Adhesive Tape Placement on Patients' Masks in the Emergency Department Increases Compliance of Proper Face Mask Use: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Adhesive Tape Placement on Patients' Masks in the Emergency Department Increases Compliance of Proper Face Mask Use (NCT04812184), a randomized na study. The primary outcome is Proper Face Mask Use up to 60 Minutes.

2. Clinical Question

The practical question is whether securing the mask at the nose was associated with a different likelihood of correct mask placement at the scheduled observation. The outcome was assessed by a trained observer who entered the room and recorded the location of the face covering. The listed categories included correct placement, chin exposed, nose exposed, and mask not on at all. The primary outcome concerns the correct-use category at the 60-minute time point, not a broader measure of infection prevention or mask effectiveness.

The registry describes random allocation to the tape or no-tape group, but masking was none. The record therefore describes a comparison of observed mask use under these two assigned conditions, rather than a blinded assessment. It does not report results for a separate clinical outcome such as infection, nor does it establish whether the mask type or source affected the comparison.

3. Trial Design

This was a randomized, parallel-group trial with no masking. The registry lists 123 enrolled participants and the status as completed. The study began on 2020-04-01, with primary completion on 2020-10-30. Indiana University is listed as the sponsor, and Eskenazi Hospital is identified in the brief summary as the trial setting.

Participants were allocated to surgical tape placed over the bridge of the nose or to standard of care, in which the mask was used without tape. The brief summary says participants could use their own mask, or receive a surgical or cloth mask. It also notes that donated cloth masks were used early in the study because of limited institutional resources. The record does not report how many participants used each mask type or whether mask type was balanced between groups.

Mask use was assessed at 30- and 60-minute intervals. The primary outcome is specifically described as proper face-mask use up to 60 minutes, with its timeframe listed as 60 minutes on Day 1. No separate result for the 30-minute assessment is posted among the registry entries for this analysis. The primary outcome population is described as smaller than the total enrollment, and the record notes that two standard-of-care participants were discharged before the 60-minute reevaluation.

The registry lists one outcome measure and no separate analysis records. It does, however, post a group comparison for the primary result. The record does not report further details about the randomization procedure, allocation concealment, protocol deviations, or the handling of all participants without a recorded primary outcome. It also does not report a sample-size justification or a more detailed prespecified statistical 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

Analysis population for the primary outcome, as defined in the registry: Overall number of participants analyzed less than total 123. 2 patients were discharged prior to the 60 minute reevaluation from the standard of care group.

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 Proper Face Mask Use up to 60 Minutes, measured over 60 minutes on Day 1.

The primary endpoint counts participants observed using their face mask properly at the 60-minute reevaluation on Day 1. Proper use is defined as the mask completely covering the mouth and nose, rather than being at or under the chin. The observer recorded the face covering's position, with categories that also included an exposed nose, an exposed chin, or no mask on at all.

This endpoint captures mask placement at a specified observation time. It is useful for the trial's immediate behavioral question because the intervention was intended to hold the mask against the face at the bridge of the nose, and the outcome directly records whether the mask was correctly positioned. It is a count outcome: each participant is classified according to whether proper use was observed at the assessment. The record does not describe a continuous measure of adherence or the duration of correct use between assessments.

The endpoint should not be read as a measure of infection, transmission, or overall health. It records an observer's assessment of mask position at the scheduled reevaluation. The registry does not report the observer's reliability, whether the observer knew the assigned group, or how observations were handled when a participant was unavailable. The listed primary population is smaller than the total enrollment; two standard-of-care participants are specifically noted as discharged before the 60-minute assessment.

7. Results Posted in the Registry

• Surgical Tape to Bridge of Nose: 100.0% (58/58) versus 85.2% (52/61) on control; risk difference 14.8 percentage points (95% CI 5.9 to 23.7), risk ratio 1.17 (1.06–1.30); unadjusted two-proportion z-test p = 0.002.

8. Statistical Interpretation

9. Statistical Methods Explained

The posted analysis presents a binary outcome: whether proper face-mask use was observed at the primary assessment. A participant contributes to the count of proper use or does not. For this type of outcome, the group result can be expressed as a count, a proportion, a difference between proportions, or a ratio of proportions. The registry posts counts, a risk difference, a relative risk, a confidence interval, and an unadjusted p-value.

What does the risk difference describe?

A risk difference compares the proportion with the outcome in one group against the proportion in the other. Its natural interpretation is an absolute contrast on the probability scale. A positive value in the posted direction means the observed proportion of proper mask use was higher in the tape group. The estimate is based on the outcome counts, and its confidence interval describes a range of values compatible with the data under the interval procedure used. The method used to construct that interval is not reported in the registry record.

What does the relative risk describe?

A relative risk compares the outcome proportion in one group with the outcome proportion in the comparison group. The posted estimate is 1.173, with a confidence interval from 1.057 to 1.302. A value of 1 would represent equal proportions under this measure; a value above 1 indicates a higher proportion in the numerator group. Relative risks communicate a proportional contrast, whereas risk differences communicate an absolute contrast. Neither measure alone describes the full context of the outcome or determines its clinical importance.

How should the p-value be read?

The posted unadjusted p-value is 0.002. In general, a p-value describes how unusual data at least as incompatible with a stated null hypothesis would be if that hypothesis and the assumptions of the analysis were true. It is not the probability that the null hypothesis is true, and it does not give the size or importance of an effect. The record does not state which specific test produced the p-value, so the test procedure and its assumptions are not reported in the registry record. The value is labeled unadjusted; an adjustment for multiple comparisons is not reported.

Why does the endpoint's binary form matter?

Each participant is classified as having or not having proper mask use at the scheduled observation. This produces a proportion for each group and supports the risk-based comparisons posted. The endpoint does not retain detail about how far a mask was displaced, how long it remained correctly positioned, or whether use changed between observation times. Those questions are not answered by a single binary assessment.

The count structure also matters when interpreting uncertainty. The endpoint groups are not identical in the number of participants listed, and the primary outcome population is described as smaller than the total enrollment. Confidence intervals reflect uncertainty in the estimated contrast under a particular calculation, but they do not automatically account for biases from missing observations, unmasked assessment, or differences in mask type. The registry does not report methods for addressing those concerns.

What does randomization contribute?

Random allocation is intended to make assigned groups comparable, on average, with respect to measured and unmeasured characteristics before intervention. It gives the group contrast a stronger basis for causal interpretation than a comparison in which participants select their own group. The record confirms randomized allocation but does not report the sequence-generation method, allocation concealment, or any baseline balance results. Randomization does not remove uncertainty due to missing outcome data or measurement procedures, and it does not ensure that chance differences are absent in a particular trial.

The study was unmasked. In general, knowledge of assignment can affect participant behavior or how an outcome is assessed, especially when the endpoint depends on observation. Here the endpoint was observed mask position, and the record does not report whether observers were unaware of assignment. This does not establish that bias occurred; it identifies a design feature that readers should consider alongside the posted estimate.

The record gives a planning-illustration assumption based on the observed effect: two-sided significance level 0.05, equal allocation, and a normal approximation, with the effect to detect stated as a fraction of the observed effect. These are planning assumptions, not evidence of the trial's original design rationale. The sample-size justification for the trial is not reported in the registry record. A planning calculation is not observed power and does not revise the uncertainty in the result already observed.

Finally, the record posts no separate analysis records, although it does give a primary comparison. It does not report covariate adjustment, a prespecified testing hierarchy, the method for any confidence interval, or a sensitivity analysis for missing outcomes. Those methods should not be inferred from the displayed estimates. General statistical interpretation can explain what the measures mean, but the exact analysis procedures beyond the posted labels remain unreported in the registry record.

10. Confidence Intervals and Precision

The relative-risk estimate is 1.173, with a confidence interval from 1.057 to 1.302. The interval is entirely above 1, the value corresponding to equal outcome proportions for a relative risk. This conveys the direction and range of the estimated relative contrast under the interval method used. The risk-difference confidence interval is also posted, but its numerical limits are not repeated.

In general, a confidence interval describes uncertainty in an estimate: values inside the interval are compatible with the observed data under the calculation and assumptions used. It does not guarantee that the true effect lies within the interval, and it does not account automatically for sources of bias that the analysis does not address. The method for calculating the posted confidence intervals is not reported in the registry record, so their exact inferential properties cannot be assessed from the record alone.

The interval gives more information than a point estimate alone because it shows a range of plausible relative effects, but precision is not the same as validity. The absence of masking, incomplete accounting of the primary-outcome population, and unreported observer masking may affect interpretation independently of the interval's width. The registry's notes indicate that the outcome population was smaller than enrollment and that two standard-of-care participants left before assessment. How other unavailable observations were handled is not reported.

The confidence interval and p-value address sampling uncertainty under the analysis, not whether the observed difference is important in every setting. No threshold for a clinically meaningful difference is reported. The posted result should therefore be read as an estimate with uncertainty for proper mask use at the 60-minute assessment in this trial, rather than as a guarantee of the same magnitude elsewhere.

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists one outcome measure and no secondary outcomes. It posts an unadjusted p-value of 0.002 for the primary comparison. It does not report a multiplicity adjustment, a testing hierarchy, or a plan specifying which analyses would be treated as confirmatory. The brief summary mentions assessments at 30 and 60 minutes, but no separate 30-minute result is included in the registry record for the posted analysis. Whether that assessment was prespecified as another formal comparison is not reported in the registry record.

Multiplicity matters in general when several outcomes, time points, or subgroup comparisons are tested: the chance of at least one apparently unusual result can increase as the number of tests grows. That general concern does not establish that the posted p-value is invalid. The available record does not describe the full set of analyses conducted, so the extent of any multiplicity cannot be determined.

The primary outcome population is described as smaller than total enrollment, and two participants in standard of care were discharged before the 60-minute reevaluation. Counts are posted for each group, but the record does not explain the disposition of every enrolled participant or all reasons an assessment might be missing. It also does not report an imputation method, a missing-data sensitivity analysis, or a rule for classifying participants without an observed assessment.

The analysis population is therefore not fully characterized in the registry record. The reported result should be interpreted as applying to the participants represented in the posted outcome counts. Whether the estimate would change under a different approach to missing outcomes is not reported. Nor does the record establish whether the analysis followed an intention-to-treat principle. These are separate questions from the numerical size of the reported group contrast.

12. 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's serious adverse event figures list zero serious events in the tape group and zero in standard of care. Deaths are also listed as zero in both groups. Other adverse events are listed as zero in both groups. The safety groups have 60 participants at risk in the tape group and 63 in standard of care for the reported event categories.

These entries mean that no events were recorded in the posted safety fields for the listed groups. They should not be interpreted as proof that no adverse events occurred outside the registry's definitions, reporting process, or observation period. The record does not give detailed safety definitions, event ascertainment procedures, or a safety follow-up timeframe. It also does not explain why the safety group counts differ from the primary-outcome group counts.

Zero recorded events do not establish that an intervention is risk-free. With no recorded events, the posted figures do not permit a comparative estimate of the frequency of those events. The record lists no serious-event terms. These safety figures are distinct from the primary endpoint, which concerns observed mask placement at 60 minutes.

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

The posted data show that, at the 60-minute assessment, proper mask use was recorded for 58 of 58 participants in the tape group and 52 of 61 participants in standard of care. The risk-difference estimate favors the tape group, and the posted relative risk is 1.173, with a confidence interval from 1.057 to 1.302. The unadjusted p-value is 0.002. Together, these statistics describe a difference in the observed binary outcome in this randomized comparison.

The result does not establish that tape placement changes infection risk, transmission, or any other clinical endpoint. Those outcomes are not reported. Nor does a single observation at 60 minutes establish how consistently participants wore masks over time, whether the position persisted after observation, or whether the result applies beyond the trial's emergency-department context.

The study used no masking, and the observer's awareness of group assignment is not reported. Participants could use their own masks or receive surgical or cloth masks; mask type distribution by group is also not reported. These aspects of measurement and implementation matter because the endpoint is observed behavior and the available record does not show whether other relevant conditions were similar between groups.

Enrollment was 123, while the primary outcome population is described as smaller. Two standard-of-care participants were discharged before the primary reevaluation, and the handling of all other participants not represented in outcome counts is not detailed. This leaves uncertainty about the possible influence of missing assessments. The confidence interval conveys sampling uncertainty under an analysis, but it does not resolve these design and reporting limitations.

Accordingly, the result is best understood as evidence of a difference in observed proper mask use at the specified assessment among participants represented in the posted outcome counts. It is not a universal estimate or a statement about benefits or harms beyond the recorded outcome. The registry record does not report a threshold for a meaningful difference, a longer follow-up result, or a broader clinical evaluation.

14. Why This Trial Matters Statistically

This trial illustrates how a clearly defined behavioral endpoint can turn an everyday practice question into a comparison of measurable outcomes. Proper mask use was defined by whether the mask covered both the nose and mouth at a scheduled observation. That definition makes the endpoint interpretable, while also making clear what it leaves out: duration of correct use and outcomes beyond mask position.

The randomized parallel-group design supports a direct comparison of assigned strategies. The posted result includes both an absolute measure, the risk difference, and a relative measure, the relative risk. These express the same group contrast on different scales. Reading both types of measure helps distinguish an absolute change in outcome frequency from a proportional comparison. The relative-risk estimate and its confidence interval indicate the direction and uncertainty of the posted contrast, while the p-value addresses compatibility with a null hypothesis under the analysis assumptions.

The record also demonstrates why statistical interpretation cannot rely on a point estimate alone. Enrollment and the primary-outcome population are not the same, and the record identifies some participants who left before the 60-minute assessment without fully explaining the remaining disposition. No-masking design, potentially varying mask type, and unreported observer masking are relevant to the credibility and scope of the estimate. These factors do not erase the observed comparison, but they frame what it can support.

Finally, a statistically distinguishable result is not equivalent to evidence about every consequence of an intervention. This endpoint concerns a specific observation in an emergency department, not infection or longer-term behavior. Separating the outcome actually measured from broader interpretations is an important part of sound clinical-trial reading.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The primary outcome is measured at one stated assessment time, 60 minutes on Day 1. Although the brief summary mentions 30- and 60-minute observations, the registry entries do not include a separate 30-minute result. A single observation cannot describe mask use throughout the visit or persistence after the assessment.

The trial was unmasked. Because the endpoint was recorded by an observer, knowledge of the assigned group could be relevant, but whether the observer knew assignment is not reported. The registry also does not report observer training beyond identifying a trained observer, or any assessment of agreement between observers.

Mask availability and type varied in the setting: participants could use their own mask or receive a surgical or cloth mask, and donated cloth masks were used early in the study. The number using each type and its distribution across groups are not reported. The record therefore does not establish whether mask type or source could have contributed to differences in the observed endpoint.

The primary-outcome population was smaller than total enrollment, with two standard-of-care participants specifically reported as discharged before reevaluation. The record does not describe the disposition of every participant, all missing outcome reasons, or sensitivity analyses. It also does not report baseline characteristics, the details of random-sequence generation, allocation concealment, or whether the analysis followed an intention-to-treat principle.

The registry does not report a trial sample-size justification, a detailed analysis plan, confidence-interval construction method, or multiplicity strategy. These omissions constrain assessment of the analysis and its precision. The findings should be interpreted for the recorded mask-use outcome and study setting, not as evidence about unreported clinical outcomes or other populations.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Adhesive Tape Placement on Patients' Masks in the Emergency Department Increases Compliance of Proper Face Mask Use — NCT04812184.
• Registry record last updated 2022-10-04; status last verified 2022-09.
• Results first posted 2022-10-04.
• 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.

19. Record Summary

NCT04812184 is a completed randomized, parallel-group trial sponsored by Indiana University. It enrolled 123 participants at Eskenazi Hospital, with the study beginning on 2020-04-01 and primary completion on 2020-10-30. Masking was none.

The intervention was tape placed over the bridge of the nose to adhere the mask to the face; standard of care involved a mask without tape. The primary endpoint counted participants with proper mask use at 60 minutes on Day 1. Proper use meant the mask completely covered the mouth and nose and was not at or under the chin.

The posted outcome counts were 58 of 58 in the tape group and 52 of 61 in standard of care. The relative risk was 1.173, with a confidence interval from 1.057 to 1.302, and the unadjusted p-value was 0.002. The primary-outcome population was smaller than enrollment; two standard-of-care participants were discharged before reevaluation. The record does not report a sample-size justification, detailed analysis plan, or results for a separate 30-minute assessment.