Trial to Assess Efficacy and Safety of Lacosamide in Subjects With Osteoarthritis of the Knee: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Trial to Assess Efficacy and Safety of Lacosamide in Subjects With Osteoarthritis of the Knee (NCT00485472), a randomized phase 2 study. The primary outcome is Change of the Western Ontario and McMaster Universities (WOMAC) Pain Subscale Score (Visual Analogue Scale Version) From Baseline to the End of the 8 Week Maintenance Period.

2. Clinical Question

3. Trial Design

The registry record describes a phase 2, randomized, double-blind, placebo-controlled, parallel-group trial of lacosamide in people with osteoarthritis of the knee. The purpose was to evaluate effectiveness, safety, and tolerability of lacosamide 400mg/day for signs and symptoms of knee osteoarthritis. Participants were allocated to lacosamide or placebo. The record reports 194 enrolled participants.

The listed study start was 2007-03, and primary completion was 2007-11. The study status is recorded as terminated. The reason for termination is not reported in the registry record, so the status alone does not establish why the study ended or what consequences that had for the analysis.

The primary outcome was change in WOMAC pain from baseline to the end of the 8 week maintenance period. Secondary outcomes included other WOMAC scores, patient-reported change, response criteria, rescue medication use, pain interference with sleep, and mood disturbance. The record lists eight secondary outcomes and reports three of them with group-level results: physical function, stiffness, and total WOMAC score.

The primary analysis population was the Full Analysis Set, defined in the record as randomized participants who received at least one dose of trial medication and had at least one post-baseline WOMAC assessment. Last observation carried forward was used when a WOMAC assessment was missing. The posted primary outcome includes 71 participants in the lacosamide group and 74 in the placebo group. The registry record does not report the original sample-size justification, the planned enrollment for each arm, or whether the design included interim analyses.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: Of the 194 enrolled subjects, 149 subjects have been randomized until trial termination. The Participants flow refers to the randomized population. Of the 149 randomized subjects, 148 subjects have been treated and are included in the safety population, 145 have been included in the ITT population (Full Analysis Set).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set (FAS), defined as all randomized subjects that have received at least one dose of trial medication and had at least one post-baseline WOMAC assessment. Last observation carried forward (LOCF) imputation method was applied in case of missing WOMAC assessment.

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 of the Western Ontario and McMaster Universities (WOMAC) Pain Subscale Score (Visual Analogue Scale Version) From Baseline to the End of the 8 Week Maintenance Period, measured over Baseline, end of 8 week Maintenance Period.

The primary endpoint was the change in the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) pain subscale score from baseline to the end of the 8 week maintenance period. The measure was the visual analogue scale version of the subscale. Its range is 0 to 100, with higher values describing a higher grade of pain. The endpoint is continuous: it records the amount of change on a scale rather than classifying participants only as responders or nonresponders.

Change scores make the result a comparison of how group averages moved from baseline through the stated assessment period. Negative group means in the posted results indicate reductions in the scale score; the meaning of those reductions should be read with the between-group estimate and its uncertainty, not by considering a group mean in isolation. The comparison is not a comparison of each participant’s baseline value with another participant’s value. It estimates the difference between the groups’ average changes.

WOMAC pain is used as a patient-reported measure of a central symptom in knee osteoarthritis. A scale can capture degrees of reported pain, allowing an average change to be described and compared across randomized groups. The endpoint does not, by itself, encompass every aspect of the condition or establish how individual participants experienced the study. The registry record specifies the population and missing-assessment approach for the primary analysis, but a minimal important difference or other threshold for interpreting the size of the change is not reported in the registry record.

7. Results Posted in the Registry

• Lacosamide: mean -24.85 versus -28.49 on control; difference 3.64 (95% CI -3.86 to 11.14), standardized effect d = 0.16; z-test p = 0.342.

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 to End of 8 Week Maintenance Period in WOMAC Physical Function Subscale Score.

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Lacosamide: mean -17.09 versus -23.31 on control; difference 6.22 (95% CI -0.97 to 13.41), standardized effect d = 0.28; z-test p = 0.090.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Lacosamide and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline to End of 8 Week Maintenance Period in WOMAC Stiffness Subscale Score.

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Lacosamide: mean -18.92 versus -23.43 on control; difference 4.51 (95% CI -3.66 to 12.68), standardized effect d = 0.18; z-test p = 0.279.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Lacosamide and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline to End of 8 Week Maintenance Period in Total WOMAC Score.

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Lacosamide: mean -60.85 versus -75.24 on control; difference 14.39 (95% CI -7.18 to 35.96), standardized effect d = 0.22; z-test p = 0.191.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Lacosamide and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary WOMAC results follow a broadly similar pattern to the primary outcome: mean scores decreased in both groups, while the unadjusted between-group estimates were positive for lacosamide relative to placebo. For the secondary WOMAC outcomes with posted comparisons, the confidence intervals include no difference. The sponsor’s ANCOVA intervals for these outcomes also include no difference. This overall pattern does not show a sharply separated treatment-group profile across the reported WOMAC domains.

These secondary measures add context because they address physical function, stiffness, and the total WOMAC score, rather than pain alone. They are related aspects of the same broader condition and should be considered alongside, not as substitutes for, the primary endpoint. The registry lists other secondary outcomes, including patient-reported change, response criteria, rescue medication use, sleep interference, and mood disturbance, but results for those outcomes are not reported in the registry record.

Secondary results usually carry less inferential weight than a primary outcome because they may be one among multiple tests. When many outcomes are considered, the chance of seeing an apparently notable result by chance can increase. Whether or how the trial adjusted for multiple comparisons is not reported in the registry record. The absence of a reported adjustment does not show that none was used, but it means the record does not permit readers to evaluate the multiplicity strategy.

Accordingly, the secondary results are best treated as additional descriptive evidence about the outcome pattern, not as independent confirmation of the primary result. Their interpretation should account for the related measures, their uncertainty, the number of outcomes under consideration, and the lack of reported multiplicity details. None of the posted secondary WOMAC comparisons establishes a distinct between-group difference on its own.

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

• Change From Baseline to End of 8 Week Maintenance Period in WOMAC Physical Function Subscale Score.
• Change From Baseline to End of 8 Week Maintenance Period in WOMAC Stiffness Subscale Score.
• Change From Baseline to End of 8 Week Maintenance Period in Total WOMAC Score.
• Patient's Global Impression of Change From Baseline at the End of 8 Week Maintenance Period.
• Response at the End of 8 Week Maintenance Period Versus Baseline Based on the (Slightly Modified)Criteria of the Osteoarthritis Research Society International (OARSI) and the Outcome Measures in Rheumatology Initiative (OMERACT).
• Amount of Rescue Medication Use During 8 Week Maintenance Period.
• Change From Baseline to End of 8 Week Maintenance Period in Perception of Pain Interference With Subject's Sleep.
• Change From Baseline to End of 8 Week Maintenance Period in Profile of Mood States (Total Mood Disturbance Score).

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous, so the posted group summaries use means and standard deviations. A mean gives the average change in each group; a standard deviation describes how spread out individual changes are around that group average. A mean difference then compares the average changes between randomized groups. The recalculated estimate is an unadjusted contrast of the posted summaries, not a participant-level model refit.

What does an unadjusted mean difference represent?

The unadjusted estimate compares the lacosamide mean change with the placebo mean change. The comparison is reported in the direction lacosamide minus placebo. For the primary outcome, the group means were -24.85 and -28.49, and the recalculated mean difference was 3.64. This means the observed average change was less negative in the lacosamide group than in the placebo group; it does not, on its own, establish that the groups differ beyond chance variation. The confidence interval and p-value add information about uncertainty under the chosen analysis.

The recalculated results are based on the posted summary statistics and use a simple unadjusted approach. They may differ from a model that adjusts for other information. The registry reports ANCOVA as the method for its own analyses. ANCOVA is a form of analysis of covariance that estimates a group contrast while accounting for one or more covariates included in the model. The covariates and full model specification are not reported in the registry record, so the adjusted analysis cannot be reproduced from the listed summary values alone.

Why does the registry report ANCOVA?

In general, ANCOVA compares groups while adjusting for covariates that can explain variation in the outcome. When used for a change outcome, the model may differ from a direct comparison of group-level change means. The estimate and its standard error can consequently differ from an unadjusted recalculation. The record identifies the method as ANCOVA and gives the adjusted mean difference, confidence interval, and p-value, but details such as the specific adjustment variables and model diagnostics are not reported in the registry record. Those details should not be inferred from the method label alone.

Randomization is intended to make treatment groups comparable on average, but an adjusted analysis can still use baseline or other covariate information to improve estimation or follow a prespecified analysis plan. Whether a particular adjustment was planned, and the exact rationale for the registry’s model, are not reported in the registry record. The sponsor’s estimates are the posted trial analyses; the unadjusted recalculations provide a separate descriptive comparison from the available group summaries.

What does the confidence interval contribute?

A confidence interval gives a range of values compatible with the observed data under the statistical model and its assumptions. It communicates precision and direction more directly than a p-value alone. For the primary outcome, the recalculated 95% confidence interval runs from -3.861 to 11.14. It crosses zero, the value representing no difference between groups, and includes both negative and positive contrasts. The sponsor’s 95% interval, from -5.30 to 10.02, also crosses zero. These intervals do not establish equivalence: an equivalence conclusion would require an appropriate design, prespecified margins, and an analysis directed at that question, none of which is reported in the registry record.

A p-value evaluates how unusual the observed data, or data more extreme, would be under a specified null model. It is not a measure of clinical importance and does not state the probability that the null hypothesis is true. The primary recalculated p-value is 0.342; the registry-reported p-value is 0.544. Since the estimates come from different approaches, the values should be understood in the context of their respective analyses rather than treated as competing readings of one identical calculation.

How should spread and sample size be understood?

Standard deviations are measures of variability among observations, not uncertainty in the group mean itself. The variability of the outcome, the number of participants, and the statistical model all contribute to the precision of an estimated group contrast. A larger standard deviation generally means more variability to distinguish from a group difference. In general, over-dispersion means that observed variability is greater than a model assumes; when that happens, standard errors and confidence intervals from a model that ignores the extra variability can be too small. The registry does not report an over-dispersion assessment, and the primary endpoint is analyzed as a continuous measure rather than a count outcome.

The sample-size illustrations use the observed effect as a planning reference and apply stated assumptions, rather than describing the trial’s original design. Power is the probability, under specified assumptions and a particular true effect, of detecting an effect using a chosen test. The planning values indicate how many participants per arm would be needed under those assumptions for the stated power targets. They do not tell how likely this completed trial was to produce a statistically significant result after its outcomes were observed.

The primary analysis population is defined as randomized participants who received at least one dose and had at least one post-baseline WOMAC assessment. The record says that last observation carried forward was used for missing WOMAC assessments. In general, this imputation method carries a participant’s last observed score forward to fill a later missing assessment. Its use can affect estimates, particularly when missingness is related to the outcome or when the outcome would otherwise change over time. The registry does not report the amount or pattern of missingness, the reasons for missing assessments, or sensitivity analyses evaluating alternative assumptions.

Multiplicity is the issue of interpreting results when several outcomes or comparisons are tested. With more tests, the chance of at least one apparently noteworthy result can rise if each is considered in isolation. The registry lists a primary outcome and multiple secondary outcomes, but the multiplicity adjustment strategy is not reported in the registry record. Secondary results should therefore be interpreted as supportive or exploratory evidence unless the analysis plan and inferential status of those tests are known.

11. Confidence Intervals and Precision

The primary recalculated mean difference is 3.64, with a 95% confidence interval from -3.861 to 11.14. The interval is wide enough to include a range of possible between-group contrasts, including values below and above no difference. It therefore communicates limited precision about the direction and size of the primary contrast. The interval does not mean there is a 95% probability that the true effect lies within these particular endpoints; under repeated use of the same method and assumptions, confidence intervals have their stated coverage interpretation.

The registry-reported ANCOVA estimate is 2.36, with a 95% confidence interval from -5.30 to 10.02. It too includes no difference. The endpoints differ from those of the recalculation because the registry reports an ANCOVA analysis, whereas the recalculation is unadjusted and based on posted summary statistics. Both results leave uncertainty about whether the underlying contrast favors either group and about its magnitude.

Precision is not the same as clinical importance. A narrow interval can precisely estimate a small difference, while a broad interval may be compatible with multiple values; neither alone specifies whether any value matters to participants. A minimal important difference for the WOMAC pain scale is not reported in the registry record, so the clinical importance of the interval endpoints cannot be judged against a registry-stated threshold.

The primary results include 71 participants assigned to lacosamide and 74 assigned to placebo. The enrollment total is 194, and the Full Analysis Set required at least one dose and a post-baseline WOMAC assessment. The record’s handling of missing WOMAC assessments and lack of a reported missingness summary limit how fully the precision can be evaluated. The interval widths describe uncertainty within the stated analyses; they do not capture every possible source of bias or uncertainty about design and reporting.

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, not total event counts. They are illustrations computed from the observed effect, not descriptions of the trial’s original design. The stated 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. The trial’s own original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the number of participants per arm estimated to be needed, under those assumptions, for an 80% chance of detecting the specified effect if that effect were the true one. The 90% power column applies the same idea to a 90% chance of detection. These are planning probabilities conditional on the assumptions, not guarantees about a future study’s result. The numbers are not a measure of the probability that the observed trial result is true, and this is not observed power.

The rows use different fractions of the observed effect as the planning target. Planning for 75% or 50% of the observed effect means targeting a smaller difference than planning for 100% of that effect. Smaller effects are harder to distinguish from ordinary variability, so they require more participants under the same assumptions. The figures are best read as sensitivity illustrations: they show how required per-arm enrollment changes when the target effect changes. They should not be read as proof that a particular sample size would produce the same result in another trial, since the calculation depends on its assumptions and the actual study conditions.

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 = 3.640; pooled standard deviation σ = 23.006.
2. n = 2 × (1.96 + 0.842)² × 23.006² / 3.640² = 627.1, rounded up to 628 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 <- 3.64                      # observed difference in means
sigma <- 23.0063744131135                     # 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(485472)
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 = 628 (80% power), 840 (90% power)
 75% of observed effect: n per arm = 1,115 (80% power), 1,493 (90% power)
 50% of observed effect: n per arm = 2,509 (80% power), 3,358 (90% power)
power.t.test: 628.1 
Simulated power at n = 628 per arm: 0.804 (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 analysis as ANCOVA, with a mean difference (net) of 2.36, a 95% confidence interval from -5.30 to 10.02, and p = 0.544. This is the analysis reported for the trial. The recalculated result uses the posted group means and standard deviations for an unadjusted comparison: the mean difference is 3.64, its 95% confidence interval is -3.861 to 11.14, and its p-value is 0.342.

The two estimates are not identical because they come from different analytical approaches. The registry-reported ANCOVA result is adjusted, while the recalculation is a simple contrast of group summaries. The covariates and detailed model specification for the ANCOVA are not reported in the registry record, so the reason for the exact numerical difference cannot be determined from the record alone. The recalculation is useful as a transparent check on the posted summary statistics, but it does not replace the sponsor’s model-based analysis.

Both confidence intervals include no between-group difference. The p-values also do not provide evidence of a clear separation between the groups under their respective analyses. These observations describe the statistical results and their uncertainty; they do not establish clinical equivalence or determine whether the observed changes matter to participants.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when an analysis considers several outcomes, comparisons, time points, or subgroups. Even if each individual test uses a conventional threshold, the chance of at least one result appearing unusual can increase as the number of tests grows. This matters for interpretation because a striking secondary result may reflect chance variation, particularly when many outcomes have been examined.

The registry identifies a primary outcome and lists eight secondary outcomes. It also reports five analyses. The multiplicity strategy, including whether the primary and secondary tests were organized in a hierarchy or whether any adjustment was applied, is not reported in the registry record. It is therefore not possible to determine from the record how the family of tests was intended to be interpreted. The primary outcome remains the clearest focal endpoint, while secondary findings should be read with caution rather than treated as equivalent independent tests.

The primary analysis used the Full Analysis Set, defined as randomized participants who received at least one dose of trial medication and had at least one post-baseline WOMAC assessment. Last observation carried forward was applied when a WOMAC assessment was missing. This gives a stated rule for handling missing values, but it does not explain how many assessments were missing, when they were missing, or why they were missing. The record also does not report sensitivity analyses under alternative assumptions about missing outcomes.

In general, imputation is needed when outcome data are absent, but any method relies on assumptions about the unobserved values. Carrying the last observation forward treats that earlier value as the value for the later assessment. If a participant’s outcome would have changed after the last observed measurement, the imputed value may differ from the unobserved outcome. The direction and size of any resulting effect cannot be determined without information about the missingness pattern and appropriate sensitivity analyses.

The trial status is terminated, but the reason is not reported in the registry record. It is also not reported whether the termination affected planned enrollment, follow-up, or analysis decisions. These omissions limit assessment of potential reporting and missing-data concerns, but they are not evidence by themselves that the analyses are biased. They identify information needed to judge the robustness of the reported results.

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: angina pectoris (1.4%), sick sinus syndrome (1.4%), liver disorder (1.4%), shock hypoglycaemic (1.4%), breast cancer in situ (1.4%).

The registry lists serious adverse events for 4 of 72 participants at risk in the lacosamide group and 2 of 76 participants at risk in the placebo group. These are group-level counts as recorded in the safety results. They are not the same as a comparison of every type of adverse event, and the counts alone do not describe timing, duration, severity beyond the serious classification, or whether an event was judged related to trial medication.

The record also lists other adverse events affecting 16 of 72 participants at risk in the lacosamide group and 13 of 76 participants at risk in the placebo group. The registry’s top serious-event terms include angina pectoris, sick sinus syndrome, liver disorder, shock hypoglycaemic, breast cancer in situ, and intervertebral disc protrusion, with the listed percentages ranging from 1.3% to 1.4%. The record does not assign these listed terms to a specific study group in the information, so they should not be attributed to one group.

Deaths are not reported in the registry record. Safety counts should be read as descriptive trial findings, not as a complete assessment of risk or a causal comparison. The available results do not include enough detail to determine whether the groups differed in the types or timing of events, or how the study team assessed relatedness.

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

The results describe average changes in a patient-reported pain measure over the study’s 8 week maintenance period. The posted group means were negative in both arms, indicating that WOMAC pain scores decreased from baseline on average. The key statistical question is whether the average change differed between randomized groups. The recalculated unadjusted estimate was 3.64, and the sponsor-reported ANCOVA estimate was 2.36; both corresponding 95% confidence intervals include no difference.

These data do not precisely determine the direction or size of the between-group contrast. A confidence interval that includes no difference is not proof that the treatments are equivalent, just as a p-value above a conventional threshold does not prove there is no effect. Equivalence or noninferiority requires a specific design and prespecified margins, which are not reported in the registry record. The results also do not establish whether a difference of any particular size would be important to participants, because a minimal important difference is not reported.

The findings apply to the population and endpoint as recorded, including the Full Analysis Set definition and last-observation-carried-forward handling of missing WOMAC assessments. They do not provide a complete account of every enrolled participant’s experience. The registry records 194 enrolled participants, while the primary analysis groups include 71 and 74 participants; the record does not fully explain the flow from enrollment to analysis.

The trial’s terminated status is a registry fact, but the reason for termination is not reported in the registry record. It would be speculative to infer whether termination affected the results. Safety event counts provide descriptive information but do not by themselves establish causation or quantify every possible risk. Overall, the posted results support a cautious reading of average changes and substantial uncertainty about the group contrast, rather than a definitive conclusion about clinical benefit, lack of benefit, or equivalence.

18. Why This Trial Matters Statistically

This trial illustrates why within-group improvement and between-group evidence answer different questions. Both groups had negative average changes in WOMAC pain, but the trial’s comparative question concerns whether the average change differed between lacosamide and placebo. Looking only at the direction of change in one group would not answer that question. Randomized comparison and an estimate with uncertainty are needed to describe the contrast.

It also shows why a confidence interval adds useful information to a p-value. The primary intervals include zero and extend across values in both directions. That pattern signals that the estimated contrast is not precise enough to determine a clear direction, while still allowing a range of possible differences. A p-value alone would not show the range of effects compatible with the data or how uncertain the estimate is.

The distinction between the sponsor’s ANCOVA and the unadjusted recalculation is also statistically important. The registry’s analysis incorporates a model-based adjustment, while the recalculation uses the posted group summaries. They are different estimands or analytical procedures, and their results need not match exactly. Reporting both helps readers understand the relationship between the official analysis and a transparent summary-based comparison without confusing one for the other.

Finally, interpretation depends on more than the primary estimate. The Full Analysis Set definition, last-observation-carried-forward approach, multiple outcomes, and unreported details about missingness and multiplicity all shape how confidently the results can be generalized or treated as robust. Recognizing these limits is part of reading clinical trial statistics accurately, not a substitute for interpreting the posted findings.

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.

Several trial-specific details needed to assess the results are not reported in the registry record. The reason the study was terminated is not reported, nor is whether termination altered planned enrollment, follow-up, or analysis. The original sample-size justification and design assumptions are also not reported, so the planning illustrations should not be confused with the trial’s intended enrollment target.

The primary analysis population is defined, and missing WOMAC assessments were handled using last observation carried forward. However, the number and pattern of missing assessments, reasons for missingness, participant flow by group, and sensitivity analyses are not reported in the registry record. Enrollment was 194, while the primary analysis results list 71 participants assigned to lacosamide and 74 assigned to placebo. Without further flow details, the relationship between enrollment and analysis populations cannot be fully assessed.

The registry identifies ANCOVA for the sponsor’s reported analyses but does not report the covariates or detailed model specification. It therefore is not possible to reproduce the sponsor estimates using only the posted arm summaries. The registry also does not report a multiplicity strategy for the primary and secondary outcomes, or a minimal important difference for interpreting WOMAC changes.

The record lists safety counts and selected serious-event terms, but does not provide a complete narrative of timing, relatedness, or group attribution for each term in the available results. Deaths are not reported in the registry record. These are limits on interpretation of the posted information; they do not establish that any particular outcome was absent or that the study’s analysis was invalid.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Trial to Assess Efficacy and Safety of Lacosamide in Subjects With Osteoarthritis of the Knee — NCT00485472.
• Registry record last updated 2017-08-28; status last verified 2017-07.
• Results first posted 2009-09-22.
• 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 record describes a phase 2 randomized, double-blind, placebo-controlled, parallel-group trial of lacosamide 400mg/day for osteoarthritis of the knee. It reports 194 participants enrolled and a terminated study status. The reason for termination is not reported in the registry record.

The primary endpoint was change in WOMAC pain from baseline to the end of the 8 week maintenance period. The unadjusted recalculated mean difference was 3.64, with a 95% confidence interval from -3.861 to 11.14. The sponsor-reported ANCOVA estimate was 2.36, with a 95% confidence interval from -5.30 to 10.02. Both intervals include no between-group difference. The primary analysis used the stated Full Analysis Set and last-observation-carried-forward approach.

The posted results describe average changes and uncertainty, not a definitive conclusion about clinical importance, equivalence, or causation. Details about the original sample-size justification, multiplicity strategy, missingness patterns, and reason for termination are not reported in the registry record.