A Clinical Trial of Omalizumab in Participants With Chronic Rhinosinusitus With Nasal Polyps: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Clinical Trial of Omalizumab in Participants With Chronic Rhinosinusitus With Nasal Polyps (NCT03280537), a randomized phase 3 study. The primary outcome is Change From Baseline in Nasal Polyp Score (NPS) at Week 24.

2. Clinical Question

The trial was intended to assess efficacy and safety in this population. The principal statistical result concerns the scored size of nasal polyps, rather than every symptom, quality-of-life measure, or subsequent intervention. Other recorded outcomes include nasal symptoms, SNOT-22, rescue medication, surgery, and an asthma quality-of-life measure for participants with comorbid asthma.

3. Trial Design

This was a Phase III, randomized, multicenter, double-blind, placebo-controlled, parallel-group clinical trial. The registry records quadruple masking. The study enrolled 127 participants and is marked completed. The recorded start date is 2017-11-21, and the primary completion date is 2019-03-07.

Participants were assigned to omalizumab or matching placebo. Omalizumab was administered by subcutaneous injection every 2 weeks or every 4 weeks, with dose and frequency determined by serum total IgE level and body weight using the study-drug dosing table. The placebo schedule was likewise every 2 weeks or every 4 weeks. The treatment descriptions indicate that all participants also received additional treatment during the study, but the registry text for that detail is incomplete; the specific treatment cannot be established from the registry record.

The primary outcome was change from baseline in Nasal Polyp Score at Week 24. The primary analysis population is described as all randomized participants, with only participants who had both Baseline and Week 24 assessments included in the analysis. The arm summaries list 65 participants for placebo and 62 for omalizumab; these are the posted analysis counts, not a substitute for a detailed account of participant flow.

The registry describes a parallel Phase III study by the sponsor with identical objectives and design, run at the same time. Information about the full randomization procedure, allocation concealment, site count, adherence, treatment discontinuation, and other protocol details is not reported in the registry record. The statistical plan beyond the stated outcome analyses is also 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: At the first visit of the 5-week screening/run-in period, participants were asked to standardize their nasal corticosteroids to a regimen of mometasone, 200 micrograms twice a day (BID). If intolerant to a BID regimen, then they remained on a stable dosage of mometasone once a day (QD) during the run-in period and throughout the treatment period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set: all participants randomized to study treatment. Only participants with assessments at Baseline and Week 24 were included in the analysis.

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 Change From Baseline in Nasal Polyp Score (NPS) at Week 24, measured over Baseline, Week 24.

The primary endpoint is change from baseline in total Nasal Polyp Score at Week 24. The score ranges from 0 to 8, formed from left and right nasal passage scores, each scored from 0 to 4. A lower score indicates smaller-sized nasal polyps. The component categories run from no polyps to large polyps causing complete obstruction of the inferior nasal cavity.

This endpoint turns endoscopic observations into an ordinal score that can be compared over time between treatment groups. It focuses on polyp size and obstruction, rather than relying only on participant-reported symptoms. Two blinded primary independent expert readers reviewed each participant’s post-screening video endoscopy. If their total scores differed, a third reader selected one of the two scores for analysis. Blinded review is relevant because it can reduce the influence of knowledge of treatment assignment on outcome scoring.

The registry reports a least-squares mean change and a 95% confidence interval for each group, and a model-based contrast between groups. In this analysis, a more negative change corresponds to a larger reduction in score, while the between-group contrast describes the estimated difference in mean change. The score’s scale and scoring rules give the result clinical context, but the registry record does not report a threshold for a clinically important difference. The endpoint therefore indicates change in the scored polyp measure, not by itself the overall value of treatment across all outcomes.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a least-squares mean represent?

General explanation: a least-squares mean is a model-based estimate of a group mean. It is not necessarily the same as the ordinary arithmetic mean of every observed value, because its calculation depends on the statistical model and how that model handles repeated observations and other included terms. The registry reports least-squares means for the change in Nasal Polyp Score and a difference in those means. The full model specification, including all included terms and any covariance structure, is not reported in the registry record.

The posted changes were -0.31 for placebo and -0.9 for omalizumab. The reported contrast was -0.59. The negative sign indicates that the estimated change in the omalizumab group was more negative relative to placebo. Since lower scores indicate smaller polyps, the direction corresponds to a greater decrease in the score in the omalizumab group. The contrast is an estimated group-level difference, not an individual treatment effect.

How should the confidence interval be read?

General explanation: a confidence interval describes the precision of an estimate under the statistical model and its assumptions. A narrower interval conveys greater precision than a wider interval. The reported 95% confidence interval for the primary contrast runs from -1.05 to -0.12. It excludes zero, so the values in this interval all indicate a negative contrast. The interval still permits a range of possible magnitudes; it should not be treated as a guarantee that the true effect lies within those exact endpoints for this particular trial.

A confidence interval does not express the probability that the treatment works, and it does not show how many participants experienced improvement. It is an interval for the model-based difference in mean change. The arm-level intervals are -0.63 to 0.01 for placebo and -1.23 to -0.57 for omalizumab. The sponsor-reported contrast interval is the more direct interval for comparing the groups; comparing overlap between separate group intervals is not a substitute for examining the contrast interval.

What does the reported p-value contribute?

General explanation: a p-value measures how incompatible the observed data are with a specified null hypothesis under the model and assumptions used. It is not the probability that the null hypothesis is true, nor a measure of the size or clinical importance of a difference. For the primary outcome, the registry reports p = 0.014. Read together with the confidence interval and estimated contrast, this is evidence against a zero difference under the reported model. The registry record does not report enough detail to independently verify the model assumptions or reproduce the test.

Why use a repeated-measures model?

General explanation: repeated-measures methods are designed for outcomes measured at more than one time, accounting for the fact that measurements from the same participant are related. They can use available repeated observations according to the model, rather than treating every measurement as independent. The primary analysis is identified as a Mixed-Effect Model of Repeated Measures. However, the record does not specify the exact time points entered in the model, the treatment of missing observations, or the assumptions used for missing data. Those omissions limit assessment of how sensitive the result may be to missingness.

The analysis population is described as randomized participants, but inclusion in the primary endpoint analysis required assessments at Baseline and Week 24. That qualification means the stated analysis does not necessarily include every randomized participant. The record does not report the number missing either assessment or the reasons for missingness. It also does not report a sensitivity analysis showing how alternative assumptions about missing outcomes would affect the estimate.

Why are rare binary outcomes less precise?

General explanation: when an outcome occurs infrequently, a small change in the event count can have a substantial influence on an estimated relative effect. Confidence intervals can consequently be wide, and some estimates may be unstable when a group has no events. The posted rescue-medication and surgery counts are small, and the surgery outcome has no reported events in the omalizumab group. The sponsor used a Wald Chi-Square analysis for rescue medication and a Fisher Exact analysis for surgery. Different methods can behave differently with sparse data, so the estimates and intervals should be read with their event counts in view.

For the AQLQ response among participants with comorbid asthma, the registry reports a Wald Chi-Square odds-ratio analysis. The recalculateable comparison uses a risk difference, which is a different way to express a treatment contrast. General explanation: a risk difference compares event proportions by subtraction, while an odds ratio compares the odds of an event. They answer related but nonidentical descriptive questions and need not have the same numerical scale or inference. The registry’s analysis is the sponsor-reported result; the posted summary-statistic recalculation is an unadjusted complementary calculation, not a replacement for the reported model.

What does over-dispersion mean?

General explanation: over-dispersion occurs when variability in the data is greater than a statistical model expects. It can make standard errors too small if the model does not account for that extra variation. The primary endpoint is a continuous score analyzed with a repeated-measures model, and the registry does not report an over-dispersion assessment. This concept is relevant generally, but no conclusion about over-dispersion in this trial can be drawn from the registry record.

The recalculated risk-difference confidence intervals and planning illustrations are based on posted summary counts and are not the same as the sponsor’s model-based analyses. Planning illustrations use assumed design conditions and an effect fraction; they are not observed power and do not establish that the trial was adequately powered. The trial’s own sample-size justification and assumptions are not reported in the registry record.

10. Analyses Reported by the Sponsor

For the primary endpoint, the registry reports the sponsor’s mixed-effect model of repeated measures: a difference in least-squares means of -0.59, with a 95% confidence interval from -1.05 to -0.12 and p = 0.014. The group estimates and this contrast should be treated as the reported analysis. The model specification is not detailed enough in the registry record for an independent reconstruction.

For the binary secondary outcomes, the sponsor’s methods differ from the summary-count recalculations. Rescue medication is reported using a Wald Chi-Square odds-ratio analysis, surgery using a Fisher Exact analysis, and the AQLQ response using a Wald Chi-Square odds-ratio analysis. The recalculated quantities are unadjusted risk differences derived from posted counts. An odds ratio and a risk difference describe the contrast on different scales, and their confidence intervals or p-values need not match. The sponsor’s own analysis takes precedence if the two approaches disagree; the registry’s discrepancy flag is false.

These calculations are useful as checks on direction and scale, but they do not reproduce the sponsor’s model. The registry record does not provide the full analysis code, detailed model specifications, or all assumptions needed for an exact independent replication.

11. Multiplicity, Missing Data and Analysis Populations

The registry identifies the primary endpoint and reports a model-based analysis, but it does not report a complete statistical analysis plan. In particular, a multiplicity strategy for the numerous secondary outcomes is not reported in the registry record. General explanation: when multiple outcomes or hypotheses are tested, the chance of at least one apparently positive result can rise. Prespecified ordering or statistical adjustment can help control that issue. Without a documented strategy, secondary p-values should not be interpreted as though each were the sole test in the study.

The primary analysis population is described as the Full Analysis Set: all randomized participants, with only participants assessed at Baseline and Week 24 included in the analysis. This definition indicates an assessment-based restriction within the stated population. The registry record does not report how many randomized participants lacked either assessment, why they were missing, or how missing observations were handled in the repeated-measures model. It does not report sensitivity analyses for alternative missing-data assumptions.

The record also does not report a per-protocol population, an as-treated analysis population, or a detailed participant disposition by reason for exclusion or discontinuation. These details would help readers understand how closely the analyzed participants correspond to the randomized groups and whether missingness may have affected interpretation.

Interim analyses, stopping rules, and any adjustment for repeated looks at the data are not reported in the registry record. The trial’s sample-size justification, target effect, and assumptions are also not reported. The posted planning illustrations are based on observed effects and stated illustrative assumptions; they are not evidence of observed power and do not establish the trial’s original design rationale. These omissions do not negate the reported estimates, but they limit independent evaluation of the analysis choices and robustness.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: hand fracture (1.6%), snake bite (1.6%), asthma (1.6%), pneumonia (1.6%).

The serious adverse event counts were 1 among 64 participants at risk in the placebo group and 3 among 63 participants at risk in the omalizumab group. The registry reports 0 deaths in each group. These counts describe the posted safety data; they do not by themselves establish whether an event was caused by treatment. The registry lists Hand fracture, Snake bite, Asthma, and Pneumonia among the leading serious-event terms, each reported as 1.6%.

Other adverse event counts were 20 among 64 participants at risk with placebo and 17 among 63 participants at risk with omalizumab. Serious and other event summaries are distinct categories and should not be combined. The at-risk counts for safety differ from the primary endpoint arm counts, so the denominators should be read as specific to the safety summaries rather than assumed to match the endpoint analysis population.

Safety counts are descriptive and do not establish comparative risk with precision, particularly when event counts are small. The registry record does not report detailed event timing, severity gradations beyond the serious-event classification, relatedness assessments, or a complete treatment-emergent safety analysis plan. These figures therefore provide a limited account of observed events, not a complete benefit-risk assessment.

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

The primary result is an estimated difference in mean change in Nasal Polyp Score at Week 24. The omalizumab group’s reported least-squares mean change was -0.9, compared with -0.31 for placebo; the model-based contrast was -0.59, with a 95% confidence interval from -1.05 to -0.12. Because lower scores indicate smaller-sized polyps, the contrast points toward a larger reduction in the score with omalizumab during the measured period. The confidence interval and p-value describe statistical uncertainty under the reported model.

This result does not show that every participant’s polyps became smaller, nor does it quantify each person’s response. It does not establish the importance of the score difference to participants, because a threshold for clinical importance is not reported in the registry record. It also does not, by itself, establish effects on all symptoms, quality of life, need for surgery, or longer-term outcomes.

The trial’s population was adults with chronic rhinosinusitis with nasal polyps who had an inadequate response to standard-of-care treatments. Results should be understood in that study context. The primary analysis required Baseline and Week 24 assessments, and the registry does not report enough detail about missing observations to determine how much the result might depend on those data.

Statistical evidence of a difference is not equivalent to proof of an overall treatment benefit. A complete interpretation also considers precision, clinical relevance, secondary outcomes, safety, and limitations in reporting. The serious adverse event counts and secondary comparisons add context but do not resolve every uncertainty. The record supports a model-based difference in the primary score; it does not establish a comprehensive conclusion about long-term outcomes or all dimensions of treatment value.

14. Why This Trial Matters Statistically

This trial is statistically informative because it reports a continuous primary outcome with group-level estimates, a model-based between-group contrast, a confidence interval, and a p-value. Those elements allow readers to consider not only the direction of the difference but also its uncertainty. The use of blinded expert review for the endoscopic score is also relevant to measurement: the endpoint depends on interpreting recorded examinations, and the registry describes a process for resolving disagreement between readers.

The record also illustrates why the analysis method matters. A repeated-measures model produces a contrast that is not simply the difference between two raw summaries. For sparse binary outcomes, the sponsor uses odds-ratio analyses, while summary-count recalculations can express risk differences. These measures answer related but different questions, and a reader should not mistake one for an exact replication of the other.

Finally, the record shows the limits of interpreting a result in isolation. Secondary testing, missing data, the analysis population, and safety all affect how much confidence can be placed in a broad conclusion. Here, the primary estimate is accompanied by useful uncertainty information, but several details of the analysis plan and missing-data handling are not reported. Recognizing both the evidence and those limits is central to sound statistical interpretation.

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 registry record gives the primary result and identifies the repeated-measures method, but it does not provide the full model specification. Details such as the model terms, covariance structure, exact handling of incomplete repeated observations, and any sensitivity analyses are not reported in the registry record. That limits independent reproduction and assessment of robustness.

The primary analysis required both Baseline and Week 24 assessments. Participant flow and reasons for missing assessments are not reported in the registry record. Without those details, it is not possible to determine from this record whether missingness differed by treatment group or how that may have influenced the estimate.

The threshold for a clinically important change in Nasal Polyp Score is not reported. Thus, the statistical evidence for a difference cannot be translated from this record alone into a judgment about clinical importance. The secondary outcomes span different measures and populations, and a multiplicity strategy is not reported. Rare event outcomes also have limited precision, as reflected by the small counts and wide intervals.

The record’s intervention descriptions include a dose range and dosing schedule but do not fully specify all treatment details in the available text. It also does not report adherence, treatment discontinuation details, site count, allocation concealment, interim analyses, or a detailed sample-size justification. The trial is marked completed, but follow-up beyond the stated outcome timeframes is not described in the registry record. These limitations narrow what can be concluded from the posted results and do not imply that any unreported procedure was or was not conducted.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Clinical Trial of Omalizumab in Participants With Chronic Rhinosinusitus With Nasal Polyps — NCT03280537.
• Registry record last updated 2020-03-23; status last verified 2020-03.
• Results first posted 2020-03-23.
• 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, randomized, multicenter, double-blind, placebo-controlled Phase III parallel-group trial of omalizumab for adults with chronic rhinosinusitis with nasal polyps and an inadequate response to standard-of-care treatments. It reports enrollment of 127 and quadruple masking.

The primary outcome was change from baseline in Nasal Polyp Score at Week 24. The reported difference in least-squares means was -0.59, with a 95% confidence interval from -1.05 to -0.12 and p = 0.014. Lower scores indicate smaller-sized polyps.

The registry also reports secondary outcomes and adverse event counts, but details about multiplicity, missing-data handling, model specification, and the trial’s sample-size justification are not reported in the registry record. The primary result should therefore be read as evidence about the measured Week 24 score, alongside the stated uncertainty and reporting limitations.