A Study In Patients With Neuropathic Pain From Post-Herpetic Neuralgia (PHN): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study In Patients With Neuropathic Pain From Post-Herpetic Neuralgia (PHN) (NCT00619476), a randomized phase 2 study. The primary outcome is Change From Baseline in the Mean 24-hour Average Pain Intensity (API) Score at the End of Maintenance Treatment (EOMT) Using Last Observation Carried Forward (LOCF) Data.

2. Clinical Question

3. Trial Design

This completed Phase 2 trial was randomized, triple-masked, and parallel-group. The registry lists 376 enrolled participants and four groups: placebo and GEn at 1200 mg/day, 2400 mg/day, or 3600 mg/day. The active-treatment descriptions specify maintenance treatment for 14 weeks. The trial began in 2008-02, and primary completion is recorded as 2009-07.

The primary outcome was assessed in the ITT Population, defined in the registry as all randomized participants who took at least one dose of investigational product and provided at least one post-baseline efficacy measurement. The primary outcome's arm-level analysis counts were 95 for placebo, 107 for GEn 1200 mg/Day, 82 for GEn 2400 mg/Day, and 87 for GEn 3600 mg/Day. These analysis counts should not be mistaken for the overall enrollment.

The endpoint timeframe is baseline and end of maintenance treatment (EOMT), described as the earliest date of the Week 13 visit, withdrawal visit, or last dose of study drug. The registry record does not report the original sample-size justification, detailed randomization procedures, or the allocation ratio. Further detail on masking procedures is not reported in the registry record.

The record lists 19 outcome measures and 18 posted secondary outcomes. It reports three primary comparisons, each comparing an active-treatment dose with placebo. The posted primary analyses use ANCOVA and describe adjusted mean differences versus placebo. The registry identifies the trial as completed, but completion status alone does not convey the degree of missing outcome data or the full analysis plan.

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: ITT Population: all randomized participants who took at least one dose of investigational product and provided at least one post-baseline efficacy measurement.

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 the Mean 24-hour Average Pain Intensity (API) Score at the End of Maintenance Treatment (EOMT) Using Last Observation Carried Forward (LOCF) Data, measured over Baseline and EOMT (representing the earliest date of Week 13 visit/withdrawal visit).

The primary endpoint is change from baseline in mean 24-hour average pain intensity at EOMT, using last observation carried forward (LOCF) data. A participant's baseline value is the mean of daily 24-hour average pain-intensity scores during the last 7 days before randomization. The EOMT value is based on daily scores up to the earliest applicable EOMT date specified in the registry record.

Participants recorded average pain over the preceding 24 hours in a hand-held diary, using an 11-point PI-Numerical Rating Scale. The scale ranges from 0, meaning no pain, to 10, meaning pain as bad as the participant can imagine. The endpoint is calculated as EOMT score minus baseline score. Thus, negative change values indicate that the recorded score was lower at EOMT than at baseline; a more negative mean change indicates a greater average reduction in the score.

This continuous measure retains information about the size of score changes rather than reducing responses to a binary category. Comparing mean changes between randomized groups provides an estimate of how the groups differed over the treatment period. The endpoint is relevant to the stated trial question because it records participants' ratings of average pain over a full 24-hour period. It remains a self-reported scale measure, and its interpretation depends on the diary data, the timing of the EOMT measurement, and the LOCF procedure used when diary data were limited.

7. Results Posted in the Registry

• GEn 1200 mg/Day: mean -2.47 versus -1.66 on control; difference -0.81 (95% CI -1.39 to -0.23), standardized effect d = -0.38; z-test p = 0.006.
• GEn 2400 mg/Day: mean -2.36 versus -1.66 on control; difference -0.70 (95% CI -1.33 to -0.07), standardized effect d = -0.33; z-test p = 0.029.
• GEn 3600 mg/Day: mean -2.72 versus -1.66 on control; difference -1.06 (95% CI -1.67 to -0.45), standardized effect d = -0.50; z-test p = <0.001.

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.

Change From Baseline in the Mean Night-time Average Pain Intensity (API) Score at EOMT Using LOCF Data

• 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 errors.
• Result:
  • GEn 1200 mg/Day: mean -2.35 versus -1.65 on control; difference -0.70 (95% CI -1.29 to -0.11), standardized effect d = -0.33; z-test p = 0.020.
  • GEn 2400 mg/Day: mean -2.44 versus -1.65 on control; difference -0.79 (95% CI -1.42 to -0.16), standardized effect d = -0.37; z-test p = 0.015.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for GEn 1200 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for GEn 2400 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in the Mean Current Morning Pain Intensity Score at EOMT Using LOCF Data

• 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 errors.
• Result:
  • GEn 1200 mg/Day: mean -2.29 versus -1.34 on control; difference -0.95 (95% CI -1.55 to -0.35), standardized effect d = -0.44; z-test p = 0.002.
  • GEn 2400 mg/Day: mean -2.13 versus -1.34 on control; difference -0.79 (95% CI -1.43 to -0.15), standardized effect d = -0.36; z-test p = 0.016.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for GEn 1200 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for GEn 2400 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in the Mean Night-time Worst Pain Intensity Score at EOMT Using LOCF Data

• 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 errors.
• Result:
  • GEn 1200 mg/Day: mean -2.49 versus -1.76 on control; difference -0.73 (95% CI -1.37 to -0.09), standardized effect d = -0.31; z-test p = 0.026.
  • GEn 2400 mg/Day: mean -2.65 versus -1.76 on control; difference -0.89 (95% CI -1.58 to -0.20), standardized effect d = -0.38; z-test p = 0.012.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for GEn 1200 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for GEn 2400 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists 18 secondary outcomes, including pain ratings at different times of day, worst pain, sleep interference, and pain quality. These measures broaden the description of pain-related outcomes beyond the primary 24-hour average score. The posted secondary results available in the record include numerical results for night-time average pain intensity, current morning pain intensity, and night-time worst pain intensity.

Across those secondary outcomes with posted arm-level means, changes from baseline are negative in the placebo and active-treatment groups. The available recalculated comparisons against placebo are also negative for the dose comparisons listed. This general pattern is directionally consistent with the primary outcome's group-level pattern, but it is not a substitute for the primary adjusted analysis. The registry does not report sponsor ANCOVA comparisons for these secondary outcomes.

The secondary results should be interpreted with more caution than a single prespecified primary comparison. Multiple outcomes and comparisons create opportunities for apparently notable findings to arise by chance, especially when p-values are unadjusted. The registry record does not report a multiplicity adjustment or a hierarchy of secondary hypotheses. The posted secondary analyses therefore add context about the range of measured outcomes, but their p-values should not be treated as confirmatory evidence without knowing the analysis plan.

Not all listed secondary outcomes have complete numerical comparisons in the registry record. The absence of a posted comparison is not evidence that the outcome showed no difference. The secondary outcomes are most useful for understanding which aspects of pain were measured and whether the posted descriptive direction broadly aligns with the primary endpoint, while recognizing that the reporting and multiplicity details are limited.

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

• Change From Baseline in the Mean Night-time Average Pain Intensity (API) Score at EOMT Using LOCF Data
• Change From Baseline in the Mean Current Morning Pain Intensity Score at EOMT Using LOCF Data
• Change From Baseline in the Mean Night-time Worst Pain Intensity Score at EOMT Using LOCF Data
• Change From Baseline in the Mean Sleep Interference Score at EOMT Using LOCF Data
• Change From Baseline in the Mean Day-time Average Pain Intensity(API) Score at EOMT Using LOCF Data
• Change From Baseline in the Mean Current Evening Pain Intensity Score at EOMT Using LOCF Data
• Change From Baseline in the Mean Day-time Worst Pain Intensity Score at EOMT Using LOCF Data
• Change From Baseline in Pain Quality as Assessed by the Neuropathic Pain Scale (NPS) Summary Scores at EOMT Using LOCF Data

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: it is a score and a change in score, rather than a count or a yes/no event. The registry reports least-squares means for the arm-level changes, along with standard errors. A least-squares mean is a model-based estimate of a group mean; in this trial, the sponsor's reported comparisons were based on ANCOVA. ANCOVA estimates a between-group difference while accounting for covariates in the model. The covariates and other details of the sponsor's model are not reported in the registry record.

The primary analysis compares each GEn dose group with the concurrent placebo group. The adjusted mean difference describes the estimated difference in change scores between an active-treatment group and placebo. A negative adjusted difference means the active-treatment group had a more negative change score on average. The confidence interval gives a range of values compatible with the estimate under the analysis model, while the p-value summarizes how inconsistent the data are with a null difference under that model. Neither measure alone describes clinical importance.

The recalculated comparisons are simple, unadjusted calculations from the posted summary statistics. They are not a reconstruction of the ANCOVA model. In the recalculation, the standard deviations are approximated from the reported standard errors and group sizes. That approach does not use participant-level data, and it cannot reproduce model adjustments or account for covariates and other details that are not present in the summary statistics. Because the registry record has a discrepancy between the recalculated and sponsor-reported analyses, the sponsor's own analysis takes precedence for interpreting the primary comparisons.

The posted analysis uses LOCF when fewer than 4 days of diary data were provided. LOCF carries the last observed value forward to stand in for a later measurement. This can preserve participants in an analysis when a later diary value is unavailable, but it relies on an assumption about how the unobserved score relates to the last recorded score. If pain changes after the last recorded diary entry, carrying that earlier value forward may not represent the participant's later status. The registry record does not report sensitivity analyses evaluating alternative approaches to missing diary data.

The reported standard error describes the estimated sampling variability of a mean estimate under its analysis. It is not the spread of individual participant scores. A confidence interval combines an estimate and its uncertainty to show a range of plausible values under the model. Here, confidence intervals are reported for the adjusted between-group comparisons, while the arm-level means are accompanied by standard errors.

General statistical point: an unadjusted comparison and a covariate-adjusted comparison can differ because they use different information and model structures. An adjusted estimate may account for baseline or other covariates, whereas a calculation from group summaries uses only the summary information available. A difference between these estimates does not, on its own, identify which model component caused the difference. That requires details of the model and data that are not reported in the registry record.

General statistical point: multiplicity arises when several hypotheses are tested. Considering many comparisons can increase the chance that at least one result appears unusual even when there is no underlying difference. Procedures that control this issue, or a prespecified hierarchy that defines which tests are confirmatory, can affect how p-values should be interpreted. The registry record does not report whether such a procedure was used for the primary comparisons or secondary outcomes.

The primary endpoint is a mean-based continuous outcome. The planning illustration associated with the recalculated comparisons uses a normal approximation and equal allocation between the two arms being compared. Those are planning assumptions for that illustration, not evidence about the trial's original design assumptions. The original sample-size justification and design assumptions are not reported in the registry record.

General statistical point: over-dispersion is relevant when count data vary more than a model assumes, and may require methods that allow extra variability. The primary endpoint is continuous rather than a count, so count-data over-dispersion is not the central issue for this analysis. The registry does not provide enough model detail to assess all assumptions underlying the ANCOVA analysis.

11. Confidence Intervals and Precision

The sponsor-reported 95% confidence intervals for the adjusted mean differences are -1.40 to -0.23 for GEn 1200 mg/Day, -1.33 to -0.07 for GEn 2400 mg/Day, and -1.68 to -0.45 for GEn 3600 mg/Day. Each interval expresses uncertainty about the size of the between-group difference, in points on the pain-intensity scale, under the sponsor's ANCOVA analysis.

The intervals provide more information than the point estimates alone. For example, a point estimate identifies the center of an estimated difference, while the confidence interval indicates a range of values that are compatible with the data and model at the stated confidence level. The intervals do not mean that there is a 95% probability that the fixed treatment effect lies within a particular interval. They also do not account for uncertainty arising from unreported analysis choices or missing-data assumptions.

The upper and lower limits are both negative for each sponsor-reported comparison. This indicates that the reported intervals lie on the side corresponding to a more negative change score in the active-treatment group than in placebo. Their widths show that the exact magnitude remains uncertain. Whether a difference is important to participants cannot be established from statistical precision alone; a threshold for clinical importance is not reported in the registry record.

The recalculated intervals differ slightly from the sponsor-reported intervals, particularly in their unrounded limits and related p-values. The calculations use posted summary statistics and approximate standard deviations rather than the sponsor's ANCOVA model. Given the discrepancy, the sponsor-reported estimates and intervals are the appropriate results to prioritize when describing the trial's own analysis.

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 planning figures are participants per arm for 80% power and participants per arm for 90% power. They are not total sample sizes for the whole trial. The planning illustration is based on a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It considers an effect equal to 100%, 75%, or 50% of the observed effect. The trial's original sample-size assumptions are not reported in the registry record.

The 80% power column gives the estimated participants per arm for a planning scenario designed to have an 80% chance of detecting the stated effect under the planning assumptions, if that effect is the true one and the assumptions hold. The 90% power column describes the analogous planning target with a higher chance of detection, which generally requires more participants. These figures are planning illustrations, not observed power.

The rows that plan for a smaller fraction of the observed effect require more participants per arm. This is because a smaller between-group difference is harder to distinguish from random variation when the variability is otherwise similar. The figures are recalculated using effects observed in this trial; they do not validate the trial's original enrollment target or replace a design calculation based on a prespecified clinically important effect.

The related planning curve communicates the same general relationship: detecting a smaller effect requires a larger planned sample. It should be interpreted as an illustration under the stated assumptions, not as a forecast of the result in another study. The calculation is pairwise and should not be read as addressing multiplicity across all primary comparisons or secondary outcomes.

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 = -0.810; pooled standard deviation σ = 2.108.
2. n = 2 × (1.96 + 0.842)² × 2.108² / -0.810² = 106.3, rounded up to 107 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 <- -0.81                      # observed difference in means
sigma <- 2.10789794819389                     # 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(619476)
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 = 107 (80% power), 143 (90% power)
 75% of observed effect: n per arm = 189 (80% power), 254 (90% power)
 50% of observed effect: n per arm = 426 (80% power), 570 (90% power)
power.t.test: 107.3 
Simulated power at n = 107 per arm: 0.799 (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. Analyses Reported by the Sponsor

The registry reports the sponsor's primary comparisons as ANCOVA-adjusted mean differences versus placebo, with 95% confidence intervals and p-values. The unadjusted recalculations use the posted arm-level means, standard errors, and group sizes. They are useful as a check on the broad direction and approximate scale of the comparisons, but they do not reproduce the sponsor's model.

The recalculated estimate for GEn 1200 mg/Day is -0.81, with a recalculated p-value of 0.006; the sponsor reports -0.81 and p = 0.013. For GEn 2400 mg/Day, the recalculated estimate is -0.7 with p = 0.029, while the sponsor reports -0.70 with p = 0.029. For GEn 3600 mg/Day, the recalculated estimate is -1.06 with p < 0.001, while the sponsor reports -1.07 with p = 0.002. The sponsor's reported confidence intervals also differ slightly from the recalculated intervals.

These discrepancies are consistent with the fact that the recalculation is unadjusted and relies on approximated variability, whereas the registry identifies ANCOVA as the sponsor's method. The covariates and full model details are not reported in the registry record. Accordingly, the sponsor's own analysis takes precedence; the recalculations should not be substituted for it.

15. Multiplicity, Missing Data and Analysis Populations

The primary results involve three comparisons of GEn doses with placebo. The record also lists 18 secondary outcomes, creating a broader set of potential statistical tests. When many hypotheses are examined, the chance of at least one apparently unusual result can increase. Statistical practice may address this through multiplicity adjustment, a prespecified testing hierarchy, or a clear distinction between confirmatory and exploratory analyses.

The registry record does not report whether the primary comparisons were adjusted for multiplicity, whether a testing sequence was specified, or whether secondary analyses were adjusted. The reported p-values should therefore be understood as the p-values attached to the listed sponsor analyses, not assumed to represent multiplicity-adjusted evidence. The detailed statistical analysis plan is not reported in the registry record.

Missing-data handling is described in part: LOCF was used if fewer than 4 days of diary data were provided. This specifies a rule for diary data, but does not fully explain the amount or pattern of missingness, the number of participants with LOCF values, or whether other missing outcomes were handled differently. Sensitivity analyses for the LOCF assumption are not reported in the registry record.

The primary analysis population is defined as randomized participants who received at least one dose and had at least one post-baseline efficacy measurement. This definition excludes randomized participants who did not meet either condition. The registry does not report how many randomized participants were excluded from this population or how their outcomes were handled. The term ITT is used in the record, but its stated operational definition is important when considering how closely the analysis reflects all randomized participants.

The original sample-size justification, interim analyses, and full statistical plan are not reported in the registry record. This limits assessment of whether the trial was designed around a prespecified effect, how multiple endpoints were prioritized, and whether the reported analyses followed a prespecified procedure.

16. 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: intracranial aneruysm (1.2%), multiple sclerosis (1.2%), chest pain (1.2%), sinusitis (1.2%), blood pressure increased (1.2%).

The registry reports serious adverse events by group with participants at risk and participants affected. The serious adverse event counts affected were 2 of 95 for placebo, 0 of 107 for GEn 1200 mg/Day, 6 of 82 for GEn 2400 mg/Day, and 2 of 87 for GEn 3600 mg/Day. These are descriptive group counts, not adjusted comparisons, and the registry does not report statistical tests comparing serious adverse events between groups.

The adverse-event data also list participants at risk and affected for other, non-serious adverse events: 120 and 63 for placebo, 107 and 75 for GEn 1200 mg/Day, 82 and 64 for GEn 2400 mg/Day, and 87 and 71 for GEn 3600 mg/Day. These denominators differ for placebo from the serious-event denominator, so the figures should be read according to the specific event category rather than assumed to share one analysis population.

The record lists serious adverse-event terms and includes 1.2% for each of the listed terms, but does not provide enough context to attribute those terms to a particular treatment group. Death counts are not reported in the registry record. These registry summaries do not establish a comparative safety profile; they describe the adverse-event counts and terms recorded.

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

The primary results describe average changes in a self-reported pain-intensity score over the trial's baseline-to-EOMT period. The sponsor's adjusted comparisons estimate more negative change scores for each GEn dose than for placebo. The confidence intervals convey uncertainty about the magnitude of those adjusted differences, and the reported p-values describe the statistical tests used by the sponsor.

These findings do not, by themselves, establish whether a difference is large enough to matter to participants. A threshold for clinical importance is not reported in the registry record. Statistical evidence and clinical importance are different questions: a result can be statistically distinguishable from no difference without demonstrating that the size of the difference is meaningful in everyday experience.

The results also do not establish that one GEn dose is better than another. The listed primary comparisons are each against placebo, not direct comparisons between active doses. Comparing the arm means informally cannot replace a prespecified statistical test of dose differences or a dose-response analysis.

Interpretation depends on the outcome definition, the diary records, the LOCF rule, and the analysis population. The primary outcome reflects mean diary scores, and LOCF was used under the registry's stated condition when fewer than 4 days of data were provided. The registry does not report sensitivity analyses that would show how results might change under alternative missing-data assumptions.

The statistical results are specific to this trial's participants, procedures, time period, and analysis. They do not establish an effect in every population or setting, and they do not replace a broader evaluation of evidence. The safety counts are descriptive and do not permit a firm between-group safety conclusion from the registry summaries alone. No medical advice or treatment recommendation follows from these statistical results.

18. Why This Trial Matters Statistically

This trial illustrates several issues that arise when interpreting a multi-arm randomized study. The primary question involves three active-dose comparisons with a shared placebo group, so interpretation depends not only on the estimated differences but also on how multiple comparisons were handled. The registry record does not report a multiplicity strategy, making that uncertainty part of the statistical reading.

The record also distinguishes the sponsor's adjusted ANCOVA results from simple unadjusted recalculations based on arm-level summaries. The estimates are broadly similar in direction and magnitude, but some p-values and limits differ. This is a practical example of why a recalculation from summary statistics is a check rather than a replacement for the trial's own model-based analysis.

Use of LOCF is another important feature. Carrying the last diary value forward gives a defined approach to incomplete diary data, but it rests on assumptions about unobserved measurements. Without reported missingness patterns and sensitivity analyses, readers cannot assess how robust the estimates are to alternative approaches.

Finally, the continuous pain score produces interpretable mean changes, but statistical precision does not answer whether a difference is clinically important. The registry does not report a threshold for meaningful change or a sample-size justification tied to such a threshold. The trial is therefore informative about the posted estimates and their uncertainty while leaving important design and interpretation details unresolved.

19. 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 or the assumptions used to set enrollment. The planning illustrations based on observed effects cannot establish what effect the trial was designed to detect. Interim analyses and the full statistical analysis plan are also not reported.

Although the primary analyses are identified as ANCOVA, the record does not specify the covariates, model diagnostics, or other details needed to fully evaluate the model. The recalculated comparisons depend on approximated standard deviations derived from summary information and are unadjusted. The documented discrepancy means the sponsor's reported analysis should take precedence.

The LOCF rule addresses diary data when fewer than 4 days were provided, but the registry does not report the extent or pattern of missing diary data, nor sensitivity analyses under different missing-data assumptions. The stated ITT Population definition requires at least one dose and at least one post-baseline efficacy measurement; counts excluded under this definition are not reported.

The multiplicity approach for the primary comparisons and the many secondary outcomes is not reported. This limits interpretation of the reported p-values as a family of tests. Numerical results are not posted for every listed secondary outcome, and sponsor-reported ANCOVA comparisons are absent for the secondary results included in the record.

Safety summaries are descriptive, with different participant-at-risk counts across some event categories. The registry does not report comparative tests for these events, and deaths are not reported in the registry record. These reporting limitations constrain conclusions about the completeness and comparative interpretation of the safety data.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study In Patients With Neuropathic Pain From Post-Herpetic Neuralgia (PHN) — NCT00619476.
• Registry record last updated 2013-07-22; status last verified 2013-01.
• Results first posted 2011-05-20.
• 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.

23. Record Summary

The registry describes a completed, randomized, triple-masked, parallel-group Phase 2 trial enrolling 376 participants with neuropathic pain associated with PHN. The groups received placebo or GEn at 1200 mg/day, 2400 mg/day, or 3600 mg/day, with active-treatment maintenance described as 14 weeks.

The primary endpoint was change in mean 24-hour average pain intensity from baseline to EOMT, using diary scores and LOCF under the stated missing-diary condition. The sponsor reported ANCOVA-adjusted mean differences versus placebo, with 95% confidence intervals and p-values for each dose comparison. The recalculated results differ in some details, so the sponsor's analysis takes precedence.

The registry also lists secondary outcomes and descriptive adverse-event counts. Multiplicity procedures, original sample-size assumptions, detailed model specifications, and sensitivity analyses for missing data are not reported in the registry record.