Study of the Safety and Efficacy of OmegaD Softgels in the Treatment of Dry Eye Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of the Safety and Efficacy of OmegaD Softgels in the Treatment of Dry Eye Disease (NCT02980224), a randomized phase 3 study. The primary outcome is Change From Baseline in Tear Break up Time(TBUT ) at Day 84.

2. Clinical Question

3. Trial Design

The registry describes NCT02980224 as a completed phase 3, randomized, multicenter, parallel-group, placebo-controlled study of OmegaD softgels for dry eye disease. Its official title calls the study double-masked, while the registry’s masking field says quadruple. The record does not explain the difference between those descriptions or identify which roles were masked. Allocation is listed as randomized. Details of sequence generation, allocation concealment, and procedures for maintaining masking are not reported in the registry record.

The brief summary describes oral dosing of 2 OmegaD softgels BID and matching placebo softgels BID for 84 days. It says approximately 164 subjects would be evaluated for signs and symptoms and safety. The registry lists enrollment as 180; the posted primary endpoint groups include 89.0 participants for OmegaD and 91.0 for placebo. Those counts refer to different record elements, and the registry does not explain their relationship. The planned sample-size rationale and the original design assumptions are not reported in the registry record.

The primary outcome was change from baseline in tear break up time at Day 84, measured in seconds. It is described as a least-squares mean, with standard error as the dispersion measure, for the Intent to Treat Population. The record lists three outcome measures and identifies the frequency and severity of adverse events as a secondary outcome. It posts one primary comparison, with an unadjusted p-value and an interval estimate. A detailed statistical analysis plan, including the model specification and handling of missing endpoint measurements, is 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:

Analysis population for the primary outcome, as defined in the registry: Intent to Treat Population

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 Tear Break up Time(TBUT ) at Day 84, measured over Baseline and 84 Days.

The primary endpoint is change from baseline in tear break up time (TBUT) at Day 84, measured in seconds. TBUT is a clinical test used to assess evaporative dry eye disease. As described in the registry, fluorescein is placed in the tear film, the participant is asked not to blink, and the tear film is observed under cobalt blue illumination. The recorded time is the interval between the last blink and the appearance of the first dry spot, observed using a slit lamp.

The endpoint therefore captures a timed physical sign of tear-film stability, rather than a direct report of symptoms. The registry describes the result as a least-squares mean change from baseline and reports standard errors for the arm estimates. The primary comparison is the difference in estimated mean changes between OmegaD and placebo at Day 84. The posted arm estimates are 1.45 seconds for OmegaD and 1.23 seconds for placebo; the estimated difference is 0.22 seconds.

Using change from baseline focuses the comparison on how the measured value differs from each participant’s starting value, rather than on the Day 84 measurement alone. The registry does not report a clinically important difference threshold or explain how this endpoint relates to symptoms for individual participants. The secondary outcome named in the record concerns the frequency and severity of adverse events; it is distinct from the TBUT efficacy endpoint.

7. Results Posted in the Registry

• OmegaD: mean 1.45 versus 1.23 on control; difference 0.22 (95% CI -0.50 to 0.94), standardized effect d = 0.09; z-test p = 0.550.

8. Statistical Interpretation

9. Statistical Methods Explained

What does a least-squares mean represent?

The registry labels the primary endpoint statistic as a least-squares mean. In general, a least-squares mean is an estimated group mean derived from a statistical model. Depending on the model, it may account for specified covariates or other features of the analysis. The registry record does not report the model specification or identify covariates, so the particular adjustments behind these estimates cannot be assessed from the entry. The posted endpoint is change from baseline to Day 84, and the displayed arm estimates are 1.45 seconds for OmegaD and 1.23 seconds for placebo.

In general, a change score is formed by comparing an endpoint measurement with a baseline measurement for the same participant. A group summary then describes the average change among participants included in the analysis. The registry identifies the primary population as Intent to Treat, but does not describe how missing baseline or Day 84 values were treated, or whether all participants assigned to a group contributed to this endpoint result.

What does the mean difference describe?

The posted mean difference is 0.22 seconds for OmegaD compared with placebo. It summarizes the difference between the two reported group estimates on the endpoint’s original measurement scale. A value of zero would represent no difference between the group estimates; values on either side represent different directions of contrast. The interval reported for the comparison extends on both sides of zero. The registry’s comparison is unadjusted, and details of any model used for the comparison are not reported.

In general, an unadjusted comparison uses the group results without an adjustment for multiple testing. The phrase does not, by itself, specify whether covariates were included in the underlying model. That model information is not reported in the registry record. The reported p-value is 0.55. A p-value is calculated under a null hypothesis and statistical assumptions; it describes how unusual the data or a more extreme result would be under that framework. It is not a measure of the probability that an effect exists, and it does not state the probability that results are due to chance.

Why report standard errors and an interval?

The registry gives standard errors of 0.261 seconds for OmegaD and 0.26 seconds for placebo. In general, a standard error describes the sampling uncertainty of an estimate under the statistical method used. It is not the same as the spread of individual participant measurements. The registry does not report standard deviations for the endpoint groups; the dispersion field identifies standard error. The comparison also has an interval estimate, but its confidence level is not reported in the registry record. Its span across zero is important because it leaves compatible values in both directions of the group contrast.

In general, a confidence interval combines an estimate with a measure of uncertainty under a statistical method. A narrower interval indicates greater precision under that method; a wider interval indicates less precision. An interval that contains zero does not prove there is no effect. It indicates that zero is among the values not excluded by that interval. Interpretation also depends on the model, population, and data-handling assumptions, some of which are not described in the registry record.

How do randomization and masking relate to the comparison?

Random allocation is intended, in general, to reduce systematic differences between treatment groups at the point of assignment. It does not guarantee that the groups will be identical in every characteristic, and it does not address every source of bias after assignment. The registry identifies the study as randomized and parallel, but does not report its sequence-generation or concealment procedures. The official title describes a double-masked study, whereas the masking field states quadruple; the record does not explain these labels. It is therefore possible to describe the registry’s design labels, but not to reconstruct all operational details.

A parallel-group design assigns participants to a group and compares outcomes between groups over the study period. The comparator is placebo softgels, with oral dosing described in the summary for 84 days. Whether adherence, protocol deviations, or other post-randomization events were handled in a particular way is not reported in the registry record.

What analysis details remain unclear?

The record lists zero separate analysis records, while still posting the primary endpoint estimates and a comparison with an unadjusted p-value. It does not provide a detailed statistical analysis plan, the exact test or model for the comparison, the confidence level for the interval, or the missing-data method. The reported analysis population is Intent to Treat, but the record does not explain the operational definition used for that population. These omissions matter because analysis choices can influence estimates and uncertainty. They do not invalidate the posted result, but they constrain how fully its statistical assumptions can be evaluated.

10. Confidence Intervals and Precision

The estimated difference in change from baseline is 0.22 seconds, with OmegaD’s group estimate above the placebo group estimate. The interval for the difference extends below and above zero. The registry does not state the confidence level, so the interval should not be assigned a conventional confidence label based on this record alone. Its key interpretive feature is that it includes both negative and positive values: the data are compatible with effects in either direction under the method used.

This interval indicates limited precision for determining the direction and size of the group difference. It does not show that the true difference is zero, nor does it prove that a clinically important difference is impossible. The registry does not report the threshold that would distinguish a clinically important TBUT change from a smaller one. Without that threshold, statistical uncertainty cannot be translated into a judgment about clinical importance.

The reported standard errors are 0.261 seconds for OmegaD and 0.26 seconds for placebo. In general, a standard error reflects uncertainty in an estimated mean, not the variability of individual measurements. The registry identifies standard error as the dispersion measure and does not report the endpoint’s group standard deviations. The interval and standard errors should therefore be understood as summaries of uncertainty in group estimates, not as descriptions of the range of individual participants’ outcomes.

The unadjusted p-value is 0.55, consistent with the interval’s inclusion of zero for the reported comparison. Neither statistic determines the probability that the null hypothesis is true. Precision is also conditional on the analysis method and data included. Details about the model, missing measurements, interval confidence level, and any multiplicity strategy are not reported in the registry record, limiting a fuller appraisal of uncertainty.

11. 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 sample-size figures are planning illustrations based on the observed effect, not a report of the trial’s original design calculation. They are stated as participants per arm, not total events. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers detecting a stated fraction of the observed effect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the planned number of participants per arm for a hypothetical study designed to have an 80% chance of detecting the specified effect under the listed assumptions, if that effect and the assumptions were correct. The 90% power column applies the same interpretation at a higher target chance of detection. These are planning calculations, not a guarantee about what a future study would find. This is not observed power.

The illustration considers 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. For 100% of the observed effect, the figures are 1,981 participants per arm for 80% power and 2,652 for 90% power. For 75% of the observed effect, they are 3,522 and 4,715 participants per arm, respectively. For 50% of the observed effect, they are 7,924 and 10,608 participants per arm, respectively. The plotted curve conveys the same general planning relationship rather than additional observed trial results.

Smaller effects require more participants to detect under the same planning assumptions, because a smaller separation between group outcomes is harder to distinguish from sampling variation. The figures should not be read as a recommendation for a future study or as evidence about the trial’s actual statistical power. They are sensitive to the observed effect used as their starting point and to the stated assumptions.

12. 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 = 0.220; pooled standard deviation σ = 2.471.
2. n = 2 × (1.96 + 0.842)² × 2.471² / 0.220² = 1,980.9, rounded up to 1,981 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 <- 0.22                      # observed difference in means
sigma <- 2.47137280687512                     # 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(2980224)
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 = 1,981 (80% power), 2,652 (90% power)
 75% of observed effect: n per arm = 3,522 (80% power), 4,715 (90% power)
 50% of observed effect: n per arm = 7,924 (80% power), 10,608 (90% power)
power.t.test: 1981.9 
Simulated power at n = 1,981 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.

13. Multiplicity, Missing Data and Analysis Populations

The registry lists the primary endpoint and identifies the frequency and severity of adverse events as a secondary outcome. It also records three outcome measures. The number of separate analysis records is zero, although the primary endpoint estimates and a comparison with an unadjusted p-value are posted. This distinction means the entry contains a statistical comparison without a separate analysis record describing its methods.

Multiplicity arises when several outcomes, time points, subgroups, or comparisons are tested. In general, conducting multiple tests can increase the chance of at least one small p-value even when no real difference exists. Methods to address this can include a prespecified hierarchy or statistical adjustment, but whether either approach was planned or used is not reported in the registry record. The posted p-value is explicitly unadjusted, so it should not be interpreted as corrected for testing multiple outcomes.

The primary population is identified as the Intent to Treat Population. The registry does not describe how that population was defined in practice, whether every randomized participant had endpoint data, or how missing data were handled. It also does not state whether the analysis retained participants according to assigned group after treatment discontinuation or protocol deviations. Such details affect interpretation of an intention-to-treat analysis and cannot be inferred from the label alone.

The endpoint is described as change from baseline to Day 84. The record does not report how participants without a Day 84 measurement were treated, whether measurements at other times were used, or whether any imputation or sensitivity analyses were conducted. The statistical model, covariate adjustment, and confidence level for the reported interval are also not reported in the registry record. These gaps limit assessment of the analysis assumptions and robustness. They do not change the numbers posted, but they make it harder to evaluate how dependent those numbers may be on analytic choices.

14. 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 non-serious adverse event terms

The registry reports serious adverse event counts of 0 for OmegaD and 0 for placebo. The corresponding numbers at risk are 89 in the OmegaD group and 91 in the placebo group. No serious adverse event terms are listed in the record, and deaths are reported as 0 in each group. These are the posted counts; the registry does not provide event descriptions or additional details about assessment and follow-up in this entry.

The record also reports other adverse events affecting 12 participants in the OmegaD group and 1 participant in the placebo group. Those figures are distinct from the serious adverse event counts and should not be conflated with them. The secondary outcome is described as the frequency and severity of adverse events, but detailed event categories and severity results are not posted in the registry record. The posted serious-event figures are counts, not estimates of comparative risk, and no statistical comparison of safety outcomes is reported.

Zero reported serious events in a group does not establish that an event is impossible or that the treatment has no safety concerns. The figures describe the registry’s reported observations for this study, without resolving how safety might differ in other populations or settings. Further details on collection methods and follow-up are not reported in the registry record.

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

The result describes a group-level comparison of change in TBUT from baseline to Day 84. The OmegaD estimate is 1.45 seconds, the placebo estimate is 1.23 seconds, and the estimated difference is 0.22 seconds. The interval crosses zero and the unadjusted p-value is 0.55. Together, these results indicate that the posted comparison does not precisely determine the direction or size of a difference between groups under the analysis used.

That interpretation is not equivalent to saying the groups were identical. An interval that includes zero leaves room for no difference, but also for values on either side. Conversely, the positive point estimate alone does not establish a reliable or clinically meaningful advantage. The registry does not report a threshold for clinical importance, and the interval’s confidence level is not reported. The evidence should therefore be read as uncertain rather than converted into a categorical claim about benefit or lack of benefit.

The endpoint is a measured clinical sign related to tear-film stability. It is not itself a measure of every symptom or experience associated with dry eye disease. The record does not report a symptom endpoint result in the posted primary comparison. Nor can a group average describe how each individual participant responded. The primary outcome result should not be used to infer an individual outcome.

The safety counts provide a separate description: no serious adverse events or deaths are reported in either group, while other adverse events are reported in both groups. These counts are limited to the registry’s posted information and do not establish safety beyond the study record. Overall, the entry supports a cautious reading of the measured endpoint and reported events during the study; it does not resolve clinical importance, individual response, or results in settings beyond this trial.

16. Why This Trial Matters Statistically

This trial is statistically informative because its primary outcome is a continuous measure and the registry reports both group means and a direct comparison. The estimated contrast is expressed in seconds, the unit used for TBUT. A reader can therefore distinguish the observed group estimates from the uncertainty around their difference. The interval spanning zero makes that uncertainty central to interpretation: the point estimate alone is not an adequate summary.

The record also illustrates why a non-small p-value should not be treated as proof of no effect. The unadjusted p-value is 0.55, while the interval permits values on both sides of zero. These results do not establish exact equality. They instead show that the posted comparison does not sharply identify the direction or magnitude of a group difference. The registry does not report a clinical importance threshold, so statistical results cannot be mapped to a threshold for meaningful change.

There are useful distinctions between the design description and analysis details. Randomization and a placebo comparator define the basic comparison, while the parallel design separates the groups over the study period. Yet the record does not describe the statistical model, missing-data approach, or multiplicity strategy. It identifies the primary population as Intent to Treat but does not explain its implementation. These missing details matter when judging how estimates were obtained and how robust they may be.

Finally, the planning illustration shows how sample-size requirements depend on the target effect size. It is explicitly based on the observed effect and stated assumptions, not the trial’s own design rationale or an observed-power calculation. This distinction helps separate a hypothetical planning exercise from the trial’s actual design and results.

17. 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 entry leaves important details about the primary analysis unspecified. It identifies the outcome as a least-squares mean change but does not report the model, covariates, exact comparison procedure, or confidence level for the interval. It also does not describe the handling of missing Day 84 values, protocol deviations, or treatment discontinuation. The Intent to Treat label is present, but its operational definition is not reported in the registry record.

The masking description is inconsistent across registry elements: the official title says double-masked, while the masking field says quadruple. The entry does not explain which people were masked or how masking was maintained. Although the study is described as randomized, details of sequence generation and allocation concealment are not reported. These are design details that could help readers assess potential sources of bias.

The registry lists enrollment as 180, while the brief summary describes approximately 164 subjects to be evaluated and the primary results list group counts of 89.0 and 91.0. The record does not explain the relationship among these figures. It also does not report the original sample-size rationale or the planned analysis strategy. The sample-size illustration is based on the observed effect and should not be confused with the trial’s original design calculation.

The posted primary comparison focuses on TBUT at Day 84. The entry does not provide a clinically important difference threshold, and the interval’s confidence level is unspecified. The record names a secondary adverse-event outcome but supplies limited detail on event types and analysis. These gaps restrict conclusions about clinical importance, robustness, and the breadth of outcomes. They do not change the reported estimates, but they limit how fully the trial can be appraised from the registry record alone.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Study of the Safety and Efficacy of OmegaD Softgels in the Treatment of Dry Eye Disease — NCT02980224.
• Registry record last updated 2019-12-13; status last verified 2019-11.
• Results first posted 2019-09-11.
• 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.

21. Record Summary

NCT02980224 is a completed phase 3 randomized, multicenter, parallel-group, placebo-controlled study of OmegaD softgels for dry eye disease. The brief summary describes oral dosing of 2 softgels BID for 84 days in each group. The official title calls the study double-masked, while the registry masking field says quadruple.

The primary outcome is change from baseline in TBUT at Day 84, measured in seconds, for the Intent to Treat Population. The posted estimates are 1.45 seconds for OmegaD and 1.23 seconds for placebo, with a mean difference of 0.22 seconds, an interval that crosses zero, and an unadjusted p-value of 0.55. Serious adverse event counts and deaths are reported as 0 in both groups; other adverse events are reported for 12 OmegaD participants and 1 placebo participant.

The registry does not report the detailed statistical model, missing-data methods, multiplicity approach, confidence level, or original sample-size justification.