Safety Study of XP12B in Women With Menorrhagia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety Study of XP12B in Women With Menorrhagia (NCT00113568), a non-randomized phase 3 study. The primary outcome is Number of Subjects With at Least One Adverse Event During the Study.

2. Clinical Question

3. Trial Design

This was a phase 3, multicenter study of tranexamic acid tablets (XP12B) in women with heavy menstrual bleeding associated with menorrhagia. The registry lists a non-randomized allocation, no masking, and a single-group model. The study was completed, with a recorded start of 2005-06 and primary completion of 2009-05. Enrollment was 784.

The single-group structure is central to interpreting the evidence. Participants received XP12B, and the registry record does not describe a randomized or concurrent comparator group. The safety figures therefore characterize events recorded among participants in the XP12B group; they do not estimate a difference between treatments. Other factors, such as participants’ underlying conditions or events that would have occurred without study treatment, cannot be separated from treatment-related effects by a within-group count alone.

The primary outcome was the number of participants with at least one adverse event during the study, with a timeframe of up to 27 menstrual cycles. The registry names the intent-to-treat population for this endpoint. It also reports safety figures for 723 participants at risk. The record does not explain how that safety group relates to the enrollment count or provide participant flow details that would clarify inclusion in the reported safety counts.

The registry lists nine outcome measures and no statistical analyses. It does not report a statistical analysis plan, methods for handling missing observations, a sample-size justification, or an explanation of the relationship between the primary endpoint and the separately listed serious and other adverse-event counts. Those omissions limit what can be reconstructed about how the study was intended to summarize safety.

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: intent to treat population

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 Subjects With at Least One Adverse Event During the Study, measured over Up to 27 menstrual cycles.

The primary endpoint was the number of participants with at least one adverse event during the study, assessed over a timeframe of up to 27 menstrual cycles. It is a participant-count endpoint: each participant is classified according to whether at least one qualifying event was recorded. The endpoint definition is broad. It includes clinical signs, symptoms, disease, and laboratory or physiological observations, and does not require the event to be judged causally related to the study drug.

Counting participants with any adverse event is a common way to describe the breadth of reported safety experience. It answers how many participants had at least one event under the study’s definition, rather than how many events occurred in total, how long events lasted, or how severe they were. A participant with several events may still contribute only once to this particular participant-level outcome.

The registry identifies the intent-to-treat population for the primary endpoint, but the primary endpoint result itself is not reported in the registry record. The separate safety entry gives serious and other adverse-event counts for 723 participants. These figures do not establish the total number with at least one adverse event: the record does not state whether participants appear in both categories, and it does not provide a combined count for the primary endpoint. Nor does the broad endpoint definition imply that every recorded event was caused by XP12B.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation starts with the design. This study is listed as non-randomized, unmasked, and single-group. Those features determine what the reported statistics can answer. A count within the XP12B group can describe events recorded among participants in that group. It cannot, on its own, distinguish events associated with treatment from events related to the underlying condition, other circumstances, or the background occurrence of illness. A concurrent comparator and a suitable design would be needed for a direct comparative estimate; neither is described in this record.

What a participant-count endpoint means

The primary endpoint is a count of participants who experienced at least one adverse event, rather than a count of all individual events. This distinction matters because a participant may experience multiple events, but a participant-level endpoint treats that person as having met the outcome once the qualifying condition is met. Such a measure gives a broad account of how many people had an event; it does not summarize the total event burden, the number of recurrent events, or the timing of events.

The endpoint definition includes events regardless of causal relationship to study drug. That makes it a broad safety-collection measure, not a count restricted to events judged treatment-related. It is also important that the registry’s serious and other adverse-event categories are reported separately. The record does not describe whether these categories are mutually exclusive at the participant level. Adding them would risk double-counting, so the reported values should remain separate.

What a confidence interval would convey

In general, a confidence interval expresses the precision of an estimated quantity by giving a range of values compatible with the data under the assumptions of the statistical method. A narrow interval indicates greater precision than a wide interval, but an interval does not correct bias from design limitations, missing data, or poor measurement. No confidence interval for the primary endpoint or the posted safety counts is reported in the registry record. The figures therefore do not provide a registry-reported measure of statistical precision.

Counts and denominators

A participant count is easiest to interpret when its denominator and population are clear. The serious and other adverse-event entries each list 723 participants at risk. The registry also records enrollment of 784 and names the intent-to-treat population for the primary endpoint. It does not explain the relationship between these populations or why the at-risk count differs from enrollment. Without participant flow or a detailed analysis-population description, the reason for that difference is not reported in the registry record.

Denominators also matter for percentages. The serious-event terms are accompanied by reported percentages, but the record does not provide additional methodological detail about how those percentages were calculated. The percentages can be quoted as posted, but further assumptions about their denominator or their precision should not be added. The registry does not report confidence intervals for these term-specific percentages.

Why over-dispersion can matter generally

For event-count outcomes, a simple statistical model may assume that the variability in counts follows a specified relationship to the average count. In real data, event counts can vary more than that model expects, a situation called over-dispersion. When over-dispersion is present, a method that assumes less variability can produce uncertainty estimates that are too small. This is a general statistical concern for event counts; the registry record does not report an over-dispersion assessment or a model for recurrent events. The primary endpoint is described as a participant count, and no statistical model is reported.

Multiplicity and analysis choices

Multiplicity refers to the interpretive problem that can arise when several outcomes or statistical tests are considered. The registry lists nine outcome measures and no statistical analyses. It does not report which outcomes were designated for formal testing, whether any multiplicity procedure was planned, or whether analyses were adjusted. The number of listed outcomes alone does not establish that formal tests were conducted. Consequently, no claim about statistical significance across outcomes can be reconstructed from the registry record.

Planning calculations are not study results

The record describes a sample-size planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It states that the effect to detect is a fraction of the observed effect. This is a hypothetical planning framework, not a description of the study’s actual single-group design. The record does not report a sample-size justification for the trial itself, and no numerical planning output is available in the registry record. Such illustrations are not observed power and do not change the limits of the posted single-group safety data.

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("Tranexamic Acid Tablets (XP12B)")
n      <- c(723)
events <- c(678)
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  Tranexamic Acid Tablets (XP12B)  723  678  93.8  91.8  95.4  91.8  95.3  91.8  95.3

11. Multiplicity, Missing Data and Analysis Populations

The registry lists nine outcome measures but reports no statistical analyses. It does not state which outcomes were included in a formal testing strategy, whether there was a prespecified hierarchy among outcomes, or whether any adjustment for multiple comparisons was planned or performed. The number of registered outcomes is not evidence that each was tested, and no multiplicity-adjusted or unadjusted statistical result is reported.

Missing-data methods are also not reported in the registry record. There is no description of how participants with incomplete follow-up were handled, how missing outcome information was treated, or whether any sensitivity analyses were undertaken. The primary endpoint is identified with the intent-to-treat population, but the record does not give operational details for that population or explain how it was used in the endpoint calculation.

Enrollment was 784, while the safety entry gives 723 participants at risk. The registry record does not explain this difference, so the available information does not establish whether it reflects follow-up availability, analysis eligibility, or another reason. No such explanation should be inferred.

The record also does not report a sample-size justification for the trial, interim analyses, or a statistical analysis plan. It describes a planning illustration using assumptions for a hypothetical two-arm comparison, although the recorded design is single-group and non-randomized. That illustration is not evidence of the study’s actual analysis plan, observed power, or treatment effect. Overall, the posted information does not support reconstruction of multiplicity control, missing-data handling, or the complete analysis population.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: migraine (0.6%), menorrhagia (0.6%), uterine leiomyoma (0.4%), cellulitis (0.3%), post procedural complication (0.3%).

The safety entry lists 28 participants affected by serious adverse events among 723 participants at risk in the XP12B group. It separately lists 678 participants affected by other adverse events among the same at-risk count. These are distinct reported categories and should not be added: the registry record does not say whether a participant could be represented in both. Neither figure is the reported primary endpoint result, which is not reported in the registry record.

The serious adverse-event terms are accompanied by these registry percentages: Migraine, 0.6%; Menorrhagia, 0.6%; Uterine Leiomyoma, 0.4%; Cellulitis, 0.3%; Post procedural complication, 0.3%; and Partial seizures with secondary generalization, 0.3%. The record does not give further detail about the calculation or uncertainty for these term-specific percentages. They are descriptive entries, not comparisons between treatment groups.

The primary endpoint definition includes adverse events regardless of causal relationship to the study drug. The serious-event figures therefore should not be read as proof that XP12B caused the reported events. The deaths field is null; deaths are not reported in the registry record, which is not the same as a reported count of zero.

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

The registry record describes safety observations among participants who received XP12B in a non-randomized, single-group study. It provides counts for participants affected by serious and other adverse events, along with selected serious-event terms and their reported percentages. Those data characterize the events recorded in the study group; they do not establish a treatment effect.

The primary endpoint was the number of participants with at least one adverse event during the study, but its result is not reported in the registry record. The separate serious and other adverse-event counts cannot be used to reconstruct that endpoint, because the record does not clarify overlap between categories or provide a combined participant count. The record also does not explain why the safety entry lists 723 participants at risk while enrollment is 784.

Without randomization or a comparator, the reported counts cannot distinguish effects of treatment from other explanations. The event definition includes observations regardless of causal relationship, so an event recorded during the study is not necessarily an event caused by XP12B. The reported percentages for serious-event terms do not provide a comparison with another group, and no confidence intervals or statistical analyses are reported.

Accordingly, the record supports a limited descriptive reading: it reports specified adverse-event counts and terms in the XP12B group. It does not provide a comparative estimate, a causal conclusion, or a complete statistical account of the primary outcome. Missing-data handling, multiplicity methods, and the rationale for the trial’s enrollment are not reported in the registry record.

14. Why This Trial Matters Statistically

This study is statistically instructive because its central outcome is a safety measure, but its design is single-group and non-randomized. That combination highlights the difference between describing events and estimating a treatment effect. Counts can document what was recorded among participants receiving XP12B, while causal interpretation requires a comparison that this registry record does not describe.

The endpoint also illustrates why the unit of analysis matters. The primary outcome is the number of participants with at least one adverse event, not the total number of events. A participant-level count gives a broad measure of how many people experienced an event, while leaving event frequency, recurrence, and timing unanswered. The record’s separate serious and other adverse-event counts do not yield the primary outcome unless the relationship between categories is known; it is not reported.

Another important issue is the distinction between a registered endpoint and a posted result. The registry identifies the primary endpoint and its population, but does not report the endpoint value or statistical analyses. This limits reproducibility and prevents readers from assessing precision or the analysis choices used to obtain the result.

Finally, the enrollment count and the safety risk set are not the same, and the record does not explain why. That gap shows how participant flow and analysis-population definitions are essential for interpreting even straightforward counts. The study is therefore a useful example of the statistical limits that arise when design, endpoint reporting, and analysis details are incomplete.

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 principal limitation for interpreting this study is its single-group, non-randomized design. No like-for-like comparator is described, so the posted counts cannot estimate a difference between XP12B and another treatment or no treatment. The lack of masking is also recorded, but the registry does not describe how outcome assessment was conducted or whether this feature affected reporting.

The primary endpoint result is not reported in the registry record, even though the endpoint and its timeframe are specified. The separately listed serious and other adverse-event figures do not replace that missing result, and the record does not explain whether participants could contribute to both categories. The counts are therefore not sufficient to reconstruct the total number of participants with at least one adverse event.

Enrollment was 784, whereas the safety entry lists 723 participants at risk. The registry record does not explain the difference or provide participant flow information. It also does not report missing-data methods, details of the intent-to-treat population, confidence intervals, a statistical analysis plan, or formal statistical analyses. Although nine outcome measures are listed, the record does not say how multiplicity was handled.

The serious-event terms and percentages are descriptive entries, with no comparative estimates or reported uncertainty. Deaths are not reported in the registry record. A sample-size planning illustration is described for a hypothetical two-arm comparison, but the trial’s own sample-size justification is not reported. These limitations restrict interpretation to the posted within-group safety counts and prevent stronger conclusions about comparative risk, causality, precision, or the completeness of outcome reporting.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Safety Study of XP12B in Women With Menorrhagia — NCT00113568.
• Registry record last updated 2010-06-15; status last verified 2010-06.
• Results first posted 2010-01-20.
• 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.

19. Record Summary

The registry record describes a completed phase 3, multicenter, non-randomized, unmasked, single-group study of tranexamic acid tablets (XP12B) in women with heavy menstrual bleeding associated with menorrhagia. Enrollment was 784. The primary endpoint was the number of participants with at least one adverse event during the study, assessed over up to 27 menstrual cycles in the intent-to-treat population.

The primary endpoint result and statistical analyses are not reported in the registry record. The XP12B safety entry lists 723 participants at risk, 28 affected by serious adverse events, and 678 affected by other adverse events. The record does not explain the difference between enrollment and the safety risk set or whether participants overlap between the adverse-event categories.

Because no comparator is described, the safety counts are descriptive rather than comparative. The registry record does not report a sample-size justification, missing-data methods, multiplicity procedures, confidence intervals, or deaths.