Tourniquet on Total Knee Arthroplasty: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Tourniquet on Total Knee Arthroplasty (NCT04923724), a randomized na study. The primary outcome is Pain After TKA Measured by VAS Pain Survey on Focusmotion App.

2. Clinical Question

3. Trial Design

The registry describes a randomized, single-masked, parallel-group trial comparing tourniquet use during surgery with no tourniquet during surgery. The planned enrollment was 165, and the study status is completed. The recorded study dates are 2020-11-01 for the start and 2023-11-30 for primary completion. Washington University School of Medicine is listed as the sponsor. The phase is listed as not applicable.

The two groups represent distinct surgical strategies for total knee arthroplasty. The registry record does not say which people were masked, so “single-masked” cannot be interpreted more specifically from this information. It also does not report the randomization procedure, allocation ratio, concealment method, study sites, participant eligibility criteria, or the protocol for delivering the intervention. Those omissions limit the detail available for assessing how the groups were formed and how consistently the strategies were applied.

The posted primary outcome is pain measured at 1 year. Three functional recovery outcomes are also posted at 1 year: Oxford Knee Score Scale, Forgotten Joint Score, and Normal Knee Survey. The registry lists 6 outcome measures, while the posted results include the primary outcome and these three secondary outcomes. The registry record does not give results for the other outcome measures. Outcome-specific participant counts are not uniform, and the reason for those differences is not reported in the registry record.

This is a comparison of assigned groups as described in the registry, but the analysis population is not reported. The record also does not say whether results were analyzed according to original assignment, treatment received, or another population definition. These design details matter when interpreting a randomized comparison, so the posted summaries can describe group results without resolving all questions about the conduct and analysis of the trial.

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 Pain After TKA Measured by VAS Pain Survey on Focusmotion App, measured over 1 year.

The primary endpoint is pain after total knee arthroplasty, measured at 1 year with a VAS pain survey on the Focusmotion App. The endpoint is a score on a 0-10 scale, with higher scores indicating higher pain. The registry reports group means and standard deviations, so the posted comparison describes average scores and the spread of scores within each group.

Pain is a patient-reported outcome: the measure captures the participant’s rating rather than a laboratory value or an assessor’s direct measurement of function. A continuous score retains gradations in reported pain, instead of reducing the outcome to a yes-or-no category. In general, such a score can be useful for comparing average symptom levels between groups, while the spread and confidence interval help show how much uncertainty remains around that comparison.

The registry record does not identify a threshold for a clinically important difference, explain how the survey was administered beyond naming the app, or report how missing survey responses were handled. The posted mean difference therefore describes the observed contrast in average scores, but does not by itself establish whether a difference would be important to participants. It also does not show the full distribution of individual scores or changes from an earlier assessment.

7. Results Posted in the Registry

• No Tourniquet During Surgery: mean 2.60 versus 2.80 on control; difference -0.20 (95% CI -0.81 to 0.41), standardized effect d = -0.12; z-test p = 0.518.

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.

Functional Recovery Measured by Oxford Knee Score Scale

• 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:
  • No Tourniquet During Surgery: mean 41.37 versus 43.00 on control; difference -1.63 (95% CI -4.44 to 1.18), standardized effect d = -0.21; z-test p = 0.255.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between No Tourniquet During Surgery and the control. The interval gives the range of effects that remain compatible with the data.

Functional Recovery Measured by Forgotten Joint Score

• 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:
  • No Tourniquet During Surgery: mean 70.90 versus 68.40 on control; difference 2.50 (95% CI -22.80 to 27.80), standardized effect d = 0.04; z-test p = 0.846.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between No Tourniquet During Surgery and the control. The interval gives the range of effects that remain compatible with the data.

Functional Recovery Measured by Normal Knee Survey

• 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:
  • No Tourniquet During Surgery: mean 81.50 versus 79.30 on control; difference 2.20 (95% CI -24.84 to 29.24), standardized effect d = 0.03; z-test p = 0.873.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between No Tourniquet During Surgery and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary outcomes address functional recovery through three measures: Oxford Knee Score Scale, Forgotten Joint Score, and Normal Knee Survey. Taken together, their estimated differences do not establish a clear separation between groups. The confidence intervals include zero, and the unadjusted p-values do not give strong evidence of a difference. This overall pattern is consistent with the uncertain primary pain comparison, but the outcomes measure different aspects of recovery and should not be treated as interchangeable measures of one underlying result.

The uncertainty differs among the secondary measures. The posted participant counts vary by outcome, and the reported standard deviations indicate that variability is not uniform across measures. These features affect precision and make it inappropriate to treat the three estimates as equally informative. The registry record does not explain why participant counts differ or report how missing observations were handled, so the reason for variation in available outcome data remains unclear.

Unadjusted secondary results carry less weight when several outcomes are examined. In general, considering many comparisons increases the chance that at least one result will appear notable by chance. The registry record does not report a multiplicity adjustment or a hierarchy specifying how secondary outcomes were to be interpreted. The posted secondary p-values therefore should not be read as confirmatory evidence on their own. Nor should a non-significant result be read as showing that the groups are equivalent on functional recovery.

The secondary outcomes complement the primary endpoint by offering additional descriptions of reported function at 1 year. They do not resolve the primary estimate’s uncertainty, and their findings should be considered exploratory unless the prespecified analysis plan establishes otherwise. That plan is not reported in the registry record.

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

• Functional Recovery Measured by Oxford Knee Score Scale
• Functional Recovery Measured by Forgotten Joint Score
• Functional Recovery Measured by Normal Knee Survey

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, and the registry reports it as a mean with a standard deviation for each group. A mean describes the central average of the scores. A standard deviation describes how dispersed individual scores are around that mean. These answer different questions: the mean compares average pain scores, while the standard deviation describes variability among participants. A small difference between group means does not imply that participants’ scores were all similar or that every participant had a score close to the mean.

What does the mean difference represent?

The posted mean difference compares the no-tourniquet group with the tourniquet group. Its negative sign indicates that the first group’s average score is lower under the stated comparison order. Since higher values on this pain scale mean higher pain, the direction is interpretable as a lower average pain score in the no-tourniquet group in the posted data. This is a group-level comparison, not a statement about the experience of every participant. The registry’s primary comparison is unadjusted; an adjusted estimate is not reported in the registry record.

What does the confidence interval add?

A confidence interval gives a range of estimates compatible with the observed data under the method used to calculate it. In general, a narrower interval indicates greater precision, while a wider interval indicates more uncertainty. For the primary mean difference, the interval spans zero. That means the posted result is compatible with no average difference as well as with differences in either direction. It should not be interpreted as a range containing a guaranteed proportion of individual participants’ scores, nor as proof that all values inside it are equally plausible.

How should the p-value be read?

The unadjusted p-value is 0.518. In general, a p-value measures how unusual the observed result, or a more extreme one, would be if the null hypothesis and analysis assumptions held. It is not a measure of effect size, clinical importance, or the chance that the result is due to chance. A p-value above a conventional significance threshold does not demonstrate equivalence and does not rule out a meaningful effect. The confidence interval and the scale’s interpretation are needed alongside it.

Why consider dispersion?

Variation within groups influences how precisely group averages can be compared. In general, when scores vary more widely, a study needs more information to estimate a mean difference with comparable precision. The primary outcome’s standard deviations describe this within-group variation. For continuous outcomes, a mean-based summary is easiest to interpret when the mean and spread adequately describe the distribution; the registry record does not report distribution checks or alternative analyses. The posted summaries alone cannot show whether unusual values or skew influenced the mean.

The registry also reports a standardized effect-size estimate for the primary comparison, but that summary is not required to interpret the score-scale mean difference. A standardized effect expresses a difference relative to variability and can help compare measures with different units. It does not translate directly into a clinically important score change. The registry does not identify a threshold for meaningful change on the pain scale, and the standardized estimate should not be treated as a substitute for that missing context.

What do the planning illustrations represent?

Planning illustrations use the observed effect as an input to show the sample sizes that would be needed under stated assumptions. They are not a reconstruction of the trial’s original design. Here, the registry record identifies a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation for the planning calculation. The planning scenarios use the full observed effect or smaller stated portions of it. Such calculations are sensitive to the assumed effect: planning for a smaller effect requires more participants to achieve the same target power, all else equal.

The registry record does not report the original sample-size justification or the assumptions used when the trial was designed. The planning illustrations therefore cannot establish whether the trial was designed to detect a particular difference, and they do not explain the enrollment target. They are prospective-style calculations based on the posted effect estimate, which itself is uncertain. Using an observed estimate for planning can yield unstable illustrations, especially when the original estimate is imprecise.

No sponsor-reported statistical analyses are listed for the primary comparison, and the record does not describe model covariates, repeated-measures methods, or any adjustment for baseline values. The posted calculation is consequently best read as a simple, unadjusted comparison of group means. It should not be assumed to represent a more complex analysis that the registry does not describe. The registry record also does not report interim analyses, stopping rules, or a detailed statistical analysis plan.

11. Confidence Intervals and Precision

The primary mean difference is -0.2, with a confidence interval extending from -0.806 to 0.406 in the registry record. The interval crosses zero and includes estimates in both directions. This means the observed point estimate is not precise enough to distinguish confidently between a lower average pain score with no tourniquet and a higher average pain score with no tourniquet. It also includes the possibility of little or no average difference.

In general, confidence intervals express uncertainty about an estimated group-level quantity under the statistical method used. Their width depends on the amount of information and the variability in the data. They do not describe the spread of individual scores; the standard deviations serve that different purpose. A confidence interval that crosses zero is not evidence that the true difference is exactly zero. It indicates that zero is among the values compatible with the data under the calculation.

The unadjusted p-value of 0.518 is consistent with the interval’s inclusion of zero. Neither statistic answers whether any compatible difference would be important to participants. The registry record does not report a threshold for a meaningful pain-score difference, and the interval should not be used to invent one. More precise evidence would ordinarily require a narrower interval, but the posted information does not establish what degree of precision was intended by the study design.

The secondary outcome intervals are also broad in relation to their estimates, particularly for measures with substantial reported variability. Their width limits how narrowly the corresponding group differences can be characterized. Since there are no sponsor-reported analyses and no reported analysis plan for these outcomes, the posted intervals are descriptive evidence rather than a complete inferential account.

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 planning figures are participants per arm for 80% power and participants per arm for 90% power. They are not total participants across both arms, and they are not total events. The display’s rows represent planning for 100%, 75%, and 50% of the observed effect. The corresponding values illustrate how the required number changes when the effect assumed for planning changes.

The 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. The 80% power column means the calculation targets an 80% chance of detecting the assumed effect at the stated significance level if that effect is real and the model assumptions hold. The 90% power column makes the analogous calculation for a 90% target. These are design targets for hypothetical future studies, not guarantees about what a study will find.

Smaller effects require more participants to reach the same power target, all else equal. This is why planning for 75% or 50% of the observed effect produces larger figures than planning for the full observed effect. The observed effect is itself uncertain, so these values should be treated as illustrations rather than dependable forecasts. This is not observed power.

The registry record does not report the trial’s original sample-size justification or original design assumptions. The planning values therefore should not be used to infer why enrollment was set at 165 or whether the trial met an intended design target. They show only what follows from the stated planning assumptions and the observed effect estimate.

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 = -0.200; pooled standard deviation σ = 1.655.
2. n = 2 × (1.96 + 0.842)² × 1.655² / -0.200² = 1,075.5, rounded up to 1,076 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 <- -0.2                      # observed difference in means
sigma <- 1.65548164261237                     # 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(4923724)
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 = 1,076 (80% power), 1,440 (90% power)
 75% of observed effect: n per arm = 1,913 (80% power), 2,560 (90% power)
 50% of observed effect: n per arm = 4,303 (80% power), 5,760 (90% power)
power.t.test: 1076.5 
Simulated power at n = 1,076 per arm: 0.802 (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 lists 6 outcome measures and posts results for the primary pain measure and three secondary functional recovery measures. The record does not report a plan for controlling multiplicity, such as a prespecified testing sequence or adjustment of significance levels. When multiple outcomes are tested, unadjusted p-values can overstate the strength of evidence if interpreted as though only one comparison had been considered. This concern is particularly relevant to the secondary outcomes, whose results are presented without a reported multiplicity strategy.

The registry indicates 0 analyses, and sponsor-reported analyses are not listed for the posted outcome comparisons. This does not mean that no analysis was conducted; it means that the registry record does not provide those analyses as reported results. Details of the statistical analysis plan, including any planned adjustments or sensitivity analyses, are not reported in the registry record.

Outcome-specific participant counts are not the same across the posted results. The registry record does not explain whether this reflects missed assessments, exclusions, unavailable measurements, or another reason. Missing-data methods are not reported: there is no stated approach to imputation, complete-case analysis, or sensitivity analysis. As a result, the posted summaries cannot show how missing observations may have affected the estimates.

The analysis population is also not reported. The record does not state whether participants were analyzed according to randomized assignment, treatment received, or another rule. The masking detail is limited to “single,” without identifying who was masked. These omissions leave important questions about the analysis and risk of bias unresolved. They do not invalidate the posted numbers, but they limit how fully those numbers can be assessed.

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

Serious events with the highest arm-level rate: urinary retention lower abdominal and back pain (1.8%).

The registry reports serious adverse events for 57 at-risk participants in the tourniquet group, with 1 affected, and for 58 at-risk participants in the no-tourniquet group, with 0 affected. It lists urinary retention lower abdominal and back pain as the top serious-event term, with 1.8%. The record also reports other adverse events for 57 at-risk participants in the tourniquet group and 58 in the no-tourniquet group, with 0 affected in each group.

Deaths are listed as 1 in the tourniquet group and 0 in the no-tourniquet group. These are registry counts, not evidence that the assigned intervention caused an event or death. The registry record does not provide event narratives, timing, severity details beyond the serious-event classification, or an assessment of relatedness. The at-risk counts and affected counts should be read as separate posted safety summaries; they should not be combined with the outcome-specific participant counts or interpreted as a complete account of all safety monitoring.

Small event counts provide limited information about comparative safety. The record does not report a statistical comparison of adverse events. These figures describe what was posted and do not establish whether one strategy is safer than the other.

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

The primary posted result describes average pain scores at 1 year that were close between the two groups, with a mean difference of -0.2 for no tourniquet relative to tourniquet. The confidence interval crosses zero, and the unadjusted p-value is 0.518. Together, these findings indicate substantial uncertainty about the direction and size of the average difference. They do not establish that the strategies produce identical outcomes, nor do they demonstrate a clinically important difference.

The result applies to the reported comparison and outcome: pain measured with the named survey on a 0-10 scale at 1 year. It is not a direct estimate of pain at other times, an individual participant’s response, or a broader measure of recovery. The three posted functional outcomes offer additional information, but their uncertainty and unadjusted status mean they cannot be treated as definitive evidence that the groups differ or are equivalent on function.

The randomized design is relevant because random allocation is intended to support a fair comparison between groups. However, the registry record does not report enough detail to assess the allocation process, analysis population, missing-data handling, or full statistical plan. Those omissions mean the posted summaries should be interpreted within the limits of the information recorded, rather than as a complete clinical report.

The registry does not identify a threshold for a meaningful change in pain, report adjusted analyses, or describe the other care participants received. It also does not provide results for every listed outcome measure. Consequently, the posted data do not settle whether a difference would matter to patients, whether results generalize to people outside the study population, or whether any observed event was caused by a study strategy. The appropriate conclusion is limited to the estimates and uncertainty recorded.

17. Why This Trial Matters Statistically

This trial illustrates why an estimated difference should be read together with its uncertainty. The primary point estimate is small, but the interval extends to both sides of zero. Reporting only the direction of the point estimate could suggest a clearer conclusion than the data support; reporting only the p-value would also omit the range of compatible differences. The combination makes the uncertainty visible without turning a non-significant result into proof of no effect.

It also shows the importance of distinguishing an endpoint’s scale from its clinical meaning. The pain measure has a defined direction, with higher scores indicating higher pain, but the registry does not state a clinically important threshold. Statistical evidence about an average score difference therefore does not, by itself, establish whether participants would regard the difference as meaningful.

The functional outcomes and safety counts add context but raise different interpretive questions. Secondary results are subject to multiplicity concerns when no analysis hierarchy or adjustment is reported. Adverse-event counts are descriptive and do not establish a comparative safety effect. Participant counts vary across outcomes, while missing-data methods and analysis populations are not reported. These limitations demonstrate how registry summaries can provide useful numerical evidence while leaving important analytic details unresolved.

Finally, planning illustrations based on an observed effect are not a substitute for a documented original sample-size rationale. They show how assumed effects and target power relate under stated assumptions, but do not reveal the trial’s design intent. Keeping these roles separate helps prevent a planning calculation from being mistaken for an observed study finding.

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 the registry record constrain interpretation. It does not report eligibility criteria, participant characteristics, study sites, the randomization procedure, allocation concealment, or the identity of the person or group masked. The single-masked designation therefore offers only limited information about protection against bias. The record also does not describe how the pressure-regulating tourniquet was applied or detail other aspects of perioperative care.

The primary endpoint is reported as a group mean and standard deviation, without a distributional description or an identified threshold for a clinically important pain difference. The confidence interval includes zero, and the posted estimate is consequently imprecise with respect to direction and magnitude. The registry record does not report an adjusted comparison or a sponsor-reported analysis for this endpoint.

There are outcome-specific differences in the number of participants represented in the posted summaries. The registry does not explain these differences, identify missing-data procedures, or state the analysis population. It also lists 6 outcome measures but posts results for only the primary measure and three secondary measures. Results for the other measures are not reported in the registry record.

Multiplicity handling, interim analyses, stopping rules, and the original sample-size justification are not reported. The secondary results are unadjusted, and their interpretation is therefore less secure when considered alongside several outcomes. Safety reporting includes counts but does not provide event narratives or relatedness assessments. These limitations are about what can be established from the registry record; they do not show that any particular procedure was or was not followed.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Tourniquet on Total Knee Arthroplasty — NCT04923724.
• Registry record last updated 2025-05-15; status last verified 2025-05.
• Results first posted 2025-05-15.
• 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

NCT04923724, titled “Tourniquet on Total Knee Arthroplasty,” is a completed randomized, single-masked, parallel-group study sponsored by Washington University School of Medicine. It compares a tourniquet during surgery with no tourniquet during surgery in total knee arthroplasty. The registry lists enrollment of 165 and records the study start as 2020-11-01 and primary completion as 2023-11-30.

The primary outcome is pain on a 0-10 VAS survey at 1 year, with higher scores indicating higher pain. The posted mean difference for no tourniquet relative to tourniquet is -0.2, with a confidence interval that includes zero and an unadjusted p-value of 0.518. Three secondary functional recovery outcomes are also posted. The registry record does not report the analysis population, missing-data methods, multiplicity plan, or original sample-size justification.