Effect of Tranexamic Acid on Postoperative Bleeding Following Sinus and Nasal Surgery: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Effect of Tranexamic Acid on Postoperative Bleeding Following Sinus and Nasal Surgery (NCT04754230), a randomized phase 4 study. The primary outcome is Bleeding VAS - POD1.

2. Clinical Question

This question focuses on a patient-reported symptom rather than a direct measure of blood loss. The registry describes additional outcomes concerning requests for postoperative bleeding evaluations and interventions, but detailed results for those outcomes are not presented in the posted primary comparison. The record does not establish whether the day-one score captures all aspects of postoperative bleeding; it reports one defined diary measure at one specified time point.

3. Trial Design

This was a Phase 4, randomized, triple-masked, parallel-group trial sponsored by Stanford University. The registry lists an enrollment of 40 participants: 19 in the normal saline group and 21 in the 1,000mg intravenous tranexamic acid group for the reported endpoint. The record gives a start date of 2021-06-17, a primary completion date of 2022-02-20, and a completed status.

In a parallel-group design, participants are assigned to one of the study groups and the groups are compared. Randomization is intended, in general, to make the groups comparable on average at the start of a trial; it does not guarantee that every characteristic will be balanced in a small sample. The registry identifies the trial as triple-masked but does not report which people or roles were masked, or how masking was maintained. Those details are not reported in the registry record.

The intervention was a 1,000mg intravenous tranexamic acid infusion 15 minutes before the end of surgery. The comparator group received normal saline and no additional study intervention beyond routine anesthetic care. Both groups were asked to record daily bleeding experiences until the first routine postoperative clinic visit, described as one week after surgery in the intervention-arm text. The general study description characterizes assessment as covering the first 7 days after surgery.

The primary outcome description names the patient-reported bleeding visual analog scale score on each day after surgery. The posted comparison analyzed the score for postoperative day 1, assessed within the first 24 hours following surgery. The registry also describes secondary outcomes involving postoperative evaluations and interventions; the listed secondary outcome is frequency of participant follow-up. The record does not report the trial's original sample-size assumptions, detailed allocation procedures, masking procedures, or a complete analysis plan.

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 Bleeding VAS - POD1, measured over Postoperative Day 1 (assessed within first 24 hours following surgery).

The primary endpoint reported for comparison is the patient-reported visual analog scale bleeding score on postoperative day 1, assessed within the first 24 hours after surgery. The scale ranges from 0, indicating no bleeding, to 10, indicating uncontrolled bleeding. It is a continuous score: each participant's response can take a value along the scale rather than being classified only as a yes-or-no event.

A diary measure can capture a participant's experience of bleeding in the period after surgery, including symptoms that may not lead to a clinical visit or intervention. In general, patient-reported outcomes are used when the experience being measured is directly perceived by the participant. A scale can make that experience recordable and comparable across participants, though it remains a subjective rating and may not correspond exactly to a clinician's assessment or a measure of blood loss.

The registry's broader primary-outcome description refers to scores on each day after surgery, and the study summary describes daily recording over the first 7 days. The numerical primary comparison posted in the record is specifically for day 1. The day-one result therefore describes that time point; it does not by itself describe the full pattern of diary scores across all days. Results for other days, and details of how daily measurements were handled in any broader repeated-measures analysis, are not reported in the registry record.

7. Results Posted in the Registry

• 1,000mg IV Tranexamic Acid: mean 4.82 versus 5.03 on control; difference -0.21 (95% CI -1.55 to 1.13), standardized effect d = -0.10; z-test p = 0.759.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is a continuous score, so the posted group summaries use means and standard deviations. A mean describes the average score within a group. A standard deviation describes how spread out participants' scores are around that group average. The registry reports a mean of 5.03 and standard deviation of 2.14 for normal saline, and a mean of 4.82 and standard deviation of 2.18 for tranexamic acid. The scores are on a scale from 0 to 10, with higher values representing more bleeding according to the scale description.

The comparison of interest is the difference between group means. The recalculated difference is defined as the tranexamic acid mean minus the normal saline mean, giving -0.21. In general, a negative difference under this ordering means that the observed mean is lower in the tranexamic acid group. This is an unadjusted comparison based on the posted summary statistics; it does not account for any covariates. An adjusted analysis is not reported in the registry record.

A confidence interval gives a range of values compatible with the observed data under the assumptions of the interval method. It conveys uncertainty around the estimated mean difference. The reported recalculated interval runs from -1.55 to 1.13. Because it includes zero, the data do not distinguish clearly between a zero difference and differences on either side of zero at the level represented by this interval. A confidence interval is not a guarantee that the true effect lies in the interval, nor does it indicate the probability that a particular value is true.

The registry reports a two-sided Z-test for the comparison and a p-value of 0.8. A two-sided test considers departures in either direction, not only a decrease or only an increase. In general, a p-value measures how unusual data at least as inconsistent with a specified no-difference model would be if that model and the test assumptions were correct. It is not the probability that the no-difference model is true, and it does not measure the size or clinical importance of a difference. The recalculated unadjusted p-value is 0.759; the small numerical distinction from the registry's p-value is consistent with reporting at different precision. The registry record does not describe any further adjustment or test details.

The recalculation uses the posted group means, standard deviations, and sample sizes to form an unadjusted comparison. This kind of calculation is useful as a check on the direction and scale of the result, but it is not a substitute for an analysis that might use participant-level data, account for prespecified covariates, or follow a fuller protocol-defined plan. The registry record does not report whether such analyses were conducted or whether the posted test was the only analysis used by the investigators.

General statistical context: a standard deviation describes variation among individual observations, whereas a standard error describes uncertainty in an estimated quantity such as a mean. A confidence interval for a difference reflects both group sizes and variability. Greater variability or fewer observations generally leads to less precise estimates, all else being equal. Here, the standard deviations are reported for the groups, but no participant-level score distribution is reported. The record also does not report checks of model assumptions, distributional summaries, or handling of unusual values.

General statistical context: repeated observations from the same participant are usually correlated; a person's score on one day may be related to that person's score on another day. Analyses that combine multiple days need to account for this dependence rather than treating every daily score as unrelated. The study description refers to daily diary scores, but the posted primary comparison is for postoperative day 1. Any method used to analyze repeated daily observations is not reported in the registry record.

General statistical context: over-dispersion occurs when observed variation is greater than a model expects. It matters because standard errors and confidence intervals can be too narrow if a model fails to represent that extra variation. The posted endpoint is a continuous score, and the registry provides group standard deviations; it does not report a count model or an over-dispersion assessment. That concept is therefore general context rather than a reported feature of this analysis.

The planning illustrations are separate from the trial's observed comparison. They use a two-sided significance level of 0.05, equal allocation, a normal approximation, and effects defined as stated fractions of the observed effect. They indicate how many participants per arm would be used under those assumptions for specified power targets. These are planning illustrations, not evidence about the power achieved in this completed trial. The trial's original design assumptions and any original sample-size justification are not reported in the registry record.

There are 9 outcome measures and 1 analysis listed in the record, while one secondary outcome is posted. Those counts do not establish how many analyses were planned or performed outside what is entered in the registry. The record does not explain whether this day-one comparison was prespecified as the sole primary time point, whether testing across multiple outcomes or time points was adjusted, or how any multiplicity was addressed. Those details are not reported in the registry record.

10. Confidence Intervals and Precision

The recalculated mean difference is -0.21 score points, with a confidence interval from -1.55 to 1.13. The interval is the main guide to precision: it shows that the estimate is compatible with a range of possible group differences, including values below and above zero. The observed point estimate alone gives a much narrower impression than the full interval.

In general, a confidence interval combines the estimated difference with its sampling uncertainty. A narrower interval indicates greater precision, while a wider interval indicates more uncertainty about the size and direction of the difference. The interval crosses zero and includes both a lower mean score for tranexamic acid and a higher mean score for tranexamic acid under the stated subtraction order. It therefore does not support a precise directional conclusion from the day-one score comparison.

The group sizes for this endpoint are 19 and 21, and the within-group standard deviations are 2.14 and 2.18. These summaries help describe why an estimate can be uncertain: individual scores vary, and the comparison is based on a modest number of participants. No claim about a clinically important threshold can be made from the record because a threshold for interpreting the scale difference is not reported in the registry record.

The interval concerns the mean difference for the reported endpoint, not the range of individual participants' scores and not the difference for every day in the diary period. It also does not account for uncertainty from unreported analysis choices or missing-data procedures. The registry's own test reports p=0.8, while the unadjusted recalculation reports p=0.759; both are consistent with the interval's inclusion of zero. The appropriate reading is limited precision around the average day-one difference, rather than proof of equality.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm for this continuous endpoint, not total events. They are illustrations based on the observed effect, with rows describing planning for 100%, 75%, or 50% of that observed effect. The columns for 80% and 90% power describe the number of participants per arm used in a plan intended to have those chances of detecting the specified effect under the stated assumptions, if the assumptions hold.

The listed 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 the stated fraction of the observed effect. For example, planning for the full observed effect requires fewer participants per arm than planning for a smaller fraction; planning for 75% or 50% of the observed effect requires larger numbers. The general reason is that smaller differences are harder to distinguish from random variation, so more information is needed to detect them with the same target power.

For each assumed effect, the 90% power column calls for more participants per arm than the 80% power column. In general, a higher power target means designing for a greater chance of detecting the specified effect under the model assumptions, which requires more information. These columns are planning targets, not descriptions of what happened in the trial. They are not observed power.

The trial's own original design assumptions, including its sample-size justification, are not reported in the registry record. The planning illustration uses an effect estimated from the trial's posted results and should not be read as a reconstruction of the investigators' original plan. It is also not evidence that the observed estimate is the true effect; the estimate itself has uncertainty.

12. 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 = -0.210; pooled standard deviation σ = 2.161.
2. n = 2 × (1.96 + 0.842)² × 2.161² / -0.210² = 1,662.5, rounded up to 1,663 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 <- -0.21                      # observed difference in means
sigma <- 2.16114492073555                     # 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(4754230)
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 = 1,663 (80% power), 2,226 (90% power)
 75% of observed effect: n per arm = 2,956 (80% power), 3,957 (90% power)
 50% of observed effect: n per arm = 6,651 (80% power), 8,903 (90% power)
power.t.test: 1663.5 
Simulated power at n = 1,663 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.

13. Analyses Reported by the Sponsor

The registry's own analysis is identified as a two-sided Z-test and reports p=0.8. A separate recalculation from the posted group means, standard deviations, and group sizes gives an unadjusted mean difference of -0.21, a confidence interval from -1.55 to 1.13, and p=0.759. The two p-values are close, and the registry's reported value is rounded to one decimal place.

The recalculation is a simple, unadjusted comparison derived from summary statistics. It helps make the direction and uncertainty of the mean difference explicit, but it does not replace the sponsor's analysis or any analysis based on participant-level data. The record does not give the sponsor's estimated difference or confidence interval, only the reported test method and p-value. It also does not report whether the sponsor conducted additional adjusted or sensitivity analyses.

No discrepancy is flagged between the posted result and the recalculation. The sponsor's reported test and the recalculated result are therefore read as broadly consistent in their statistical interpretation: neither indicates clear evidence of a difference in the day-one mean score. This does not establish that the groups are equivalent, and the recalculated interval retains uncertainty in both directions.

14. Multiplicity, Missing Data and Analysis Populations

The primary outcome description refers to bleeding scores on each day after surgery, and the study summary describes diary entries over the first 7 days. The posted primary comparison is for postoperative day 1. When multiple time points or outcomes are examined, the chance of at least one apparently unusual result can increase if each is tested separately. In general, multiplicity procedures can address that issue, but the appropriate approach depends on which outcomes and comparisons were planned.

The registry lists 9 outcome measures, 1 analysis, and one posted secondary outcome, identified as frequency of participant follow-up. These entries do not explain the full set of analyses conducted or the planned hierarchy of endpoints. Whether testing across days or across outcomes was adjusted, and whether day 1 was selected in advance as the principal time point, are not reported in the registry record. No adjustment should be assumed from the listed analysis count alone.

Missing-data handling can also affect interpretation. The record gives endpoint group sizes of 19 and 21, but does not explain whether all enrolled participants contributed a day-one score, whether any scores were missing, how missing diary entries were treated, or whether any imputation was used. The enrollment total is 40, but the registry does not provide a participant flow account or an explicit analysis-population definition. Those details are not reported in the registry record.

The registry record does not state whether the analysis followed an intention-to-treat, per-protocol, or other population definition. It does not report exclusions, protocol deviations, or the treatment of participants who did not complete the diary. These points matter because an analysis of everyone as randomized and an analysis restricted to participants with available outcomes can answer different questions if data are missing or participants depart from the assigned intervention.

Accordingly, the numerical comparison is interpretable as the posted day-one group summary and test, but the record does not provide enough detail to assess multiplicity control, missing-data assumptions, or the analysis population. These omissions do not prove that the analyses were inadequate; they limit what can be evaluated from the registry record.

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.

The registry reports 0 serious adverse events in the normal saline group among 19 participants at risk and 0 in the tranexamic acid group among 21 participants at risk. It also reports 0 other adverse events in each group, with the same group counts at risk, and 0 deaths in both groups. No serious adverse event terms are listed.

These figures describe events recorded in the registry for the reported groups. Zero reported events in a group means that none were recorded in that category in this trial; it does not establish that the risk is zero or rule out uncommon events. The number of participants is limited, so the figures provide limited information about events that might occur infrequently. The registry does not give further definitions, event-collection procedures, or timing details for these adverse-event summaries; those details are not reported in the registry record.

The adverse-event counts are distinct from the bleeding-score endpoint. They should not be used to infer that no postoperative bleeding occurred: the primary endpoint records patient-reported bleeding scores, while the adverse-event table gives counts of serious and other adverse events. The registry also describes postoperative bleeding evaluations and interventions as secondary outcomes, but those outcome results are not included in these safety counts.

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

The posted result describes average patient-reported bleeding scores on postoperative day 1 in two randomized groups. The observed mean was 5.03 in the normal saline group and 4.82 in the tranexamic acid group. The recalculated mean difference, tranexamic acid minus normal saline, was -0.21, with a confidence interval from -1.55 to 1.13. The registry's own two-sided test reports p=0.8.

These data do not show a clear statistical distinction between the group means for this endpoint and time point. They also do not demonstrate that the groups are equivalent, or establish that no difference exists. The confidence interval spans values on either side of zero, so the estimate is not precise enough to make a firm claim about the direction or size of the underlying mean difference. A result that does not meet a conventional threshold for statistical evidence is not, by itself, evidence that an effect is exactly absent.

The finding applies to the day-one bleeding score, not automatically to every day in the diary period, the number of clinical evaluations, the use of interventions, or other postoperative outcomes. Although daily recording over the first 7 days is described, results for other days are not included in the posted primary comparison. Results for the separately described secondary outcomes are also not presented in that comparison.

The registry does not report a threshold for what would count as an important difference on the 0-to-10 scale. Statistical uncertainty can therefore be described, but the record does not support a definitive judgment about the practical importance of the estimated difference. The reported sample sizes, group variability, and interval are important context for interpreting the estimate.

More broadly, the trial result is evidence about the groups and endpoint as recorded in this trial. It does not settle all questions about postoperative bleeding, nor does it supply information about unreported outcomes or analysis details. The appropriate conclusion is narrow: the posted day-one scores were similar in their observed averages, while uncertainty remains about the size and direction of the underlying difference.

17. Why This Trial Matters Statistically

This trial illustrates why an estimated difference should be read alongside its uncertainty. The observed means are close, but the confidence interval extends in both directions from zero. The point estimate alone could invite an overly definite reading; the interval shows that the data are compatible with a range of possible mean differences.

It also highlights the distinction between a patient-reported score and other measures of postoperative bleeding. A daily visual analog scale records participants' impressions on a defined range. Requests for clinical evaluation, hemostatic interventions, or return to the operating room are different outcomes and cannot be inferred from the mean score. The registry describes some of those outcomes, but their detailed results are not included in the posted primary comparison.

The trial is small in terms of its enrolled group, and the result is correspondingly best understood as an estimate with limited precision rather than a definitive test of equivalence. The planning illustration makes a related statistical point: under its assumptions, detecting smaller effects requires more participants per arm. That illustration is not a statement about the trial's original design or its observed power.

Finally, the registry shows why transparency about time points, missing data, analysis populations, and multiplicity matters. The posted result can be interpreted for day 1, but other analysis details are not reported in the registry record. Such information helps readers understand whether a result represents a prespecified analysis and how much confidence to place in comparisons across multiple measures.

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 comparison is limited to the postoperative day-one score, even though the study description refers to daily entries over the first 7 days. The registry record does not report numerical results for the other diary days, so the pattern or persistence of scores over time cannot be assessed from this comparison.

The endpoint is a participant-reported rating from 0 to 10. It captures the participant's impression of bleeding, but it is not itself a direct measurement of blood volume or a record of clinical intervention. The record does not report how participants interpreted the scale, whether diary completion was monitored, or whether scores were collected in a standardized way beyond the description of a daily diary.

The endpoint groups contain 19 and 21 participants, and the interval around the mean difference is broad enough to include differences in both directions. The record does not report a scale threshold for a clinically important difference. Consequently, neither the statistical precision nor the practical importance of the observed difference can be settled from the posted result alone.

The registry does not report participant flow, missing day-one scores, the analysis population, handling of missing data, allocation concealment, or detailed masking procedures. It also does not report the trial's original sample-size rationale, analysis protocol, multiplicity strategy, or results for the other described outcomes. These absences limit assessment of design and analysis details; they should not be interpreted as proof that the procedures were not performed.

The trial enrolled people undergoing sinus or nasal surgery and lists several related conditions. The registry record does not give enough detail to assess whether the enrolled participants represent all people undergoing such procedures or how results might vary across types of surgery. The findings should therefore be kept within the population, endpoint, and time point actually described.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Effect of Tranexamic Acid on Postoperative Bleeding Following Sinus and Nasal Surgery — NCT04754230.
• Registry record last updated 2023-04-05; status last verified 2023-03.
• Results first posted 2023-04-05.
• 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 Phase 4, randomized, triple-masked, parallel-group trial sponsored by Stanford University, with 40 participants enrolled. It compares a 1,000mg intravenous tranexamic acid infusion given 15 minutes before the completion of surgery with normal saline.

The posted primary comparison is patient-reported bleeding on postoperative day 1, measured on a scale from 0, no bleeding, to 10, uncontrolled bleeding. Mean scores were 5.03 among 19 participants receiving normal saline and 4.82 among 21 receiving tranexamic acid. The recalculated unadjusted mean difference was -0.21, with a confidence interval from -1.55 to 1.13; the registry reports p=0.8 for a two-sided Z-test.

The registry describes daily diary entries over the first 7 days and additional postoperative outcomes, but detailed results beyond the day-one comparison are not reported in the registry record. It reports 0 serious adverse events, 0 other adverse events, and 0 deaths in both groups.