. It does not, by itself, show how individual participants responded, whether the average difference is clinically important, or whether it persists beyond Week 12.

The posted arm values are least-squares means, with standard errors as the dispersion measure. The endpoint is relevant to the stated study question because it quantifies disease-related impairment using a measure developed for myasthenia gravis. The registry record does not report a threshold for a clinically important QMG change or a separate responder definition for the primary endpoint.

7. Results Posted in the Registry

• RA101495 0.1 mg/kg (mITT): mean -5.50 versus -3.20 on control; difference -2.30 (95% CI -5.63 to 1.03), standardized effect d = -0.49; z-test p = 0.175.
• RA101495 0.3 mg/kg (mITT): mean -6.00 versus -3.20 on control; difference -2.80 (95% CI -6.13 to 0.53), standardized effect d = -0.61; z-test p = 0.099.

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.

Main Portion: Change From Baseline to Week 12 in the Myasthenia Gravis - Activities of Daily Living (MG-ADL) Scale

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • RA101495 0.1 mg/kg (mITT): mean -3.30 versus -1.10 on control; difference -2.20 (95% CI -4.69 to 0.29), standardized effect d = -0.63; z-test p = 0.084.
  • RA101495 0.3 mg/kg (mITT): mean -3.40 versus -1.10 on control; difference -2.30 (95% CI -4.79 to 0.19), standardized effect d = -0.67; z-test p = 0.071.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between RA101495 0.1 mg/kg (mITT) 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 RA101495 0.3 mg/kg (mITT) and the control. The interval gives the range of effects that remain compatible with the data.

Main Portion: Change From Baseline to Week 12 in the Myasthenia Gravis - Quality of Life 15r (MG-QOL15r) Survey

• 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:
  • RA101495 0.1 mg/kg (mITT): mean -7.40 versus -2.10 on control; difference -5.30 (95% CI -10.01 to -0.59), standardized effect d = -0.80; z-test p = 0.027.
  • RA101495 0.3 mg/kg (mITT): mean -5.90 versus -2.10 on control; difference -3.80 (95% CI -8.51 to 0.91), standardized effect d = -0.59; z-test p = 0.114.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for RA101495 0.1 mg/kg (mITT) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between RA101495 0.3 mg/kg (mITT) and the control. The interval gives the range of effects that remain compatible with the data.

Main Portion: Change From Baseline to Week 12 in the MG Composite Scale Total Score

• 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:
  • RA101495 0.1 mg/kg (mITT): mean -5.30 versus -3.30 on control; difference -2.00 (95% CI -6.30 to 2.30), standardized effect d = -0.33; z-test p = 0.362.
  • RA101495 0.3 mg/kg (mITT): mean -7.40 versus -3.30 on control; difference -4.10 (95% CI -8.53 to 0.33), standardized effect d = -0.67; z-test p = 0.070.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between RA101495 0.1 mg/kg (mITT) 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 RA101495 0.3 mg/kg (mITT) and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary outcomes cover several kinds of information: daily functioning, quality of life, a composite measure, a QMG responder definition, rescue therapy, adverse events, and laboratory measures. Of the continuous secondary measures with detailed numerical results in the registry record, the displayed group means generally move downward from baseline in active-treatment and placebo groups. The size and pattern of the dose-versus-placebo estimates vary across measures. This broad pattern gives context to the primary QMG result, but it does not independently confirm or overturn it.

The detailed secondary results for MG-ADL, MG-QOL15r, and MG Composite Scale include sponsor-reported ANCOVA contrasts and recalculated unadjusted comparisons. Those findings are estimates for distinct scales and should be interpreted according to each measure's definition and analysis. The registry record names additional secondary outcomes, including the QMG responder threshold, rescue therapy, and laboratory measures, but does not report numerical results for all listed measures in the information available. Their results cannot be inferred from the continuous outcomes.

Secondary endpoints are often considered supportive or exploratory, particularly in a phase 2 study. When many outcomes and comparisons are examined, some apparently notable results can arise by chance. In general, multiplicity adjustment controls the increased chance of false-positive findings across a collection of tests. Whether the sponsor applied a multiplicity procedure to these secondary analyses is not reported in the registry record. Their p-values should therefore carry less weight than a prespecified primary analysis, and should not be treated as stand-alone proof of a consistent effect across domains. The registry record also does not report a hierarchy of secondary outcomes or which analyses were designated confirmatory.

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

• Main Portion: Change From Baseline to Week 12 in the Myasthenia Gravis - Activities of Daily Living (MG-ADL) Scale
• Main Portion: Change From Baseline to Week 12 in the Myasthenia Gravis - Quality of Life 15r (MG-QOL15r) Survey
• Main Portion: Change From Baseline to Week 12 in the MG Composite Scale Total Score
• Main Portion: Percentage of Participants With >= 3-point Reduction in QMG Total Score at Week 12
• Main Portion: Percentage of Participants Who Required Rescue Therapy Over the 12-week Treatment Period
• Main Portion: Number of Participants With Adverse Events (AEs) and Serious Adverse Events (SAEs)
• Main Portion: Change From Baseline in Sheep Red Blood Cell (sRBC) Lysis Assay at Week 12 (Pre-dose)
• Main Portion: Change From Baseline in C5 Levels at Week 12 (Pre-dose)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: it is a score measured on a scale, and the posted arm summaries are least-squares means with standard errors. A mean describes the group average, while a standard error describes the precision of that estimated average. A smaller standard error generally corresponds to a more precise estimate, but precision also depends on the number of participants and variability in the outcome. Standard errors are not the same as the spread of individual participant scores.

What does the ANCOVA estimate represent?

The registry record identifies the sponsor's primary comparisons as ANCOVA and reports least-squares mean differences. In general, analysis of covariance estimates group differences while accounting for one or more covariates in a statistical model. The posted least-squares mean difference is the model-based contrast between a dose group and placebo. The full set of covariates, model assumptions, handling of missing observations, and other implementation details are not reported in the registry record, so the model cannot be reconstructed from these summaries alone.

The recalculated contrasts use the posted arm means and standard errors to produce simple unadjusted comparisons. In general, an unadjusted contrast does not account for baseline or other covariates in the way an ANCOVA may. The recalculated standard deviations are approximate, as indicated in the calculation details, rather than direct summaries of participant-level variability. These recalculations can help readers compare an unadjusted estimate with the reported adjusted estimate, but they do not reproduce the sponsor's model.

How should a p-value be read?

In general, a p-value describes how compatible the observed data are with a specified null model, under the assumptions used for the analysis. It does not give the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The registry record gives sponsor p-values for the ANCOVA comparisons and separate unadjusted p-values for the recalculated comparisons. They arise from different analyses and should not be treated as interchangeable. The sponsor-reported primary p-values are =0.094 and =0.054; the unadjusted recalculated values are 0.175 and 0.099.

The registry record labels the sponsor comparisons as superiority analyses. That label identifies the direction and type of comparison, not a guarantee that an effect has been established. Interpretation should also consider the estimated contrasts, their intervals, the limited group sizes, the analysis population, and the uncertainty about multiplicity and missing data. The record does not report whether any decision threshold was prespecified for the primary outcome.

Why do intervals matter?

In general, a confidence interval gives a range of values compatible with the data and the method used to construct it. A wider interval indicates less precision. An interval that includes zero for a difference is compatible with no difference under that interval's construction; an interval excluding zero does not by itself establish clinical importance. The sponsor's intervals are explicitly reported at the 80% level. The confidence level of the recalculated intervals is not stated in the registry record and should not be inferred from the values alone.

What does the allocation imply?

The planned 1:1:1 allocation indicates that participants were intended to be assigned among two dose groups and placebo in equal proportions. The analyzed QMG groups contain 15, 14, and 15 participants, respectively. Randomization is generally used to reduce systematic differences between assigned groups, but it does not guarantee that all baseline characteristics are balanced, especially in a small study. Baseline characteristics and the randomization implementation details are not reported in the registry record.

The mITT definition excludes participants who did not receive any study drug, according to the registry description. The precise handling of participants without a Week 12 measure, missed visits, rescue therapy, or treatment discontinuation is not reported in the registry record. Those details matter because missing outcomes or post-randomization events can affect which observations contribute to an analysis and how estimates should be interpreted.

Why can over-dispersion matter?

In general, over-dispersion means that observed variability is greater than a model expects. It can make standard errors too small if the analysis assumes less variability than the data contain, which can make intervals appear narrower and tests appear more decisive than they should. The primary endpoint is continuous, and the posted summaries give standard errors. The registry record does not identify an over-dispersion issue for this analysis; this is a general statistical consideration, not a reported finding from this study.

More broadly, the registry record identifies the outcome, analysis population, summary measures, and sponsor method, but does not report the complete statistical analysis plan. Choices such as covariate adjustment, missing-data handling, multiplicity control, or sensitivity analyses can affect inference. Any account of such choices beyond the posted information would be speculative, so they remain unknown.

11. Confidence Intervals and Precision

Precision is conveyed by the intervals around the estimated contrasts, not by the point estimate alone. The sponsor's ANCOVA estimate for 0.1 mg/kg was -2.3, with an 80% confidence interval from -4.5 to -0.1. For 0.3 mg/kg, the estimate was -2.8, with an 80% confidence interval from -5.1 to -0.6. These intervals are relatively broad in relation to the estimates, leaving uncertainty about the size of the contrast. Both sponsor-reported intervals lie below zero, but the registry record does not provide a clinically important difference threshold with which to judge their practical meaning.

The unadjusted recalculated contrasts were -2.3, with an interval from -5.626 to 1.026, and -2.8, with an interval from -6.126 to 0.526. The recalculated intervals include zero. They are based on posted summary statistics and approximate standard deviations, and the registry record does not state their confidence level. They therefore should not be read as the same inferential result as the sponsor's 80% ANCOVA intervals.

In general, a confidence interval represents uncertainty under a particular model and method; it is not a guarantee that the true value lies within that specific realized interval. Wide intervals indicate that the data are compatible with a range of effect sizes. Small groups can produce imprecise estimates, and the primary endpoint analysis included 15, 14, and 15 participants in the three groups. Precision is also affected by variability and analytic choices, not sample size alone. The intervals do not resolve questions about clinical importance, durability beyond Week 12, or generalizability beyond the study population.

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 participants per arm for comparisons of two groups; they are not total event counts. They are illustrations derived from the observed effect, not the trial's original sample-size design. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers detecting the stated fraction of the observed effect. For example, planning for 75% of the observed effect means assuming a smaller effect than the observed estimate when considering a future study.

The 80% power column gives the number of participants per arm in a planning calculation designed to have an 80% chance of detecting the assumed effect under the stated assumptions. The 90% power column gives the per-arm number for a higher planned chance of detecting that same assumed effect. These are design targets, not probabilities that the results of the completed study are correct or that a treatment effect exists. The figures are not observed power.

Smaller effects are harder to distinguish from random variation under the same assumptions, so planning for a smaller fraction of the observed effect requires more participants per arm. The display includes planning scenarios based on 100%, 75%, and 50% of the observed effect. Because the calculations start from effects observed in a small phase 2 study, the assumed effect for planning may not represent the effect in a future study. The original sample-size justification, intended power, and design assumptions for this trial are not reported in the registry record. These illustrations should not be mistaken for those original protocol decisions or as a recommendation for a future study size.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -2.300; pooled standard deviation σ = 4.648.
2. n = 2 × (1.96 + 0.842)² × 4.648² / -2.300² = 64.1, rounded up to 65 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -2.3                      # observed difference in means
sigma <- 4.6475800154489                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(3315130)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 65 (80% power), 86 (90% power)
 75% of observed effect: n per arm = 114 (80% power), 153 (90% power)
 50% of observed effect: n per arm = 257 (80% power), 344 (90% power)
power.t.test: 65.1 
Simulated power at n = 65 per arm: 0.798 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor's primary outcome comparisons use ANCOVA and are reported as least-squares mean differences with 80% confidence intervals. The registry record reports an estimate of -2.3 for 0.1 mg/kg versus placebo and -2.8 for 0.3 mg/kg versus placebo. The accompanying p-values are =0.094 and =0.054. These are the analyses identified in the registry as the sponsor-reported comparisons.

The simple recalculations use the posted group summary statistics to estimate unadjusted mean differences. They reproduce the displayed differences of -2.3 and -2.8, but their intervals and p-values differ from the ANCOVA results. The recalculated intervals are -5.626 to 1.026 and -6.126 to 0.526, and the unadjusted p-values are 0.175 and 0.099. This difference is expected to be possible when a model-adjusted analysis is compared with a simple unadjusted calculation, particularly when the full model details and participant-level data are unavailable.

The registry does not flag a discrepancy between the analyses. The recalculations are useful as a transparent comparison based on posted summaries, but they do not replace the sponsor's adjusted analysis or permit a reconstruction of its covariates and assumptions. The sponsor's own estimates should therefore be read as the primary reported analysis, while the recalculations show how a simpler summary-statistic comparison looks.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates multiple outcomes, doses, time points, or contrasts. In general, the more statistical tests considered, the greater the chance that at least one result appears notable by chance if each test is interpreted separately. This trial has a primary QMG outcome, two dose-versus-placebo comparisons, and numerous secondary outcomes. The registry record lists 13 outcome measures and 12 analyses. It does not report whether the primary dose comparisons or secondary analyses were adjusted for multiplicity, whether a testing hierarchy was prespecified, or how the primary comparison was intended to control the family-wise error rate.

Missing data can also affect the analysis. The stated mITT population included participants in the intention-to-treat population who received at least one dose of study drug, and the posted group sizes were 15, 14, and 15. The registry record does not report the number of participants with missing Week 12 QMG measurements, how missing values were handled, or whether sensitivity analyses assessed the impact of missingness. It also does not report how discontinuation, rescue therapy, or other events during the study were incorporated into the primary analysis. Without these details, the effect of missing observations on the estimates cannot be assessed.

Different analysis populations can answer different questions. The mITT definition excludes those who did not receive any study drug, whereas an intention-to-treat analysis generally retains randomized participants in their assigned groups. The registry record does not provide a full account of how the intention-to-treat population was defined or whether a separate analysis in that population was performed. The primary results should therefore be understood as applying to the stated mITT population, not assumed to represent every randomized participant.

The registry record does not report the complete statistical analysis plan, prespecified covariates for ANCOVA, model diagnostics, or all sensitivity analyses. These omissions limit independent evaluation of robustness and multiplicity. They do not establish that an analysis was inappropriate; they mark matters that cannot be verified from the posted 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: worsening of myasthenia gravis (20.0%), pancreas infection (9.5%), post procedural complication (9.5%), cholecystitis (9.5%), pneumonia (9.1%).

For the main portion, the registry reports participants with serious adverse events and participants with other adverse events, alongside the number at risk in each group. Serious adverse events were reported for 0 of 15 participants in the 0.1 mg/kg group, 5 of 14 in the 0.3 mg/kg group, and 3 of 15 in the placebo group. Other adverse events were reported for 15 of 15, 12 of 14, and 14 of 15 participants, respectively. These are counts of participants with at least one event, not counts of all events or measures of severity beyond the serious-event classification.

The registry also lists safety groups combining the main and extension portions, including groups described before and after a switch in dose. Those groups have different at-risk counts and should not be combined with the main-portion comparisons as if they were the same randomized groups. Deaths are listed in the combined main and extension groups: 1 in the 0.1 mg/kg before-switch group, 0 in the after-switch group, and 2 in the 0.3 mg/kg group. The registry record does not establish causes or treatment relationships for these deaths in the listed summary.

Serious adverse event terms and percentages are also listed, including worsening of myasthenia gravis. The percentages should be read as the registry reports them; their event-specific denominators are not stated in the summary. These descriptive safety counts do not by themselves establish comparative risk or causation.

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

The posted results describe average QMG score changes over 12 weeks in a small phase 2 study of two RA101495 doses and placebo. All three groups had negative mean changes from baseline, and the sponsor's ANCOVA estimates for both dose groups were negative relative to placebo. The estimated contrasts, intervals, and p-values express the direction and uncertainty of those comparisons; they are not a complete account of individual experiences or a measure of clinical importance.

The findings do not establish whether the observed average differences are meaningful to participants. The registry record does not report a clinically important QMG difference threshold. Nor do the results show whether any difference would persist beyond Week 12, apply to people outside the study population, or be reproduced in a larger study. The registry record describes this as a phase 2 study evaluating safety, tolerability, and preliminary efficacy. Its results should be read in that context, rather than as a final answer to broader clinical questions.

Statistical uncertainty remains relevant even when a point estimate favors one group in the direction of a lower QMG score. The sponsor's posted analyses and the simple recalculations use different methods and yield different interval and p-value results. The sponsor-reported intervals are 80% intervals, while the confidence level for the recalculated intervals is not reported. Multiple outcomes are listed, and adjustment for multiplicity is not reported. These features limit how strongly an isolated result can be interpreted.

Safety summaries provide counts of participants with serious and other adverse events, as well as deaths in groups covering the main and extension portions. They are descriptive and do not establish that an event was caused by study treatment. The information does not support medical advice or an individual treatment decision. It identifies what was measured and what the registry reports, while leaving important questions about analysis details, precision, clinical importance, and generalizability unresolved.

18. Why This Trial Matters Statistically

This study illustrates why estimates, intervals, and analysis methods need to be considered together. The sponsor reports ANCOVA contrasts for the primary QMG outcome, while simple recalculations from the arm summaries give unadjusted estimates. Their point estimates are similar, but their uncertainty intervals and p-values differ. That distinction shows why a recalculation from summary statistics is a useful check but not a substitute for a model-based analysis whose full specification is unavailable.

The trial also highlights the limits of interpreting a result from small analysis groups. A point estimate gives one summary of the data, but broad intervals indicate that a range of effects remains compatible with the observed information. The registry's 80% intervals for the sponsor analysis should not be confused with intervals at another confidence level, and the recalculated intervals should not be assigned a confidence level that the record does not state.

Multiplicity and missing-data handling are not minor technical details. With a primary endpoint, two dose comparisons, and multiple secondary measures, the interpretation of secondary p-values depends in part on whether a testing plan or adjustment was specified. The record does not report those details, so the results must be considered with that uncertainty. Likewise, the stated mITT population clarifies who contributed to the primary analysis, but missing Week 12 outcomes and their handling are not described.

Finally, the safety summaries demonstrate the importance of distinguishing participants with events from event counts and of separating main-portion groups from groups that include extension follow-up or a dose switch. Careful reading of denominators and analysis populations is central to avoiding misleading comparisons.

19. Limitations

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

Several limitations specific to this trial follow from the registry record. The primary QMG analysis includes 15, 14, and 15 participants in the three groups, so the estimates are based on small groups and have substantial uncertainty. The sponsor's reported intervals are at the 80% level. The record does not supply a clinically important difference threshold, which prevents judging the practical significance of the estimated QMG contrasts from the registry statistics alone.

The ANCOVA analyses are reported without the full model specification. Covariates, model diagnostics, missing-data procedures, and sensitivity analyses are not reported in the registry record. The simple recalculations use approximate standard deviations from summary statistics and are not adjusted, so they cannot reproduce the sponsor analysis. The confidence level for their intervals is not stated in the registry record.

The registry lists multiple primary and secondary analyses but does not report whether multiplicity was addressed or how outcomes were prioritized. It also does not report how many primary endpoint values were missing or how participants who discontinued, used rescue therapy, or missed visits were handled. The mITT definition is available, but the full population definitions and any parallel analyses are not.

The study description sets the primary outcome at Week 12. Longer-term effectiveness and safety conclusions cannot be drawn from that endpoint alone. Some listed safety groups combine main and extension portions and include participants before or after a dose switch; these are not directly equivalent to the randomized main-portion groups. The registry summary does not report causal attribution for the listed adverse events or deaths. These limitations define what the posted information can support; they do not determine the unreported protocol or analysis choices.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Safety and Efficacy Study of RA101495 in Subjects With Generalized Myasthenia Gravis — NCT03315130.
• Registry record last updated 2022-07-27; status last verified 2022-07.
• Results first posted 2022-06-27.
• 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

NCT03315130 is a completed phase 2 randomized, double-blind, placebo-controlled, parallel-group study of RA101495 in generalized myasthenia gravis. The registry describes 45 enrolled participants, planned 1:1:1 allocation to daily subcutaneous 0.1 mg/kg, 0.3 mg/kg, or matching placebo, and a 12-week treatment period.

The primary endpoint was change from baseline to Week 12 in QMG score. In the mITT analysis, the sponsor reported ANCOVA contrasts of -2.3 and -2.8 versus placebo, with 80% confidence intervals and p-values recorded in the registry. Unadjusted recalculations based on summary statistics produce different intervals and p-values. The record also lists multiple secondary outcomes and descriptive safety counts. Important details—including the original sample-size justification, multiplicity procedures, missing-data handling, and full ANCOVA specification—are not reported in the registry record.