Cilostazol 50 mg Tablets Under Fasting Conditions: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Cilostazol 50 mg Tablets Under Fasting Conditions (NCT00839930), a randomized phase 1 study. The primary outcome is Cmax - Maximum Observed Concentration.

2. Clinical Question

3. Trial Design

This was a phase 1, randomized, open-label, crossover study in healthy adults. Enrollment was 30, and the registry marks the study as completed. The study dates are reported to the month: start and primary completion were both recorded as 2004-02. No day-level dates are reported in the registry record.

In a crossover design, each participant receives more than one treatment in separate periods, so comparisons can be made using measurements from the same participants. The registry describes two treatment sequences: one began with the test cilostazol tablet and then used Pletal® in the second period; the other began with Pletal® and then used the test tablet. Allocation was randomized, while masking was listed as none.

The study summary describes a single oral dose of one 50 mg tablet for each product, under fasting conditions. The primary outcome population is described as data from all subjects who completed the study. Each posted arm entry reports 30 participants, though the registry record does not separately describe participant flow, withdrawals, or the number completing each period.

The record does not report the interval between treatment periods, any washout procedure, the method used to generate or conceal the random sequence, or the original statistical analysis plan. These details should not be inferred from the crossover label alone.

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.

First Intervention

Washout: 7 Days

Second Intervention

Analysis population for the primary outcome, as defined in the registry: Data from all subjects who completed the study were included in the statistical 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 Cmax - Maximum Observed Concentration, measured over Blood samples collected over 72 hour period.

The primary endpoint was Cmax, the maximum observed concentration of cilostazol in the blood after dosing. Concentration was expressed in ng/mL, and blood samples were collected over a 72 hour period. The registry describes the outcome as a mean with standard deviation and states that bioequivalence was based on Cmax.

In general, Cmax is used in pharmacokinetic comparisons because it describes the highest measured concentration during the sampling period. It therefore captures a feature of the observed concentration profile, rather than the total exposure over time. The study summary refers to relative bioavailability as the rate and extent of absorption, but Cmax alone does not describe every aspect of that profile.

The posted group means and standard deviations provide a descriptive comparison of observed concentrations. The sponsor also reported a geometric test-to-reference ratio and a 90% confidence interval. These are different ways of expressing a comparison: one uses arithmetic means and a mean difference, while the other expresses a ratio on a geometric scale. The registry record does not state the acceptance margins for a bioequivalence decision or provide the full sampling and analysis procedures.

7. Results Posted in the Registry

• Pletal®: mean 398.06 versus 376.46 on control; difference 21.60 (95% CI -35.10 to 78.30), standardized effect d = 0.19; z-test p = 0.455.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: each observation is a concentration measured on a numerical scale. The registry reports the mean and standard deviation for each treatment group. In general, a mean describes the central level of measurements, while a standard deviation describes how spread out individual measurements are around that mean. These summaries are useful for describing distributions, but they do not retain all the information in participant-level data.

What does the mean difference describe?

The recalculated comparison expresses the Pletal® mean relative to the Cilostazol mean as a mean difference of 21.6 ng/mL. This direction follows the posted comparison, where Pletal® is compared with Cilostazol. The estimate is in the original concentration units, making its scale directly interpretable as a difference in mean observed Cmax. The interval from -35.1 to 78.3 ng/mL describes uncertainty around that recalculated difference. The registry record does not state a confidence level for this interval, so no level should be inferred.

The unadjusted p-value is 0.455. In general, a p-value describes how compatible the observed data are with a specified null model, under the assumptions of the test. It does not give the probability that the null hypothesis is true, and it does not measure the size or importance of an effect. The registry record does not name the test used for this recalculation. The p-value is explicitly unadjusted, and it should not be presented as a result from the sponsor's separate geometric-ratio analysis.

Why are arithmetic and geometric comparisons different?

An arithmetic mean is calculated on the original measurement scale. A geometric comparison is based on multiplicative relationships and is commonly expressed as a ratio. In general, ratios can be useful when the scientific question concerns relative rather than absolute differences, especially when measurements are analyzed on a logarithmic scale. The sponsor's reported geometric test-to-reference ratio is 93.39, with a 90% confidence interval from 87.33 to 99.86. The record does not state the analysis method, transformation details, or equivalence margins for that result. The ratio and the recalculated mean difference therefore answer related but non-identical statistical questions.

The standardized difference, 0.193, scales the observed mean difference by the pooled standard deviation reported for the comparison. In general, standardization can help describe effect magnitude across measures with different units. It is not a substitute for the concentration-scale result and should not be interpreted as a clinical threshold. The registry record does not report a threshold for interpreting this standardized estimate.

What does the crossover design mean for analysis?

In general, a crossover design allows each participant to serve as their own comparison across treatments. An analysis that uses this structure can account for the relationship between measurements from the same person and may include terms for treatment, period, and sequence, depending on the protocol and analysis plan. The posted mean-and-standard-deviation summaries do not show those within-person relationships. The recalculated mean difference is therefore an unadjusted summary-based comparison, not a reconstruction of a crossover analysis.

The primary outcome description says that the statistical analysis included data from all subjects who completed the study. The registry record does not report how incomplete treatment periods, missing concentration measurements, protocol deviations, or unusual observations were handled. Nor does it identify a specific statistical model for the sponsor's analysis. Those omissions limit what can be concluded about the analysis procedures, even though the record provides a group summary and a reported geometric ratio.

In general, over-dispersion means that observed variation is greater than a model assumes. When that occurs, standard errors may be too small if the model fails to represent the extra variation, making intervals too narrow and tests too optimistic. The registry does not report an over-dispersion assessment or indicate that such a model was used. It is therefore appropriate to explain the concept as a general statistical consideration, not as a feature established for this trial.

10. Confidence Intervals and Precision

Precision concerns how narrowly an estimate is determined by the data. The recalculated mean difference is 21.6 ng/mL, and its reported interval extends from -35.1 to 78.3 ng/mL. The interval spans values on both sides of zero, so the posted summary does not pin down the direction of the arithmetic mean difference with high precision. It also includes differences of varying magnitude; the estimate should not be treated as an exact value.

In general, a confidence interval gives a range of values compatible with the data and the assumptions of the method used to calculate it. Wider intervals indicate greater uncertainty about the estimated quantity. The confidence level for the recalculated mean-difference interval is not reported in the registry record, so it is not appropriate to assign one. The sponsor's interval is explicitly reported as 90%: the geometric test-to-reference ratio is 93.39, with limits of 87.33 and 99.86.

These intervals concern different estimands and scales. One is an absolute difference in arithmetic mean concentration, expressed in ng/mL; the other is a geometric ratio. Their limits cannot be compared as though they were alternative versions of the same quantity. The ratio interval is also not, by itself, enough to determine whether the study met a bioequivalence criterion, because the record does not report the applicable acceptance margins.

Precision is affected by the amount of information available and by variability. The posted standard deviations are 115.9 for Cilostazol and 108.1 for Pletal®, with 30 participants reported for each arm entry. In a crossover study, within-participant variability is also relevant, but it cannot be recovered from these group summaries. The registry record does not provide the paired observations or their correlation.

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 planning figures are participants per arm, not total event counts. They are planning illustrations based on the observed effect, rather than the enrollment rationale for this trial. The stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is set as a stated fraction of the observed effect. The trial's original sample-size assumptions and justification are not reported in the registry record.

The 80% power column describes the number of participants per arm that the planning calculation associates with an 80% chance of detecting the specified effect under its assumptions. The 90% power column gives the corresponding planning number for a 90% chance. In general, higher planned power requires more information when the other assumptions are held fixed. The listed scenarios consider 100%, 75%, and 50% of the observed effect; planning for a smaller effect requires more participants because smaller differences are harder to distinguish from random variation.

These figures are not evidence about the probability that this completed trial detected an effect, and they are not observed power. They do not revise the actual enrollment or demonstrate that the trial was designed around the observed results. They are hypothetical planning illustrations only. The assumptions describe a two-arm calculation and do not establish that the original crossover study used the same method or design 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 = 21.600; pooled standard deviation σ = 112.043.
2. n = 2 × (1.96 + 0.842)² × 112.043² / 21.600² = 422.4, rounded up to 423 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 <- 21.6                      # observed difference in means
sigma <- 112.043070513084                     # 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(839930)
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 = 423 (80% power), 566 (90% power)
 75% of observed effect: n per arm = 751 (80% power), 1,006 (90% power)
 50% of observed effect: n per arm = 1,690 (80% power), 2,262 (90% power)
power.t.test: 423.3 
Simulated power at n = 423 per arm: 0.802 (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. Analyses Reported by the Sponsor

The registry reports a sponsor analysis as a geometric test-to-reference ratio of 93.39, with a 90% confidence interval from 87.33 to 99.86. It does not report a p-value or name the statistical method for this result. The registry describes the primary endpoint as Cmax and says bioequivalence was based on that outcome, but it does not state the acceptance margins or the sponsor's decision rule.

The recalculated comparison uses the posted arithmetic means and standard deviations. It gives a mean difference of 21.6 ng/mL, an interval from -35.1 to 78.3 ng/mL, and an unadjusted p-value of 0.455. This is a simple unadjusted re-calculation from the posted summaries. It is not a reproduction of the sponsor's geometric analysis and does not account for the crossover structure using participant-level data.

The registry does not flag a discrepancy between the posted summaries and the recalculation. Nevertheless, the two analyses should remain distinct: they use different scales and estimands, and the record does not establish that they were intended to produce identical numerical results. The sponsor's analysis is the reported analysis; the recalculation is a descriptive cross-check. Neither result can be used to infer unreported equivalence margins or an unreported conclusion.

14. Multiplicity, Missing Data and Analysis Populations

The registry reports three outcome measures and three analyses, with Cmax identified as the primary outcome. No secondary results are posted. The record does not state whether the other outcome measures were secondary, how their analyses related to the primary analysis, or whether any outcomes were designated as exploratory.

In general, testing multiple outcomes can increase the chance of at least one apparently notable result arising by chance. Statistical plans may address this through a prespecified hierarchy, adjustment procedures, or a clear distinction between confirmatory and exploratory analyses. The registry record does not report whether any such approach was used. The unadjusted p-value of 0.455 for the recalculated mean difference should therefore be understood as unadjusted, not as evidence that a multiplicity procedure was applied.

The primary outcome description identifies the analyzed population as data from all subjects who completed the study. The posted entries list 30 participants for Cilostazol and 30 for Pletal®. The registry does not provide a participant flow account or specify whether anyone was excluded from an analysis after enrollment. It also does not report how missing samples, incomplete periods, protocol deviations, or outliers were handled.

In general, missing-data methods matter because the analysis can be affected by why measurements are absent and how the statistical procedure treats them. The record does not identify a missing-data method, an intention-to-treat population, a per-protocol population, or a sensitivity analysis. No assumptions about these procedures can be made from the completed status or the posted arm counts alone. The available information supports describing the stated completed-subject population and the posted summaries, but not reconstructing the analysis set or the handling of unobserved measurements.

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

The results describe a pharmacokinetic comparison of two 50 mg tablet products in healthy adults under fasting conditions. For the primary Cmax outcome, the registry reports arithmetic mean concentrations of 376.5 ng/mL for Cilostazol and 398.1 ng/mL for Pletal®. The unadjusted recalculation gives a mean difference of 21.6 ng/mL, with an interval from -35.1 to 78.3 ng/mL and an unadjusted p-value of 0.455. These figures characterize the observed summaries and their uncertainty; they do not establish that the products are equivalent or different.

The sponsor's result is a geometric ratio, not an arithmetic mean difference. Its reported estimate is 93.39, with a 90% confidence interval from 87.33 to 99.86. Whether that result satisfies a bioequivalence criterion cannot be determined from the registry record because the criteria and acceptance margins are not reported. The numerical range should not be interpreted as a decision by itself.

In general, absence of a statistically clear difference is not proof that two treatments are equivalent. Equivalence questions require specified margins and an analysis designed to evaluate whether the plausible differences fall within those margins. The registry record does not provide those details. It also does not report clinical outcomes, longer-term effects, or evidence beyond the pharmacokinetic endpoint described.

The population was healthy adult subjects, and the study summary concerns single doses under fasting conditions. The results therefore describe the conditions and outcome recorded in this study, not every population, dosing circumstance, or clinical setting. No medical conclusion should be drawn from these pharmacokinetic summaries alone.

16. Why This Trial Matters Statistically

This trial illustrates why the statistical scale should match the scientific question. An arithmetic mean difference describes an absolute separation in ng/mL, while a geometric test-to-reference ratio describes a relative comparison. Both can be informative, but they are not interchangeable. Keeping the estimand clear prevents a ratio from being read as an absolute difference or a mean difference from being treated as the sponsor's bioequivalence analysis.

The crossover structure also matters. In general, comparisons within the same participants can use information about how each participant responds across treatments. Group means and standard deviations do not reveal that paired information. A simple calculation from those summaries can describe the posted group values, but cannot reproduce a model that accounts for treatment period, sequence, and within-participant correlation. The distinction between a summary-based recalculation and the sponsor's reported analysis is important when interpreting the figures.

Finally, the record illustrates that a confidence interval and a p-value answer limited questions. The interval around the recalculated difference conveys uncertainty about an absolute estimate; the sponsor's 90% interval conveys uncertainty about a ratio. Neither can establish an equivalence decision without the relevant criteria. The posted results are most useful when read as statistical descriptions of Cmax under the study conditions, alongside the limits of the information recorded.

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 record does not report the original sample-size justification, the statistical analysis plan, or the methods used for the sponsor's geometric-ratio analysis. It does not state the equivalence margins or decision criteria, which prevents an independent assessment of whether the reported ratio met a prespecified bioequivalence standard.

The trial was a crossover study, but the available group summaries do not include paired participant-level values. The recalculated mean difference is therefore unadjusted and does not account for within-participant correlation, treatment sequence, or period. The record also does not describe washout procedures, the interval between treatment periods, or the randomization method beyond identifying allocation as randomized.

Although each posted arm entry reports 30 participants, the registry does not provide participant flow, period-specific completion, or detailed missing-data handling. The primary population is described as completed subjects, but the record does not identify the number initially randomized separately from enrollment or explain exclusions. No secondary results are posted despite the registry listing three outcome measures and three analyses.

The outcome description is focused on maximum observed concentration. The record does not provide full concentration-time data, detailed sampling times, or results for additional pharmacokinetic measures. The summary concerns healthy adults receiving single doses under fasting conditions, so it does not establish results for other populations or conditions.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Cilostazol 50 mg Tablets Under Fasting Conditions — NCT00839930.
• Registry record last updated 2024-08-20; status last verified 2024-08.
• Results first posted 2009-07-21.
• 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

NCT00839930 is a completed phase 1 randomized, open-label crossover study of a 50 mg cilostazol tablet and Pletal® under fasting conditions in healthy adults. Enrollment was 30. The primary endpoint was maximum observed concentration, measured in blood samples collected over a 72 hour period.

The posted arithmetic mean Cmax values were 376.5 ng/mL for Cilostazol and 398.1 ng/mL for Pletal®. The unadjusted recalculation gives a mean difference of 21.6 ng/mL, with an interval from -35.1 to 78.3 ng/mL and an unadjusted p-value of 0.455. The sponsor separately reported a geometric test-to-reference ratio of 93.39 and a 90% confidence interval from 87.33 to 99.86. The registry does not report equivalence margins or enough detail to reconstruct the sponsor's analysis.