COVID-19 Anosmia Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for COVID-19 Anosmia Study (NCT04495816), a randomized phase 2 study. The primary outcome is Change in Brief Smell Identification Test (BSIT).

2. Clinical Question

The clinical question concerns change in a smell-identification score over the trial period, with the two arms providing the comparison. The registry describes additional patient-reported measures, including the Modified Brief Questionnaire of Olfactory Dysfunction and the Sinonasal Outcomes Test. Its summary also describes a 6-week BSIT assessment alongside patient-reported outcomes. The available record does not provide numerical outcome results, estimates of the between-arm difference, confidence intervals, or hypothesis tests. Consequently, it is not possible to determine from the registry record how the arms compared or how precisely any comparison was estimated.

3. Trial Design

The COVID-19 Anosmia Study is listed as a phase 2 randomized, double-masked, parallel trial. The registry record reports enrollment of 139 and a completed status. It identifies the sponsor as Icahn School of Medicine at Mount Sinai. The listed study start was 2020-07-15, and the primary completion date was 2021-12-31.

Participants were assigned to omega-3 fatty acid supplementation or placebo/control. The omega-3 arm is described as receiving 1,000 mg per day in 2 softgels for 6 weeks; the placebo/control arm is described as taking 2 softgels per day for 6 weeks. The record identifies both interventions as drugs. It does not give further details about sequence generation, allocation concealment, or how masking was maintained, so those design features are not reported in the registry record.

The primary outcome is change in BSIT score, assessed at Week 0 and Week 6. The BSIT is described as a 12-item instrument with a full-range score from 0 to 12; higher scores indicate better olfactory performance. Secondary outcomes include the Modified Brief Questionnaire of Olfactory Dysfunction and the Sinonasal Outcomes Test. The brief summary also refers to SNOT-22 and QOD-NS patient-reported outcome measures.

The registry record lists 6 outcome measures, but does not provide numerical results or analyses for them. It records no analyses. The listed enrollment and design identify the trial’s planned comparison, but do not establish how many participants contributed data to any outcome, whether the assigned interventions were followed as planned, or whether outcome data were complete. Those details 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.

Overall Study

Reasons for not completing this period:

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 in Brief Smell Identification Test (BSIT), measured over Week 0 and Week 6.

The primary endpoint is change in Brief Smell Identification Test score between Week 0 and Week 6. The BSIT is a 12-item smell-identification instrument. Its full-range score runs from 0 to 12, and a higher score indicates better olfactory performance. The registry describes the outcome as a mean with standard deviation.

In general, a change endpoint uses measurements taken at different times to describe how a participant’s score shifts over a defined period. Comparing change between randomized arms can address whether the average pattern differed between the intervention and comparator groups. It is important to distinguish the average change within each arm from the difference in change between arms: the within-arm values alone do not establish a treatment contrast.

Using a standardized score can make a measured aspect of olfactory function easier to compare across participants than relying only on an unstructured description. The trial also lists patient-reported measures, which capture participants’ reported experience rather than performance on the BSIT. These measures address related but not necessarily identical aspects of olfactory dysfunction.

The registry record does not report the arm-specific means, changes, between-arm estimate, uncertainty interval, or analysis result for the primary endpoint. Thus, the endpoint’s definition and scoring direction are available, but the observed change and the precision of the comparison are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary outcome as a continuous measure summarized by a mean and standard deviation. General statistical concepts can clarify what those summaries and a comparison would mean, but they cannot replace the missing trial estimates. No inferential analysis of the primary outcome is reported in the registry record.

What a mean and standard deviation describe

In general, a mean represents the arithmetic average of measured values. For a change score, it describes the average change among the participants included in that calculation. The standard deviation describes the spread of individual values around the mean. A larger spread means participants’ observed values vary more, while a smaller spread means they are more clustered. The standard deviation is not the same as the standard error: the standard deviation describes variability among observations, whereas the standard error describes uncertainty in an estimated mean.

Because the endpoint is change from Week 0 to Week 6, the analysis needs to define how change is calculated and which participants have measurements contributing to it. The registry gives the measurement times and identifies the outcome as change, but the specific analysis procedure and contributing analysis population are not reported in the registry record.

Why the between-arm estimate matters

In general, a randomized comparison is interpreted through an estimate contrasting outcomes in the assigned arms. Comparing each arm’s change separately with its own starting value is not equivalent to estimating the difference between the arms. Both groups can change over time for reasons unrelated to an intervention, so the comparative estimate is the quantity that addresses the randomized contrast. The registry record does not report that estimate for BSIT change.

A confidence interval, in general, expresses uncertainty around an estimated quantity. It is compatible with a range of values under the statistical model and its assumptions. Its width conveys precision: narrower intervals indicate greater precision, and wider intervals indicate less. A confidence interval should be interpreted together with the outcome scale and the direction of benefit or harm, not as a guarantee about the true value. No confidence interval for the primary comparison is reported in the registry record.

Distributional considerations

General methods for continuous outcomes often rely on assumptions about the distribution of measurements or model residuals. For example, a normal approximation can be used in some analyses when it is reasonable for the estimator and data structure. Other methods may be considered when observations are markedly skewed, contain influential outliers, or do not fit the model assumptions. The registry record does not report diagnostic checks, a model specification, or a method chosen for the BSIT analysis.

Over-dispersion is a general concern when observed variability exceeds what a statistical model assumes. If it is ignored, standard errors may be too small and intervals or tests may convey more certainty than warranted. This concept is not a finding about this trial: the registry record reports no analysis from which to assess dispersion or model fit.

Planning illustrations and observed power

The sample-size assumptions described for planning illustrations use a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is defined as a stated fraction of the observed effect. These are planning assumptions, not a description of the trial’s own design justification, and the planning illustrations are not observed power. Sample-size values calculated under those assumptions are not reported in the registry record.

In general, a planning calculation asks how much information would be needed to detect a prespecified effect under specified assumptions. It cannot establish whether an effect was observed, and it is not a substitute for reporting the estimate and its uncertainty. A post hoc calculation based on an observed effect can also be difficult to interpret because it depends on the observed estimate, which itself is uncertain. The record does not report a sample-size justification, so the trial’s original rationale for enrollment is not reported in the registry record.

What the analysis record permits

The registry reports 0 analyses and does not give a test, model, confidence interval, or comparative estimate for the primary endpoint. No p-value is reported. The status marked completed and the outcome definition do not disclose the statistical methods actually used, if any, or the results obtained. The analysis plan, interim analyses, and any adjustment for baseline score or other covariates are not reported in the registry record. Consequently, statistical interpretation must stop at the design and endpoint definitions rather than infer an effect or precision from unavailable analyses.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 6 outcome measures, including the primary BSIT outcome and secondary outcomes such as the Modified Brief Questionnaire of Olfactory Dysfunction and the Sinonasal Outcomes Test. The brief summary also names SNOT-22 and QOD-NS. Assessing multiple outcomes or multiple time points can create a multiplicity issue: in general, the more comparisons considered, the greater the chance of obtaining an apparently unusual result by chance if each is interpreted separately. Methods such as prespecifying a primary comparison or adjusting inference can address particular multiplicity concerns, but the registry record does not report a multiplicity strategy.

The primary outcome is described at Week 0 and Week 6, and the record indicates that it was not reduced to a single comparison because it has several categories or time points. No primary-outcome analysis is reported. The number and nature of any formal tests, the hierarchy among outcomes, and whether any adjustment was applied are not reported in the registry record.

Missing outcome data can affect both the analysis population and the interpretation of a comparison. In general, the implications depend on how much data are missing, why they are missing, and the assumptions used to address them. The registry record does not report missingness by arm, reasons for missing measurements, imputation methods, or sensitivity analyses. It also does not specify whether the analysis followed an intention-to-treat approach or another population definition. The number of participants contributing to each outcome analysis is not reported in the registry record.

These gaps limit assessment of the risk that selective outcome reporting, incomplete follow-up, or analytic choices could affect interpretation. They do not establish that any such problem occurred; they mean the relevant details are not reported in the registry record.

11. 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.

Most frequent non-serious adverse event terms

The registry’s adverse-event entries report 0 serious adverse events for the Omega-3 arm and 0 for the Placebo/Control arm. The numbers at risk listed for these serious-event entries are 70 and 69, respectively. Deaths are reported as 0 in both arms. For other adverse events, the record reports 0 in the Omega-3 arm and 5 in the Placebo/Control arm; the corresponding numbers at risk are 70 and 69.

These are the counts recorded in the registry, not estimates of comparative risk. They do not show whether the events were related to study treatment, how events were defined or collected, how long each participant was observed for safety, or whether the entries include all events. Those details are not reported in the registry record. The terms for serious adverse events are also not listed.

A count of zero recorded events should be read as no events reported in that entry, not as proof that an event is impossible or that risk is absent. Likewise, the other-adverse-event counts alone do not establish a causal difference between arms. The entries provide a limited safety summary and do not replace a full account of event types, severity, timing, attribution, and follow-up.

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

The registry record describes a randomized comparison of daily omega-3 supplementation with placebo/control in a study of COVID-19-associated olfactory dysfunction. It defines the primary outcome as change in BSIT score between Week 0 and Week 6 and states that higher scores indicate better olfactory performance. These details explain what the trial was designed to compare and how the primary scale is interpreted.

The record does not report an analysis of the primary outcome. It gives no arm-specific change, between-arm estimate, confidence interval, or test result. Therefore, it does not establish whether the groups differed in BSIT change, the direction or size of any difference, or the precision of an estimate. The absence of a reported result must not be interpreted as evidence of no effect or as evidence of an effect.

The completed status is a registry status, not an outcome finding. Enrollment of 139 describes the trial record but does not identify the analysis population or the number of participants with complete outcome data. Those details are not reported in the registry record. Similarly, the safety counts are limited registry entries and do not by themselves establish the overall safety profile or causation.

General statistical interpretation depends on more than the observed direction of a mean. It also considers uncertainty, the outcome’s scale, the analysis population, missing data, and the methods used. Since the registry record does not report the analyses or those supporting details, no conclusion about the comparative result can be drawn from it. A reader can identify the intended clinical question and the outcome definition, but cannot assess the trial’s estimated effect or its statistical precision from the posted results.

13. Why This Trial Matters Statistically

This trial illustrates the distinction between a registered study design and a report of analyzed results. A randomized, double-masked, parallel design specifies an intended comparison, and the BSIT definition specifies what was to be measured. Neither design labels nor outcome definitions provide an estimate of the observed treatment contrast. When analyses are not reported, the central statistical questions—what was estimated, how uncertain it was, and which participants contributed—remain unanswered.

The endpoint also illustrates why outcome scale and direction should be stated clearly. The BSIT score ranges from 0 to 12, with higher scores indicating better olfactory performance. That information helps orient interpretation if results are available, but it does not supply the results itself. The trial’s patient-reported measures represent additional outcomes, making a clear account of outcome hierarchy and multiplicity relevant to interpretation.

For clinical researchers, the record highlights the value of reporting arm-specific summaries together with the between-arm estimate and an uncertainty interval. Clear information about analysis populations, missing measurements, and statistical methods is also needed to judge how robust an estimate may be. Without those details, design features can be described, but the strength and precision of an outcome comparison cannot be evaluated.

The statistical importance of the record is therefore methodological rather than evidentiary: it identifies a clinical question and a measurable endpoint, while leaving the outcome analysis unreported in the registry record. That distinction prevents the design from being mistaken for a demonstrated result.

14. Limitations

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

Several trial-specific limitations in interpreting the registry record arise from information that is not reported. Although the study is marked completed, no analysis is listed and no numerical result is given for the primary BSIT outcome. The record therefore does not support an estimate of the difference between arms or an assessment of its precision.

The record gives the BSIT scale and assessment times, but does not describe the analysis procedure in detail. It does not state how participants with missing Week 0 or Week 6 scores were handled, how many contributed to the primary analysis, or which analysis population was used. Baseline outcome summaries and arm-specific outcome distributions are also not reported in the registry record.

The registry lists multiple outcome measures, but does not explain the hierarchy or give a multiplicity strategy. It does not report whether results were adjusted for baseline score or other variables, whether assumptions were checked, or whether any interim analysis occurred. The trial’s sample-size justification and the rationale for the enrollment target are not reported in the registry record.

Information on eligibility criteria, allocation concealment, maintenance of masking, adherence, and follow-up completeness is not included in the registry record reported for this trial. The placebo contents and further details of adverse-event collection are also not reported. These omissions limit assessment of trial conduct and of how broadly any eventual findings might apply. They do not show that the trial had a particular design or reporting problem; they identify information not reported in the registry record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: COVID-19 Anosmia Study — NCT04495816.
• Registry record last updated 2023-10-23; status last verified 2023-10.
• Results first posted 2023-01-31.
• 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.

18. Record Summary

The COVID-19 Anosmia Study is a completed phase 2 randomized, double-masked, parallel trial sponsored by Icahn School of Medicine at Mount Sinai. The registry reports enrollment of 139 and describes a comparison of daily omega-3 fatty acid supplementation with placebo/control over 6 weeks.

The primary outcome is change in BSIT score between Week 0 and Week 6. The score ranges from 0 to 12, with higher scores indicating better olfactory performance. Secondary outcomes include the Modified Brief Questionnaire of Olfactory Dysfunction and the Sinonasal Outcomes Test. The registry lists 6 outcome measures and 0 analyses.

No numerical primary-outcome results, comparative estimate, confidence interval, or test result are reported in the registry record. The adverse-event entries report 0 serious events in each arm, 0 deaths in each arm, and other adverse-event counts of 0 for Omega-3 and 5 for Placebo/Control. Further details about outcome analyses, missing data, and adverse-event collection are not reported in the registry record.