Study of Vardenafil in Patients Suffering From Erectile Dysfunction and Metabolic Syndrome: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Vardenafil in Patients Suffering From Erectile Dysfunction and Metabolic Syndrome (NCT00738400), a randomized phase 4 study. The primary outcome is Change From Baseline in International Index of Erectile Function - Erectile Function Domain (IIEF-EF) Subscore at Week 8 or Last Observation Carried Forward (LOCF).

2. Clinical Question

3. Trial Design

This was a Phase 4 randomized, double-blind, parallel-group, placebo-controlled study. The registry describes it as prospective and multi-center. Its stated focus was the efficacy, tolerability, and safety of vardenafil for erectile dysfunction in men who also had metabolic syndrome. The study status is completed. The recorded start was 2008-11 and primary completion was 2009-10.

The record lists enrollment of 150. That figure describes enrollment, not necessarily the number analyzed for every outcome. For the primary endpoint, the registry explicitly notes that analyzed participant numbers differ because of missing data. Outcome-specific analyzed numbers are listed with their respective results.

Participants in the vardenafil group took 10 mg tablets as needed for 4 weeks, then 5 mg, 10 mg, or 20 mg tablets as needed for consecutive 4 weeks. The placebo group took matching placebo tablets as needed over a corresponding schedule. The record also identifies an interest in the number of participants who could remain on the initial 10 mg dose. The registry does not report how dose changes were decided or what criteria were used.

Randomization and double masking are reported, but the method for generating or concealing the allocation is not reported in the registry record. Details of recruitment, eligibility beyond the named conditions, site locations, and adherence are not reported in the registry record. The information therefore establishes the broad comparison and treatment schedule but does not describe every operational feature needed to assess conduct or representativeness.

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: Number of participants analyzed differs due to missing data.

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 International Index of Erectile Function - Erectile Function Domain (IIEF-EF) Subscore at Week 8 or Last Observation Carried Forward (LOCF), measured over baseline and up to 8 weeks or LOCF.

The primary endpoint was change from baseline in the International Index of Erectile Function—Erectile Function domain (IIEF-EF) subscore at week 8 or last observation carried forward (LOCF). The scale ranges from 6 to 30 ordinal points. The registry associates scores from 6-10 with severe erectile dysfunction, 11-16 with moderate, 17-21 with mild to moderate, 22-25 with mild, and 26-30 with no erectile dysfunction.

The IIEF-EF domain captures erectile function through a structured score. Assessing change from baseline uses each participant’s starting score as context for the endpoint assessment. In general, a baseline-adjusted comparison can account statistically for starting-score differences and estimate a group contrast at the endpoint. The registry says the least-squares means were derived from a baseline-adjusted endpoint measure using ANCOVA.

The endpoint is useful for comparing groups on a defined measure rather than relying only on an unstructured judgment of improvement. Its interpretation is limited to the score and follow-up definition used: the endpoint combines the week 8 assessment with LOCF where applicable. The registry does not report details about the questionnaire administration, the handling of individual missing items, or a clinically important difference for this score.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary analysis is described as ANCOVA, a general statistical method that compares an outcome between groups while adjusting for a baseline measurement. In general, adjustment can improve precision when baseline values are related to endpoint values and can account for chance differences in starting scores. The registry says the endpoint measure was baseline-adjusted and that least-squares means were used. It does not report the full model specification, any additional covariates, or the assumptions checks.

What do the least-squares means represent?

In general, a least-squares mean is a model-based group estimate, adjusted for the covariates included in the analysis. It is not necessarily the simple arithmetic average of all observed endpoint scores. For this trial, the arm estimates are 20.96 for vardenafil and 14.2 for placebo. Their confidence intervals describe uncertainty around those model-based means, conditional on the fitted model and its assumptions. The registry’s reported group contrast is -6.76, with a confidence interval from -9.03 to -4.49. Because the record does not state the contrast coding order, its negative sign cannot on its own identify which arm has the larger score.

How should the confidence intervals and p-values be read?

In general, a confidence interval communicates estimation uncertainty, while a p-value measures how surprising the observed data, or more extreme data, would be under a specified null hypothesis and analysis model. Neither is a measure of the probability that the treatment works, nor does either quantify clinical importance. The sponsor reports a 95% confidence interval and p < 0.001 for the primary comparison. This supports a statistically detectable contrast under that analysis, but the registry does not state a clinical-importance threshold for the IIEF-EF score.

For binary outcomes, a risk difference is the difference between the outcome proportions in two groups. In general, it is expressed on the same percentage-point scale as the proportions and can be more directly interpreted than a relative measure. A confidence interval for a risk difference indicates uncertainty around that absolute contrast. The secondary recalculations use the posted event counts and group sizes without adjustment. They are descriptive recalculations, not the sponsor’s adjusted analysis.

What does “recalculated” mean for the secondary results?

The recalculated risk differences and their intervals are simple, unadjusted comparisons based on the posted summary counts. They do not account for covariates or any design features beyond the two-group comparison. For the “back to normal” outcome, the posted percentages are 35.0 for vardenafil and 10.0 for placebo, and the recalculated risk difference is 0.251, with a 95% confidence interval from 0.122 to 0.381. The posted sponsor analysis reports p < 0.001 using Mantel Haenszel. The unadjusted recalculation reports p < 0.001. These p-values come from different methods and should not be treated as identical analyses.

For remaining on the initial 10 mg dose, the posted counts are 28 for vardenafil and 13 for placebo. The recalculated risk difference is 0.188, with a 95% confidence interval from 0.045 to 0.33, and the unadjusted p-value is 0.012. No sponsor-reported analysis is listed for that outcome. The two sets of estimates address different secondary questions and do not replace the prespecified primary endpoint.

How should the planning illustrations be interpreted?

In general, a sample-size calculation estimates how many participants per arm might be needed under stated assumptions to detect a chosen effect with a chosen power and significance level. The planning illustrations use a two-sided significance level of 0.05, equal allocation, and a normal approximation, with effects set at stated fractions of the observed effects. For the “back to normal” endpoint, the illustration gives 43 participants per arm for 80% power when planning for 100% of the observed effect, 68 when planning for 75%, and 135 when planning for 50%. For 90% power, the corresponding figures are 57, 91, and 180 participants per arm. For remaining on the initial dosage, the figures are 89, 150, and 318 participants per arm for 80% power, and 119, 201, and 425 for 90% power.

These are planning illustrations based on observed effects, not evidence that the completed trial had a particular power. Smaller effects generally require larger samples to detect under otherwise comparable assumptions; this is a general statistical principle. The illustrations are sensitive to the observed effect estimates, which can be imprecise, especially in a small study. The registry’s own sample-size justification and design assumptions are not reported in the registry record. The primary endpoint does not have a corresponding recalculated planning illustration in the posted results.

What is not established by the reported methods?

The registry identifies ANCOVA for the primary endpoint and Mantel Haenszel for one secondary endpoint, but does not provide a full statistical analysis plan. Model diagnostics, handling of protocol deviations, imputation beyond the stated LOCF endpoint definition, and rules for analysis populations are not reported in the registry record. Those missing details matter because statistical conclusions depend on both the model and the data included. Consequently, the numerical results can be described as posted, while the appropriateness of every modeling decision cannot be independently assessed from this record.

10. Analyses Reported by the Sponsor

The sponsor’s primary analysis is the ANCOVA comparison, reported as a mean difference (final values) of -6.76, with a 95% confidence interval from -9.03 to -4.49 and p < 0.001. The posted arm-level least-squares means are 20.96 for vardenafil and 14.2 for placebo. The registry record does not report the contrast coding order, so the negative sign of the reported difference should be read as the sponsor’s signed contrast rather than as a stand-alone indicator of the direction between arms.

The secondary recalculation for “back to normal” uses the posted counts to estimate an unadjusted risk difference and p-value. The sponsor’s reported analysis for that endpoint is Mantel Haenszel, with p < 0.001. The methods differ, so modest differences in estimates or p-values would not by themselves indicate an error. For the initial-dose outcome, a recalculated unadjusted comparison is available, but no sponsor-reported analysis is listed.

The primary result has not been replaced by a recalculation. The posted results identify the sponsor’s ANCOVA as the primary analysis, and it takes precedence over any unadjusted reanalysis of summary data. The registry does not report enough detail to reproduce the full ANCOVA model from the summary results alone.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists several secondary outcomes in addition to the primary endpoint. It reports a Mantel Haenszel analysis for the “back to normal” outcome, but does not report a multiplicity strategy: whether secondary tests were adjusted, ordered hierarchically, or designated as exploratory is not reported in the registry record. In general, testing multiple outcomes without adjustment can increase the chance of a false-positive finding. That concern does not invalidate an individual result, but it changes how strongly it should be interpreted, especially when the analysis plan is unavailable.

The primary endpoint is described as a baseline-adjusted ANCOVA at week 8 or LOCF. The record states that the analyzed participant number differs because of missing data. LOCF means, in general, carrying a participant’s last observed outcome forward to a later assessment when a later observation is unavailable. This approach can make the analysis depend on assumptions about what would have happened after the last observation; those assumptions may not hold in every trial. The registry does not report the amount or pattern of missing data, the reasons for missingness, or sensitivity analyses addressing alternative missing-data assumptions.

Analysis populations and detailed inclusion rules are not reported in the registry record. As a result, it is not possible from the posted summary alone to determine precisely how participants with protocol deviations or incomplete measurements were handled across all outcomes. The differing analyzed numbers should be kept in view when comparing endpoints; denominators are outcome-specific and should not be assumed to represent identical analysis sets.

These gaps limit independent assessment of robustness. A complete protocol or statistical analysis plan could clarify the intended outcome hierarchy, population definitions, missing-data procedures, and multiplicity control. Since those details are not reported in the registry record, the posted estimates can be described, but not all analytic choices can be verified.

12. 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 non-serious adverse event terms

The registry lists zero participants with serious adverse events among the 75 at risk in the vardenafil group and zero among the 72 at risk in the placebo group. It lists 16 participants with other adverse events in the vardenafil group and 8 in the placebo group. These are recorded counts, not a complete account of the type, timing, severity, or duration of events.

Zero reported serious adverse events in these groups does not establish that serious events cannot occur or that the groups have equivalent safety. In general, uncommon events may not appear in a study of limited size, and a count alone gives little information about the range of possible risk. The registry does not provide serious-event terms, and deaths are not reported as numerical values. That absence should not be interpreted as confirmation that there were no deaths.

Details about adverse-event definitions, collection procedures, follow-up, and statistical comparisons are not reported in the registry record. The figures should therefore be read as the safety counts posted for this trial, not as a comprehensive estimate of comparative risk.

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

The primary result is an ANCOVA comparison of a defined erectile-function score at week 8 or LOCF, adjusted for baseline. The posted least-squares means are 20.96 for vardenafil and 14.2 for placebo. The sponsor reports a signed contrast of -6.76, with a 95% confidence interval from -9.03 to -4.49 and p < 0.001. Together, these results indicate a statistically detectable between-group contrast under the reported analysis. The record does not state the contrast coding order, so the negative sign alone should not be interpreted as indicating which group’s score was higher.

Statistical evidence does not by itself establish the clinical importance of a difference. The registry does not report a minimum clinically important difference or another threshold for interpreting score changes in terms of meaningful benefit. The score is a measure of erectile function, not a direct measure of every aspect of health or experience. The reported endpoint also uses LOCF where applicable, and the assumptions behind that handling cannot be fully assessed from the registry record.

The secondary results add information about a reported “back to normal” status and remaining on the initial dosage. These outcomes are not substitutes for the primary endpoint, and the available evidence does not cover every listed secondary measure. The record does not report a multiplicity plan, so secondary results require more caution than the primary comparison.

The safety counts describe adverse events observed in the trial, but they do not prove the absence of risk or establish equivalence between groups. More generally, the study’s conclusions apply to the participants, measures, treatment schedule, and follow-up recorded in this trial. They do not establish results for other populations, schedules, or outcomes. The registry record does not provide enough information to assess every aspect of trial conduct, missing data, or model assumptions.

14. Why This Trial Matters Statistically

This trial is statistically informative because it makes a randomized, double-blind comparison using a defined patient-reported erectile-function score and a baseline-adjusted primary analysis. The registry records both model-based group estimates and the sponsor’s inferential result. That lets readers distinguish the values for each group from the signed contrast and its uncertainty, rather than relying on a p-value alone.

The endpoint also illustrates why analysis details matter. A negative contrast can be difficult to interpret when the record does not specify the group order used in the calculation, especially when the arm-level means are displayed separately. Reporting the contrast convention would make the result easier to interpret. In general, estimates, intervals, and clear group ordering provide more information than a significance label alone.

The secondary outcomes illustrate a separate statistical issue: multiple questions can be examined in one trial. Without a reported multiplicity strategy, isolated secondary p-values carry less weight. The record also shows how sample-size planning depends on assumptions about the effect to detect. The posted planning illustrations use fractions of the observed effect and should not be confused with observed power or the trial’s original design justification.

Finally, the record highlights the importance of missing-data reporting. The primary endpoint uses LOCF and the analysis count differs because of missing data, but the extent and pattern of missingness are not reported. Those details affect how confidently readers can assess the model’s assumptions and robustness. These are general statistical considerations, not evidence that a particular choice changed the findings.

15. Limitations

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

Several trial-specific details needed for a fuller appraisal are not reported in the registry record. These include the randomization method, allocation concealment, masking procedures, site details, eligibility criteria beyond the named conditions, and adherence information. The record gives a broad treatment schedule but does not explain the rules for moving between doses or how dose escalation was determined.

For the primary endpoint, the registry identifies ANCOVA and LOCF but does not report the complete model specification, covariates beyond baseline, model diagnostics, or sensitivity analyses. It notes that analyzed numbers differ because of missing data, but does not report the amount, timing, or reasons for missingness. These omissions make it difficult to assess how robust the primary estimate is to alternative assumptions.

The signed primary contrast is negative, while the displayed arm-level means are numerically higher for vardenafil. The registry record does not report the contrast coding order, which limits interpretation of the sign. The record also does not define a threshold for clinical importance on the IIEF-EF scale.

For secondary outcomes, some listed measures have no numerical results, and the multiplicity strategy is not reported. The available unadjusted recalculations are based on summary counts and do not reproduce the sponsor’s full analysis. Safety reporting is also limited: serious-event terms are absent, deaths are not given as numerical values, and event definitions and collection details are not reported. These gaps constrain interpretation without establishing that any particular result is biased.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study of Vardenafil in Patients Suffering From Erectile Dysfunction and Metabolic Syndrome — NCT00738400.
• Registry record last updated 2015-11-16; status last verified 2015-11.
• Results first posted 2011-06-01.
• 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.

19. Record Summary

This completed Phase 4 study compared as-needed vardenafil with matching placebo in men with erectile dysfunction and metabolic syndrome. The randomized, double-blind, parallel-group study enrolled 150. Its primary endpoint was baseline-adjusted IIEF-EF score at week 8 or LOCF, analyzed using ANCOVA. The sponsor reported a contrast of -6.76, with a 95% confidence interval from -9.03 to -4.49 and p < 0.001; the arm-level least-squares means were 20.96 for vardenafil and 14.2 for placebo.

Available secondary results include a “back to normal” erectile-function outcome and remaining on the initial 10 mg dosage. Other listed secondary outcomes do not have numerical results in the registry record. Serious adverse-event counts were zero in both groups, while other adverse-event counts were 16 for vardenafil and 8 for placebo. Missing-data details, multiplicity procedures, full model specifications, and several safety-reporting details are not reported in the registry record.