Study of Efficacy and Safety of MEXIDOL® in Ischemic Stroke Therapy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Efficacy and Safety of MEXIDOL® in Ischemic Stroke Therapy (NCT02793687), a randomized phase 3 study. The primary outcome is Mean Score of the 6-point Modified Rankin Scale (mRS) at Visit 5 After Completion of the Course of Therapy for Both Arms.

2. Clinical Question

The registry describes the study as a superiority trial: its stated aim was to evaluate whether long-term sequential Mexidol® treatment was better than placebo. The primary result is a comparison of group mean scores at the recorded follow-up, rather than a comparison of the proportion of participants reaching a particular disability category. The record includes outcomes for stroke severity, activities of daily living, depression symptoms and a quality-of-life visual analogue scale as secondary measures. Those measures broaden the set of outcomes described, but the primary question remains the between-group comparison on the Modified Rankin Scale.

3. Trial Design

This was a phase 3, randomized, double-blind, parallel-group, placebo-controlled study sponsored by Pharmasoft. The registry lists an enrollment of 150. The study began on 2015-03-06, had primary completion on 2016-05-27, and is marked completed. Participants were assigned to Mexidol® or matching placebo. The record does not report the method used to generate the random sequence or the procedures used to conceal allocation.

The active regimen combined an initial intravenous course with an oral course: Mexidol® solution IV 500 mg daily for 10 days, then Mexidol 125 mg orally 1 tablet 3 times a day for 8 weeks. The placebo arm received matching placebo solution IV on the same schedule, followed by matching oral placebo as described in the registry. Double masking is recorded, but the registry record does not report who specifically was masked or how masking was assessed.

The primary endpoint was the mean score on the 6-point Modified Rankin Scale at Visit 5, recorded as 67-71 days. The posted primary group summaries include 61 participants in the Mexidol® group and 63 in the placebo group. The primary outcome population is called per protocol, while the population description also says all participants assigned to either group. The record does not explain this wording or provide a flow of participants from enrollment to outcome analysis. It therefore does not establish why the analyzed counts differ from overall enrollment.

The registry lists four secondary outcomes at Visit 5: NIHSS, Barthel Index, Beck Depression Inventory and EQ-5D-3L visual analogue scale. Although five outcome measures are listed overall, numerical results are posted for the primary outcome and three secondary outcomes. Numerical EQ-5D-3L results are not reported in the registry record. The record also does not report a protocol, detailed statistical analysis plan or the intended handling of missing outcome data.

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: Of 151 screened participants, 150 met inclusion criteria and were randomized to treatment.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Per Protocol Population (all participant assigned to Mexidol or Placebo) for calculating the mean score of the 6-point Modified Rankin Scale (mRS) at Visit 5 after completion of the course of therapy for both arms.

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: ITT-population was used for description of baseline measures.

6. Primary Endpoint

The registry lists the primary outcome as Mean Score of the 6-point Modified Rankin Scale (mRS) at Visit 5 After Completion of the Course of Therapy for Both Arms, measured over Visit 5 (67-71 Day)..

The primary endpoint is the mean score on the 6-point Modified Rankin Scale (mRS) at Visit 5 after the course of therapy, with the visit timeframe recorded as 67-71 days. The mRS is used to measure disability after stroke. Its recorded range is 0 to 6: 0 means no symptoms at all and 6 means dead. Higher scores indicate a worse outcome, so a lower group mean corresponds to less disability on the scale, on average.

A group mean gives a concise summary of the score distribution, but it does not show how many participants had each individual score or how many crossed a clinically meaningful threshold. Two groups can have the same mean while having different score distributions. The registry posts means and standard deviations for the two groups, but does not provide the full distribution of mRS categories or a threshold-based analysis.

Using mRS as the primary measure makes disability the central endpoint for the comparison. The secondary measures address other dimensions, including neurological impairment, activities of daily living, depressive symptoms and quality of life. Those outcomes can complement the disability measure, but they do not replace its role as the designated primary endpoint. The record does not report a rationale for selecting the mRS over the other measures or a prespecified threshold for interpreting a difference in its mean score.

7. Results Posted in the Registry

• Mexidol®: mean 1.10 versus 1.46 on control; difference -0.36 (95% CI -0.67 to -0.06), standardized effect d = -0.42; z-test p = 0.019.

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 of the 15-item The National Institutes of Health Stroke Scale (NIHSS) at Visit 5 After Completion of the Course of Therapy for Both Arms

• 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 deviations.
• Result:
  • Mexidol®: mean 1.69 versus 2.22 on control; difference -0.53 (95% CI -1.03 to -0.03), standardized effect d = -0.38; z-test p = 0.037.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Mexidol® than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Mean Score of the 10-item Barthel Index (BI) at Visit 5 After Completion of the Course of Therapy for Both Arms

• 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 deviations.
• Result:
  • Mexidol®: mean 96.07 versus 93.57 on control; difference 2.50 (95% CI -1.10 to 6.09), standardized effect d = 0.24; z-test p = 0.174.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Mexidol® and the control. The interval gives the range of effects that remain compatible with the data.

Mean Score of the 21-item Beck Depression Inventory (BDI) at Visit 5 After Completion of the Course of Therapy for Both Arms.

• 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 deviations.
• Result:
  • Mexidol®: mean 2.21 versus 2.19 on control; difference 0.02 (95% CI -0.89 to 0.94), standardized effect d = 0.01; z-test p = 0.961.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Mexidol® and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes cover different domains: neurological impairment measured by NIHSS, activities of daily living measured by the Barthel Index, depressive symptoms measured by the Beck Depression Inventory, and quality of life measured by the EQ-5D-3L visual analogue scale. Numerical results are posted for the first three, but not for EQ-5D-3L. Across the reported secondary measures, the direction and precision are not uniform: NIHSS has an interval on the negative side of zero, while the Barthel Index and Beck Depression Inventory intervals include zero.

This pattern offers context for the primary mRS finding, but it does not independently confirm or overturn it. The mRS captures disability, while the other measures represent distinct aspects of recovery or well-being. Related measures can be correlated, but a difference on one scale does not guarantee a difference on another. Conversely, an imprecise result on a secondary scale does not establish that the groups are equivalent. The interpretation for each measure depends on its scoring direction, units and uncertainty interval.

The secondary comparisons carry less weight than the designated primary comparison for more than one reason. They are secondary outcomes, and several outcomes were examined. The registry record does not report an adjustment for multiple testing or a hierarchy governing interpretation of the secondary results. When multiple comparisons are considered without adjustment, the chance of at least one apparently notable result arising by chance can increase. This is a general statistical concern; the record does not say whether a multiplicity plan was used outside the information posted.

The secondary results should therefore be regarded as supporting or exploratory context rather than as a set of equally decisive tests. The registry does not report adjusted p-values, a prespecified secondary analysis plan or results for every listed secondary measure. Nor does it report a separate confirmatory analysis of an EQ-5D-3L result. In combination, the posted secondary outcomes suggest that the observed pattern is not identical across all measured domains, and their unadjusted nature limits the strength of conclusions that can be drawn from them.

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

• Mean Score of the 15-item The National Institutes of Health Stroke Scale (NIHSS) at Visit 5 After Completion of the Course of Therapy for Both Arms
• Mean Score of the 10-item Barthel Index (BI) at Visit 5 After Completion of the Course of Therapy for Both Arms
• Mean Score of the 21-item Beck Depression Inventory (BDI) at Visit 5 After Completion of the Course of Therapy for Both Arms.
• Mean Score of on the EQ-5D-3L PRO Measure (VAS) at Visit 5 After Completion of the Course of Therapy for Both Arms.

9. Statistical Interpretation

10. Statistical Methods Explained

The posted primary comparison concerns a continuous outcome summarized by a mean: the mRS score at Visit 5. The registry describes the measure as a 6-point scale with possible values from 0 to 6, with higher values indicating worse outcomes. The statistical contrast is the mean for Mexidol® minus the mean for placebo. With that ordering, a negative mean difference means the observed average score was lower in the Mexidol® group. The reported estimate is -0.362.

What does a mean difference represent?

In general, a mean difference describes the distance between two group averages in the original measurement units. It is not a percentage change or a count of participants who improved. For this endpoint, the unit is score on a scale. The contrast condenses each group's scores into one number, so it does not retain information about how common each mRS category was, or how scores were distributed within each group. The registry posts group standard deviations as a measure of spread around each mean, but not category-specific counts for the primary mRS outcome.

How should the confidence interval be read?

In general, a confidence interval expresses the statistical uncertainty around an estimate using a method with a stated coverage level. The primary mean difference has a 95% confidence interval from -0.665 to -0.059. Values within this range are compatible with the data under the calculation's assumptions. Since the whole interval is below zero, it is consistent with a lower mean mRS score in the Mexidol® group. The range is still broad enough to include differences of varying magnitude, so the point estimate should not be treated as exact.

What does the p-value tell the reader?

In general, a p-value measures how unusual the observed data, or more extreme data, would be under a specified null hypothesis and statistical model. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of a difference. The primary p-value is 0.019 and is explicitly unadjusted. The registry record does not report whether a different prespecified model was used by the sponsor, how covariates might have been handled, or whether any interim analyses were planned or performed. Those details are not reported in the registry record.

What are standard deviations and standard errors?

In general, a standard deviation describes variability among individual observations within a group. A standard error describes the precision of an estimated statistic, such as a group mean. They answer different questions: a group can have substantial participant-to-participant variation while its mean is estimated with greater precision as the sample grows. The posted primary standard deviations are 0.768 and 0.947. The registry also lists standard errors for the group means, but the mean-difference estimate and its confidence interval are the more direct summary for the between-group question.

Why can over-dispersion matter?

In general, over-dispersion occurs when observed variability is greater than a statistical model expects. It can make standard errors that rely on the narrower model too small, which can produce confidence intervals that are too narrow and p-values that appear more decisive than warranted. The mRS is an ordinal scale, and the registry reports an analysis of its mean as a continuous measure. The record does not describe a model checking over-dispersion, a distributional assessment, or an alternative ordinal analysis. It is therefore not possible to tell from the registry whether such issues were evaluated in the original analysis. This is a general methodological consideration, not evidence that over-dispersion occurred in this trial.

The posted secondary contrasts are also mean differences for continuous measures, with group standard deviations, confidence intervals and unadjusted p-values. The same broad ideas apply, but each outcome has its own units and interpretation. For instance, the scale direction differs across measures; the registry defines higher scores as worse for mRS, while it does not supply complete interpretation details for every secondary scale. In general, the meaning of a positive or negative contrast must be read together with the scale's direction and scoring.

The registry lists no reported analyses in its analysis fields, although it posts group summaries and comparison statistics. Those comparisons can be read as unadjusted calculations from the posted summaries; they should not be mistaken for a fully documented statistical analysis plan. The analysis population, missing-data strategy, baseline adjustment, outcome hierarchy beyond the primary designation, and multiplicity procedure are not reported in the registry record. These missing details affect the ability to evaluate whether the statistical procedures were selected before results were known and whether the posted p-values account for all relevant analyses.

11. Confidence Intervals and Precision

Precision is reflected in the width of a confidence interval: narrower intervals indicate less uncertainty about the estimate, while wider intervals indicate more. For the primary mRS contrast, the estimated mean difference was -0.362 and its 95% confidence interval extended from -0.665 to -0.059. The interval is entirely below zero, but its width shows that the data are compatible with a range of negative mean differences rather than one exact value. It does not describe the range of individual participant outcomes.

The interval should be considered alongside the scale's direction. Since higher mRS scores indicate worse outcomes, a negative contrast for Mexidol® minus placebo corresponds to a lower observed mean score in the Mexidol® group. The interval's position relative to zero speaks to statistical separation of the means under the calculation, while its endpoints convey uncertainty about the amount of that separation. Statistical precision alone does not determine whether a difference is important to patients; the registry does not report a threshold for a clinically meaningful mean difference.

Precision differs across endpoints. The NIHSS interval is below zero, whereas the intervals for Barthel Index and Beck Depression Inventory include zero. The secondary intervals therefore vary in how clearly they distinguish their group means under the posted unadjusted calculations. They also use different scales, so their widths cannot be directly compared as if they represented the same quantity. The EQ-5D-3L numerical result is not reported in the registry record.

The reported group sizes for the primary analysis are 61 and 63, within a trial enrollment of 150. The record does not explain the difference between enrollment and the number represented in those outcome summaries. Without a participant flow, missing-data details or the full outcome distributions, the confidence interval cannot address potential bias from exclusions or missing observations. It quantifies sampling uncertainty for the posted comparison, not every source of uncertainty about the trial result.

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 sample-size figures are planning illustrations based on the observed effect, not the trial's original design assumptions. For these continuous outcomes, figures are expressed as participants per arm, not as a total across both arms. The planning calculation assumes a two-sided significance level of 0.05, equal allocation between the two arms and a normal approximation; the effect to detect is the stated fraction of the observed effect. The trial's own original sample-size justification is not reported in the registry record.

The 80% power column describes the planned number of participants per arm that, under those assumptions and for the chosen effect size, would yield an 80% chance of detecting an effect if that effect were the true one. The 90% power column uses a higher target chance of detection and therefore generally requires more participants per arm. These are planning quantities, not a report of what happened in the trial. They are not observed power.

Each planning row uses a different fraction of the observed effect: 100%, 75% or 50%. A smaller effect is harder to distinguish from random variation, so more participants are needed to reach the same target power under the same calculation assumptions. This pattern can be seen across the endpoint-specific planning figures. For example, the mRS illustration estimates 90 participants per arm for 80% power when planning for 100% of the observed effect, and 358 participants per arm when planning for 50% of that effect. The corresponding 90% power figures are 120 and 479 participants per arm. These figures do not describe the actual enrollment or analysis counts, and they should not be read as evidence that the original trial was designed around the observed result.

Planning based on an observed effect is sensitive to the estimate used. An effect observed in a trial can be imprecise, and a calculation that treats it as the true effect may yield an overly optimistic planning target. Smaller-effect scenarios illustrate how substantially the required sample can increase when the goal is to detect a more modest contrast. The underlying assumptions and the estimated effect should therefore be considered together when using these figures for future planning.

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 = -0.362; pooled standard deviation σ = 0.864.
2. n = 2 × (1.96 + 0.842)² × 0.864² / -0.362² = 89.3, rounded up to 90 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 <- -0.362                      # observed difference in means
sigma <- 0.863616101338901                     # 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(2793687)
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 = 90 (80% power), 120 (90% power)
 75% of observed effect: n per arm = 159 (80% power), 213 (90% power)
 50% of observed effect: n per arm = 358 (80% power), 479 (90% power)
power.t.test: 90.3 
Simulated power at n = 90 per arm: 0.797 (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. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several statistical hypotheses are tested, such as comparisons across multiple outcomes or repeated analyses of the same outcome. In general, conducting more tests increases the chance that at least one result will appear statistically notable by chance, even if there is no underlying effect on any of the measures. Methods such as a prespecified testing hierarchy or adjustment of significance levels can address this issue, but the registry record does not report a multiplicity procedure for this trial.

The primary mRS comparison has an unadjusted p-value. The posted secondary comparisons are also unadjusted, and the record lists four secondary outcomes. It does not explain whether all were intended to be tested formally, whether one or more were designated exploratory, or how conclusions were to be ordered across outcomes. The lack of those details means the individual p-values should not be read as if they necessarily controlled the overall false-positive risk across the set of analyses.

Missing-data methods are also not reported in the registry record. The primary outcome is described for a per-protocol population, but the accompanying wording says all participants assigned to Mexidol® or placebo. The posted primary counts are 61 and 63, whereas overall enrollment is 150. The registry does not provide a participant flow explaining inclusion, exclusions or missing assessments, and it does not state whether missing values were imputed, handled with a model, or omitted from the analysis. These omissions prevent assessment of how missing outcomes may affect the group comparison.

The record does not report whether the primary analysis adjusted for baseline mRS or other prognostic factors, whether analyses were conducted according to randomized assignment, or how protocol deviations were treated. It also does not provide details of interim analyses or the original statistical analysis plan. These are not evidence that particular procedures were or were not used outside the registry record; they are simply not reported in the registry record. Without them, the posted estimates can be described, but the full prespecified analysis framework cannot be reconstructed.

15. 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 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: ischaemic stroke (1.3%), haemorrhagic stroke (1.3%), cholecystitis acute (1.3%).

The registry reports serious adverse event figures for 75 participants at risk in each group. It lists 1 serious adverse event in the Mexidol® group and 3 in the placebo group. The record lists three serious-event terms—Ischaemic stroke, Haemorrhagic stroke and Cholecystitis acute—each with a reported frequency of 1.3%. It does not map those terms to treatment groups or provide further event-level detail, so the terms should not be assigned to a particular group on the basis of the posted summary.

For other adverse events, the record lists 21 affected participants in the Mexidol® group and 16 in the placebo group, with 75 at risk in each group. Deaths are recorded as 0 in both groups. These counts describe what was reported in the registry; they do not by themselves establish whether events were caused by treatment or whether the groups differed reliably in safety. The registry record does not provide event definitions, severity detail, exposure-adjusted rates or a statistical comparison of adverse events. A small count is also not proof that an event cannot occur.

These safety figures should be read as descriptive summaries for the recorded at-risk groups. They do not replace a complete safety analysis, and the absence of further detail in the registry limits interpretation of event timing, recurrence and relatedness.

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

The primary result describes a difference in average mRS scores at the recorded follow-up. The Mexidol® group had a lower mean than the placebo group, and the unadjusted confidence interval for the mean difference remained below zero. On the scale's stated direction, this is an observed group-average difference toward lower disability scores in the Mexidol® arm. The estimate concerns the participants represented in the posted outcome summaries and the particular follow-up measurement recorded.

It does not mean that every participant in the Mexidol® group had a better outcome, or that the same difference would be expected for each person. Group means cannot show the distribution of individual outcomes, and the registry does not post the primary mRS category counts. The result also does not establish the size of a clinically meaningful benefit: the record does not state a threshold for meaningful change or report an analysis based on a predefined mRS category transition.

The statistical result does not answer every question about treatment effects. The registry does not report a detailed analysis plan, missing-data methods, a multiplicity adjustment or a clear account of how the per-protocol population was formed. The unadjusted p-value does not incorporate those uncertainties, and the posted confidence interval captures sampling uncertainty under its calculation rather than potential bias from exclusions, missing data or analysis choices. The record also contains no numerical EQ-5D-3L result and does not provide full distributions for the posted outcomes.

Secondary measures provide additional but mixed statistical context, and their unadjusted comparisons should not be treated as a set of independent confirmatory findings. Safety counts are descriptive and do not establish causation or reliably compare risk. No inference should be extended beyond the participants, intervention schedule, endpoints and follow-up represented in the registry record. In particular, the posted results alone do not settle how the findings apply to people outside this study or to outcomes and timeframes not reported.

17. Why This Trial Matters Statistically

This trial illustrates why the difference between an estimate and its uncertainty matters. The primary comparison gives a point estimate for the group mean difference, while the confidence interval communicates a range of values compatible with the data under the analysis assumptions. The p-value is another summary of the comparison, but it does not express the magnitude, precision or clinical importance of the result. Reading these quantities together provides a more informative account than treating a single threshold as a complete verdict.

It also demonstrates the value of keeping endpoint direction explicit. For mRS, higher scores are worse, so a negative Mexidol®-minus-placebo contrast points toward a lower average score in the Mexidol® group. This sign convention can be confusing when outcomes use different scales or scoring directions. A careful interpretation starts with what each scale measures and which direction represents a more favorable score, rather than relying on whether an estimate is positive or negative alone.

The secondary outcomes make multiplicity a practical concern. Several aspects of stroke recovery were measured, but the registry does not report an adjustment or a hierarchy for the secondary comparisons. Separate unadjusted results can help describe patterns, yet they do not have the same evidential weight as a single prespecified primary question when multiple tests are considered. The uneven precision across the secondary measures reinforces the importance of considering intervals and analysis plans, not only individual p-values.

Finally, the record shows why transparent reporting of analysis populations, missing data and planning assumptions is important. The primary summaries represent fewer participants than the overall enrollment, and the registry does not explain the pathway to those counts. Planning illustrations based on observed effects can show how sample requirements depend on the effect targeted, but they are distinct from the original design justification. Together, these features help readers separate what the posted numerical comparisons establish from what remains uncertain in the record.

18. 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 limitations are specific to the information posted for this study. The primary outcome population is labeled per protocol, yet its description also says all participants assigned to either group. The record does not resolve that ambiguity, report participant flow, or explain why the outcome summaries include 61 Mexidol® participants and 63 placebo participants despite an enrollment of 150. It is therefore difficult to assess selection or attrition related to the primary analysis.

The registry does not report a detailed statistical analysis plan, missing-data approach, baseline adjustment, analysis according to randomized assignment, or multiplicity procedure. It lists no reported analyses, despite displaying summary comparisons. This leaves uncertainty about whether the posted calculations match the intended primary analysis and whether decisions were prespecified. The exact method used to calculate the confidence intervals and p-values is not described in the record.

Outcome reporting is also incomplete. Numerical results are posted for three of the four listed secondary measures; EQ-5D-3L numerical results are not reported in the registry record. The primary mRS distribution by score category is not posted, so means and standard deviations alone cannot show how individual disability categories compare. The record does not provide a clinically meaningful threshold for the mean difference or a responder analysis.

Safety information is brief and descriptive. The record reports affected counts and serious-event terms, but does not provide event-level timing, relatedness or a statistical comparison. It does not explain which group the listed serious-event terms arose in. These limitations mean the available safety figures cannot support a detailed comparison of event patterns. Finally, findings are reported at the specified follow-up; outcomes outside that timeframe are not reported in the registry record.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Study of Efficacy and Safety of MEXIDOL® in Ischemic Stroke Therapy — NCT02793687.
• Registry record last updated 2025-02-24; status last verified 2024-07.
• Results first posted 2025-02-24.
• 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.

22. Record Summary

The registry record describes NCT02793687, a completed phase 3 randomized, double-blind, parallel-group, placebo-controlled trial sponsored by Pharmasoft. Enrollment was 150. The primary endpoint was mean mRS score at Visit 5, recorded as 67-71 days. The posted primary means were 1.098 for 61 Mexidol® participants and 1.46 for 63 placebo participants. The mean difference was -0.362, with a 95% confidence interval from -0.665 to -0.059 and an unadjusted p-value of 0.019.

Numerical summaries are also posted for NIHSS, Barthel Index and Beck Depression Inventory. Numerical EQ-5D-3L results are not reported in the registry record. The registry reports serious adverse event counts of 1 and 3, and no deaths in either group; other adverse-event counts were 21 and 16. The record does not report a detailed analysis plan, multiplicity adjustment, participant flow or missing-data method, limiting assessment of the posted comparisons.