Oral Versus Intravenous Tranexamic Acid: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Oral Versus Intravenous Tranexamic Acid (NCT04089865), a randomized phase 4 study. The primary outcome is Calculated Blood Loss.

2. Clinical Question

The central question is whether calculated blood loss differs between oral and intravenous tranexamic acid in patients undergoing total hip arthroplasty (THA) or total knee arthroplasty (TKA). The registry summary also asks whether transfusions differ between dosing groups. The participants were described as undergoing surgery under neuraxial anesthesia.

The intended comparison is clinically straightforward, but the posted results need careful reading: the four outcome groups separate treatment route and operation type, while the recalculated inferential contrasts use the oral THA group as the reference. Those contrasts therefore do not directly estimate oral versus intravenous treatment within THA or within TKA. The arm means can be read descriptively by procedure, but the reported confidence intervals and p-values should not be interpreted as direct treatment-route tests within each operation.

Transfusion during the hospital stay is named as a secondary outcome, but its results are not reported in the registry record. The stated goal concerns differences between routes; the statistical contrasts currently posted use the oral THA group as their reference, so they do not by themselves settle that within-procedure question.

3. Trial Design

The registry record describes a completed, randomized, parallel-group, phase 4 trial sponsored by Hospital for Special Surgery, New York. Enrollment is listed as 400. The record gives a start date of 2019-09-17 and a primary completion date of 2021-11-10. Masking is listed as none, so the trial is described as unmasked.

The planned allocation described in the registry summary divided participants by procedure as well as by treatment route: 100 THA patients and 100 TKA patients were to receive oral tranexamic acid, and 100 THA patients and 100 TKA patients were to receive intravenous tranexamic acid. Oral dosing was 1950 mg in the pre-operative area; intravenous dosing was 1 g upon transfer to the operating room. The record describes random assignment but does not report the method used to generate or conceal the allocation sequence.

For calculated blood loss, the posted group sizes are 89 for oral THA, 90 for intravenous THA, 90 for oral TKA, and 94 for intravenous TKA. The registry record does not explain why those outcome counts differ from the planned group sizes. These counts describe the participants included in the reported outcome summaries; they do not, on their own, identify which participants were excluded, why any outcome was unavailable, or what analysis population was intended.

The trial also lists transfusion during hospital stay, time to discharge from physical therapy, and length of stay as secondary outcomes. Results are posted for the latter two outcomes, but transfusion results are not reported in the registry record. The protocol, detailed eligibility criteria, allocation procedures, and original statistical plan are not reported in the registry record. The registry record also does not report whether there were interim analyses or what analysis population was specified.

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:

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.

Population: Oral Tranexamic Acid (TXA) - 9 subjects did not receive allocated intervention because withdrew from study after allocation/randomization IV Tranexamic Acid (TXA) - 4 subjects did not receive allocated intervention because withdrew from study after allocation/randomization

6. Primary Endpoint

The registry lists the primary outcome as Calculated Blood Loss, measured over post-operative day 0.

The primary endpoint is calculated blood loss (CBL), measured in mL and reported as a mean with standard deviation. The timeframe is post-operative day 0. The registry description says CBL was calculated from hematocrit before surgery and after surgery in the post-operative care unit, together with estimated blood volume. It gives the formula CBL = BV × (HctPre - HctPost), with BV = (k1 × H3) + (k2 × W) + k3. In that description, H is patient height in meters and W is patient weight in kilograms. The values of the constants k1, k2, and k3 are not reported in the registry record.

This is a derived endpoint rather than a direct collection of blood lost in a container or a direct visual estimate. It combines measurements taken at baseline and after surgery into a calculated value. The registry description says that, although the underlying measurements were taken at two time points, the calculated value is averaged across participants and reported as a group mean.

General statistical context: a continuous endpoint such as CBL can show both the average level in each group and the spread of individual values around that average. The mean describes the group average; the standard deviation describes variability among the observed participants. A group mean does not show the full distribution, and a calculated blood-loss measure depends on the formula and its inputs. The registry record does not report further validation or measurement properties for this endpoint.

7. Results Posted in the Registry

• Intravenous (IV) Tranexamic Acid (TXA) Total Hip Arthroplasty: mean 860.00 versus 842.00 on control; difference 18.00 (95% CI -75.94 to 111.94), standardized effect d = 0.06; z-test p = 0.707.
• Oral Tranexamic Acid (TXA) Total Knee Arthroplasty: mean 799.00 versus 842.00 on control; difference -43.00 (95% CI -139.98 to 53.98), standardized effect d = -0.13; z-test p = 0.385.
• Intravenous (IV) Tranexamic Acid (TXA) Total Knee Arthroplasty: mean 878.00 versus 842.00 on control; difference 36.00 (95% CI -61.94 to 133.94), standardized effect d = 0.11; z-test p = 0.471.

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.

Time to Discharge From Physical Therapy

• 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:
  • Intravenous (IV) Tranexamic Acid (TXA) Total Hip Arthroplasty: mean 1,914 versus 2,091 on control; difference -176.88 (95% CI -513.20 to 159.44), standardized effect d = -0.16; z-test p = 0.303.
  • Oral Tranexamic Acid (TXA) Total Knee Arthroplasty: mean 2,245 versus 2,091 on control; difference 153.22 (95% CI -220.91 to 527.35), standardized effect d = 0.12; z-test p = 0.422.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Intravenous (IV) Tranexamic Acid (TXA) Total Hip Arthroplasty and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Oral Tranexamic Acid (TXA) Total Knee Arthroplasty and the control. The interval gives the range of effects that remain compatible with the data.

Length of Stay

• 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:
  • Intravenous (IV) Tranexamic Acid (TXA) Total Hip Arthroplasty: mean 2,139 versus 2,552 on control; difference -413.29 (95% CI -793.38 to -33.20), standardized effect d = -0.30; z-test p = 0.033.
  • Oral Tranexamic Acid (TXA) Total Knee Arthroplasty: mean 2,693 versus 2,552 on control; difference 141.09 (95% CI -293.33 to 575.51), standardized effect d = 0.09; z-test p = 0.524.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Intravenous (IV) Tranexamic Acid (TXA) Total Hip Arthroplasty than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Oral Tranexamic Acid (TXA) Total Knee Arthroplasty and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcome summaries do not form a single consistent pattern across procedure groups. Time to discharge from physical therapy and length of stay have group means in both directions relative to the oral THA reference, and the recalculated estimates are not uniformly precise. The registry record also names transfusion during the hospital stay, but results for that outcome are not reported in the registry record.

The secondary findings do not resolve the primary question about calculated blood loss. They address different outcomes and timeframes, and they are also presented as unadjusted recalculations against oral THA rather than direct oral-versus-intravenous contrasts within each procedure. One posted length-of-stay contrast has a confidence interval that does not include zero, but it is a secondary, unadjusted comparison using the same reference group. It should not be treated as confirmatory evidence about the treatment-route question.

General statistical context: when several outcomes or contrasts are examined, the chance of observing at least one apparently notable result by chance can increase. A nominal p-value for one secondary comparison does not account for the full set of outcomes unless a multiplicity strategy is specified. The registry record does not report a multiplicity adjustment or a hierarchy of confirmatory and exploratory outcomes.

Secondary outcomes can add useful context, but their evidential weight depends on prespecification, completeness, appropriate comparisons, and control of multiplicity. The registry record does not report whether these outcomes were analyzed according to a prespecified plan. The posted summaries therefore support descriptive reading of outcome patterns, not a strong overall claim about treatment route or a substitute for the primary endpoint analysis.

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

• Transfusion During Hospital Stay
• Time to Discharge From Physical Therapy
• Length of Stay

9. Statistical Interpretation

10. Statistical Methods Explained

The registry record reports group means and standard deviations for the continuous primary endpoint. The recalculated mean differences and confidence intervals are unadjusted comparisons derived from the posted summary statistics. No sponsor-reported analysis is reported in the registry record. The distinction between a posted group summary, a recalculated contrast, and a planned analysis is important: they answer different questions and carry different evidential weight.

What does a mean difference describe?

A mean difference expresses how far one group mean is from a reference group mean, using the endpoint's original units. In the primary outcome, that unit is mL. A positive estimate means the mean for the named comparison group is higher than the reference mean; a negative estimate means it is lower. The direction only has meaning when the reference group and comparison group are clear.

For these recalculations, oral THA is the reference group. Thus the estimates compare each of the other three groups with oral THA. They are not the direct treatment-route contrasts within THA and TKA. In particular, the estimate for intravenous TKA versus oral THA changes both procedure and treatment route, so it cannot be read as the isolated route difference for TKA. General statistical context: randomization helps support causal comparisons when groups are compared as randomized and the analysis matches the randomization structure. It does not make a contrast between different procedure groups equivalent to a within-procedure treatment contrast.

What do the confidence intervals contribute?

A confidence interval gives a range of effect estimates compatible with the data and the statistical method used. It displays uncertainty around the estimate, rather than only a single point. A narrow interval indicates more precision than a wide interval, all else being equal. If an interval includes zero for a mean difference, the data are compatible with no difference as well as with positive or negative differences over the interval's range. The intervals posted for the primary recalculations include zero. The confidence level and exact interval procedure are not reported in the registry record.

General statistical context: confidence intervals are not a list of all possible true values, and they do not by themselves establish clinical importance. Their interpretation depends on the analysis assumptions and the contrast being estimated. An interval around the wrong contrast cannot answer the intended clinical question, even if the calculation itself is performed correctly.

What do the p-values say?

The primary recalculated contrasts have unadjusted p-values of 0.707, 0.385, and 0.471. These values relate to the contrasts against oral THA, not to direct oral-versus-intravenous comparisons within each operation. The word “unadjusted” means these values have not been adjusted for multiple comparisons. No multiplicity procedure is reported in the registry record.

General statistical context: a p-value is not the probability that the null hypothesis is true, nor is it a measure of the probability that a finding will reproduce. It is also not a measure of effect size. Estimates and intervals are needed to understand direction and plausible magnitude. A p-value should be interpreted in light of which comparison was tested, how many analyses were undertaken, and whether those analyses were prespecified.

Why does variability matter?

The standard deviations for CBL are 328.0 mL, 313.0 mL, 334.0 mL, and 348.0 mL across the four posted groups. These describe the observed spread around each mean. When individual outcomes vary substantially relative to a group contrast, the estimate can be imprecise unless the study has enough participants to distinguish the contrast from that variability.

General statistical context: over-dispersion means that observed variability is larger than a model assumes. If a method does not account for that extra variability, standard errors can be too small and intervals can be too narrow. The outcome is continuous, and the registry reports means and standard deviations; it does not report an over-dispersion assessment or a model-based variance adjustment. No assumption checks are reported in the registry record.

What is not established by these calculations?

The recalculated results are simple, unadjusted calculations from the posted group summaries. They are not a substitute for a prespecified analysis using participant-level data, and they do not supply adjustments for potential imbalances or other covariates. The registry record does not report the original statistical analysis plan, the method used for any sponsor analysis, or whether the sponsor performed a separate primary analysis. It also does not report a direct statistical contrast of oral versus intravenous treatment separately within THA and TKA.

General statistical context: the design and analysis should align with the scientific question. If the question concerns treatment route within procedure, the analysis should represent those within-procedure contrasts and account for the trial's allocation structure. The reported group means can help readers understand the observed data, but the current inferential contrasts are anchored to one arm across both procedure types. Therefore, the primary inferential output should be read as a set of reference-group comparisons, not as a definitive route comparison.

11. Confidence Intervals and Precision

The primary recalculated confidence intervals are broad relative to their point estimates. For intravenous THA compared with oral THA, the estimated mean difference is 18.0 mL and the interval runs from -75.94 to 111.9. For oral TKA compared with oral THA, the estimate is -43.0 mL and the interval runs from -140.0 to 53.98. For intravenous TKA compared with oral THA, the estimate is 36.0 mL and the interval runs from -61.94 to 133.9. Each interval includes zero and values on both sides of zero.

General statistical context: the point estimate is the single best estimate produced by a particular calculation, while its confidence interval communicates uncertainty around that estimate. An interval that includes both negative and positive values allows for outcomes in either direction relative to the reference group. That does not prove there is no effect; it indicates that the data, with this method and these group sizes, do not estimate the contrast precisely enough to rule out a range of possibilities.

The intervals also answer only the contrasts they were calculated for. Because oral THA is the reference group, these intervals do not quantify oral-versus-intravenous differences within THA or within TKA. Their width should not be used to claim that the treatment routes are equivalent. Equivalence or non-inferiority requires a specified margin and an analysis designed to evaluate that margin; such a margin and analysis are not reported in the registry record.

The registry record does not state the confidence level or interval method. The posted standard deviations indicate meaningful spread in observed CBL values, while the outcome group sizes range from 89 to 94. General statistical context: precision is influenced by variability, sample size, and the analysis method. A larger sample can often narrow an interval, but precision alone does not remedy a mismatch between the estimated contrast and the scientific question.

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 sample-size illustrations are planning calculations based on the observed effects, not the trial's original design justification. The registry record does not report the trial's own sample-size assumptions or justification. For these continuous outcomes, the figures are participants per arm, not total participants. The listed 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 to the stated fraction of the observed effect.

The 80% power column means the illustrated number of participants per arm for an 80% chance of detecting the specified effect under those planning assumptions, if that effect and the assumptions were correct. The 90% power column gives the corresponding planning number for a 90% chance. These are design illustrations, not guarantees about what a future study would find. The calculation uses the observed effect as its starting point, and the alternative rows plan for 75% or 50% of that observed effect.

Smaller effects are harder to distinguish from random variation, so the illustrations require more participants per arm as the targeted effect becomes smaller. This is not observed power: it does not describe the chance that the completed trial detected its actual effect, and it does not validate the original trial's design. The registry record does not report the original assumptions used to choose enrollment.

General statistical context: power is a design property calculated for a specified effect, significance level, allocation, and analysis. It is not a post hoc measure of whether a result is true. These illustrations should be read as hypothetical planning scenarios based on the recalculated effects, rather than as evidence about the validity of the trial's original enrollment target.

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 = 18.000; pooled standard deviation σ = 320.545.
2. n = 2 × (1.96 + 0.842)² × 320.545² / 18.000² = 4,978.2, rounded up to 4,979 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 <- 18                      # observed difference in means
sigma <- 320.545377416445                     # 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(4089865)
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 = 4,979 (80% power), 6,665 (90% power)
 75% of observed effect: n per arm = 8,851 (80% power), 11,848 (90% power)
 50% of observed effect: n per arm = 19,913 (80% power), 26,658 (90% power)
power.t.test: 4979.2 
Simulated power at n = 4,979 per arm: 0.797 (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. Multiplicity, Missing Data and Analysis Populations

The registry record names a primary outcome and several secondary outcomes, but it does not report a statistical plan for controlling multiplicity. The posted p-values are unadjusted recalculations. No family-wise error procedure, false-discovery procedure, testing hierarchy, or designation of which secondary comparisons were confirmatory is reported in the registry record.

General statistical context: multiplicity arises when several hypotheses are tested. Even when each test uses a conventional threshold, testing a collection of outcomes can raise the chance that at least one result appears statistically notable by chance. Adjustment procedures or a prespecified hierarchy can address this issue, but they change how results should be interpreted. Without a reported plan, individual secondary p-values should be treated cautiously, especially when considered alongside the several arm contrasts and outcomes.

The registry record does not report how missing outcome data were handled, how participants with unavailable measurements were treated, or whether any imputation was used. The primary endpoint group sizes are 89, 90, 90, and 94, while the secondary outcome group sizes vary by outcome and arm. Differences in reported denominators alone do not show why observations are absent or whether the missingness could affect the estimates. The record also does not report a missing-data sensitivity analysis.

The intended analysis population is not reported in the registry record. It is therefore not possible to determine from the record whether the posted summaries represent an intention-to-treat population, a per-protocol population, or another defined set. The record does not report interim analyses, stopping rules, allocation concealment, or a detailed statistical analysis plan. Those omissions limit assessment of whether the analyses and exclusions followed prespecified procedures.

These are reporting limitations, not proof that the procedures were absent. The registry record does not provide enough detail to establish what was done. The recalculated contrasts should consequently be understood as unadjusted analyses of posted summaries, rather than as a complete account of the trial's statistical methods.

15. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cva, cerebrovascular accident (1.1%).

The serious adverse-event counts are reported separately for the four treatment-and-procedure groups. There were zero serious events among 89 oral THA participants, one among 90 intravenous THA participants, zero among 90 oral TKA participants, and zero among 96 intravenous TKA participants. The record identifies the serious-event term as “CVA, cerebrovascular accident,” with a reported frequency of 1.1%. Deaths are reported as zero in every group.

These counts are sparse. General statistical context: when events are uncommon, a small number of observations can make group rates unstable, and simple counts do not establish whether an event was caused by treatment. The registry record does not provide a causal assessment, a detailed event narrative, or a comparison adjusted for other factors. The group at risk for serious adverse events in intravenous TKA is listed as 96, which differs from the primary endpoint group size; the registry record does not explain the difference.

Other adverse events are also listed separately, but the serious-event figures should not be read as a complete account of all possible harms. They describe the events recorded in the registry record and do not, by themselves, establish comparative safety.

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

The posted primary outcome results describe calculated blood loss in four groups formed by treatment route and operation type. The means are 842.0 mL for oral THA, 860.0 mL for intravenous THA, 799.0 mL for oral TKA, and 878.0 mL for intravenous TKA. The recalculated inferential contrasts compare each non-reference group with oral THA. Their confidence intervals include zero, and the associated unadjusted p-values do not provide evidence of a difference from that reference group under those calculations.

That is not the same as showing that oral and intravenous dosing have the same effect. The listed contrasts do not directly compare the two routes within THA or within TKA. The intervals also cover a range of possible differences, so they do not establish equivalence or rule out potentially meaningful effects. The registry record does not report a prespecified equivalence or non-inferiority margin.

General statistical context: an absence of compelling evidence for a difference is not evidence that the groups are identical. To support equivalence, the study needs a defined range of differences considered acceptably small and an analysis showing that the uncertainty lies within that range. A conventional test that fails to show a difference is not a substitute for such a design.

The trial's randomized design is relevant to the intended treatment comparison, but interpretation of the posted estimates depends on the actual contrasts used. The summaries do not report a sponsor-led primary analysis or a direct within-procedure treatment-route estimate. A conclusion about the intended comparison would require an analysis aligned with randomization and the question of oral versus intravenous treatment separately for THA and TKA, or a clearly specified combined analysis that accounts for procedure type.

The posted secondary outcomes may provide additional descriptive information, but they do not resolve the primary endpoint question. Transfusion results are not reported in the registry record, and the remaining secondary results are unadjusted and subject to the limitations. The adverse-event counts are sparse and are not a causal safety comparison.

Accordingly, the registry record supports a careful description of group means, recalculated reference-group contrasts, and reported event counts. It does not establish that one route is better, worse, equivalent, or safer. It also does not show that the original trial met a particular statistical objective, because the original design assumptions and sponsor analysis are not reported in the registry record.

17. Why This Trial Matters Statistically

This trial illustrates why the contrast being estimated matters as much as the numerical result. The clinical question concerns oral versus intravenous tranexamic acid among patients undergoing THA or TKA. The posted arm summaries distinguish both procedure and treatment route, but the recalculated comparisons use oral THA as a common reference. That reference structure means the estimates are not direct route comparisons within each procedure.

General statistical context: a randomized design supports fair comparison when the analysis preserves the randomized comparison. When groups differ in more than the treatment component of interest, an unadjusted contrast can mix treatment and procedure differences. This is not a flaw in the observed group means; it is a limitation on what those particular inferential contrasts can answer. Clear labeling of the reference group and the target contrast is essential to prevent an estimate from being interpreted as answering a different question.

The record also shows the distinction between descriptive summaries and confirmatory inference. Means and standard deviations help describe the observed outcome distributions, while confidence intervals convey uncertainty for a specified contrast. The primary recalculations have intervals that include zero, but that does not demonstrate equality. Nor does it establish that route effects are absent within either operation type.

Planning illustrations based on observed effects further show why sample-size interpretation needs care. Such calculations can help readers understand how assumed effect size affects planning, but they do not reveal the original design assumptions or the probability that the completed trial found a true effect. A registry record should make those original choices and analysis methods clear for readers to assess them.

Finally, secondary outcomes and rare safety events require context. Unadjusted findings across multiple outcomes are less secure as confirmatory evidence, and sparse event counts cannot support strong comparative conclusions. This record is a useful example of the need to connect the clinical question, trial allocation, analysis contrast, uncertainty, and reporting completeness before drawing statistical conclusions.

18. 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 limitations specific to this record affect interpretation. The primary outcome is calculated from hematocrit and estimated blood volume rather than reported as a direct blood-loss measurement. The formula is described, but the values of its constants are not reported in the registry record. The record also does not provide further information about endpoint validation or measurement reliability.

The primary recalculated contrasts use oral THA as the reference group. They do not provide direct oral-versus-intravenous contrasts within THA and TKA, which are the comparisons most closely aligned with the stated question. A participant-level analysis, its model, and any adjustment for procedure type are not reported in the registry record.

The observed primary outcome group sizes are 89, 90, 90, and 94, while the planned allocation described in the summary was 100 participants in each procedure-and-route group. The registry record does not explain these differences or report how missing outcome data were handled. Secondary outcome denominators also vary by outcome, and reasons for unavailable results are not reported.

The registry record does not report the original sample-size justification, analysis population, allocation concealment method, detailed statistical analysis plan, interim analyses, or multiplicity strategy. The listed transfusion outcome has no posted results. The record also does not report a direct sponsor analysis of the primary endpoint. These gaps limit assessment of prespecification, missingness, and the relationship between the planned analysis and the posted summaries.

Finally, the serious adverse-event counts are sparse, and the record does not provide enough detail to attribute events to treatment. These limitations do not prove that the underlying procedures were inadequate; they indicate that the registry record does not report enough information to assess them.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Oral Versus Intravenous Tranexamic Acid — NCT04089865.
• Registry record last updated 2024-12-27; status last verified 2024-12.
• Results first posted 2023-06-01.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

22. Record Summary

The registry record describes a completed, randomized, unmasked, parallel-group, phase 4 trial with enrollment listed as 400. It compares oral tranexamic acid, 1950 mg, with intravenous tranexamic acid, 1 g, in THA and TKA. The primary outcome is calculated blood loss in mL on post-operative day 0.

The posted group means are accompanied by recalculated, unadjusted contrasts against oral THA. Those contrasts are not direct oral-versus-intravenous comparisons within each procedure, and their confidence intervals include zero. The registry record does not report a sponsor-led primary analysis, the original sample-size justification, a multiplicity plan, or missing-data methods. Time to discharge from physical therapy and length of stay have posted results; transfusion is named but its results are not reported in the registry record.

Serious adverse events are uncommon in the posted groups, with one recorded serious event and zero deaths in all groups. The record supports descriptive interpretation but does not establish equivalence, a direct procedure-specific treatment-route effect, or a comparative safety conclusion.