Omalizumab in the Treatment of Peanut Allergy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Omalizumab in the Treatment of Peanut Allergy (NCT00949078), a non-randomized phase 2 study. The primary outcome is Number of Participants Who Experienced a Decrease in Pn-BHR Area Under the Curve (AUC) of > 80% Compared With Baseline Values Before Week 8.

2. Clinical Question

In statistical terms, this is a question about the frequency of a defined within-participant biological response after treatment, not a randomized estimate of the difference between treatment and control. The clinical question in the brief summary concerns symptoms, while the stated primary endpoint is a laboratory measure. The registry record does not report a primary symptom outcome result.

3. Trial Design

The registry describes a Phase 2, single-group study with non-randomized allocation and no masking. It records an enrollment of 51 and lists Johns Hopkins University as the sponsor. The study is marked completed; its recorded start is 2009-07 and its primary completion is 2011-08. The official title identifies peanut-allergic adults and cellular and clinical responses to peanut allergen after omalizumab.

Omalizumab is the listed drug intervention, and the arm descriptions say it was dosed according to the package insert. The two open-label groups were defined by participants’ change in peanut allergen-induced basophil histamine release: Group A included those with a decrease to less than 20% of baseline, while Group B included those without that decrease. These definitions classify participants by a response measure; they do not describe random assignment to treatment alternatives.

This structure matters when interpreting comparisons. Random assignment can, under appropriate conditions, support a comparison between groups that differ in assigned treatment. Here, both groups received open-label omalizumab, and their labels depend on a measured post-treatment response. A contrast between them would therefore not be a randomized treatment-versus-control effect. The registry explicitly cautions that the arms are not a like-for-like control comparison.

The registry lists nine outcome measures but no analysis entries. It does not report the protocol’s sample-size justification, a detailed analysis plan, interim analyses, or the analysis population for the primary outcome. The stated enrollment is not evidence that all enrolled participants contributed data to every outcome. The record does not explain how many participants were assessed for the primary endpoint or how missing assessments were handled.

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: 51 participants underwent screening history and laboratory evaluation. Of those, 14 underwent a screening food challenge and were randomized to subsequent arms.

Overall Study

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants Who Experienced a Decrease in Pn-BHR Area Under the Curve (AUC) of > 80% Compared With Baseline Values Before Week 8, measured over up to 6 months.

The primary endpoint is a count of participants who experienced a decrease in peanut allergen-induced basophil histamine release area under the curve of > 80% compared with baseline values before Week 8. The outcome is defined as the presence or absence of that change for each participant, then expressed as a count. The registry lists its timeframe as up to 6 months.

Basophil histamine release is a laboratory response to peanut allergen. Area under the curve represents the response across the assay’s measurement interval; the endpoint uses the change from each participant’s baseline rather than a direct comparison with a separate control group. The registry record does not provide assay details, the exact assessment schedule, or the number of participants with an evaluable baseline and follow-up result.

As a general statistical concept, a threshold endpoint can make a response definition easier to interpret: each participant either meets the specified criterion or does not. That simplification also means the result depends on the selected cutoff. Participants with changes close to the cutoff may be classified differently despite having similar underlying responses. A count alone also omits how far responses fell short of or exceeded the threshold.

The endpoint is biological, while the study’s brief summary asks about symptoms. A laboratory response may be relevant to the research question, but it is not itself a reported symptom outcome. The registry does not report the primary count, so the magnitude or precision of the observed endpoint result cannot be assessed.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation begins with the outcome definition and the way participants entered the groups. In this study, the primary endpoint is binary at the participant level: a participant either meets the stated decrease threshold or does not. The registry reports that the outcome is a count of participants. It does not report the count, the number assessed, or an analysis of that endpoint.

What does a binary endpoint represent?

As a general statistical concept, a binary endpoint reduces each participant’s measured outcome to one of two categories. A response frequency can be useful when the research question specifies a threshold that matters to the investigators. It is also easy to communicate as a count, provided the denominator is known. Without the numerator and denominator, however, the response frequency cannot be evaluated. The registry’s enrollment of 51 cannot automatically serve as the endpoint denominator because the record does not say that every enrolled participant had the required measurements or was included in the primary analysis.

Thresholding also discards detail. Two participants just on opposite sides of a cutoff are assigned different categories even if their measurements are similar. Conversely, participants in the same category can have quite different underlying changes. A continuous measure of change can preserve more information, but the registry record does not report such a primary analysis. The endpoint description alone does not tell whether the threshold was selected before data collection or how assay variability was addressed; those details are not reported in the registry record.

What can a confidence interval add?

As a general statistical concept, a confidence interval conveys uncertainty around an estimated quantity. For a binary response, an interval around the response frequency can show how much uncertainty remains given the observed count and denominator. Its interpretation depends on the statistical method and assumptions. A narrow interval suggests greater precision than a wide interval, but precision does not resolve design limitations such as the absence of a randomized control group. No confidence interval for the primary endpoint is reported in the registry record.

A p-value addresses a different question: how compatible the observed data are with a specified null model, under the analysis assumptions. It does not give the probability that the null hypothesis is true and does not measure clinical importance. A p-value can also be difficult to interpret without the estimate, its uncertainty, the analysis population, and the planned comparison. No p-value or primary endpoint analysis is reported in the registry record.

Why does allocation matter?

As a general statistical concept, randomization helps make treatment groups comparable in expectation with respect to measured and unmeasured factors, subject to the conduct of the trial. This study is recorded as non-randomized and single-group, with no masking. Its two open-label groups are defined by whether a participant’s basophil histamine release fell to less than 20% of baseline. Because group membership depends on a measured response rather than random assignment, differences between the groups cannot be interpreted as randomized treatment effects. The registry explicitly states that the arms are not a like-for-like control comparison.

The endpoint’s threshold of > 80% decrease is distinct from the less than 20% of baseline criterion used to describe Group A. The registry gives both definitions but does not explain their relationship in an analysis plan. They should not be treated as interchangeable criteria. Group assignment, endpoint classification, and the timing of measurements are separate elements of the record.

How should the planning illustration be read?

The registry’s sample-size assumptions describe a planning illustration based on the observed effect, not the trial’s own design. The assumptions specify a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is a stated fraction of the observed effect. Such planning estimates describe hypothetical requirements under assumptions. They are not observed results and are not observed power. The registry record does not report a prospective sample-size justification or the observed primary endpoint effect needed to assess the assumptions in relation to the trial.

As a general statistical concept, power is a design property calculated for a specified effect, variability, significance level, and analysis. A retrospective power calculation based on an observed estimate does not replace an estimate with a confidence interval. If the observed effect is uncertain, a planning illustration that uses it inherits that uncertainty. The posted planning assumptions should therefore be kept separate from the trial’s observed findings, which are not reported for the primary endpoint.

What is the role of dispersion?

For quantitative outcomes, dispersion describes how observations vary around a typical value. As a general concept, excess variation beyond a model’s assumptions can make standard errors and confidence intervals too narrow if it is ignored; methods that account for over-dispersion may be needed for some count models. The primary endpoint in this record is described as a participant count based on a binary classification, and no dispersion estimate or model is reported. There is therefore no basis in the registry record for describing an over-dispersion adjustment or a fitted count model.

In short, the registry establishes the intended endpoint and broad design, but not the analysis details needed to reproduce or assess an efficacy estimate. The analysis population, missing-data approach, statistical model, estimate, and uncertainty are not reported in the registry record. General statistical concepts can explain what those elements would contribute, but they cannot fill in the absent trial results.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Open Label Omalizumab Group A", "Open Label Omalizumab Group B")
n      <- c(5, 9)
events <- c(5, 9)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Open Label Omalizumab Group A  5  5  100.0  47.8  100.0  56.6  100.0  54.1  99.6
ARM  Open Label Omalizumab Group B  9  9  100.0  66.4  100.0  70.1  100.0  69.2  99.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists nine outcome measures and no analysis entries. It identifies the primary endpoint as the count of participants with a decrease in peanut allergen-induced basophil histamine release area under the curve of > 80% compared with baseline values before Week 8. The record does not describe how the other outcomes were prioritized or whether any multiplicity procedure was planned or used. A multiplicity adjustment is not reported in the registry record.

As a general statistical concept, testing multiple outcomes or comparisons can increase the chance of obtaining an apparently unusual result by chance if each is interpreted separately. Prespecified priorities and appropriate methods can help readers understand that risk. The registry’s listing of nine outcomes does not establish that all were tested or that they were tested in a particular way. With no analysis entries, the outcome listing cannot be used to infer the number of statistical tests performed.

Missing-data handling is also not reported in the registry record. The record does not state how many participants had primary endpoint measurements, how incomplete assessments were treated, or whether any participants were excluded from an analysis. The enrollment of 51 should not be assumed to be the denominator for the primary outcome.

The analysis population is not reported in the registry record. It is therefore unclear from the posted results whether the primary endpoint was intended to include all enrolled participants or a defined subset. These gaps limit assessment of both the result and its potential sensitivity to missing observations or analysis choices.

12. 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 0% reporting threshold.

The registry lists safety information for Open Label Omalizumab Group A and Open Label Omalizumab Group B. For Group A, 5 participants are listed as at risk for serious adverse events and 0 as affected; the other-adverse-event figures are also 5 at risk and 0 affected. For Group B, 9 participants are listed as at risk for serious adverse events and 0 as affected; the other-adverse-event figures are 9 at risk and 0 affected. Deaths are listed as 0 for each group.

These figures describe the safety entries in the registry, not the primary efficacy endpoint. The record lists no serious adverse events among the participants counted as at risk in either group, and no deaths in either group. It also lists no affected participants for the other-adverse-event category. The record does not provide serious adverse event terms, and no top serious adverse event terms are listed.

The at-risk counts are not the study enrollment of 51. The registry does not explain why the safety denominators are 5 and 9, how they relate to all participants, or whether the safety information covers the same population and timeframe as every other outcome. These figures should be read within their listed groups and not taken as a complete account of all possible adverse events or as an efficacy comparison.

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

The registry record identifies a study of open-label omalizumab in adults with peanut allergy and defines a primary biological endpoint based on a decrease in peanut allergen-induced basophil histamine release. It also records the broad study design and safety counts. These details clarify what investigators intended to examine, but the registry does not report the primary endpoint count or an analysis of that outcome.

Accordingly, the posted results do not show how many participants met the > 80% decrease criterion, how precise that frequency was, or whether a statistical comparison was made. The record also does not report a primary symptom result, despite the brief summary’s focus on symptoms. A laboratory endpoint and a symptom outcome are different kinds of evidence, and one cannot be substituted for the other without reported data linking them.

The study’s design further limits causal interpretation. It is recorded as non-randomized, single-group, and unmasked, and the two groups are classified by a basophil response. Those groups do not constitute a randomized control comparison. A difference between them, even if reported, would not by itself establish a treatment effect relative to a control group.

The safety entries list 0 affected participants for serious adverse events in each of the two groups, with deaths listed as 0. The corresponding at-risk counts are 5 for Group A and 9 for Group B. These entries should be understood as the registry’s listed safety data, not as a comprehensive statement about all participants or all possible outcomes.

As a general statistical principle, a well-defined endpoint is only one part of an interpretable result. Readers also need the observed count, denominator, analysis population, and uncertainty, alongside a design suited to the question being asked. Those elements are not reported for the primary endpoint in the registry record. The available description therefore supports a careful account of what was measured and how the groups were defined, but not a conclusion about the frequency or clinical significance of the primary response.

14. Why This Trial Matters Statistically

This study is statistically informative as an example of why endpoint definitions, group formation, and causal comparisons must be kept distinct. Its primary endpoint is a participant-level threshold response in a laboratory measure. Its two open-label groups, by contrast, are defined using a basophil histamine release criterion of less than 20% of baseline. The record does not present these groups as randomized treatment arms and explicitly cautions that they are not a like-for-like control comparison.

That distinction is important for readers who encounter a study with multiple group labels. A group contrast may look like a treatment comparison while actually reflecting a characteristic measured after treatment. As a general statistical concept, conditioning on a post-treatment response can make groups differ in ways that are not attributable solely to treatment assignment. The design description must therefore guide interpretation of any comparison, not the arm labels alone.

The record also illustrates the gap between a clearly stated endpoint and a reportable result. The primary outcome has a defined threshold and timeframe, yet its count, denominator, estimate, and uncertainty are not reported. Without those elements, readers can understand the intended measurement but cannot assess its observed frequency or precision. The study’s clinical aim concerns symptoms, while the stated primary endpoint is biological; this makes transparent reporting of clinical outcomes especially relevant.

Finally, the registry lists safety denominators smaller than the enrollment and gives no explanation for that difference. This highlights why outcome-specific populations and denominators matter. Enrollment, safety follow-up, and primary endpoint analysis need not involve identical sets of participants, and the record does not establish how they relate in this study. Statistical interpretation depends not only on a method, but also on clear reporting of who contributed to each result.

15. Limitations

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

The main limitation for interpreting efficacy is that the registry record does not report the primary endpoint count or an analysis. The number of participants assessed, the analysis population, an effect estimate, and its uncertainty are also not reported. The recorded enrollment of 51 cannot be assumed to be the denominator for the primary endpoint.

The design is non-randomized, single-group, and unmasked. Group A and Group B are defined by a basophil histamine release response rather than by randomized treatment assignment, and the registry cautions that they are not a like-for-like control comparison. This limits the interpretation of any contrast between the groups as a treatment effect relative to control.

The primary outcome is a laboratory measure, whereas the study’s brief summary describes a question about symptoms. The registry record does not report a primary symptom result or a link between the laboratory response and symptoms. It also does not provide assay details or enough information about assessment timing to assess measurement procedures independently.

The registry lists nine outcome measures but no analysis entries. Multiplicity handling, missing-data methods, the analysis population, and a detailed statistical plan are not reported in the registry record. The protocol’s sample-size justification and interim analyses are likewise not reported. The safety figures list at-risk groups of 5 and 9, but the record does not explain how those denominators relate to enrollment or to the efficacy population.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Omalizumab in the Treatment of Peanut Allergy — NCT00949078.
• Registry record last updated 2017-07-12; status last verified 2017-06.
• Results first posted 2017-07-12.
• 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.

19. Record Summary

The registry record describes a completed Phase 2 study of omalizumab in peanut-allergic adults, with an enrollment of 51. It is classified as non-randomized, single-group, and unmasked. The listed intervention is open-label omalizumab, described as dosed according to the package insert. The recorded start is 2009-07, and primary completion is 2011-08.

The primary endpoint is the count of participants with a decrease in peanut allergen-induced basophil histamine release area under the curve of > 80% compared with baseline values before Week 8, with a timeframe of up to 6 months. The registry record does not report the outcome count or an analysis. It lists nine outcome measures and no analysis entries.

Safety entries list no affected participants for serious or other adverse events in the two listed groups, with at-risk counts of 5 and 9, and deaths of 0 in each group. The registry does not explain how these safety populations relate to enrollment. Its group definitions are based on basophil response, and the record cautions that the groups are not a like-for-like control comparison.