Study of Efficacy and Safety of Omalizumab in Severe Japanese Cedar Pollinosis Adult and Adolescent Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Efficacy and Safety of Omalizumab in Severe Japanese Cedar Pollinosis Adult and Adolescent Patients (NCT03369704), a randomized phase 3 study. The primary outcome is Mean Nasal Symptom Score.

2. Clinical Question

The registry describes the intended comparison as an evaluation of efficacy and safety in adults and adolescents whose severe seasonal symptoms were inadequately controlled despite recommended therapies. The primary analysis concerns average symptom severity over the defined severe symptom period, rather than a single symptom report or a measure covering the entire pollen season. Other listed outcomes include ocular symptoms, medication use, symptom severity, daily activity impairment, symptom-free days, and rescue medication. Those outcomes broaden the picture of symptom burden, but they do not change the primary question or substitute for its prespecified measure.

3. Trial Design

The registry identifies this as a completed Phase III study with randomized allocation, triple masking, and a parallel-group model. It compared omalizumab with placebo, with treatment administered subcutaneously for 12 weeks. The registry lists Novartis Pharmaceuticals as sponsor and gives an enrollment of 337. The study start date is 2017-12-15, and the primary completion date is 2018-05-11.

Participants were assigned to the omalizumab or placebo arm. The posted primary outcome summaries include 158 participants in the omalizumab group and 174 in the placebo group. These are the analysis counts reported for that outcome; they should not be treated as interchangeable with the registry’s enrollment figure. The primary endpoint population was further restricted: the full analysis set consisted of patients in the randomized group who received at least 1 dose of study drug, and those patients needed nasal symptom scores for at least 50% of days during the severe symptom period to be included in the primary endpoint analysis.

The comparator was placebo in addition to the study’s standard-care context. The registry describes standard care as anti-histamine and nasal corticosteroid, and the eligibility description refers to prior inadequate control despite nasal corticosteroids plus one or more additional medications. This record does not report further details about treatment adherence, the randomization procedure, allocation concealment, or the masking procedures. The registry also does not report the original sample-size justification or additional design assumptions. Those details should not be inferred from the posted outcome data or from planning calculations based on the observed results.

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: 337 patients were randomized

Treatment Epoch

Reasons for not completing this period:

Follow-up Epoch

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full analysis set (FAS): The FAS consisted of all patients in the RAN who received at least 1 dose of study drug. Among patients in the FAS, those who had nasal symptom scores for at least 50% of days during the severe symptom period were included.

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: Randomized set (RAN): The RAN included all randomized patients, regardless of whether they received any study drug. Patients in the RAN was analyzed according to the treatment assigned at randomization.

6. Primary Endpoint

The registry lists the primary outcome as Mean Nasal Symptom Score, measured over Severe symptom period (from 23Feb2018 to 24March2018).

The primary endpoint was the mean nasal symptom score during the severe symptom period, reported as a least-squares mean with a standard error. Patients recorded symptoms every day in an e-Diary. Sneezing, rhinorrhea, and nasal congestion were each rated from 0, meaning none, to 4, meaning intense or severe. The three component scores formed a total nasal symptom score on a 0-12 point scale.

The severe symptom period was defined around the three weeks with the maximum cumulative value of the mean daily nasal symptom score. Its definition also incorporated rules concerning concomitant fluticasone propionate use: at least 70% of the relevant period had to meet one of the stated use criteria, or the period was extended to meet a criterion. The primary timeframe is listed as Severe symptom period (from 23Feb2018 to 24March2018).

An average score gives a compact measure of reported symptom burden across the period, while combining the three nasal symptoms captures more than any single symptom alone. The score is patient-reported and therefore reflects recorded symptom severity, not an objective measurement of nasal function. The registry record does not report a threshold for a clinically important score difference, so statistical separation should not by itself be treated as proof of a particular level of practical importance.

7. Results Posted in the Registry

• Omalizumab: mean 3.66 versus 4.69 on control; difference -1.03 (95% CI -1.44 to -0.62), standardized effect d = -0.54; z-test p = <0.001.

8. Secondary Efficacy Endpoints

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

Mean Score for Impairment of Daily Activities

• 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:
  • Omalizumab: mean 1.09 versus 1.43 on control; difference -0.34 (95% CI -0.48 to -0.20), standardized effect d = -0.52; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Omalizumab than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Completely Nasal Symptom Free Patients

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Omalizumab: 8.2% (13/158) versus 2.3% (4/174) on control; risk difference 5.9 percentage points (95% CI 1.1 to 10.8), risk ratio 3.58 (1.19–10.75); unadjusted two-proportion z-test p = 0.014.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Omalizumab than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists secondary outcomes spanning ocular and combined nasal-ocular symptoms, symptom-medication scores, severity ratings for nasal and eye symptoms, daily activity impairment, symptom-free days and patients, and rescue medication. This range shows that the study assessed more than the primary average nasal symptom score. The secondary measures address different dimensions of symptom burden, and their scales and interpretations are not interchangeable with the primary endpoint.

The posted secondary results include a mean score for impairment of daily activities and the count of completely nasal symptom-free patients. Their reported comparisons are directionally consistent with lower activity impairment scores and a higher count of symptom-free patients in the omalizumab group than in placebo. The registry gives a 95% interval for the activity-impairment difference and a logistic-regression odds ratio for completely symptom-free patients. These findings can add context to the primary symptom-score result, but they do not establish that every listed secondary measure followed the same pattern.

Secondary outcomes generally carry less confirmatory weight when many outcomes are examined and the registry does not report how multiplicity was controlled. Repeated testing creates more opportunities for apparently notable findings to arise by chance. The registry record does not report an adjustment strategy for the secondary analyses, nor does it specify a hierarchy that would establish which secondary outcomes were confirmatory. Their estimates are therefore best treated as supporting or exploratory context, rather than as independent proof that the primary finding generalizes across every symptom or functional measure.

The registry identifies 14 posted secondary outcomes, but the numerical results and analysis details are not present in the record summarized for every listed measure. Where an outcome-specific estimate, interval, or test is not reported in the registry record, its direction and uncertainty cannot be assessed from the available information. The broad pattern should therefore be described cautiously: the primary result concerns mean nasal symptoms, while the secondary findings offer limited additional perspectives and do not replace it.

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

• Mean Ocular Symptom Score and Mean Nasal Ocular Symptom Score
• Mean Nasal Symptom Medication Score, Mean Ocular Symptom Medication Score, and Mean Nasal Ocular Symptom Medication Score
• Mean Score for Severity of Sneezing, Rhinorrhea and Nasal Congestion
• Mean Score for Severity of Itchy and Watery Eye
• Mean Score for Impairment of Daily Activities
• Number of Symptom Free Days
• Completely Nasal Symptom Free Patients
• Rescue Medication Score

9. Statistical Interpretation

10. Statistical Methods Explained

The primary result is presented as a least-squares mean comparison analyzed with ANCOVA. The registry record reports the sponsor’s result and the arm-level least-squares means, but it does not report the ANCOVA covariates, model diagnostics, or full statistical analysis plan. The explanation below describes the general meaning of the methods; it does not fill in those unreported details.

What does a least-squares mean represent?

A least-squares mean is a model-based estimate of an outcome mean. In general, it can account for specified covariates in the model, unlike a simple arithmetic mean calculated directly from raw observations. The registry reports values of 3.66 for omalizumab and 4.69 for placebo, but the adjustment variables used to obtain these estimates are not reported in the registry record. Therefore, the posted estimates should be read as the registry’s model-based group summaries, without assuming which patient characteristics or baseline measures were included.

What does ANCOVA do?

In general, analysis of covariance compares group outcomes while adjusting for covariates included in the statistical model. Such adjustment can improve precision when the covariates are relevant and appropriately modeled, but the result depends on which variables are entered and how the model is specified. The registry names ANCOVA for the primary comparison, but does not report its covariate list, whether baseline nasal symptom score was included, or the details needed to reproduce the analysis. The posted ANCOVA estimate is therefore the reported sponsor analysis; the summary-statistic re-calculation is not a substitute for the underlying model.

How should the mean difference be read?

The reported mean difference is -1.03 points, with omalizumab compared with placebo. The negative sign indicates that the estimated mean score in the omalizumab group is lower. Because this endpoint measures symptom severity and lower component ratings mean less recorded severity, the direction describes the observed score contrast. The difference is expressed in nasal symptom score points, not as a percentage reduction. No percentage or ratio interpretation is warranted from the reported mean difference.

What does the standard error describe?

The registry reports standard errors of 0.151 for the omalizumab least-squares mean and 0.144 for the placebo least-squares mean. In general, a standard error reflects the estimated sampling variability of an estimate. It is not the same as the spread of individual patient scores. The primary outcome entries do not provide standard deviations or raw observations, so the standard errors should not be described as showing how widely individual symptoms varied.

Why use a confidence interval?

A confidence interval conveys uncertainty in the estimated contrast, in the units of the outcome. The sponsor’s 95% interval is from -1.44 to -0.62. In general, the interval indicates the range of estimates compatible with the observed data and the model at the stated confidence level. It is not a guarantee that the true value lies inside these particular endpoints, and it does not describe the range of individual patient outcomes. The interval also does not establish clinical importance, which requires context not reported for this score.

What is the role of the re-calculation?

The re-calculated comparison uses the posted arm summaries to obtain a simple unadjusted contrast and its uncertainty. It is a secondary statistical check, not an independent trial analysis. The calculations use the least-squares means and standard errors reported for the outcome, and the pooled standard deviation is approximate. Summary statistics do not retain all the information in patient-level data or in the sponsor’s ANCOVA model. Here the re-calculated difference and interval are close to the sponsor’s reported figures, and the registry record does not flag a discrepancy. The sponsor’s own analysis is the result to prioritize when describing the registered analysis.

Why can over-dispersion matter?

In general, a model for a count or binary outcome may assume a particular amount of variability. Over-dispersion means the observed variability exceeds that assumption, which can make standard errors too small and confidence intervals too narrow if it is ignored. This is a general issue for suitable outcome types, not a claim that over-dispersion occurred in the nasal symptom score analysis. The registry record does not report an over-dispersion assessment for the primary endpoint. The primary score is analyzed as a continuous measure, and its reported ANCOVA result should not be reinterpreted as a count model.

Statistical significance, effect magnitude, uncertainty, and clinical importance answer different questions. The p-value describes evidence under a statistical model; the mean difference gives the estimated contrast in score points; the confidence interval conveys uncertainty; and clinical importance requires a meaningful threshold or contextual evidence. The registry provides the first three pieces in the posted primary analysis but does not report a threshold for interpreting the size of the score difference.

11. Confidence Intervals and Precision

The sponsor’s reported primary estimate is a mean difference of -1.03 points, with a 95% confidence interval from -1.44 to -0.62. The interval is entirely below zero, indicating that the reported model’s compatible estimates are negative. Its width also makes clear that the point estimate should not be treated as exact. The data support a range of plausible contrasts rather than a single certain value.

The interval concerns the group-level mean difference, not individual patients’ symptom scores. It does not mean that each patient’s score fell within the interval, nor does it measure the dispersion of scores among patients. The standard errors reported for the arm-level least-squares means are 0.151 and 0.144; these quantify uncertainty in those estimated means, not the spread of individual symptom reports.

The re-calculation gives a 95% confidence interval from -1.439 to -0.621, compared with the sponsor’s rounded interval from -1.44 to -0.62. This close agreement is consistent with rounding and the use of a simple summary-statistic calculation alongside the reported ANCOVA. It does not establish that the methods are identical. The sponsor’s analysis uses the registered model, while the re-calculation is unadjusted and based on posted summaries.

Precision should be considered alongside the endpoint definition and the analysis population. The result applies to the severe symptom period and to the population meeting the registry’s full analysis set and diary-completion criteria. The registry record does not report a clinically important difference threshold, so the interval cannot determine by itself whether every value it contains would be important in practice. It supports a statistically distinct score contrast, while leaving the practical interpretation dependent on context not included in the record.

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 the primary continuous outcome, not total events. They are illustrations computed from the observed effect, using a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The planning calculation considers the stated effect as 100%, 75%, or 50% of the observed effect. These are assumptions for the illustration; the trial’s original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the illustrated number of participants per arm for a design with an 80% chance of detecting the assumed effect under the planning assumptions, if that effect and those assumptions held. The 90% power column gives the corresponding figure for a design with a 90% chance. These percentages describe planned sensitivity to a specified effect, not the probability that the trial result is correct. For example, the primary-outcome illustration lists 54 participants per arm for 80% power and 72 participants per arm for 90% power when planning for 100% of the observed effect. Planning for 75% lists 95 and 127; planning for 50% lists 214 and 286.

Smaller effects are harder to distinguish from random variation under otherwise similar assumptions, so the illustrated participant requirements increase as the assumed fraction of the observed effect gets smaller. These figures are not the trial’s original enrollment target and are not evidence that the completed trial had a particular probability of success. This is not observed power: it is a forward-looking planning illustration calculated from the observed effect, and it should not be used as a measure of how convincing the observed result is.

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 = -1.030; pooled standard deviation σ = 1.899.
2. n = 2 × (1.96 + 0.842)² × 1.899² / -1.030² = 53.3, rounded up to 54 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 <- -1.03                      # observed difference in means
sigma <- 1.89880080018623                     # 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(3369704)
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 = 54 (80% power), 72 (90% power)
 75% of observed effect: n per arm = 95 (80% power), 127 (90% power)
 50% of observed effect: n per arm = 214 (80% power), 286 (90% power)
power.t.test: 54.3 
Simulated power at n = 54 per arm: 0.795 (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 registry reports the sponsor’s primary analysis as ANCOVA, with a least-squares mean difference of -1.03, a 95% confidence interval from -1.44 to -0.62, and p < 0.001. The summary-statistic re-calculation gives a mean difference of -1.03, a 95% confidence interval from -1.439 to -0.621, and an unadjusted p-value of p < 0.001. The estimates are closely aligned, with the small display differences in the interval reflecting the precision at which the results are reported.

The re-calculation is a simple unadjusted check based on the posted outcome summaries. It does not reproduce ANCOVA, because the registry record does not provide the model covariates or patient-level data. The sponsor’s ANCOVA result is therefore the appropriate primary analysis to cite when describing the registry’s reported statistical analysis. Since the registry record does not flag a discrepancy, the re-calculation serves as a consistency check rather than a competing estimate.

Agreement between these results is reassuring about the direction and approximate magnitude of the summary contrast, but it does not verify every modeling choice or resolve unreported details. In particular, the registry record does not report the full analysis plan, covariate specification, or missing-data sensitivity analyses. Those omissions limit independent reproduction of the sponsor’s model, even though the displayed estimate and interval can be compared with the simple re-calculation.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several statistical comparisons are made. Even when each comparison is evaluated using a conventional significance threshold, the chance of at least one false-positive finding can increase across a collection of tests. This is a general statistical concern, especially for secondary outcomes that cover multiple symptoms, medication scores, and functional measures.

The registry lists 14 posted secondary outcomes and reports a range of secondary analyses. It does not report whether the sponsor controlled the family-wise error rate, used another multiplicity procedure, or specified an ordered testing strategy. The handling of multiplicity is therefore not reported in the registry record. The primary endpoint has a reported p-value, but the record does not provide enough information to infer how the full set of analyses was treated in the original statistical plan.

The registry does define the primary analysis population. The full analysis set consisted of patients in the randomized group who received at least 1 dose of study drug. Among those patients, the primary endpoint included those with nasal symptom scores for at least 50% of days during the severe symptom period. This is a specific diary-completeness criterion, and it means that the posted primary estimate is not simply a summary of all enrolled participants.

The registry record does not report how missing daily scores were handled, whether missingness was imputed, or whether sensitivity analyses assessed alternative assumptions. It also does not report whether the secondary outcomes used the same analysis population or distinct completion criteria. Missing-data methods can affect estimates when incomplete records are related to symptom severity or treatment assignment, but the record does not establish whether such a relationship occurred in this study.

These gaps do not negate the reported primary result, but they limit assessment of the robustness of the full analysis program. A reader can describe the sponsor’s stated endpoint, analysis population, estimate, and uncertainty. A reader cannot reconstruct the multiplicity plan, verify missing-data assumptions, or determine whether alternative analysis choices would materially change the results from the registry record alone.

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 2% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: testicular neoplasm (0.6%).

The registry reports serious adverse events and deaths by group. In the IGE025 group, 1 of 161 patients at risk had a serious adverse event, and there were 0 deaths. In the placebo group, 0 of 175 patients at risk had a serious adverse event, and there were 0 deaths. The most frequent serious adverse event term listed is Testicular neoplasm, reported as 0.6%.

These are descriptive counts from the registry. The zero serious adverse events recorded in the placebo group means none were reported in that group in the listed data; it does not establish that the underlying risk is absent. Likewise, the small number of serious events limits how precisely a group difference can be characterized. The registry also lists other adverse events affecting 26 of 161 patients in the IGE025 group and 21 of 175 in the placebo group. Those counts should not be conflated with serious adverse events.

The record does not provide event narratives, timing, duration, causality assessments, or detailed follow-up information in the registry record reported. The adverse-event figures therefore describe what was recorded in the registry and should not be read as a complete account of safety or as a causal comparison.

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

The primary result describes a lower mean recorded nasal symptom score in the omalizumab group than in the placebo group during the defined severe symptom period. The sponsor’s ANCOVA estimate is -1.03 points, with a 95% confidence interval from -1.44 to -0.62 and p < 0.001. The score was based on patient daily reports of sneezing, rhinorrhea, and nasal congestion, with lower ratings corresponding to less recorded severity.

This is a result for a particular population, comparison, measure, and period. The enrolled population consisted of adults and adolescents with severe Japanese cedar pollinosis and inadequate symptom control despite recommended therapies. The primary endpoint population was further defined by receipt of at least 1 dose and diary scores on at least 50% of days during the severe symptom period. The study evaluated subcutaneous omalizumab or placebo for 12 weeks on top of standard care as described in the registry.

The result does not, by itself, establish how patients would experience the difference in daily life. The record does not report a clinically important threshold for the nasal symptom score. Statistical evidence that the group means differ is distinct from evidence about whether the size of that difference is meaningful to patients. The result also does not establish effects on every secondary outcome, on symptoms outside the defined period, or in populations not described by the study eligibility criteria.

Nor does the primary endpoint alone provide a full safety assessment. The serious adverse event counts are descriptive and limited, and the registry record does not provide detailed event-level context in the information reported. Broader conclusions about safety, durability, or outcomes after the 12-week treatment period are not established by these results. The appropriate interpretation is therefore specific: the posted data show a negative between-group mean-score contrast for the defined endpoint, with the stated statistical uncertainty and the limitations of the reported analysis.

18. Why This Trial Matters Statistically

This trial illustrates why a clinical result should be read through its endpoint definition, not only through its p-value. The primary measure is an average of three patient-recorded nasal symptoms over a selected severe symptom period. Its interpretation depends on the rating scale, the period-selection rules, and the diary-completion criterion. Those details determine what the estimate represents and which patients contribute to it.

The record also makes it possible to contrast a model-based sponsor analysis with a simple summary-statistic re-calculation. Their close agreement supports the stability of the displayed direction and approximate magnitude, while the methods remain distinct. ANCOVA may account for covariates, but those covariates are not reported in the registry record. A re-calculation can check the posted summaries without reproducing a patient-level model.

The study also demonstrates the difference between statistical and practical interpretation. The confidence interval excludes zero, and the reported p-value is small, but the registry does not give a clinical-importance threshold for the score. Statistical evidence about a group contrast does not answer every question about relevance to patients.

Finally, the varied secondary outcomes and the limited safety counts show why outcome multiplicity and precision deserve attention. Secondary measures can add context, yet their interpretation depends on the testing strategy, which is not reported. Rare or infrequent serious events can be described, but the counts do not provide a precise characterization of comparative risk. These are useful reminders to interpret each result within the design and the limits of the registry record.

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.

The primary endpoint is a patient-reported score, and the registry record does not report a clinically important difference threshold. The statistical contrast can therefore be described in score points, but its practical importance cannot be determined from this record alone. The severe symptom period is selected using symptom patterns and rules about fluticasone propionate use; the result applies to that defined period rather than necessarily to the entire pollen season.

The primary analysis population requires at least 1 dose and nasal symptom scores for at least 50% of days during the severe symptom period. The registry does not report how missing daily scores were handled or whether sensitivity analyses explored alternative missing-data assumptions. This leaves uncertainty about the potential influence of incomplete diaries on the estimate.

The registry names ANCOVA but does not report its covariates, model diagnostics, or the full analysis plan. The simple re-calculation uses posted summary statistics and cannot reproduce the sponsor’s patient-level model. The record also does not report the original sample-size justification, interim analyses, or multiplicity procedure for the range of secondary outcomes. These elements cannot be inferred from the observed results.

The listed serious adverse event counts are limited and lack event-level context such as timing, duration, or causality assessment in the information reported. The registry record also does not provide enough numerical detail to characterize all listed secondary outcomes. These limitations define what can be concluded from the posted record; they do not establish that unreported procedures or analyses were absent from the full study documentation.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study of Efficacy and Safety of Omalizumab in Severe Japanese Cedar Pollinosis Adult and Adolescent Patients — NCT03369704.
• Registry record last updated 2026-01-12; status last verified 2025-12.
• Results first posted 2019-11-04.
• 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

NCT03369704 is a completed, randomized, triple-masked, parallel-group Phase III study sponsored by Novartis Pharmaceuticals. It enrolled adults and adolescents with severe Japanese cedar pollinosis whose symptoms were inadequately controlled despite recommended therapies. The registry lists 337 enrolled participants and a 12-week comparison of subcutaneous omalizumab with placebo on top of standard care.

The primary outcome was mean nasal symptom score during the severe symptom period. The sponsor-reported ANCOVA difference was -1.03, with a 95% confidence interval from -1.44 to -0.62 and p < 0.001. The posted primary endpoint analysis applied the stated full analysis set and diary-completion criteria.

The record lists secondary symptom, medication, and functional outcomes, as well as serious adverse event counts. Important details—including the original sample-size justification, multiplicity strategy, missing-data methods, ANCOVA covariates, and clinical-importance threshold—are not reported in the registry record.