An Open-Label Extension Study Of Lamotrigine In Subjects With Bipolar Disorder: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for An Open-Label Extension Study Of Lamotrigine In Subjects With Bipolar Disorder (NCT00360126), a non-randomized phase 4 study. The primary outcome is Number of Participants With Serious Adverse Events (SAEs).

2. Clinical Question

The study asked about serious adverse events during open-label lamotrigine treatment in participants with bipolar disorder who had completed a precursor study. The official title describes the eligible participants as being in remission following a manic or hypomanic index episode, or a depressive index episode. The registry does not report a concurrent control group or a randomized comparison, so the result addresses what was recorded among participants in this extension, not a comparative treatment effect.

This is a safety-description question, not an efficacy question. The primary outcome records the number of participants with serious adverse events; it does not summarize symptom change, remission, or a benefit relative to another treatment. The registry record does not report a comparative hypothesis or a statistical estimate of treatment effect.

3. Trial Design

This was a phase 4, open-label extension study of lamotrigine in participants with bipolar disorder. Its allocation is recorded as non-randomized, its masking as none, and its model as single group. These features describe a study in which participants received the study intervention without a randomized control arm. They also mean that the record does not support a like-for-like comparison between treatment groups.

The registry describes the study as providing 12 months of post-study access to open-label lamotrigine for participants of the SCA101469 study. That precursor is described as a prospective, multicentre study in adults diagnosed with bipolar disorder, with 36 weeks of lamotrigine treatment. Those precursor-study details give context for who could enter the extension; they are not outcomes of the extension itself. The official title identifies participants in remission following a manic or hypomanic index episode or a depressive index episode.

The extension is listed as starting in 2005-10, with primary completion in 2007-02, and its status is completed. Enrollment is recorded as 11. The intervention listed is lamotrigine. The sponsor is GlaxoSmithKline.

The registry record does not report the method used to select participants, the details of their dosing, adherence, treatment changes, or the duration each individual remained under observation. The primary outcome timeframe is stated as up to 54 weeks; this is the timeframe attached to the outcome, rather than a report of identical follow-up for every participant. Because the study had one group and no masking, the safety count is best read as a descriptive observation from this extension, not as a controlled estimate of the effect of lamotrigine.

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: Participants who had completed 32 weeks treatment period in study SCA101469 were enrolled in this extension study.

Overall Study

Analysis population for the primary outcome, as defined in the registry: All subject population consisted of all participants enrolled into the study and received study drug.

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 Number of Participants With Serious Adverse Events (SAEs), measured over Up to 54 weeks.

The primary endpoint is the number of participants with serious adverse events (SAEs), reported in participants. An adverse event is defined in the registry as an untoward medical occurrence after study treatment began, whether or not it was considered related to the study drug. The SAE definition includes an occurrence that results in death, is life-threatening, requires hospitalization or prolongation of hospitalization, results in disability or incapacity, or involves a congenital anomaly or birth defect. The record says that only SAEs were recorded and reported in this extension.

This endpoint counts participants who experienced an SAE, rather than providing a total count of every SAE occurrence. A participant with more than one such occurrence would still be represented in a participant count as someone with an SAE. The registry does not give event-level details or a list of the serious-event terms for this group.

General: serious-event outcomes are used to describe severe or consequential safety events that meet specified criteria. They do not capture every symptom or unfavorable occurrence. In this study, the endpoint therefore describes the recorded serious events within the stated follow-up, not the full range of possible adverse experiences. It also does not establish whether any event was caused by treatment: the adverse-event definition explicitly includes events whether or not considered related to study drug.

The reported timeframe is up to 54 weeks. The primary outcome population is described as participants enrolled who received study drug. The registry record does not report additional details about how outcome information was collected or adjudicated.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The statistical information available for this outcome is a participant count: the number of participants recorded with an SAE. The group summary reports 11 participants at risk and 0 participants affected. The outcome is binary at the participant level: a participant either was or was not recorded as having at least one SAE during the stated timeframe. The registry does not provide participant-level records, event dates, or a breakdown of multiple events.

What does a participant count describe?

General: a count tells how many observations met a defined condition. Here, the condition is having an SAE as defined by the registry. A count is not the same as a rate per unit of time, because the record does not provide person-time or individual follow-up durations. It is also not the total number of serious events: the primary outcome is explicitly the number of participants with SAEs. The registry does not report how many separate SAE episodes, if any, occurred for an individual participant.

The reported count is tied to the stated outcome population, described as all participants enrolled who received study drug. The at-risk group is reported as 11. The registry record does not provide a participant flow account or information about withdrawals, incomplete follow-up, or missing outcome assessments. Consequently, the available summary alone cannot show whether every enrolled participant contributed complete follow-up for the full timeframe.

Why does the study design matter?

This study is recorded as non-randomized, unmasked, and single group. There is no randomized control group against which the SAE count can be compared. General: random allocation can help balance known and unknown participant characteristics between groups, while a concurrent comparator can support a direct comparison over the same study period. Without those design features, a single-group count is descriptive and can be affected by participant selection, observation time, and other factors. This does not invalidate the count; it limits the questions the count can answer.

Open-label means the study is listed as having no masking. The record does not explain how knowledge of treatment was handled in event reporting or assessment. Because the outcome concerns serious events, the registry’s criteria define which occurrences qualify, but the record does not report an adjudication procedure or independent review. It also does not give an event list for this group.

What can statistical uncertainty add?

General: an estimate based on a sample is subject to uncertainty because other samples could yield different observations. A confidence interval is one way to communicate a range of values compatible with the data under a specified statistical method. For a binary outcome, an interval may be used to describe uncertainty around an event probability. The registry record does not report such an interval or name a method for estimating one. No interval or probability should be attributed to the sponsor from the posted count.

A zero observed count needs careful interpretation. General: it means the event was not observed in the recorded group; it does not prove that the event cannot occur or that its underlying probability is zero. The limited group size and lack of a comparator are important context. The registry does not provide a statistical test or a comparative estimate, and no test can be reconstructed from this group summary alone as a sponsor analysis.

What analyses are documented?

The record lists one outcome measure and zero analyses. It does not report an analysis plan, a planned hypothesis test, a model, an adjustment strategy, or interim analyses. The absence of a reported analysis is not evidence that a particular method was or was not used outside the registry record. It means the posted information does not document one. Likewise, the record does not report a sample-size justification or a power calculation for the trial. Planning calculations, when presented for other contexts, are illustrations rather than observed power; no trial-specific planning result is available in this record.

General: over-dispersion is a concern for count models when observed variability exceeds what a chosen model assumes. It is relevant when analyzing event counts or rates with more variation than the model allows. This outcome, however, is reported as the number of participants with an event, not as a repeated-event count or person-time rate, and the record contains no fitted count model. Over-dispersion should not be invoked as an explanation of this result.

Overall, the available method is a descriptive participant count within a single treatment group. It directly answers how many participants were recorded with an SAE under the registry definition. It does not, by itself, estimate a causal effect, compare treatments, quantify uncertainty with a reported interval, or describe the timing and recurrence of events.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Lamotrigine")
n      <- c(11)
events <- c(0)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Lamotrigine  11  0  0.0  0.0  28.5  -0.0  25.9  0.2  26.5

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one outcome measure and zero analyses. It does not report a set of multiple primary endpoints, secondary analyses, or a multiplicity-adjustment procedure. This does not establish that no multiplicity considerations existed outside the registry record; the analysis plan is not reported in the registry record. Since no inferential analyses are listed, there are no reported adjusted or unadjusted statistical tests to interpret for this SAE outcome.

Missing-data information is also limited. The primary-outcome population is defined as all participants enrolled who received study drug, and the group summary reports 11 at risk. The registry record does not report the number of participants with incomplete follow-up, the handling of missing safety information, reasons for withdrawal, or whether any observation was imputed. It is therefore not possible to assess from the registry summary whether missingness could affect the reported count.

The outcome timeframe is up to 54 weeks. The record does not describe individual follow-up durations or establish that every participant was observed for the same length of time. A participant count without those details should not be interpreted as a time-adjusted rate.

The record does not report a separate safety-analysis population beyond the stated primary-outcome population, nor does it describe exclusions from that population. The absence of those details limits assessment of how the analysis set was formed. The reported result remains interpretable as the count posted for the group at risk, with these documentation gaps kept in view.

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.

The serious-adverse-event result is 0 participants affected among 11 at risk in the lamotrigine group, for a timeframe of up to 54 weeks. This is a participant-level count: it indicates that no participant was recorded as having at least one SAE under the registry definition. It is not a count of all adverse events, because the record says that only SAEs were recorded and reported in this extension.

The registry definition includes events after study treatment began, whether or not they were considered related to study drug. It covers events resulting in death, life-threatening events, hospitalization or prolongation of hospitalization, disability or incapacity, and congenital anomaly or birth defect. The record does not list serious-event terms for the group. It also does not report event-level details or whether any non-serious adverse events occurred.

General: a zero observed count means no event meeting the reporting definition was recorded in the group; it does not mean the underlying possibility of an event is zero. The group size and the absence of a comparator limit what can be inferred about risk or relative safety. The registry record does not report an uncertainty interval or a comparison with another group. The count should therefore be read as a description of the recorded experience, not as proof that SAEs cannot occur or that treatment caused no harm.

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

The result means that the registry reports no participants with serious adverse events in the lamotrigine group: 0 among 11 at risk during follow-up of up to 54 weeks. It is a straightforward description of the primary outcome as recorded. The endpoint applies the registry’s SAE definition, and the record says only SAEs were recorded and reported in this extension.

It does not mean that no adverse events of any kind occurred. The record does not provide a count of non-serious adverse events. It does not mean that serious events are impossible, or that the risk is zero; an unobserved event in this group is not proof that an event would never occur in a larger group or under other circumstances. No confidence interval or other estimate of uncertainty is reported.

The result also does not show that lamotrigine is safer than another treatment or than no treatment. The design is non-randomized and single group, with no comparator and no masking. Thus there is no treatment contrast from which to estimate a relative difference. The SAE definition includes events regardless of whether they were considered related to the study drug, and no event-level details are reported to support judgments about causation.

Nor does this safety count answer whether lamotrigine changed bipolar symptoms, maintained remission, or improved other clinical outcomes. The primary outcome is serious adverse events, not efficacy. The registry does not report analyses of symptom outcomes in this extension.

The finding applies to the participants who entered this extension and the reported timeframe. The registry describes them as participants from a precursor study, and defines the outcome population as enrolled participants who received study drug. It does not provide enough information to assess how closely this group represents a broader population, how follow-up varied across participants, or how missing safety information was handled. The result is useful as a record of what was observed in this group, but its scope should remain limited to that description.

14. Why This Trial Matters Statistically

This trial is statistically informative chiefly because it illustrates the distinction between a safety count and a comparative treatment effect. The record documents 0 participants with serious adverse events among 11 at risk, but it has a single group and no randomized comparator. That count communicates what was recorded in the extension; it cannot answer whether the outcome would have differed under another treatment or no treatment.

Small, single-group safety extensions can contribute descriptive information about events recorded during continued access to treatment. Their interpretation depends on the outcome definition, the group observed, and the period covered. Here, the SAE definition is explicit, and the timeframe is up to 54 weeks. The record also states that only SAEs were recorded and reported. This makes it important not to treat the reported count as a complete accounting of all adverse experiences.

The design and reporting also show why a zero count needs context. General: observing no event is not equivalent to establishing that the event is impossible or that the underlying risk is zero. The group size is limited, and the registry does not report an uncertainty interval, individual follow-up, or handling of missing safety information. Those gaps restrict the precision and scope of interpretation.

Finally, the record lists one outcome measure and no analyses. It does not document a statistical comparison or an inferential model. The result is therefore best understood as a descriptive safety observation rather than a test of a hypothesis. Keeping that distinction clear prevents an observed count from being mistaken for evidence of comparative safety, treatment causality, or efficacy.

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.

The main limitation is the single-group, non-randomized design. With no comparator, the SAE count cannot estimate a difference between lamotrigine and another treatment or a control condition. The open-label design means there was no masking, and the registry record does not describe how events were assessed or whether they underwent independent review.

The group summary is limited in size, with 11 participants at risk. The posted result is 0 participants with an SAE, but the record does not report a confidence interval or another measure of statistical uncertainty. A zero observed count should not be interpreted as proof of zero underlying risk.

The primary outcome captures serious adverse events only. The registry says only SAEs were recorded and reported in this extension, so the result does not summarize non-serious adverse events or all possible unfavorable experiences. No serious-event terms are listed for the group, and the record does not provide event-level details, timing, recurrence, or assessments of relatedness to study drug.

The outcome timeframe is up to 54 weeks, but individual follow-up durations are not reported. The record also does not describe withdrawals, missing safety information, or how missing observations were handled. It is not possible to determine from the registry summary whether everyone contributed the same amount of observation time or whether incomplete follow-up affected ascertainment.

The registry lists one outcome measure and no analyses. It does not report an analysis plan, sample-size justification, interim analyses, or statistical uncertainty estimates. These omissions limit assessment of planned methods and reporting choices. Finally, the extension’s participants came from a precursor study; the registry record does not establish how representative they were of people with bipolar disorder more broadly.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: An Open-Label Extension Study Of Lamotrigine In Subjects With Bipolar Disorder — NCT00360126.
• Registry record last updated 2017-03-30; status last verified 2017-02.
• Results first posted 2017-03-30.
• 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

NCT00360126 is a completed phase 4, open-label, non-randomized, single-group extension study of lamotrigine in participants with bipolar disorder. The registry lists GlaxoSmithKline as sponsor, enrollment of 11, a start date of 2005-10, and primary completion in 2007-02. The study was intended to provide 12 months of post-study open-label lamotrigine access to participants in the SCA101469 precursor study.

The primary outcome is the number of participants with serious adverse events, with a timeframe of up to 54 weeks. The registry reports 0 participants with an SAE among 11 at risk. The outcome population is defined as all participants enrolled who received study drug. Only SAEs were recorded and reported in the extension.

The registry lists one outcome measure and no analyses. It does not report a comparator, inferential results, confidence intervals, a sample-size justification, or details of missing safety data. The result is therefore a descriptive count for this group and timeframe, not a comparative estimate of treatment effect.