A Study to Assess the Efficacy and Safety of Efgartigimod in Adult Patients With Primary Immune Thrombocytopenia (ITP).: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Assess the Efficacy and Safety of Efgartigimod in Adult Patients With Primary Immune Thrombocytopenia (ITP). (NCT04188379), a randomized phase 3 study. The primary outcome is Percentage of Participants With Chronic ITP With a Sustained Platelet Count Response Defined as Achieving Platelet Counts of at Least 50×10^9/L for at Least 4 of the 6 Visits Between Week 19 and 24 of the Trial..

2. Clinical Question

This question concerns a sustained response over repeated visits late in the trial, rather than a platelet count at a single visit. The outcome is expressed as the percentage of participants meeting the specified response definition. The registry also lists outcomes concerning disease control, bleeding events, and platelet-count responses in broader populations or over different visit windows. Those outcomes address related but distinct questions and should not be treated as interchangeable with the primary endpoint.

3. Trial Design

NCT04188379 is recorded as a completed phase 3 trial of efgartigimod in adults with primary ITP. The registry describes a randomized, double-blind, placebo-controlled, multicenter design. The official title additionally describes the trial as quadruple-masked and parallel-group. The sponsor is argenx.

The record gives an enrollment of 131. The listed trial start date is 2019-12-16, and the primary completion date is 2022-02-03. These dates describe the registry record; they do not by themselves establish when each participant began or completed treatment. The record does not report additional details about recruitment, follow-up duration for each participant, or the conduct of the study at individual centers.

The two intervention groups were efgartigimod and placebo. The official title specifies efgartigimod 10 mg/kg intravenously. The primary analysis population was the Full Analysis Set-Chronic population, defined as all randomized participants with chronic ITP. The primary endpoint was the percentage in that population achieving platelet counts of at least 50×10^9/L for at least 4 of the 6 visits between Week 19 and Week 24.

The primary endpoint results use group denominators of 78 for efgartigimod and 40 for placebo. Other posted outcome results use denominators of 86 and 45. Those different denominators indicate that the reported outcome populations are not identical; the registry record does not explain the full flow of participants into each analysis population. Details of allocation concealment, the exact masking procedures, treatment adherence, and the original sample-size justification 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: During the screening period (up to 2 weeks) the participant's eligibility for trial participation was evaluated. A total of 205 participants were screened, of which 74 participants were screen failures. 131 of 205 were enrolled and randomized at a ratio of 2:1 to receive efgartigimod or placebo.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set-Chronic population: all randomized participants with chronic ITP.

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 randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With Chronic ITP With a Sustained Platelet Count Response Defined as Achieving Platelet Counts of at Least 50×10^9/L for at Least 4 of the 6 Visits Between Week 19 and 24 of the Trial., measured over From Week 19 up to Week 24.

The primary endpoint is a binary participant-level outcome: each participant either met the sustained platelet-count response definition or did not. To qualify, a participant with chronic ITP had to achieve a platelet count of at least 50×10^9/L at 4 or more of the 6 visits between Week 19 and Week 24. The registry reports the percentage of participants meeting that definition, rather than a mean platelet count or a result at a single visit.

Using repeated visits makes the endpoint a measure of response sustained across a late-treatment window. This can distinguish a pattern observed across several assessments from a transient threshold crossing at one assessment. The threshold, number of visits, and assessment window are part of the endpoint definition; changing any of them would define a different outcome.

The endpoint is restricted to the chronic ITP population. It therefore answers a narrower question than outcomes reported for the overall population. It is also distinct from the listed outcome describing cumulative weeks with platelet counts at or above the threshold, and from the outcome concerning bleeding events. Each captures a different aspect of disease control. As a general statistical point, a binary endpoint is straightforward to interpret as a proportion, but it compresses the underlying pattern of measurements: participants who narrowly miss the visit criterion are counted in the same nonresponse category as those with fewer qualifying visits.

7. Results Posted in the Registry

• Efgartigimod: 21.8% (17/78) versus 5.0% (2/40) on control; risk difference 16.8 percentage points (95% CI 5.4 to 28.2), risk ratio 4.36 (1.06–17.94); unadjusted two-proportion z-test p = 0.019.

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.

Percentage of Participants With a Sustained Platelet Count Response for at Least 4 of the 6 Visits Between Week 19 and 24 of the Study

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Efgartigimod: 25.6% (22/86) versus 6.7% (3/45) on control; risk difference 18.9 percentage points (95% CI 7.2 to 30.7), risk ratio 3.84 (1.21–12.13); unadjusted two-proportion z-test p = 0.009.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Efgartigimod than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants in the Overall Population Achieving Platelet Counts of at Least 50×10^9/L for at Least 6 of the 8 Visits Between Week 17 and Week 24

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Efgartigimod: 22.1% (19/86) versus 6.7% (3/45) on control; risk difference 15.4 percentage points (95% CI 4.0 to 26.8), risk ratio 3.31 (1.04–10.60); unadjusted two-proportion z-test p = 0.025.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Efgartigimod than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The additional posted outcome results point in the same broad direction as the primary result: the reported response proportions favor the efgartigimod group over placebo for the listed sustained-response measures and for the overall-population response measure. These endpoints use different analysis populations, visit windows, or response definitions, so their estimates are related to but not identical with the primary chronic ITP endpoint. They provide context rather than a direct replication of the primary analysis.

The registry lists secondary measures covering cumulative weeks with platelet counts above the threshold in the chronic ITP population, sustained response in the Week 19 to Week 24 window, bleeding events, and response across visits in the overall population. The additional numerical results include an overall-population endpoint using a different visit window. Because the endpoint definitions and populations differ, the results should not be combined into one summary claim or assumed to describe a single common outcome.

Unadjusted secondary comparisons generally carry less confirmatory weight than a prespecified primary analysis when the record does not report a multiplicity procedure or testing hierarchy. As a general statistical principle, making several comparisons creates more opportunities for chance findings. A nominal p-value for a secondary endpoint does not, by itself, account for that broader set of tests. The record does not say whether such adjustment was performed, so the secondary results are best read as supportive descriptive evidence with the stated uncertainty, rather than as independent confirmation of the primary result.

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

• Extent of Disease Control Defined as the Number of Cumulative Weeks Over the Planned 24-week Treatment Period With Platelet Counts of ≥50×10^9/L in the Chronic ITP Population
• Percentage of Participants With a Sustained Platelet Count Response for at Least 4 of the 6 Visits Between Week 19 and 24 of the Study
• Incidence and Severity of the WHO-classified Bleeding Events
• Percentage of Participants in the Overall Population Achieving Platelet Counts of at Least 50×10^9/L for at Least 6 of the 8 Visits Between Week 17 and Week 24

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary because it classifies participants according to whether they met the sustained-response criterion. A natural descriptive summary is the percentage meeting that criterion in each randomized group. The registry reports 21.8% for efgartigimod and 5.0% for placebo in the chronic ITP primary analysis population. The denominators recorded for those groups are 78 and 40. These summaries describe the observed analysis groups, not a guarantee that the same percentages would occur in another trial or population.

What does the risk difference convey?

The unadjusted recalculation expresses the group contrast as a risk difference of 0.168, with an interval from 0.054 to 0.282. A risk difference is an absolute-scale comparison: it describes the difference between the proportions meeting the outcome in the two groups. It is often useful because the scale corresponds directly to a change in the proportion of participants meeting the endpoint. The interval gives a range of values compatible with the data under the calculation's statistical assumptions. It is not a range containing a known fixed effect with certainty.

This recalculation is unadjusted and based on posted summary statistics. It does not reproduce every feature of the sponsor's analysis. In particular, it should not be treated as a substitute for the registry-reported Cochran-Mantel-Haenszel analysis. The registry analysis reports an odds ratio, which compares the odds of response rather than the response proportions themselves. Odds ratios and risk differences use different scales, and an odds ratio should not be read as a percentage-point difference.

Why use a Cochran-Mantel-Haenszel analysis?

The Cochran-Mantel-Haenszel method is a general approach for estimating an association across strata. In a randomized trial, a stratified analysis can account for specified grouping factors while combining information across those strata. The registry identifies this method for the sponsor-reported odds ratio but does not identify the stratification factors or provide enough detail to reconstruct the analysis. It would therefore be inappropriate to infer which factors were used or how they were defined.

The sponsor-reported result is an odds ratio of 4.884, with a 95% confidence interval from 1.007 to 43.591 and p=0.032. The interval is on the odds-ratio scale; the value 1 represents no odds contrast. A p-value summarizes how incompatible the observed data are with a specified null hypothesis under the model and test used. It is not the probability that the null hypothesis is true, and it does not measure the clinical importance or precision of the result by itself.

What is a confidence interval?

As a general statistical explanation, a confidence interval describes the uncertainty in an estimate using a method with a specified long-run coverage property, assuming the analysis model and its conditions are appropriate. A narrower interval indicates greater precision on the scale of the estimate; a wider interval indicates less precision. The interval does not account automatically for every source of uncertainty, including choices made in the analysis plan, missing data, or the selection of an endpoint from multiple outcomes.

The primary recalculation's interval and the sponsor's interval are attached to different effect measures and analyses. They should not be treated as competing estimates of precisely the same quantity. The registry does not flag a discrepancy between its reported analysis and the recalculation. The sponsor's method and estimate remain the registry-reported analysis; the unadjusted calculation is a separate descriptive check based on the posted summary data.

Why can binary outcomes be sensitive to small counts?

For a binary outcome, the number of participants meeting the definition can be small even when a group denominator is larger. Estimates based on relatively few outcome events can be sensitive to the outcome status of individual participants, and confidence intervals may be wide. That general consideration is relevant when interpreting an odds ratio with a broad interval. The registry record does not give enough information to evaluate model diagnostics, alternative analyses, or the effect of individual observations.

General statistical methods also rely on correct outcome classification and appropriate handling of incomplete assessments. The response definition depends on repeated platelet-count visits during a specified period. Missing or unavailable measurements could affect whether a participant satisfies the criterion, depending on the rule used. The rule for incomplete visit data is not reported in the registry record. No missing-data assumption should be inferred from the posted percentages alone.

What does over-dispersion mean in general?

Over-dispersion is a general concept for data whose variability exceeds what a model assumes. It is especially discussed for count outcomes and some generalized linear models. The primary endpoint is reported as a binary participant-level percentage, and the registry does not report an over-dispersion assessment or a model for repeated visit-level counts. It would not be appropriate to claim that over-dispersion was present or that a particular correction was used. More generally, checking that a model's assumptions fit the data matters because incorrect assumptions can affect standard errors, intervals, and tests.

Finally, the primary endpoint is one of several outcome measures. Testing multiple outcomes can increase the chance of at least one apparently notable result if no multiplicity strategy is applied. The record lists secondary endpoints but does not report a multiplicity adjustment or a hierarchy of tests. This limits how strongly unadjusted secondary p-values can be interpreted as confirmatory evidence. The primary result should be distinguished from exploratory or otherwise unadjusted secondary comparisons.

11. Confidence Intervals and Precision

Precision concerns how tightly the data estimate an effect, not simply whether a test crosses a conventional significance threshold. The registry-reported odds ratio for the primary outcome is 4.884, with a 95% confidence interval from 1.007 to 43.591. This interval is wide, so the estimated odds contrast is not pinned down closely. Its lower end is close to 1, while its upper end is much larger; the data are therefore compatible with a broad range of effect magnitudes on the odds-ratio scale.

The interval does not include 1, and the reported p-value is 0.032. Those features indicate that the registry-reported analysis meets a conventional threshold for statistical evidence against the null odds ratio of 1, under the method used. They do not remove uncertainty about the size of the association. A p-value is not a measure of precision, and a result with a small p-value can still have an interval that spans meaningfully different magnitudes.

The unadjusted recalculation reports a risk difference of 0.168, with an interval from 0.054 to 0.282. This is an absolute-scale estimate, whereas the sponsor's result is an odds ratio. The two intervals are not directly comparable because they describe different effect measures and analyses. The risk-difference interval also conveys uncertainty, but its endpoints should be interpreted on the risk-difference scale rather than as odds ratios.

As a general point, confidence intervals reflect sampling uncertainty under the method used; they do not automatically include uncertainty from choices among endpoints, unreported analysis decisions, measurement error, or missing-data assumptions. Those considerations matter because the registry record does not report the missing-data method, multiplicity approach, or full statistical plan. Precision should therefore be considered together with the trial's outcome definition, analysis population, and reporting gaps.

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, not total events. They are illustrations calculated from the observed effect, not the trial's original design calculations. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; each planning scenario uses the stated fraction of the observed effect to be detected. The trial's own original sample-size assumptions are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the assumed effect under the stated assumptions, if the effect and model assumptions were correct. The 90% power column gives the corresponding planning number for a higher target chance of detection. These are design targets, not guarantees about a future trial's result.

For the primary endpoint, planning for 100% of the observed effect gives 64 participants per arm for 80% power and 85 participants per arm for 90% power. Planning for 75% of the observed effect gives 98 participants per arm for 80% power and 131 participants per arm for 90% power. Planning for 50% of the observed effect gives 185 participants per arm for 80% power and 247 participants per arm for 90% power. The pattern illustrates a general planning principle: smaller effects are harder to distinguish from chance variation and require more participants under otherwise similar assumptions.

These figures are not observed power and do not describe the probability that the completed trial was successful. They are prospective planning illustrations based on the observed estimate, which may itself be uncertain. A planning curve can help show how the required sample size changes as the assumed effect changes, but the assumptions remain essential to its interpretation.

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 = 0.050; treatment proportion p₁ = 0.218; average p̄ = 0.134.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4817 = 0.9441.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4668 = 0.3929.
4. n = (0.9441 + 0.3929)² / (0.1679)² = 63.4, rounded up to 64 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 <- 0.05                          # control proportion
p1 <- 0.217948717948718                          # 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(4188379)
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 = 64 (80% power), 85 (90% power)
 75% of observed effect: n per arm = 98 (80% power), 131 (90% power)
 50% of observed effect: n per arm = 185 (80% power), 247 (90% power)
power.prop.test: 63.4 
Simulated power at n = 64 per arm: 0.830 (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-reported primary analysis uses the Cochran-Mantel-Haenszel method and reports an odds ratio of 4.884, with a 95% confidence interval from 1.007 to 43.591 and p=0.032. The unadjusted recalculation from the posted group summaries instead expresses the contrast as a risk difference of 0.168, with an interval from 0.054 to 0.282 and an unadjusted p-value of 0.019. These are distinct estimates on different scales and should not be expected to match numerically.

The recalculation is a simple unadjusted check using the posted summary statistics. The registry-reported analysis is the sponsor's stated analysis method and effect measure. The record does not provide the details needed to reproduce the Cochran-Mantel-Haenszel analysis, including any strata used. The registry does not flag a discrepancy between the sponsor-reported result and the recalculation. Their shared broad direction is that the observed response was more frequent in the efgartigimod group, while the sponsor's interval indicates substantial uncertainty about the size of the odds contrast.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary endpoint and several secondary outcome measures, but it does not report a multiplicity strategy. It is therefore not reported in the registry record whether secondary tests were adjusted for multiple comparisons, whether a fixed testing hierarchy was used, or whether any secondary outcomes were designated as confirmatory. Without those details, secondary p-values should not be interpreted as though they necessarily preserve a trial-wide type I error rate.

The registry reports the Full Analysis Set-Chronic population for the primary outcome as all randomized participants with chronic ITP. It does not provide a complete participant-flow account for that analysis or explain how participants with missing platelet-count assessments were handled. The missing-data method is not reported in the registry record. This matters because the primary endpoint requires qualifying measurements across repeated visits; incomplete assessments could affect endpoint classification depending on the prespecified rule.

The outcome records also use different denominators. The primary result has group denominators of 78 and 40, whereas the additional posted outcome results include denominators of 86 and 45. The registry record does not provide enough information to reconcile these analysis populations or explain all exclusions and missing observations. The denominators should be interpreted within their own outcome records rather than assumed to refer to an identical analysis set.

The full statistical analysis plan, including the prespecified handling of missing data, covariate or stratification factors, sensitivity analyses, and interim analyses, is not reported in the registry record. The original sample-size justification is also not reported in the registry record. These omissions limit assessment of how closely the posted analyses follow the planned approach and how robust the conclusions are to alternative analytic choices.

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: thrombocytopenia (2.3%), road traffic accident (2.2%), anaemia (2.2%), immune thrombocytopenia (2.2%), mouth haemorrhage (2.2%).

The registry reports serious adverse event figures separately by group. For efgartigimod, 7 participants were recorded with serious adverse events among 86 at risk; for placebo, 7 were recorded among 45 at risk. The record reports zero deaths in each group. These are descriptive counts from the posted safety record and do not by themselves establish whether an event was caused by treatment.

The record also gives other adverse-event counts: 80 among 86 at risk in the efgartigimod group and 43 among 45 at risk in the placebo group. Serious adverse events and other adverse events are different categories and should not be conflated. The registry lists thrombocytopenia at 2.3%, and road traffic accident, anaemia, immune thrombocytopenia, mouth haemorrhage, and acute kidney injury at 2.2% each among the top serious-event terms. The record does not provide enough context to interpret those term percentages as comparative risks between groups.

Safety counts are not a randomized comparison of causation, and the number of participants with an event does not convey event severity, duration, recurrence, or relationship to treatment. The registry also lists bleeding events as a secondary outcome, which is distinct from the serious-adverse-event summaries.

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

The posted primary results show that the sustained platelet-count response, as defined for the chronic ITP population, was observed more often in the efgartigimod group than in the placebo group. The registry-reported analysis and the unadjusted recalculation both point in that direction, while using different effect measures and methods. The confidence intervals, especially the wide interval for the sponsor-reported odds ratio, show that the magnitude remains uncertain.

This endpoint measures whether participants met a specified platelet-count threshold across a defined set of visits. It does not describe every platelet-count measurement, the timing of individual responses, or response outside the assessment window. It also does not directly establish effects on bleeding, disease burden, quality of life, or other outcomes. Those questions require their own outcome data and interpretation.

The result should not be read as a guarantee that an individual participant will meet the response definition. Group-level percentages summarize outcomes across trial participants; they do not predict an individual's experience. The record also does not establish how missing assessments were handled or provide the complete analysis plan, which limits evaluation of the effect of those decisions on the estimates.

Finally, statistical evidence is not the same as clinical importance. The endpoint threshold and sustained-response rule define what was measured, but the registry record alone does not establish how much a change in this measure matters to patients or how the result balances against other outcomes. The result is best understood as a comparison of observed endpoint frequencies within this trial, with uncertainty and reporting limitations, rather than as a complete account of benefits and harms.

18. Why This Trial Matters Statistically

This trial is statistically informative because it uses a randomized, placebo-controlled design to compare a defined binary endpoint between intervention groups. Randomization is intended, in general, to support a fair comparison by balancing prognostic factors on average, while masking can reduce some forms of bias in outcome assessment and participant or investigator behavior. The registry describes this study as randomized and quadruple-masked, although it does not report all operational details.

The primary outcome is defined using repeated measurements rather than a single platelet count. That makes the estimand more specific: it concerns sustained attainment of a threshold over a stated late-treatment visit window in the chronic ITP population. Clear endpoint definitions are essential because small changes in thresholds, visit counts, or populations can change what a percentage means.

The analysis also illustrates why effect scale and precision matter. The sponsor reports an odds ratio, while an unadjusted recalculation reports a risk difference. Each answers the contrast question on a different scale. The wide sponsor-reported confidence interval cautions against treating a statistically notable result as a precisely estimated magnitude. Looking at the outcome proportions, effect measure, interval, and analysis population together gives a fuller statistical interpretation than relying on a p-value alone.

Lastly, the registry record exposes important reporting questions common to trial interpretation: how multiple outcomes were handled, how missing repeated measurements were classified, and how the analysis populations relate to one another. Identifying what is not reported is part of sound statistical reading. It keeps the interpretation anchored to the documented evidence without filling gaps with 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 principal limitation in interpreting these results is incomplete statistical reporting. The registry record does not report the full analysis plan, multiplicity procedure, missing-data rules, interim analyses, or original sample-size justification. These details are important for assessing whether analyses were prespecified and how robust the results are to alternative assumptions.

The primary endpoint is a threshold-based binary measure across repeated visits. It does not retain the full information in the underlying platelet-count trajectory. Participants just short of the response criterion and participants with substantially fewer qualifying visits are classified alike as not meeting the endpoint. The record does not provide the distribution of visit-level counts or individual response patterns needed to examine that detail.

The primary and additional outcome records use different denominators and populations. The primary analysis concerns the chronic ITP population, while one additional outcome concerns the overall population. The registry does not explain the complete flow into each analysis set or the handling of incomplete assessments. This makes direct comparisons across outcome records less straightforward.

The sponsor-reported odds-ratio interval is broad, indicating limited precision in the estimated magnitude. The unadjusted recalculation is based on summary statistics and does not reproduce the sponsor's method. Secondary outcomes also require caution because the record does not state how multiple testing was handled. Finally, the safety summaries are counts and listed terms; they do not establish causation or provide a complete assessment of event timing, recurrence, or clinical context.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study to Assess the Efficacy and Safety of Efgartigimod in Adult Patients With Primary Immune Thrombocytopenia (ITP). — NCT04188379.
• Registry record last updated 2025-03-13; status last verified 2025-02.
• Results first posted 2025-03-13.
• 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

NCT04188379 is a completed phase 3 randomized, placebo-controlled, quadruple-masked, parallel-group trial of efgartigimod in adults with primary ITP, sponsored by argenx. The primary endpoint was sustained platelet-count response in the chronic ITP population, defined as platelet counts of at least 50×10^9/L for at least 4 of the 6 visits between Week 19 and Week 24.

The registry reports response proportions of 21.8% for efgartigimod and 5.0% for placebo. Its Cochran-Mantel-Haenszel analysis reports an odds ratio of 4.884, with a 95% confidence interval from 1.007 to 43.591 and p=0.032. The interval indicates substantial uncertainty in the magnitude. The registry record does not report the multiplicity strategy, missing-data method, full analysis plan, or original sample-size justification.