A Study of Tadalafil (LY450190) in Chinese Men With Erectile Dysfunction: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of Tadalafil (LY450190) in Chinese Men With Erectile Dysfunction (NCT02224846), a randomized phase 4 study. The primary outcome is Percentage of Participants Experiencing at Least One Treatment Emergent Adverse Event (Serious or Non-Serious).

2. Clinical Question

The primary question concerns the percentage of participants who experienced at least one treatment-emergent adverse event from baseline through Month 12. The registry record reports this outcome for participants assigned to a schedule beginning with 2.5 mg tadalafil and later changing to 5 mg, and for participants assigned to 5 mg tadalafil throughout the stated treatment periods. The comparison is about recorded adverse events, not about whether either schedule is effective or appropriate for an individual.

3. Trial Design

This was a Phase 4, randomized, open-label, parallel-group interventional study of tadalafil in Chinese men with erectile dysfunction. The registry record lists enrollment as 635. The primary endpoint analysis reports 210 participants in the 2.5 mg/5 mg group and 421 in the 5 mg group. These are different record values: enrollment describes the study, while the group counts describe the primary endpoint analysis.

Participants were assigned to one of two daily oral dosing schedules. One schedule used 2.5 mg for 3 months and then 5 mg for 21 months. The other used 5 mg for 24 months. The official title describes a randomized, open-label, 3-month interventional study and long-term safety, while the arm descriptions specify the longer treatment periods. The primary safety endpoint covers baseline through Month 12, so its observation window does not extend through all the treatment time described for either schedule.

Because the study was open-label, masking was not used. The registry record does not report further information about how randomization was generated or concealed, how treatment adherence was assessed, or whether any additional measures were taken to reduce bias. The planned original sample-size assumptions and the rationale for the enrollment target are not reported in the registry record. The trial is listed as completed, with a start date of 2014-10 and a primary completion date of 2016-05.

The study also listed secondary outcomes involving erectile-function questionnaire scores, sexual encounter diary responses, normal erectile functioning, and global assessment questions. Six secondary outcomes are listed, but the registry record reports zero analyses for the outcome measures. Their results and the methods used to analyze them 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.

Period 1 (Month 3)

Reasons for not completing this period:

Period 2 (Month 3 to Month 12)

Reasons for not completing this period:

Period 2 (Month 12 to Month 24)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All enrolled participants who fulfill the study entry criteria and who receive at least one dose of tadalafil.

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: All randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Experiencing at Least One Treatment Emergent Adverse Event (Serious or Non-Serious), measured over Baseline through Month 12.

The primary endpoint is the percentage of participants who experienced at least one treatment-emergent adverse event, whether serious or non-serious, from baseline through Month 12. The registry definition counts an event if it first occurs or worsens in severity after baseline, regardless of whether it is judged related to tadalafil or how severe it is. The percentage is based on participants with at least one such event divided by the number analyzed in the group.

This kind of endpoint is used to describe how often participants experience new or worsening events during treatment. Counting a participant once for the outcome, even if that participant has more than one event, focuses the measure on the proportion of participants affected rather than the total number of event episodes. It is therefore distinct from a count of all adverse-event reports. The registry record says that a summary of serious and other non-serious adverse events, regardless of causality, is located in the reported adverse events module.

The endpoint does not by itself establish that tadalafil caused an event. Its definition explicitly includes events regardless of causality. Nor does the percentage capture the full clinical detail of individual events, their duration, or their consequences. The posted outcome is a safety measure through Month 12, rather than a direct measure of erectile-function benefit or an account of every event over the full treatment periods.

7. Results Posted in the Registry

• 5 mg Tadalafil: 35.9% (151/421) versus 33.8% (71/210) on control; risk difference 2.1 percentage points (95% CI -5.8 to 9.9), risk ratio 1.06 (0.84–1.33); unadjusted two-proportion z-test p = 0.610.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary at the participant level: each analyzed participant either experienced at least one qualifying treatment-emergent adverse event through Month 12 or did not. The posted group values are percentages, and the comparison is expressed as a risk difference. General statistical explanation: a risk difference subtracts one group’s event probability from the other group’s event probability. A value of zero corresponds to equal probabilities; positive and negative values indicate opposite directions depending on which group is subtracted from which. The comparison’s reported interval extends from -0.058 to 0.099, crossing zero.

What does the confidence interval describe?

In general, a confidence interval describes the uncertainty associated with an estimate under the statistical method used. It is not a range that guarantees the true value lies within it, nor does it show the distribution of individual participant outcomes. For this result, the interval for the risk difference includes zero and also reaches in both directions away from zero. The interval therefore signals that the observed estimate is not highly precise enough to rule out meaningfully different underlying event percentages on either side of no difference. The registry record does not report the detailed interval-construction method.

How should the p-value be read?

The posted unadjusted p-value is 0.61. In general, a p-value measures how surprising data at least as discordant with a specified null model would be if that model held, given the assumptions of the test. It is not the probability that the null hypothesis is true, and it is not a measure of the size or importance of an effect. Here, the p-value is consistent with the broad uncertainty reflected in the confidence interval. The registry record does not report the exact test used for the posted p-value or whether any adjustment was applied to the primary comparison; the record labels this p-value unadjusted.

What do the relative measures add?

The record also posts a risk ratio of 1.061, with an interval from 0.844 to 1.333, and an odds ratio of 1.095, with an interval from 0.773 to 1.551. General statistical explanation: the risk ratio compares the event probabilities directly, while the odds ratio compares event odds. These relative measures use different scales and should not be confused with the risk difference. Their intervals include 1, the value representing no relative difference, and thus are also compatible with no difference as well as with differences in either direction. The risk difference often offers a direct absolute comparison; the ratio measures express the comparison relative to one group’s event level.

What does open-label randomization imply?

Random assignment is intended in general to make groups comparable with respect to measured and unmeasured characteristics at the start of a study, on average. It does not guarantee that every characteristic is balanced in a particular trial. Open-label means participants and study personnel were not masked to assigned treatment. For an outcome involving recorded events, knowledge of assignment could potentially affect reporting or assessment in general, though the registry record does not describe whether that occurred. It also does not report the randomization procedure or allocation concealment details.

The endpoint is defined as an event first occurring or worsening after baseline, regardless of causality or severity. That definition helps specify what counts, but the posted percentage does not distinguish events judged related from those judged unrelated. It also does not represent the total number of event episodes: it measures participants experiencing at least one event. The separate safety counts and event terms provide additional description, but they should not be substituted for the primary endpoint comparison.

The analysis population is described as enrolled participants who fulfilled entry criteria and received at least one dose. The group counts for the endpoint are 210 and 421. Missing-data methods, participant flow after randomization, any exclusions from analysis, and any adjustment for baseline characteristics are not reported in the registry record. These gaps limit assessment of how the analysis population was formed and how incomplete follow-up may have affected the outcome percentages.

The study has several listed secondary outcomes, but the registry record reports no analyses for them. It is therefore not possible to assess their results, their uncertainty, or the relationship between the primary and secondary findings from this record. The statistical analysis plan, any interim analyses, and multiplicity procedures are not reported in the registry record. These omissions matter because interpretation depends not only on an individual estimate but also on which outcomes and analyses were planned and how multiple comparisons were handled.

10. Confidence Intervals and Precision

The risk-difference estimate is 0.021, and its 95% confidence interval runs from -0.058 to 0.099. This interval spans zero, so the posted data do not narrowly identify the direction of the group difference. It also extends appreciably on either side of the point estimate, indicating uncertainty about the size of the difference. The unadjusted p-value, 0.61, is consistent with that uncertainty.

The relative estimates tell a similar story. The risk ratio is 1.061, with a 95% interval from 0.844 to 1.333. The odds ratio is 1.095, with a 95% interval from 0.773 to 1.551. Each interval includes 1, the relative-measure value that corresponds to no difference. These are not proof that the schedules have the same event risk; rather, the data do not pin down a single direction or a narrow range of plausible comparisons.

Precision is influenced by the amount of information available and by how frequently the outcome occurs. General statistical explanation: with fewer observed participants or events, estimates often have more sampling uncertainty, while larger studies can often narrow intervals if other features are similar. The endpoint analysis includes 210 participants in one group and 421 in the other, but the registry record does not report a target precision or a prespecified clinically important difference for this endpoint. The exact interval method is also not reported in the registry record.

The posted confidence intervals quantify statistical uncertainty under an analysis, not uncertainty arising from open-label assessment, incomplete follow-up, or limitations in the record. The missing-data approach and details of outcome adjudication are not reported in the registry record. As a result, the intervals should be considered alongside these design and reporting limitations rather than as a complete account of all 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 planning figures are illustrations based on the observed effect, not the trial’s original design assumptions. The registry record does not report the original sample-size justification. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set at the stated fraction of the observed effect.

For this binary outcome, the planning entries are participants per arm, not total events. The 80% power column gives the number of participants per arm that the illustration estimates would be needed for an 80% chance of detecting the specified effect under its assumptions. The 90% power column gives the corresponding number per arm for a 90% chance. These are design-planning quantities, not estimates of the trial’s achieved chance of finding a result.

The entries are 8,418 participants per arm for 80% power and 11,268 for 90% power when planning for 100% of the observed effect. For 75% of the observed effect, the entries are 14,913 and 19,964. For 50% of the observed effect, they are 33,437 and 44,762. A smaller effect is harder to distinguish from random variation, so it requires more participants under the same planning assumptions. The figures are hypothetical illustrations and should not be read as the number actually enrolled or as a recommendation for a future study.

This is not observed power. Observed power is not a useful substitute for examining the estimate and its confidence interval after results are available. The posted interval and the assumed planning effect are the more direct way to consider what the data indicate and how much uncertainty remains.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.338; treatment proportion p₁ = 0.359; average p̄ = 0.348.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6738 = 1.3206.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6737 = 0.5670.
4. n = (1.3206 + 0.5670)² / (0.0206)² = 8,417.1, rounded up to 8,418 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
p0 <- 0.338095238095238                          # control proportion
p1 <- 0.358669833729216                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(2224846)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 8,418 (80% power), 11,268 (90% power)
 75% of observed effect: n per arm = 14,913 (80% power), 19,964 (90% power)
 50% of observed effect: n per arm = 33,437 (80% power), 44,762 (90% power)
power.prop.test: 8417.1 
Simulated power at n = 8,418 per arm: 0.797 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 six secondary outcomes, including changes in erectile-function questionnaire scores and percentages for sexual encounter diary responses, normal erectile functioning, and global assessment questions. It reports zero analyses for outcome measures. Results for those outcomes, and any relationship between their analysis and the primary safety result, are not reported in the registry record.

Multiplicity arises when several outcomes or comparisons are assessed. General statistical explanation: if many statistical tests are conducted, the chance of at least one apparently unusual result can increase unless the analysis plan addresses that issue. A prespecified hierarchy, adjustment procedure, or other strategy can help clarify how multiple results should be interpreted. The registry record does not report a multiplicity plan, a hierarchy of outcomes, or whether any adjustments were used. The posted primary comparison is labeled unadjusted.

The primary endpoint population is described as all enrolled participants who fulfilled the entry criteria and received at least one dose of tadalafil. The analysis groups contain 210 and 421 participants. The record does not report a detailed flow from random assignment to analysis, the number of participants with missing endpoint information, or the handling of missing observations. It also does not report whether all randomized participants were analyzed in their assigned groups or whether any other analysis populations were used.

Those omissions limit evaluation of potential bias due to incomplete follow-up or post-randomization exclusions. General statistical explanation: missingness can affect an estimate if the probability of having an observed outcome is related to participant characteristics or outcomes. Different assumptions about missing outcomes can lead to different estimates. Without the registry’s methods and relevant participant flow, the extent of that issue cannot be assessed from this record.

The statistical analysis plan, the exact test used for the primary comparison, covariate adjustment, and any interim analyses are not reported in the registry record. The original sample-size rationale is also not reported. These are reporting gaps, not evidence that the procedures were or were not carried out.

14. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: large intestine polyp (1.0%), diabetes mellitus (1.0%), myocardial infarction (0.5%), maculopathy (0.5%), duodenal ulcer haemorrhage (0.5%).

For serious adverse events, the record reports 15 participants in the 2.5 mg/5 mg group and 17 in the 5 mg group. The corresponding groups at risk are 210 and 421. The record also reports other non-serious adverse events for 86 and 178 participants, respectively, using the same group denominators. These are safety counts and should not be confused with the primary endpoint percentages, which count participants with at least one treatment-emergent adverse event through Month 12.

The record lists serious-event terms with percentages: Large intestine polyp, 1.0%; Diabetes mellitus, 1.0%; Myocardial infarction, 0.5%; Maculopathy, 0.5%; Duodenal ulcer haemorrhage, 0.5%; and Cholelithiasis, 0.5%. These terms give additional descriptive information but do not, on their own, establish causality or compare the risk between treatment schedules.

The adverse-event summaries are described as regardless of causality. The number of deaths is not reported in the registry record. The record does not provide enough detail to infer event timing, recurrence, severity beyond the serious/non-serious distinction, or the basis for attributing any event to treatment.

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

The result describes the proportion of analyzed participants who experienced at least one treatment-emergent adverse event through Month 12. The observed percentages were 33.8% for the schedule beginning with 2.5 mg and 35.9% for the schedule using 5 mg. The estimated risk difference was 0.021, with a 95% confidence interval from -0.058 to 0.099, and the unadjusted p-value was 0.61. The uncertainty interval includes no difference and values in both directions.

This is a comparison of two assigned dosing schedules, not a comparison of tadalafil with no treatment or with a different drug. It does not isolate the effect of 2.5 mg versus 5 mg throughout the full endpoint period, because one schedule changes to 5 mg after 3 months. The endpoint captures events that began or worsened after baseline, whether or not they were considered treatment-related. It is therefore a description of events during treatment, not proof that tadalafil caused them.

The result does not establish equivalence between the schedules. A non-small p-value is not proof that the groups have identical risks, and the interval remains broad enough to allow a range of differences. It also does not show that an individual participant will or will not experience an adverse event. Group-level percentages cannot determine an individual outcome.

The primary outcome covers baseline through Month 12, while the arm descriptions give treatment periods extending to 24 months. The primary result should not be treated as a summary of all events over those longer periods. The record’s serious and other non-serious adverse-event counts add descriptive context but do not replace the primary endpoint or supply causal attribution.

Finally, the registry record does not report the missing-data methods, detailed analysis plan, or results for the listed secondary outcomes. Those limitations constrain how fully the result can be assessed. The posted statistics support a cautious description of the observed groups and their uncertainty, not a broader claim about treatment effects beyond the registered comparison.

16. Why This Trial Matters Statistically

This study illustrates why safety results need both a descriptive estimate and an account of precision. The percentages alone give a quick comparison, but they do not convey how uncertain the difference is. The risk-difference interval crosses zero and reaches in both directions, while the p-value is 0.61. Together, these statistics show why a small apparent separation between group percentages should not be treated as a definitive difference or as proof of equivalence.

The endpoint also demonstrates the importance of defining what counts as an event. Here, treatment-emergent means first occurring or worsening after baseline, and events are counted regardless of causality or severity. The outcome is a percentage of participants with at least one event, not a total of all event reports. Clear definitions help readers distinguish a participant-level risk measure from event counts or judgments about whether treatment caused an event.

The schedule comparison requires attention to time and treatment changes. One group begins at 2.5 mg and changes to 5 mg after 3 months; the other uses 5 mg across its stated treatment periods. Since the primary endpoint runs through Month 12, the finding cannot be simplified to a comparison of two unchanged doses over that full window. Stating the schedule and endpoint window together prevents an overly broad interpretation.

Finally, the absence of reported details about missing data, analysis procedures, and secondary results matters to statistical appraisal. Randomization and the posted comparison are informative, but they do not answer every question about how the analysis was conducted. This record is a useful example of separating observed event percentages, uncertainty, study design, and limitations rather than treating one p-value as a complete account.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several trial-specific limitations shape interpretation. The study was open-label, so participants and study personnel were not masked to assigned schedule. The registry record does not describe how adverse events were collected or assessed, or whether assessment procedures were standardized across groups. Because the outcome includes events regardless of causality, the result is not a direct estimate of treatment-attributable harm.

The comparison concerns treatment schedules that differ early in follow-up, with one group changing from 2.5 mg to 5 mg after 3 months and the other using 5 mg throughout the stated periods. The primary endpoint ends at Month 12, before the full treatment durations described in the arm information have elapsed. The primary result therefore does not summarize safety over the entire stated treatment course.

The endpoint analysis groups are unequal in size, and the record does not report a detailed account of participant flow, missing outcome data, or exclusions. It also does not report the original sample-size rationale, the exact statistical test, adjustment for baseline characteristics, the analysis plan, or any interim analyses. These omissions prevent a full appraisal of the prespecified design and the possible effects of incomplete observations or analytic choices.

Although secondary outcomes are listed, analyses and results for them are not reported in the registry record. Multiplicity procedures are not reported either. Finally, the listed serious adverse-event terms and counts are descriptive. Without further information on timing, event-specific denominators, adjudication, or causal assessment, they cannot establish comparative or treatment-attributable risks for individual event types.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: A Study of Tadalafil (LY450190) in Chinese Men With Erectile Dysfunction — NCT02224846.
• Registry record last updated 2019-09-23; status last verified 2019-09.
• Results first posted 2017-10-27.
• 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

NCT02224846 is a completed Phase 4 randomized, open-label, parallel-group study of daily tadalafil in Chinese men with erectile dysfunction. The registry lists enrollment of 635 and describes two schedules: 2.5 mg daily for 3 months followed by 5 mg daily for 21 months, and 5 mg daily for 24 months.

The primary outcome is the percentage experiencing at least one treatment-emergent adverse event from baseline through Month 12. The posted values are 33.8% and 35.9%; the risk difference is 0.021, with a 95% confidence interval from -0.058 to 0.099 and an unadjusted p-value of 0.61. The record also reports serious and other non-serious adverse-event counts. Detailed missing-data procedures, the statistical analysis plan, original sample-size assumptions, and analyses of the listed secondary outcomes are not reported in the registry record.