Tranexamic Acid Dosing for Total Joint Arthroplasty: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Tranexamic Acid Dosing for Total Joint Arthroplasty (NCT02584725), a randomized phase 4 study. The primary outcome is Change in Hemoglobin From Baseline to the First Post-operative Day (POD#1).

2. Clinical Question

3. Trial Design

This was a Phase 4 randomized, parallel-group trial with triple masking. The registry record lists Columbia University as the sponsor and an enrollment of 84. The study status is completed. The recorded start was 2014-12 and the primary completion was 2015-06.

Participants were assigned to one of three tranexamic acid dose groups. In each group, the intravenous dose was administered twice, once 20 minutes before incision and once when closure began. The registry record does not describe the randomization sequence, allocation concealment, or which roles were masked; the meaning and implementation of triple masking are therefore not reported in the registry record.

The posted primary endpoint is the mean change in hemoglobin from baseline to the first postoperative day, with a timeframe of 1 day and units of g/dl. Each dose group has a reported sample size of 28 for this outcome. The registry record lists 12 outcome measures, including secondary measures concerning hemoglobin at other time points, transfusion, blood loss, and postoperative activity. Eleven secondary outcomes have posted results, while no analysis records are listed.

The record does not report the original sample-size justification, the planned primary statistical model, the intended analysis population, or details about how missing outcome measurements were handled. It also does not state whether interim analyses were planned. Those features should not be inferred from the posted outcome summaries or from the comparisons accompanying them.

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

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 in Hemoglobin From Baseline to the First Post-operative Day (POD#1), measured over 1 day.

The primary endpoint is the change in hemoglobin from baseline to the first postoperative day, reported as a mean in g/dl with a standard deviation. Hemoglobin is a blood measure, and its change over the perioperative period can serve as an indicator related to blood loss. The trial’s stated purpose was to assess whether increasing tranexamic acid doses limited blood loss, using the change in hemoglobin as the primary measure.

A change score compares a participant’s postoperative hemoglobin with their own preoperative baseline. Group means then describe the average recorded change within each dose group. The registry record reports means of 2.15 for the 5 mg/kg/dose group, 2.06 for the 10 mg/kg/dose group, and 2.11 for the 15 mg/kg/dose group. It does not specify the sign convention for the change score in the endpoint description, so interpretation should remain tied to the recorded measure rather than assume a particular subtraction order.

Hemoglobin change is an indirect measure: it is not the same as directly measuring total blood loss. The registry record also lists estimated intraoperative blood loss, suction-canister volume, transfusion, and later hemoglobin measures among the secondary outcomes. These outcomes can add context, but the primary endpoint remains the prespecified focus described in the record. The endpoint description does not report adjustment for other participant or surgical characteristics.

7. Results Posted in the Registry

• 10 mg/kg/Dose Tranexamic Acid: mean 2.06 versus 2.15 on control; difference -0.09 (95% CI -0.62 to 0.44), standardized effect d = -0.09; z-test p = 0.741.
• 15 mg/kg/Dose Tranexamic Acid: mean 2.11 versus 2.15 on control; difference -0.04 (95% CI -0.61 to 0.53), standardized effect d = -0.04; z-test p = 0.890.

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 in Hemoglobin From Baseline to POD#0

• 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:
  • 10 mg/kg/Dose Tranexamic Acid: mean 1.30 versus 1.34 on control; difference -0.04 (95% CI -0.55 to 0.47), standardized effect d = -0.04; z-test p = 0.879.
  • 15 mg/kg/Dose Tranexamic Acid: mean 1.16 versus 1.34 on control; difference -0.18 (95% CI -0.74 to 0.38), standardized effect d = -0.17; z-test p = 0.530.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 10 mg/kg/Dose Tranexamic Acid 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 15 mg/kg/Dose Tranexamic Acid and the control. The interval gives the range of effects that remain compatible with the data.

Change in Hemoglobin From Baseline to POD#2

• 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:
  • 10 mg/kg/Dose Tranexamic Acid: mean 2.59 versus 2.50 on control; difference 0.09 (95% CI -0.42 to 0.60), standardized effect d = 0.09; z-test p = 0.729.
  • 15 mg/kg/Dose Tranexamic Acid: mean 2.28 versus 2.50 on control; difference -0.22 (95% CI -0.82 to 0.38), standardized effect d = -0.19; z-test p = 0.475.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 10 mg/kg/Dose Tranexamic Acid 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 15 mg/kg/Dose Tranexamic Acid and the control. The interval gives the range of effects that remain compatible with the data.

Number of Participants Requiring Blood Transfusion From the Intra-operative Period Into the End of POD#2

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • 10 mg/kg/Dose Tranexamic Acid: 0.0% (0/28) versus 3.6% (1/28) on control; risk difference -3.6 percentage points (95% CI -10.4 to 3.3); unadjusted two-proportion z-test p = 0.313.
  • 15 mg/kg/Dose Tranexamic Acid: 0.0% (0/28) versus 3.6% (1/28) on control; risk difference -3.6 percentage points (95% CI -10.4 to 3.3); unadjusted two-proportion z-test p = 0.313.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 10 mg/kg/Dose Tranexamic Acid 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 15 mg/kg/Dose Tranexamic Acid and the control. The interval gives the range of effects that remain compatible with the data.

Across the posted secondary outcomes, the broad pattern is that the recorded hemoglobin changes and the small number of transfusion events do not provide a clear, consistent separation of the higher-dose groups from the reference group. The secondary measures cover different aspects of postoperative blood loss and recovery, so they do not all represent the same underlying quantity. Hemoglobin changes are laboratory measures, transfusion is an event count, and mobility measures describe postoperative activity.

This overall pattern is compatible with the primary endpoint summaries, in which the observed means are close across dose groups and the comparison intervals include zero. Secondary outcomes can help assess whether the primary pattern is accompanied by differences in related measures, but they should not be treated as independent confirmation when they are measured in the same participants and may be correlated. Nor can a lack of clear separation in these summaries establish that the dose groups have identical outcomes.

The record lists 11 secondary outcomes with posted results and includes no reported analyses. The secondary comparisons shown are unadjusted. When several outcomes and comparisons are examined, individual unadjusted p values can be less persuasive as confirmatory evidence because they do not reflect the full set of tests. The registry record does not report a multiplicity strategy or identify which secondary outcomes, if any, were intended as confirmatory.

Accordingly, the secondary results are best used as descriptive context for the primary result. Their differing measurement scales and time points make it important not to combine them into a single conclusion or infer a coherent dose-response pattern from isolated values. The overall secondary picture does not resolve the uncertainty in the primary comparison, and the record does not report an integrated analysis across these outcomes.

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

• Change in Hemoglobin From Baseline to POD#0
• Change in Hemoglobin From Baseline to POD#2
• Number of Participants Requiring Blood Transfusion From the Intra-operative Period Into the End of POD#2
• Total Estimated Intra-operative Blood Loss
• Volume of Blood in the Surgical Suction Canister at the End of Surgery
• Count of Participants Able to Sit on Post-Operative Day 1 (POD1) and Post-Operative Day 2 (POD2)
• Count of Participants Able to Stand on POD1 and POD2
• Count of Participants Able to Walk on POD1 and POD2

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: each participant has a measured hemoglobin change, and the group summaries use a mean and standard deviation. A mean describes the arithmetic average of the recorded values. The standard deviation describes how spread out individual values are around their group mean. It is not the uncertainty in the mean itself; uncertainty in a comparison depends on factors including group size and the variability of the measurements.

What does a mean difference represent?

Each posted primary comparison subtracts the reference-group mean from the mean in a higher-dose group. The reported mean difference is -0.09 g/dl for 10 mg/kg/dose versus 5 mg/kg/dose, and -0.04 g/dl for 15 mg/kg/dose versus 5 mg/kg/dose. A negative estimate means the higher-dose group’s reported mean is lower on the recorded change scale. Because the endpoint description does not define the subtraction direction used to calculate each participant’s change, these estimates should not be translated into a direction of blood-loss benefit without further information.

The comparisons include confidence intervals and unadjusted p values. A confidence interval gives a range of values compatible with the data and the method used to calculate it. It helps show the precision of an estimate: a narrow interval indicates less uncertainty than a wide interval, considered in context. An interval that includes zero means that no mean difference is among the values excluded by that interval. It does not show that the groups are identical.

How should the p values be read?

A p value describes how incompatible the observed data are with a specified null model, under the assumptions of the statistical procedure. It is not the probability that the null hypothesis is true, and it does not measure the clinical importance of a difference. The primary comparisons have unadjusted p values of 0.741 and 0.89. The registry record does not identify the exact test or model used for these p values, so a particular testing procedure should not be attributed to the trial.

General statistical context: unadjusted p values do not account for testing multiple outcomes or comparisons. When many hypotheses are examined, the chance of at least one apparently unusual result can increase. Whether and how to adjust depends on the prespecified analysis strategy and the role of each outcome. A multiplicity plan is not reported in the registry record.

What do the secondary comparisons add?

The record also posts mean comparisons for hemoglobin at other time points and risk-difference comparisons for transfusion. A risk difference expresses the difference between the observed proportions in two groups; unlike a relative measure, it is an absolute difference on the risk scale. The transfusion comparison is based on one event in the reference group and none in either higher-dose group. With sparse events, an estimate can be particularly uncertain, and its interval should be considered alongside the counts rather than read as a definitive dose effect.

The secondary outcome summaries include continuous and count outcomes. The registry record does not list reported analyses for those measures. No adjusted model, covariate set, or method for handling repeated outcomes is reported in the registry record. General statistical context: repeated observations on the same participants are not independent in the way measurements from different participants may be. An analysis of multiple time points may need to account for that dependence, but the record does not say whether such an analysis was undertaken.

What do the planning illustrations represent?

The sample-size illustrations use the observed comparison effect as a planning input, with rows for planning for 100%, 75%, and 50% of the observed effect. Their stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The 80% and 90% power columns describe planning targets: under the listed assumptions, they indicate the participants per arm needed for the chosen target probability of detecting the specified effect if that effect were the true one. Smaller target effects require more participants to detect with the same power target. These are prospective planning illustrations, not descriptions of the trial’s original design rationale.

General statistical context: power calculations depend on assumptions about the effect to detect, variability, significance threshold, allocation, and analysis method. Changing an assumption can change the resulting planning estimate. The original sample-size assumptions and justification for this trial are not reported in the registry record. The illustrations should not be treated as evidence about the trial’s chance of detecting an effect after the data were collected.

11. Confidence Intervals and Precision

The primary mean-difference estimates are close to zero, but their confidence intervals are not narrowly concentrated around zero. For 10 mg/kg/dose compared with 5 mg/kg/dose, the estimate is -0.09 g/dl and the 95% confidence interval is -0.623 to 0.443. For 15 mg/kg/dose compared with 5 mg/kg/dose, the estimate is -0.04 g/dl and the 95% confidence interval is -0.609 to 0.529. Each interval spans values below and above zero, so the data do not pin down the direction of a possible mean difference.

Precision is not the same as whether an estimate is statistically significant. It concerns how tightly the available data constrain plausible values. The group standard deviations range from 0.81 to 1.19 g/dl, and each group has 28 participants for the primary endpoint. These summaries provide context for the width of the intervals, but they do not make the intervals disappear: uncertainty remains around both comparisons.

It would be inaccurate to interpret the intervals as proving no difference. They also should not be read as evidence that every value inside them is equally likely or as a range that will contain the true value with certainty. A confidence interval is a statistical procedure with a long-run coverage interpretation under its assumptions. The registry record does not report the interval method or model details, limiting assessment of those assumptions.

For the transfusion comparisons, the risk-difference interval is -0.104 to 0.033 for each higher-dose group versus the reference group. Those estimates arise from sparse event counts, making the uncertainty especially important to emphasize. Across outcomes, the posted intervals offer a more informative account of precision than a simple focus on whether a p value crosses a threshold.

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 figures are planning illustrations, not the enrollment target or a reconstruction of the trial’s original design. For the continuous comparisons and the binary transfusion comparisons, the listed sample sizes are participants per arm. The record’s general convention says that time-to-event tables would instead show total events, but the outcomes are not time-to-event outcomes.

The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect, with rows for planning for 100%, 75%, and 50% of that effect. The 80% power column describes the participants per arm for a design intended to have an 80% probability of detecting the specified effect under those assumptions, if that effect is true. The 90% power column uses a higher probability target, again under the stated assumptions.

Smaller effects are harder to distinguish from random variation, so the planning figures increase when the effect used is reduced. The displayed figures should be understood in relation to the observed estimates and their uncertainty, rather than as a recommended enrollment number. The trial’s original sample-size justification and assumptions are not reported in the registry record. These figures are not observed power.

A curve, where shown, is a visual representation of the planning relationship rather than additional trial evidence. It does not change the assumptions behind the calculations. The planning values should not be interpreted as the number of participants actually enrolled; the registry record reports total enrollment of 84 and 28 participants in each primary-outcome group.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.090; pooled standard deviation σ = 1.018.
2. n = 2 × (1.96 + 0.842)² × 1.018² / -0.090² = 2,008.0, rounded up to 2,008 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -0.0899999999999999                      # observed difference in means
sigma <- 1.01788997440784                     # 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(2584725)
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 = 2,008 (80% power), 2,689 (90% power)
 75% of observed effect: n per arm = 3,570 (80% power), 4,779 (90% power)
 50% of observed effect: n per arm = 8,032 (80% power), 10,753 (90% power)
power.t.test: 2008.9 
Simulated power at n = 2,008 per arm: 0.796 (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 lists one primary endpoint and multiple secondary outcomes, with comparisons of each higher dose against the 5 mg/kg/dose group for the posted continuous and transfusion results. It does not report a multiplicity adjustment, a hierarchy among secondary outcomes, or a rule for interpreting results across the family of comparisons. The p values accompanying comparisons are unadjusted. This matters because interpreting each result as if it were the only test can overstate the strength of evidence when many outcomes or contrasts are examined.

The original statistical analysis plan is not reported in the registry record. The record does not state whether the primary comparison was prespecified in the form shown, whether any covariate adjustment was planned, or which statistical tests were intended. Interim analyses and stopping rules are also not reported in the registry record. The absence of these details does not establish that such procedures were absent; it means they cannot be evaluated from the registry record.

Outcome denominators are reported as 28 in each group for the primary endpoint and for the secondary measures described in the posted results. However, the registry record does not describe participant flow for each outcome, distinguish missing measurements from other reasons for non-inclusion, or state how missing data were handled. It also does not specify whether the analyses followed an intention-to-treat, per-protocol, or other analysis population. Matching reported group sizes do not, on their own, answer those questions.

These omissions limit assessment of whether the posted comparisons follow the original plan and whether missingness or multiple testing could affect their interpretation. They also restrict evaluation of model assumptions and analysis robustness. The numerical results remain interpretable as posted summaries and comparisons, but the record does not give enough methodological detail to treat them as a complete account of the trial’s statistical analysis.

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 non-serious adverse event terms

The registry record reports serious adverse events among 28 participants in each dose group: 0 in the 5 mg/kg/dose group, 0 in the 10 mg/kg/dose group, and 0 in the 15 mg/kg/dose group. Deaths are also reported as 0 in each group. For other, non-serious adverse events, the counts are 0 in the 5 mg/kg/dose group, 0 in the 10 mg/kg/dose group, and 1 in the 15 mg/kg/dose group.

These are event counts for the groups and outcome categories recorded, not proof that no other harms occurred. The registry record does not list serious adverse-event terms, and it does not provide details about the single other adverse event, its type, timing, or relationship to treatment. It also does not report additional safety analyses or longer-term follow-up in the posted information.

Because each group contains 28 participants, the absence of recorded serious events in these groups should be interpreted as a limited observation from this trial, not as evidence that serious events cannot occur. Safety counts are descriptive and do not establish comparative safety with precision. The registry record’s adverse-event categories and counts should be read as reported, with the limits of the recorded detail in mind.

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

The posted results show that the mean hemoglobin changes in the three dose groups were similar in their observed values, and that the estimated mean differences for each higher dose versus 5 mg/kg/dose were small relative to the uncertainty expressed by their confidence intervals. The intervals include zero and extend in both directions. This is a description of what the recorded data estimate, not a finding that the doses are equivalent.

The primary endpoint is an indirect indicator related to blood loss, not a direct measure of total blood loss. Other outcomes in the registry address transfusion, estimated intraoperative blood loss, suction-canister volume, hemoglobin at other time points, and postoperative activity. The presence of these secondary measures does not convert the primary result into a direct assessment of every aspect of blood loss or recovery. The registry record does not report an integrated analysis across all measures.

The comparisons concern higher doses against the 5 mg/kg/dose reference. They do not establish how the doses compare with no tranexamic acid or with another treatment, because no such group is listed. Nor do the results identify a best dose: the record does not report a formal dose-response analysis, an equivalence margin, or a decision rule for selecting a dose.

Confidence intervals and p values describe statistical uncertainty under the analysis used; they do not determine whether any difference is clinically important. The registry record does not state a threshold for a clinically meaningful hemoglobin difference. The small enrollment and uncertainty around estimates mean that a lack of strong evidence for a difference should not be translated into proof of no effect.

In short, the posted primary summaries do not show a clear separation in mean hemoglobin change across the three groups, while leaving uncertainty about the size and direction of possible differences. The secondary summaries add descriptive context but do not remove that uncertainty. These findings are specific to the recorded trial population, outcomes, doses, and follow-up described in the registry record.

17. Why This Trial Matters Statistically

This trial is statistically informative because it illustrates the distinction between a small observed difference and a precisely estimated difference. The primary mean differences are close to zero, but the confidence intervals remain broad enough to include values on either side of zero. A point estimate alone would hide that uncertainty; a p value alone would not communicate its range.

The design compares three dose levels of the same intervention, with equal reported group sizes for the primary outcome. This makes the dose contrasts straightforward to describe, while also making clear that they are not comparisons against no treatment. The comparator structure determines what the results can answer: the posted estimates address higher doses relative to 5 mg/kg/dose.

The record also highlights how sparse event outcomes differ from continuous measures. The transfusion counts are small, so the associated risk-difference estimates have substantial uncertainty. Seeing a zero in a group does not imply that the underlying risk is zero. Counts, estimates, and intervals each contribute different information.

Finally, the planning illustrations demonstrate why sample-size calculations depend on the effect size selected. Planning for a smaller effect calls for more participants under the stated assumptions. Such illustrations can clarify design trade-offs, but they do not substitute for the original design rationale, which is not reported in the registry record. The broader statistical lesson is to separate descriptive summaries, uncertainty, planning assumptions, and confirmatory claims rather than treating them as interchangeable.

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.

The primary outcome groups each contain 28 participants, and the primary comparison intervals are wide enough to include differences in both directions. This limits precision and makes it difficult to distinguish a small true difference from sampling variation. The posted results should not be used to claim equivalence, particularly because no equivalence margin or equivalence analysis is reported in the registry record.

The endpoint is a hemoglobin change, which is an indirect measure related to blood loss. The record does not specify the sign convention for the change, explain how the measure relates to direct blood-loss estimation, or report an analysis connecting it to other outcomes. The registry record lists hip and knee arthroplasty but does not report subgroup results by procedure type, so it is not possible to assess whether results differ between those populations.

The comparison structure has no untreated or placebo group. It can address contrasts among the three tranexamic acid doses, but cannot establish a comparison with no tranexamic acid. The posted comparisons also use the lowest dose as reference; a direct higher-dose-versus-higher-dose comparison is not listed.

Important design and analysis details are not reported in the registry record, including the original sample-size justification, the statistical analysis plan, the intended analysis population, missing-data handling, and multiplicity strategy. The record does not report participant characteristics or detailed outcome distributions. These gaps limit assessment of generalizability, analytic assumptions, and robustness. The reported adverse-event information is also brief, with no serious-event terms listed and limited detail about the single other adverse event.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Tranexamic Acid Dosing for Total Joint Arthroplasty — NCT02584725.
• Registry record last updated 2020-10-30; status last verified 2020-10.
• Results first posted 2020-10-30.
• 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.

22. Record Summary

NCT02584725 is a completed Phase 4 randomized, triple-masked, parallel-group trial sponsored by Columbia University. It enrolled 84 participants and compared intravenous tranexamic acid at 5 mg/kg/dose, 10 mg/kg/dose, and 15 mg/kg/dose, administered twice around surgery for total hip or knee arthroplasty.

The primary outcome was mean change in hemoglobin from baseline to the first postoperative day. Each group had 28 participants in the posted primary results. The reported comparisons of the higher doses against 5 mg/kg/dose have estimates close to zero, confidence intervals that include zero, and unadjusted p values of 0.741 and 0.89. The registry record also lists secondary outcome results and adverse-event counts. It does not report the original sample-size justification, statistical analysis plan, missing-data methods, or multiplicity approach.