Midvastus Versus Medial Parapatellar Approach for Minimally Invasive Total Knee Arthroplasty: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Midvastus Versus Medial Parapatellar Approach for Minimally Invasive Total Knee Arthroplasty (NCT01132378), a randomized na study. The primary outcome is Knee Society Score.

2. Clinical Question

3. Trial Design

The registry record describes a randomized, single-masked, parallel-group trial comparing mini-midvastus and medial parapatellar surgical approaches for total knee arthroplasty. Randomization means the study assigned participants to approaches by chance, according to the record. The record identifies single masking but does not report who was masked or how masking was carried out. The phase is listed as NA.

The stated enrollment is 40. The arm descriptions say that 40 patients underwent the mini-midvastus approach and describe the medial parapatellar approach, while the posted primary outcome results list 40 participants in each group. The registry record does not explain the relationship between the enrollment figure and the outcome counts. These figures should therefore be read as separately reported record entries, not reconciled by assumption.

The study was sponsored by Heekin Orthopedic Research Institute. The listed start is 2006-01, primary completion is 2012-01, and status is completed. The intervention is total knee arthroplasty, with the surgical approach differing between groups. The brief study description frames the comparison around the amount and location of muscle and tendon dissection while keeping the skin incision the same. The registry record does not report further operative details, such as surgeon experience, procedure standardization, or whether other aspects of care were controlled.

The primary outcome was the Knee Society Score at 2 year. Quadriceps strength is listed as a secondary outcome, but numerical results for that measure are not reported in the registry record. The record lists two outcome measures and zero analyses. It does not report a statistical analysis plan, the original design assumptions, or the intended analysis population.

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.

Before assignment: Forty consecutive patients who underwent staged bilateral Total Knee Arthroplasty were prospectively randomised to receive mini MedialParapatellar Approach in one knee and mini-midvastus approach in the other knee (left or right)within no more than 7 days.

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.

Population: Forty consecutive patients who underwent staged bilateral Total Knee Arthroplasty were prospectively randomised to receive mini MedialParapatellar Approach in one knee and mini-midvastus approach in the other knee (left or right)within no more than 7 days.

6. Primary Endpoint

The registry lists the primary outcome as Knee Society Score, measured over 2 year.

The primary endpoint was the Knee Society Score at 2 year, reported as a continuous measure using a mean and standard deviation for each group. The description gives a 0-100 scale and states that higher scores represent better results. It also says the score reflects outcomes and patients’ perceptions regarding function and pain. These features make the measure relevant to a comparison of patient-reported and functional outcomes after knee replacement surgery.

A group mean describes the average score among the participants included in that group’s result. The standard deviation describes how spread out individual scores are around that mean; it is not the uncertainty around the mean difference. The posted means were 98.7 for the medial parapatellar group and 99.03 for the mini-midvastus group. Their closeness indicates that the observed group averages were similar on this scale, but the means alone do not show how precisely the comparison was estimated.

The endpoint is reported at a single stated timeframe, 2 year. The registry record does not provide details about the assessment instrument’s administration, the timing window, or how missing score values were handled. It also does not report the score’s component-level results. The posted mean comparison therefore addresses the recorded overall score, not every separate dimension of function or pain.

7. Results Posted in the Registry

• Mini-midvastus Approach: mean 99.03 versus 98.70 on control; difference 0.33 (95% CI -0.60 to 1.26), standardized effect d = 0.15; z-test p = 0.488.

8. Statistical Interpretation

9. Statistical Methods Explained

The posted primary result compares group means for a continuous endpoint. Several statistical ideas help distinguish the observed averages, their variability, the estimated contrast, and the uncertainty around that contrast. The registry record does not report a detailed protocol analysis plan, so the explanations below describe general concepts and identify what is and is not documented for this trial.

What does a mean difference represent?

For a continuous outcome, a mean is the arithmetic average of observed scores in a group. A mean difference subtracts one group mean from the other. The reported contrast is defined as mini-midvastus minus medial parapatellar: 99.03 minus 98.7 is reported as 0.33. A positive estimate therefore indicates a higher observed average in the mini-midvastus group, while a negative estimate would indicate a higher observed average in the medial parapatellar group. The estimate alone does not show whether the difference is distinguishable from sampling variation.

The score is bounded from 0-100. General statistical interpretation of a bounded measure should keep its possible range in view. In this trial, the reported means are near the upper end of that range. A mean summarizes the group but does not reveal the full distribution, such as whether scores cluster tightly or whether a smaller number of participants have notably different scores.

What does the standard deviation describe?

The standard deviation describes dispersion among individual observations within a group. The posted values are 2.32 for the medial parapatellar group and 1.92 for the mini-midvastus group. A smaller standard deviation indicates less spread around that group’s mean; it does not by itself imply a better outcome, greater precision in the treatment comparison, or a difference between approaches. Precision of a group mean also depends on the amount of information contributing to it, including the number of observed participants.

The registry record reports 40 participants for each arm’s outcome result. It does not explain how those counts relate to the overall enrollment of 40, nor does it describe missing observations. Consequently, the recorded counts should not be used to infer participant flow or an unreported analysis set.

How should the confidence interval be understood?

A confidence interval gives a range of estimates compatible with the observed data under the statistical method and its assumptions. The reported interval for the mean difference is -0.603 to 1.263. It describes uncertainty about the group contrast, rather than the range containing most individual participants’ scores. It also does not assign a probability to the true effect being inside this particular interval. The stated interval includes zero, so the posted estimate does not rule out no mean difference at the confidence level used.

General statistical interpretation depends on the method used to calculate the interval, including assumptions about the data and sampling. The registry record does not report the interval method, whether it accounted for any design features, or whether the result was adjusted. The record lists the outcome as a mean with standard deviation and gives an unadjusted p-value of 0.488, but it does not provide a detailed test specification. The interval and p-value should therefore be described as posted rather than attributed to an undocumented procedure.

What does a p-value tell the reader?

In general, a p-value assesses how unusual data at least as incompatible with a null hypothesis would be if that null hypothesis and the test assumptions held. Here, the reported unadjusted p-value is 0.488. It is not a probability that either surgical approach is better, and it is not a measure of clinical importance. A larger p-value does not prove that the groups are identical. The estimated difference and its confidence interval provide essential context alongside the p-value.

The term unadjusted indicates that the reported p-value is presented without a multiplicity adjustment in the posted comparison. The registry record does not state whether additional tests were part of a prespecified analysis, how any family of tests was defined, or whether another analysis was used by the study team. No adjusted result is reported in the registry record.

Why does over-dispersion matter in general?

Some outcome analyses assume that variability follows a particular model. If the observed variation is greater than that model expects, standard errors can be too small and confidence intervals can be too narrow. This is commonly called over-dispersion. It matters because uncertainty estimates should reflect actual variation. The primary endpoint is reported as a continuous score with standard deviations; the registry record does not report an over-dispersion assessment or a model that would require one. This general concept should not be mistaken for a finding about this trial.

What is not described about the analysis?

The registry record reports zero analyses and does not describe covariate adjustment, the exact statistical test, model diagnostics, an intention-to-treat approach, or a per-protocol approach. It does not report prespecified analysis populations, missing-data methods, or how participants with incomplete outcome assessments were handled. It also does not report whether any interim analyses were planned or conducted. These details are important for understanding how a randomized comparison was translated into an estimate, but their absence does not establish which methods were or were not used by the study team.

The registry record reports no discrepancy between the posted comparison and recalculated unadjusted summary-statistic results. Recalculated results, when present, are simple unadjusted checks based on posted summaries; they do not substitute for the sponsor’s own analysis. For this comparison, the posted result remains the reported estimate and uncertainty. General statistical methods can clarify what those quantities mean, but they cannot fill gaps in the documented analysis plan.

10. Confidence Intervals and Precision

The estimate of the mean difference is 0.33 points, with a reported confidence interval from -0.603 to 1.263. The interval is an important part of the result because it displays how uncertain the estimated contrast is. It includes zero and extends in both directions, so the posted data are compatible with a small difference favoring either group as well as no average difference.

The confidence interval is not a range for individual Knee Society Scores, and it is not a guarantee that the true difference lies within its limits. In general, it describes a range of values that would be compatible with the observed data under the method’s assumptions. The registry record does not report which procedure was used to calculate this interval, so its assumptions and any adjustments cannot be evaluated from the record.

The two standard deviations, 2.32 and 1.92, describe variation in scores among participants in each arm. They are distinct from the confidence interval for the difference. The posted group counts are 40 for each arm; however, the registry record does not explain how these outcome counts relate to the enrollment figure of 40. It also does not report missing-data handling or an analysis population, which leaves uncertainty about the observations contributing to the endpoint result.

No threshold for a clinically meaningful difference is reported in the registry record. Statistical precision therefore cannot, by itself, establish whether values within the interval would matter to patients. The interval supports a cautious reading of the estimate, rather than a conclusion of equivalence.

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, not total events. They are illustrations based on the observed mean difference and stated planning assumptions, not the original trial’s sample-size justification. The registry record does not report the trial’s own design assumptions or sample-size calculation.

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 set to a stated fraction of the observed effect. For planning at 100% of the observed effect, the figures are 654 participants per arm for 80% power and 876 participants per arm for 90% power. At 75% of the observed effect, they are 1,163 participants per arm for 80% power and 1,556 participants per arm for 90% power. At 50% of the observed effect, they are 2,615 participants per arm for 80% power and 3,501 participants per arm for 90% power.

In plain language, the 80% power column gives the planned number per group under which the calculation would have an 80% chance of detecting the specified effect if that effect were real and the planning assumptions held. The 90% column describes the corresponding calculation for a 90% chance. These are prospective planning quantities, not observed power for this completed trial.

Smaller target effects require more participants under the stated assumptions, because a smaller separation between group means is harder to distinguish from random variation. These calculations use the observed effect as their reference, and the observed estimate is uncertain. They should not be read as proof that the trial was underpowered or as evidence about the original design rationale.

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 = 0.330; pooled standard deviation σ = 2.129.
2. n = 2 × (1.96 + 0.842)² × 2.129² / 0.330² = 653.6, rounded up to 654 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 <- 0.329999999999998                      # observed difference in means
sigma <- 2.12941306467299                     # 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(1132378)
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 = 654 (80% power), 876 (90% power)
 75% of observed effect: n per arm = 1,163 (80% power), 1,556 (90% power)
 50% of observed effect: n per arm = 2,615 (80% power), 3,501 (90% power)
power.t.test: 654.6 
Simulated power at n = 654 per arm: 0.800 (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. Multiplicity, Missing Data and Analysis Populations

The registry record lists the Knee Society Score as the primary outcome and Quadriceps Strength as a secondary outcome. It reports two outcome measures and zero analyses. Numerical results for the secondary measure are not reported in the registry record. No prespecified hierarchy of endpoints, family of statistical tests, or multiplicity adjustment is described.

Multiplicity arises when several outcomes, time points, subgroups, or comparisons are tested. In general, conducting more tests can increase the chance of obtaining at least one apparently unusual result by chance. A prespecified plan can clarify which result is primary and how other tests should be interpreted. The registry record does not report whether additional analyses were planned or conducted, so the scope of testing cannot be reconstructed from the posted entry. The primary comparison’s p-value is described as unadjusted.

Missing-data information is also limited. The primary outcome timeframe is 2 year, and the posted primary results list 40 participants per arm. The registry record does not report the number assessed at that time point separately from the outcome counts, the number with incomplete scores, reasons for missingness, or any imputation or other missing-data procedure. The enrollment entry is 40, and the registry record does not explain its relationship to the two arm-level outcome counts. Without participant flow and missing-data details, the possibility of selective availability of endpoint data cannot be assessed.

The analysis population is not reported in the registry record. It does not say whether the primary comparison followed an intention-to-treat principle, included only participants who received the assigned procedure, or used another population definition. Randomization is reported, but the analytic handling of randomized participants is not described. The record also does not report covariate adjustment, subgroup analyses, or interim analyses. These gaps limit review of how the reported endpoint estimate was selected and calculated; they should not be filled by assuming a particular protocol or analysis practice.

14. Safety Results

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

Other (non-serious) adverse events

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

The serious adverse event entry reports 0 affected among 40 at risk in the combined group labeled Midvastus or Medial Parapatellar Approach. The registry record lists no serious adverse event terms. It also reports 0 other affected among 40 at risk in that group. These are the posted event counts for the registry entry, not a detailed account of event types or timing.

The safety information is presented for a combined approach group rather than as separate results for each surgical approach. The registry record does not report the observation period, event definitions, methods for event collection, or whether participants were assessed uniformly. It therefore does not support a comparison of safety event rates between the two randomized groups.

Deaths are not reported in the registry record. Zero affected participants in the posted event fields should be read as the recorded counts for the stated group and at-risk denominator, not as proof that no events could occur outside the record’s reporting scope. The entry provides limited information for characterizing safety across the trial.

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

The posted primary outcome comparison describes average Knee Society Scores at 2 year for the two surgical approaches. The estimated difference is 0.33 points in the direction of a higher mean in the mini-midvastus group. Its 95% confidence interval, -0.603 to 1.263, includes zero and includes values favoring either group. The unadjusted p-value is 0.488. Together, these statistics indicate that the observed comparison does not provide a precise estimate of the direction or size of any small average difference.

This result does not establish that the approaches are identical. A conventional comparison that does not distinguish the observed contrast from zero is not the same as an equivalence test. The registry record does not report an equivalence or non-inferiority design, a prespecified margin, or a threshold for a meaningful difference. It is therefore not possible to conclude from this endpoint result that differences of potential clinical importance have been excluded.

The result also does not establish that either approach works better or worse in clinical practice. It describes one posted outcome at one stated timeframe, in the participants represented by the recorded data. It does not capture every possible outcome, surgical complication, or patient experience. The secondary outcome, Quadriceps Strength, is listed, but its numerical results are not reported in the registry record.

Several details needed to judge the scope of inference are absent. The registry record does not explain why enrollment is 40 while the primary outcome counts are 40 per arm. It does not report participant flow, missing-data methods, analysis populations, or a detailed analysis plan. Safety events are listed in a combined group, rather than separately by approach, and the event observation period is not reported. These limitations warrant restraint in extending the primary score comparison to broader claims.

The defensible statistical reading is narrow: the posted group means were close, the estimated mean difference was small on the stated scale, and the interval leaves uncertainty about the direction and size of the difference. Judgments about clinical importance, comparative safety, or equivalence require information and criteria that the registry record does not provide.

16. Why This Trial Matters Statistically

This trial is statistically instructive because it separates the observed effect estimate from evidence about its precision. The reported means, 98.7 and 99.03, are close, and the mean difference is 0.33. But the confidence interval, -0.603 to 1.263, is necessary to understand how much uncertainty accompanies that estimate. A small point estimate alone does not demonstrate that two approaches have the same outcome.

The distinction between a conventional difference test and an equivalence question is especially important. The reported p-value is 0.488, but no equivalence margin is reported. Without a prespecified margin and an appropriate design, a result that does not rule out zero cannot establish that clinically relevant differences have been excluded. The score’s upper limit of 100 and the reported means near that limit also provide context for interpreting this particular measure, without determining the clinical meaning of a difference.

The record also illustrates why data provenance and reporting consistency matter. It lists enrollment of 40 but reports 40 participants per arm for the primary endpoint. Since the relationship is not explained, readers should avoid silently converting these entries into a participant flow narrative. The missing analysis population and missing-data information further limit reconstruction of the path from randomization to the final comparison.

Finally, the planning illustrations show how sample-size needs depend on the effect chosen for detection and the desired power. They are not the trial’s original design justification and are not observed power. Keeping planning calculations separate from the completed trial’s observed results helps prevent retrospective calculations from being misrepresented as evidence about the study’s original adequacy.

17. 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 registry entry has limitations specific to interpreting this comparison. First, enrollment is listed as 40, while the primary outcome results list 40 participants in each arm. The record does not explain whether these entries refer to different populations or how participant counts changed across the study. No participant flow is reported, so the randomized, treated, followed, and analyzed groups cannot be reconciled.

Second, the outcome is recorded at 2 year, but the registry record does not give a specific assessment window, the number assessed at that time point beyond the posted arm counts, or the handling of missing score data. It does not define the analysis population or provide the full statistical analysis plan. The method used for the confidence interval and the reported unadjusted p-value is not specified.

Third, no threshold for a clinically meaningful difference is reported, and there is no stated equivalence or non-inferiority margin. The primary comparison therefore cannot answer whether a difference of a particular size would matter to patients. The secondary outcome, Quadriceps Strength, is listed without numerical results. The serious and other adverse event counts are reported for a combined approach group rather than separately by arm; the registry record does not report the observation period or detailed event definitions.

Finally, the registry record does not report the original sample-size justification, interim analyses, or any planned subgroup analyses. These missing details limit assessment of design and analysis choices. They are reporting gaps, not evidence that any particular procedure was or was not followed.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Midvastus Versus Medial Parapatellar Approach for Minimally Invasive Total Knee Arthroplasty — NCT01132378.
• Registry record last updated 2014-01-17; status last verified 2012-02.
• Results first posted 2013-11-19.
• 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.

21. Record Summary

The registry record describes a completed, randomized, single-masked, parallel-group study of mini-midvastus versus medial parapatellar approaches for total knee arthroplasty in people with osteoarthritis. Enrollment is listed as 40, and the primary endpoint is the Knee Society Score at 2 year, scored from 0-100 with higher scores indicating better results.

The posted means were 98.7 for medial parapatellar and 99.03 for mini-midvastus. The reported mean difference was 0.33, with a confidence interval from -0.603 to 1.263 and an unadjusted p-value of 0.488. The record also lists Quadriceps Strength as a secondary outcome but gives no numerical result for it. Safety counts are reported for a combined group; the relationship between enrollment and arm-level outcome counts, the analysis population, and missing-data methods are not explained.