Evaluating the Need for Pneumatic Compression Devices: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluating the Need for Pneumatic Compression Devices (NCT02641080), a randomized na study. The primary outcome is Number of Participants With Venous Thromboembolism.

2. Clinical Question

The registry describes the comparison in terms of evaluating equivalence, but it does not report a prespecified equivalence margin or a formal equivalence analysis. That distinction matters: a trial can compare two strategies without its data being sufficient to establish that their effects are equivalent. The posted primary outcome is a count of participants with a clinically diagnosed event, not a measure of device use or patient experience. The additional outcomes address aspirin use, pump compliance, and overall pump experience. Those measures provide context about treatment use, but they do not replace the primary comparison of DVT or PE diagnoses.

3. Trial Design

This was a randomized, parallel-group trial with no masking. The registry records enrollment of 80 participants and a completed status. The listed start date is 2016-01, and the listed primary completion date is 2016-10. West Virginia University is identified as the sponsor. The phase is listed as NA; that entry does not describe the trial’s allocation or analysis methods.

Participants were assigned to aspirin alone or aspirin with a portable compression device. The registry lists 40 participants in each arm for the primary endpoint. The aspirin-alone arm was advised to take 325mg per day as outpatient DVT/PE prophylaxis. The device arm was asked to use the portable device for 20 hours a day for 2 weeks and take 325mg of aspirin per day. The record does not describe the randomization sequence, allocation concealment, recruitment sites, or procedures for maintaining adherence beyond the stated instructions.

The primary outcome was the number of participants with venous thromboembolism, defined as a clinically diagnosed DVT or PE during the immediate 90 days after surgery. Secondary outcomes concern aspirin usage over the 6 week postoperative period, compression-pump compliance over 2 weeks, and overall pump experience after 2 weeks. Four outcome measures are recorded, while three secondary outcomes are posted. The registry does not give further details about eligibility criteria, the timing or method of outcome assessment, or whether the people assessing outcomes knew the assigned group.

The completed status indicates that the registry marks the trial as completed; it does not, by itself, establish how many randomized participants contributed data to each outcome or whether every planned assessment was completed. The analysis population and participant flow are not reported in the registry record. The statistical analysis plan, protocol-specific sample-size justification, and any interim-analysis plan are also not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With Venous Thromboembolism, measured over 90 days.

The primary endpoint counts participants clinically diagnosed with DVT or PE during the immediate 90 days after surgery. It combines two types of venous thromboembolism into a participant count: each participant with a qualifying diagnosis contributes to the outcome. The record does not give separate counts for DVT and PE, and it does not describe the diagnostic criteria or adjudication process.

This endpoint addresses a clinically relevant event after total hip or knee arthroplasty, the setting named in the trial description. A count of affected participants makes the comparison understandable as an event occurring or not occurring within the stated follow-up window. It is not a time-to-event measure: the registry does not report when within the 90 days an event occurred, and no time-to-event analysis is posted.

In general, a binary participant-level endpoint is useful when the question is whether participants experienced an event during a defined period. It can be summarized by the number of participants with an event in each arm and compared using an absolute difference in observed risks. That summary does not capture event severity, duration, recurrence, or differences between DVT and PE. Those details are not reported in the registry record. The endpoint also does not directly measure bleeding, device adherence, or patient experience; those topics are either described in the trial rationale or represented among the secondary outcomes, rather than in the primary endpoint definition.

7. Results Posted in the Registry

• Aspirin With Portable Compression Device: 7.5% (3/40) versus 0.0% (0/40) on control; risk difference 7.5 percentage points (95% CI -0.7 to 15.7); unadjusted two-proportion z-test p = 0.077.

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.

Aspirin Usage Over 6 Week Post op Period

• 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:
  • Aspirin With Portable Compression Device: 2.5% (1/40) versus 5.0% (2/40) on control; risk difference -2.5 percentage points (95% CI -10.8 to 5.8), risk ratio 0.50 (0.05–5.30); unadjusted two-proportion z-test p = 0.556.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Aspirin With Portable Compression Device and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes address several aspects of postoperative use and experience: aspirin usage over the 6 week postoperative period, compression-pump compliance over 2 weeks, and overall pump experience after 2 weeks. Together, these topics concern whether participants followed or experienced the assigned strategies, rather than directly measuring the primary DVT/PE endpoint. They can help contextualize how an assigned intervention was used, but the registry does not report enough detail to establish how these measures were collected or how complete their data were.

The posted secondary results should be interpreted as exploratory context alongside the primary comparison, not as confirmation or contradiction of it. The primary endpoint concerns clinically diagnosed venous thromboembolism over 90 days, while the secondary outcomes concern use and experience over shorter specified periods. Differences in outcome definition and follow-up mean that the measures answer different questions. They do not independently resolve the uncertainty around the primary risk difference.

The registry posts a secondary comparison for aspirin usage, but does not post reported analyses for the other listed secondary outcomes. The analysis details and any prespecified hierarchy among outcomes are not reported in the registry record. The sample-size planning illustration is based on the observed effect for the aspirin-usage comparison, so it should not be mistaken for a design justification for the primary endpoint.

In general, interpreting several outcomes creates a multiplicity concern: the more comparisons examined, the more opportunity there is for an apparently notable result to occur by chance. This does not make secondary outcomes uninformative, but it lowers the weight that should be placed on isolated unadjusted results, especially when the analysis plan and multiplicity approach are unknown. No multiplicity adjustment is reported in the registry record. The secondary measures are best regarded as descriptive or exploratory evidence that may motivate further study, rather than as decisive evidence about the primary clinical question.

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

• Aspirin Usage Over 6 Week Post op Period
• Compression Pump Compliance Over 2 Weeks Post op
• Overall Pump Experience After 2 Weeks

9. Statistical Interpretation

10. Statistical Methods Explained

The primary comparison is reported as a risk difference. In general, a risk is the proportion of participants in a group who experience the specified event during the stated follow-up. A risk difference subtracts the comparator group’s risk from the intervention group’s risk. Positive values therefore indicate a higher observed risk in the intervention group under that sign convention, while negative values indicate a lower observed risk. The registry’s primary risk difference is 0.075 for aspirin with the portable compression device relative to aspirin alone. This is an absolute contrast, rather than a ratio of the risks.

What does the interval describe?

In general, a confidence interval is a range of values compatible with the observed data under the statistical method used and its assumptions. It communicates the uncertainty around an estimate; it is not a range containing a stated proportion of individual participant outcomes. The primary interval extends across zero, so the posted results are compatible with no risk difference as well as differences in either direction. Its breadth is consequential because the event counts are sparse. A point estimate alone would conceal how uncertain the comparison remains.

The exact procedure used to form the primary interval is not reported in the registry record. With low event counts, different statistical procedures can behave differently, especially when one arm has no observed events. The record does not identify the interval method, whether it was adjusted for any covariates, or whether the analysis followed a prespecified plan. The posted interval can be described as recorded, but its construction cannot be independently characterized from the registry entries.

What does the p-value contribute?

The posted p-value for the primary comparison is 0.077. In general, a p-value describes how unusual data at least as inconsistent with a specified null model would be if that model and the assumptions of the test were correct. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. It should be interpreted with the estimated difference and its interval, rather than as a standalone verdict. The test used to obtain the posted p-value is not reported in the registry record.

The registry comparison is labeled unadjusted in its reported summary. The record does not describe adjustment for baseline characteristics, stratification factors, or other covariates. Random assignment supports a comparison of assigned groups in general, but it does not remove uncertainty from a small sample or make unreported analysis choices known. The population included in the analysis is not reported in the registry record, so it is not possible to determine whether the estimate represents all randomized participants or a subset with recorded outcomes.

Why do sparse counts matter?

When event counts are small, each observed event can have substantial influence on an arm-level estimate. In general, this can produce wide uncertainty and make standard large-sample approximations less dependable. The registry does not specify whether the primary analysis used an exact method, a continuity correction, a regression model, or another approach. No such method should be inferred from the posted point estimate alone. The reported risk difference is useful as a descriptive contrast, while the uncertainty around it limits how strongly it can support broader conclusions.

Over-dispersion is a concern mainly for outcomes where observed variability exceeds what a chosen model expects, such as some count or repeated-measure outcomes. It is not possible to assess over-dispersion from a single binary participant count in each arm without additional model and data details. In general, if over-dispersion is present in a model that assumes less variability, standard errors can be too small and intervals too narrow. The registry does not report a model for the primary endpoint, so there is no basis to say over-dispersion was assessed or found.

How should the planning illustration be read?

The sample-size illustration is a planning exercise based on an observed effect, not evidence of the trial’s original design or its achieved power. It uses a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the effect set to a stated fraction of the observed effect. The illustration is attached to the secondary aspirin-usage comparison, not to a reported primary-outcome design justification. The registry does not report the trial’s own sample-size assumptions or justification. Planning figures are therefore prospective illustrations under stated assumptions; they are not observed power and cannot establish that the completed trial was adequately powered for its primary question.

For binary outcomes, a planning calculation depends on assumptions about event frequency, the effect worth detecting, the significance level, allocation, and the chosen method. In general, smaller target effects require more information to distinguish them from no difference under the same framework. A planning exercise based on the observed effect uses an estimate from the completed data, which may itself be unstable when outcomes are sparse. Its results should not be treated as a retrospective validation of the trial design.

The registry lists no reported analyses for the primary outcome and no reported analyses for the posted secondary outcomes in the analysis-count fields. It nevertheless contains a primary comparison estimate and p-value, and a secondary comparison with a p-value. The record does not explain the relationship between those entries and the analysis-count fields. The safest reading is to describe the posted results without inferring a complete statistical analysis plan, model specification, or set of prespecified analyses.

11. Confidence Intervals and Precision

The primary risk-difference estimate is 0.075, and the reported confidence interval extends from a negative value to a positive value. Because zero lies within that interval, the data do not distinguish the observed contrast clearly from no difference using the interval as a guide. The range also permits a difference in the opposite direction from the point estimate. The registry’s precision information therefore tempers interpretation of the point estimate: it identifies the direction of the observed contrast but does not tightly determine the underlying effect.

Precision concerns how narrowly an estimate is determined by the data. In general, an interval becomes narrower when data contain more information about the quantity being estimated, and wider when information is limited. Here, 40 participants are listed in each arm, with 0 primary events in one arm and 3 in the other. With so few events, uncertainty about the event risk and the between-arm difference remains substantial. The zero count should not be read as proof that the true risk in that arm is zero.

The p-value of 0.077 and the interval address related but distinct aspects of the comparison. The p-value summarizes compatibility with a null model under a test’s assumptions; the interval conveys a range of plausible values under an interval method. Neither alone establishes equivalence. A formal equivalence conclusion requires a prespecified margin defining how much difference would still count as equivalent and an analysis that evaluates that margin. Such a margin and analysis are not reported in the registry record.

The registry’s primary interval endpoints are recorded with more decimal places than the permitted display precision; the qualitative interpretation is that the interval crosses zero. The exact interval method is not reported in the registry record. Sparse counts and the absence of a described method make it especially important not to interpret the displayed point estimate as a precise forecast or as proof of a particular clinical effect.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary outcome and three secondary outcomes. It does not report a prespecified hierarchy, a family of hypotheses, or an adjustment for multiple comparisons. The multiplicity plan is not reported in the registry record. In general, testing multiple outcomes without accounting for that process can increase the chance that one result appears notable by chance. This concern applies particularly to secondary outcomes, which are often interpreted with less weight than a designated primary outcome when their analysis plan is unclear.

Missing-data handling is not reported in the registry record. The listed arm sizes describe the participants recorded for the outcomes, but the registry does not specify whether those numbers represent everyone randomized, whether anyone withdrew, or whether outcome status was unavailable for any participant. It also does not describe imputation, complete-case analysis, or sensitivity analyses. As a result, the effect of missing outcome information on the estimates cannot be assessed from the record.

The analysis populations are not reported in the registry record. It is not stated whether the primary comparison was based on all randomized participants, participants who received their assigned strategy, or another population. The record also does not describe protocol deviations, crossovers, or how adherence affected inclusion in analyses. These details matter because an analysis based on assignment and an analysis restricted by treatment received can answer different questions.

The statistical analysis plan, covariate adjustment, interim analyses, and stopping rules are not reported in the registry record. Nor are details of the randomization sequence or allocation concealment. These omissions do not prove that such procedures were absent; they limit what can be evaluated from the registry entry. For the same reason, the posted p-values and estimates should not be assumed to reflect a complete or prespecified analysis strategy. The sample-size justification for the primary endpoint is not reported in the registry record.

13. 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.

For the aspirin arm, the registry lists 0 serious adverse events among 40 participants at risk, 0 other adverse events among 40 participants at risk, and 0 deaths. For the aspirin-with-portable-compression-device arm, it likewise lists 0 serious adverse events among 40 participants at risk, 0 other adverse events among 40 participants at risk, and 0 deaths. No serious adverse-event terms are listed.

These are recorded counts, not proof that no adverse events occurred outside the registry’s definitions, collection period, or reporting process. The record does not describe adverse-event definitions, ascertainment methods, reporting completeness, or a separate safety analysis. Zero observed events in these groups should therefore be read as no events recorded in the listed categories, rather than as evidence that either strategy has no risks.

The safety counts are also distinct from the primary DVT/PE endpoint. The registry does not provide a separate bleeding endpoint result, despite describing interest in bleeding in its summary. The adverse-event figures alone cannot establish comparative safety or resolve the balance between thromboembolic outcomes and bleeding.

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

The posted primary data describe a randomized comparison in which 0 participants in the aspirin arm and 3 in the aspirin-with-device arm were recorded with a clinically diagnosed DVT or PE during the immediate 90 days after surgery. The risk-difference estimate is 0.075, and the reported p-value is 0.077. The interval includes zero and values on either side of it. Together, these statistics describe a difference in the observed counts while also showing that the estimate is uncertain.

The result does not establish equivalence. Equivalence is not demonstrated merely because a comparison does not provide clear evidence of a difference. A formal equivalence assessment ordinarily requires a prespecified margin and an analysis designed to evaluate that margin; neither is reported in the registry record. Nor does the posted result establish a definitive difference. The event counts are sparse, the interval crosses zero, and the analysis method and analysis population are not described in sufficient detail to support a stronger conclusion.

The finding is specific to this trial’s recorded participants, assigned strategies, outcome definition, and postoperative follow-up period. It does not describe the timing or type of thromboembolism separately, and it does not provide a separate primary result for bleeding. The secondary measures of aspirin use, pump compliance, and device experience address other questions and should not be substituted for the primary clinical endpoint.

In general, randomized allocation can support a comparison of assigned strategies by reducing systematic differences at baseline, but the registry entry does not provide enough detail to evaluate every implementation and analysis feature. No masking was used, and the record does not describe outcome adjudication or missing-data procedures. These gaps are relevant context, not proof that the results are biased.

The result is best understood as an imprecise estimate from a completed trial with 80 enrolled participants and few recorded primary events. It neither proves that adding a device changes outcomes nor proves that the strategies are interchangeable. It is a statistical description of the posted data, not medical advice or a recommendation about postoperative care.

15. Why This Trial Matters Statistically

This trial illustrates why the point estimate, uncertainty interval, and event counts need to be read together. The primary risk difference is positive, reflecting more recorded events in the device arm, but the confidence interval crosses zero and the p-value is 0.077. A single summary statistic cannot resolve the uncertainty created by the small number of events. The clinical question is framed around equivalence, making the absence of a reported equivalence margin especially important: a nonsignificant result and an equivalence result are not interchangeable.

The study also highlights the distinction between enrollment and information for a particular endpoint. The registry records 80 participants, with 40 listed in each primary-outcome arm, but only 3 primary events are recorded across the arms. For binary outcomes, the number and distribution of events affect precision; participant totals alone do not guarantee a precise estimate. This is a general statistical point, not a claim that a particular design choice was inappropriate.

There is a further planning lesson. The registry contains a sample-size illustration based on an observed secondary effect, but that illustration is not the trial’s own design rationale and is not observed power. A planning exercise can show how assumptions about the effect to detect influence a future study’s required information. It cannot retrospectively establish that a completed study had adequate power for its primary question.

Finally, the record illustrates how limitations in registry reporting affect interpretation. Without the analysis plan, outcome-assessment details, missing-data approach, or analysis populations, readers cannot fully evaluate how the posted estimates were produced. Transparent reporting of these features helps distinguish a descriptive comparison from a prespecified confirmatory analysis. The available result remains useful as a record of what was observed, while its precision and reporting context constrain the conclusions that can be drawn.

16. 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 endpoint combines DVT and PE into a single participant count. Separate event counts, diagnostic criteria, and adjudication procedures are not reported in the registry record, so the data cannot show whether the observed events differed by diagnosis or how diagnoses were confirmed. The endpoint is limited to the immediate 90 days after surgery; later outcomes are not represented in the primary result.

The recorded arm size is 40 participants per group, and the primary event counts are sparse. This limits precision and makes the estimated contrast sensitive to a small number of outcomes. The registry’s description of an equivalence objective is not accompanied by a reported equivalence margin or formal equivalence analysis. The primary sample-size justification is not reported in the registry record, and the secondary-outcome planning illustration should not be treated as that justification.

The trial was unmasked. In general, awareness of assignment can influence behavior, adherence, reporting, or outcome assessment, although the registry does not indicate whether such effects occurred. The record does not describe blinded outcome assessment, adherence monitoring results, diagnostic review, or allocation concealment. The requested device schedule and the separate compliance outcome do not, by themselves, establish how consistently participants used the device.

Participant flow, withdrawals, missing outcome data, analysis populations, and handling of protocol deviations are not reported in the registry record. The statistical analysis plan, model details, interval method, covariate adjustment, and multiplicity approach are also not reported. These missing details prevent a full assessment of analysis choices and the possibility of selective reporting. The registry lists aspirin use, compression-pump compliance, and pump experience as secondary outcomes, but does not post reported analyses for all of them. The record also does not provide a separate primary result for bleeding, despite mentioning bleeding in the study rationale.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Evaluating the Need for Pneumatic Compression Devices — NCT02641080.
• Registry record last updated 2020-11-06; status last verified 2020-11.
• Results first posted 2020-11-06.
• 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.

20. Record Summary

NCT02641080 is a completed randomized, parallel-group trial sponsored by West Virginia University. The registry records 80 participants and no masking. The comparison was aspirin alone versus aspirin with a portable compression device after total hip or knee arthroplasty. The device arm was asked to use the device for 20 hours a day for 2 weeks and take 325mg of aspirin per day; the aspirin arm was advised to take 325mg per day.

The primary outcome was the number of participants clinically diagnosed with DVT or PE during the immediate 90 days after surgery. The registry lists 0 events among 40 participants in the aspirin arm and 3 among 40 in the device arm. The posted risk difference is 0.075, with a confidence interval that crosses zero, and the posted p-value is 0.077. These results are uncertain and do not establish equivalence or a definitive difference.

Secondary outcomes concern aspirin use, pump compliance, and pump experience. The registry does not report a primary sample-size justification, detailed analysis plan, missing-data approach, or analysis populations. It records zero serious adverse events, zero other adverse events, and zero deaths in each arm.