Novel Myofunctional Water Bottle to Reduce OSA and Snoring Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Novel Myofunctional Water Bottle to Reduce OSA and Snoring Study (NCT05371509), a randomized na study. The primary outcome is Adherence to Therapy.

2. Clinical Question

3. Trial Design

The registry describes a randomized, double-masked, parallel-group study sponsored by Mayo Clinic. It is listed as completed. The recorded enrollment is 43. Participants were assigned to receive either the myofunctional therapy nozzle or the placebo nozzle, with both interventions described as water bottles for daily use. The registry lists the study phase as not applicable.

The study began on 2023-09-07, and the primary completion date is 2024-12-10. These dates describe the registry record; they do not by themselves explain how long each participant was followed. The primary outcome has a 60-day timeframe, while the description says participants were asked to meet their daily water-consumption goal 5 days per week for 8 weeks.

Random allocation is intended, in general, to reduce systematic differences between assigned groups, while masking is intended to limit the influence of knowing the assigned intervention. Those are general features of these design choices, not evidence that all sources of bias were eliminated in this study. The registry does not report the specific randomization procedure, who was masked, or how masking was maintained.

The posted primary outcome results are based on 20 participants in the myofunctional therapy nozzle group and 21 in the placebo nozzle group. Results for the secondary outcomes use different reported group counts. The registry does not report why those counts differ from the primary outcome counts, whether the analysis included all randomized participants, or how missing outcome data were handled. The trial's original sample-size assumptions, detailed statistical plan and reported analysis procedures are 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.

Before assignment: 43 subjects were enrolled in the study and 1 subject withdrew prior to randomization.

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 Adherence to Therapy, measured over 60 days.

The primary endpoint is adherence to the daily water-consumption goal, expressed as the mean number of days participants met that goal during a 60-day timeframe. The registry description says participants were asked to reach the goal 5 days per week for 8 weeks. The endpoint therefore records days meeting a behavioral target; it does not directly measure apnea, oxygen saturation or snoring.

Adherence is useful in a device study because it describes whether participants followed the requested daily-use routine. A difference in adherence can help characterize how consistently the assigned routine was followed, which is relevant when interpreting outcomes that might depend on repeated use. As a general statistical point, adherence is a measure of behavior rather than a direct measure of clinical benefit. The endpoint alone cannot establish whether sleep-related outcomes changed.

The posted mean was 18.4 days in the myofunctional therapy nozzle group and 26.1 days in the placebo nozzle group. The posted mean difference, calculated as the myofunctional therapy group minus the placebo group, was -7.7 days. The registry does not report a separate endpoint definition beyond the stated daily goal, the number of days, and the specified timeframe.

7. Results Posted in the Registry

• Myofunctional therapy (MT) nozzle: mean 18.40 versus 26.10 on control; difference -7.70 (95% CI -17.39 to 1.99), standardized effect d = -0.49; z-test p = 0.119.

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.

Change in Apnea Hypopnea Index (AHI)

• 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:
  • Myofunctional therapy (MT) nozzle: mean -0.90 versus 2.70 on control; difference -3.60 (95% CI -8.02 to 0.82), standardized effect d = -0.55; z-test p = 0.111.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Myofunctional therapy (MT) nozzle and the control. The interval gives the range of effects that remain compatible with the data.

Change in Oxygen Saturation (SpO2)

• 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:
  • Myofunctional therapy (MT) nozzle: mean 0.37 versus -0.07 on control; difference 0.44 (95% CI -0.18 to 1.06), standardized effect d = 0.48; z-test p = 0.163.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Myofunctional therapy (MT) nozzle and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary outcomes broaden the study beyond adherence to include sleep-apnea severity and oxygen saturation, as well as myofunction assessment and measures of snoring. Results are posted for change in AHI and change in oxygen saturation. The record does not post results for the other listed secondary outcomes, so the overall pattern cannot be assessed across every outcome named in the registry.

Across the two available secondary comparisons, the numerical directions differ: one estimate is lower for the myofunctional therapy nozzle group and the other is higher. Their intervals include zero, and neither unadjusted comparison provides clear evidence of a between-group difference. This differs from the primary adherence measure, which is a behavioral endpoint rather than a direct measure of sleep-related outcomes. The secondary outcomes therefore add context but do not resolve the uncertainty in the primary result.

As a general statistical concern, examining several outcomes creates more opportunities for apparently notable findings to arise by chance. Adjustment procedures can address some multiplicity concerns, but the registry record does not report a multiplicity strategy or adjusted secondary analyses. The posted secondary p-values are unadjusted and should carry less evidential weight than a prespecified primary analysis, particularly when the full set of planned outcome results is not posted.

The registry lists five secondary outcomes, while results are posted for two. It is not reported in the registry record why the remaining outcomes have no posted results, whether they were measured, or whether their analyses were completed. Without that information, the secondary findings should be viewed as incomplete and exploratory rather than as a consistent body of confirmation.

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

• Change in Apnea Hypopnea Index (AHI)
• Change in Myofunction Assessment
• Change in Oxygen Saturation (SpO2)
• Change in Snoring Intensity
• Change in Snoring Frequency

9. Statistical Interpretation

10. Statistical Methods Explained

What does a mean difference describe?

For a continuous outcome, a group mean represents the average observed value among the participants included in that outcome's summary. A mean difference compares those averages. The posted primary comparison subtracts the placebo nozzle mean from the myofunctional therapy nozzle mean, so a negative estimate indicates a lower mean in the active-device group. This is a description of the observed group summaries, not a causal conclusion by itself.

Means can be informative, but they do not show all features of the data. Different distributions can have the same mean, and a mean can be affected by unusually high or low observations. The registry gives standard deviations as measures of within-group spread, but it does not provide individual observations, medians, ranges or distribution plots in the registry record for this record. Interpretation of distribution shape is consequently limited.

What does the standard deviation add?

As a general statistical explanation, a standard deviation describes how dispersed observations are around their group mean. A larger standard deviation indicates greater variability among observed values, although the units remain those of the outcome. For adherence, the standard deviation is expressed in days. For the secondary outcomes, the units follow each outcome's definition.

Spread matters because a difference between averages is estimated with uncertainty. When observations vary considerably within groups, it can be harder to distinguish a group difference from random variation. Standard deviations do not, on their own, measure uncertainty in the estimated mean difference; that also depends on the number of observations and the analysis method.

How should the interval be read?

A confidence interval is generally a range of values compatible with the data and the method used to calculate it. It conveys uncertainty about an estimated effect more directly than a point estimate alone. If an interval for a mean difference includes zero, then a zero difference is among the values not excluded by that interval. That does not show that the true difference is zero, and it does not establish equivalence.

The posted primary interval runs from -17.39 to 1.991 days and includes zero. The registry record does not state the confidence level or the method used to calculate the posted interval. The numerical limits should therefore be read as the posted interval, without assigning it a confidence level that is not reported. For the secondary comparisons, the posted intervals also include zero.

What does the p-value say?

As a general explanation, a p-value describes how unusual data at least as incompatible with a specified null model would be if that model and the test assumptions held. It is not the probability that the null hypothesis is true, and it is not a measure of the size or clinical importance of an effect. A p-value should be interpreted alongside the estimated difference, its interval, the design and the analysis plan.

The primary comparison has an unadjusted p-value of 0.119. The registry gives unadjusted p-values for the two posted secondary comparisons as well. The record does not identify the test used, the full model, or a prespecified decision threshold for the primary outcome. The stated sample-size illustration uses a two-sided significance level of 0.05, but that planning assumption is not evidence that the same threshold was prespecified for the trial's primary analysis.

What does randomization contribute?

In general, random assignment is used to make treatment groups comparable in expectation with respect to factors measured and unmeasured before assignment. It does not guarantee that groups will be identical in a particular trial, especially when the study is small. Masking can reduce some behavioral or assessment influences, but its effectiveness depends on how it was implemented. The registry identifies the design as randomized and double-masked; the specific procedures and the identities of those masked are not reported.

The posted numerical comparisons are unadjusted re-calculations from the summary statistics. They do not replace an analysis based on the trial's prespecified statistical plan. The registry record contains no reported analyses, so the original analysis model, covariate adjustments, treatment of missing data and analysis population are not reported. The record also does not report whether any interim analyses were planned or conducted.

Why can unequal variability matter?

As a general statistical point, methods for comparing means make assumptions about how variation is represented. If group variability differs or the outcome distribution is unusual, a method that assumes a common spread or a normal approximation may not describe uncertainty well. Over-dispersion, in settings where a model expects less variability than the data contain, can make standard errors too small and intervals too narrow if it is not addressed. The registry does not report diagnostics or methods for checking or addressing such issues in this study.

For this record, the posted comparison includes a pooled standard deviation and standard errors, but the registry does not state the inferential procedure used for the posted interval or p-value. The analysis should not be described as adjusted, model-based, or robust unless those methods are reported. The available summaries support a plain description of the calculated group difference and its uncertainty, not a reconstruction of the trial's full statistical analysis.

11. Confidence Intervals and Precision

The primary estimate is a mean difference of -7.7 days, with a posted interval from -17.39 to 1.991 days. Because that interval includes zero, the data do not rule out no group difference under the method used to form the interval. Its span also includes values on either side of zero, so the estimate is not precise enough to identify a single direction with certainty. The registry record does not report the interval's confidence level or calculation method.

Precision is not the same as whether an estimate is important. An interval describes uncertainty in the estimate, while judgments about importance require context about the outcome and what size of difference would matter. The registry does not report a threshold for a meaningful adherence difference. The point estimate should not be interpreted as a guaranteed difference for future participants.

The primary groups have standard deviations of 16.4 and 15.2 days, indicating variation around their respective means. The group counts used for this outcome are 20 and 21. These features help explain why a point estimate is accompanied by uncertainty, but they do not reveal the full distribution of individual results.

The secondary comparisons also have posted intervals that include zero. The registry does not state their confidence level or the method used to form them. A confidence interval, in general, depends on both the observed data and the analysis assumptions. The record's lack of a reported analysis plan and missing-data methods limits how fully the precision can be evaluated.

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, not total events. They are illustrations based on the observed effect, rather than the trial's original design calculation. The assumptions listed for this illustration are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect equal to the stated fraction of the observed effect. The trial's own original sample-size assumptions are not reported in the registry record.

For planning at 100% of the observed effect, the figures are 67 participants per arm for 80% power and 89 participants per arm for 90% power. At 75% of the observed effect, they are 118 participants per arm for 80% power and 158 participants per arm for 90% power. At 50% of the observed effect, they are 265 participants per arm for 80% power and 354 participants per arm for 90% power.

In plain terms, the 80% column gives the modeled number per arm for an 80% chance of detecting the specified effect under the listed assumptions; the 90% column gives the modeled number per arm for a 90% chance under those assumptions. Detecting a smaller effect requires more participants per arm in these illustrations. These are planning calculations, not observed power for the completed trial.

The figures should not be read as a finding that the trial was or was not adequately designed. They are based on the observed effect, and the observed estimate itself is uncertain. The registry record does not report the effect size, variability, power target or analysis assumptions used when the trial was originally designed.

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 = -7.700; pooled standard deviation σ = 15.796.
2. n = 2 × (1.96 + 0.842)² × 15.796² / -7.700² = 66.1, rounded up to 67 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 <- -7.7                      # observed difference in means
sigma <- 15.7960072851922                     # 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(5371509)
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 = 67 (80% power), 89 (90% power)
 75% of observed effect: n per arm = 118 (80% power), 158 (90% power)
 50% of observed effect: n per arm = 265 (80% power), 354 (90% power)
power.t.test: 67 
Simulated power at n = 67 per arm: 0.798 (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 multiple outcomes: a primary adherence measure and secondary measures involving AHI, myofunction assessment, oxygen saturation and snoring. Considering several outcomes raises a multiplicity issue. In general, if many statistical tests are performed, the chance of at least one apparently unusual result can increase. Prespecifying a primary outcome and using a stated strategy for secondary outcomes can help readers distinguish confirmatory questions from exploratory ones.

The record identifies the primary endpoint and lists five secondary outcomes, but it does not report a multiplicity adjustment, a hierarchy for testing outcomes, or a plan for interpreting secondary results. The two posted secondary comparisons have unadjusted p-values. They should not be treated as if they had been adjusted for the number of outcomes considered. No corrected or family-wise results are reported in the registry record.

Results are posted for two secondary outcomes, not all five listed. The record does not say whether the unreported outcomes were not measured, were measured but not analyzed, or were analyzed but not posted. The reasons for this incomplete outcome reporting are not reported in the registry record. The record also does not report whether the listed endpoints were changed or added after study start.

Missing-data handling and analysis populations are likewise not reported. The outcome-specific participant counts differ, but the registry does not explain the reasons. It does not state whether analyses used all randomized participants, only those with available measurements, or another population; nor does it describe imputation, exclusions or sensitivity analyses. These omissions matter because the way missing observations are handled can affect both the estimated group difference and its uncertainty.

The registry reports no analyses in its reported-analysis listing. The specific statistical model, prespecified hypothesis tests, interim-analysis plans and original analysis plan are not reported in the registry record. Consequently, the posted summaries allow descriptive comparisons but do not establish how closely the displayed calculations align with the trial's planned primary analysis.

15. Safety Results

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

Deaths

Other (non-serious) adverse events

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

The serious adverse event figures report zero affected participants in each arm. The at-risk count is 21 for the myofunctional therapy nozzle group and 21 for the placebo nozzle group. The registry also reports zero other adverse events and zero deaths in each group.

These figures describe events recorded in the registry and should be read as counts, not as proof that no adverse event could occur. The record does not provide event-level descriptions, follow-up completeness, severity details beyond the serious-versus-other categories, or a separate account of how events were collected. It also does not explain why the at-risk counts for safety differ from the primary outcome counts.

A zero count in the posted record means no affected participants were reported in these categories for the stated groups. It does not establish equal safety between groups or rule out uncommon harms. The registry record does not report a formal statistical comparison of adverse events.

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

The posted primary result is an unadjusted comparison of mean adherence days between the two randomized groups. The observed mean was lower in the myofunctional therapy nozzle group than in the placebo nozzle group, and the interval around the difference includes zero. The result therefore leaves uncertainty about the direction and size of any underlying group difference. The registry record does not report a prespecified threshold for interpreting the primary result or the full analysis plan.

This endpoint measures days meeting a water-consumption goal. It is not itself a measure of obstructive sleep apnea, snoring, oxygen saturation or myofunction. A difference in adherence would describe reported behavior under the study routine; it would not, on its own, establish a change in the clinical conditions listed in the record. Likewise, the posted secondary summaries cannot be taken as proof of a clinical effect, especially given the intervals, unadjusted comparisons and missing secondary results.

The results do not establish equivalence between the nozzles. Failure to show a clear difference is not the same as demonstrating that the groups are sufficiently similar. Equivalence or non-inferiority would require appropriate prespecified margins and analyses, which are not reported in the registry record.

The data also do not establish how broadly the findings apply. The registry provides a limited population description and does not report detailed eligibility criteria, participant characteristics or outcome distributions. Nor does it report how missing observations were handled. These limits affect interpretation of the posted comparisons and any attempt to generalize beyond the participants represented in each outcome summary.

The most defensible reading is descriptive: the registry reports group means, variability and unadjusted comparisons for adherence and two secondary outcomes. The primary comparison is uncertain, while the secondary evidence is partial. Conclusions about the intervention's effects on sleep-related health outcomes are not established by the posted summaries.

17. Why This Trial Matters Statistically

This trial illustrates why the identity of an endpoint matters in clinical research. Adherence and clinical outcomes answer different questions. Adherence describes whether participants met a behavioral target, while AHI, oxygen saturation and snoring measures address other aspects of the study question. A favorable or unfavorable pattern on one cannot automatically stand in for results on another.

It also demonstrates the importance of reading an estimate together with its uncertainty. The primary mean difference is not a complete result without its interval and p-value, and neither the interval nor the p-value alone gives a full account. The posted interval includes zero, while the group summaries show substantial variation. Statistical interpretation therefore requires attention to both the direction of the estimate and the range of values compatible with the analysis.

The record also highlights reporting questions that matter for reproducibility: the original sample-size rationale, analysis plan, missing-data approach, multiplicity strategy and analysis population are not reported. Such information helps readers distinguish a prespecified primary test from exploratory calculations and assess whether outcome-specific counts reflect missingness or other analysis choices.

Finally, planning illustrations based on an observed effect can help readers understand how sample size relates to target effect and power, but they are not evidence of the study's original design assumptions or observed power. For this completed study, the registry's concise summaries support a careful account of what was posted, while leaving important details of analysis and interpretation unresolved.

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 are specific to the available record. The primary endpoint is adherence to a water-consumption goal, rather than a direct sleep-related clinical outcome. It records the number of days the goal was met, but the registry does not describe how adherence was verified or whether the measure was self-reported or otherwise recorded. The record also does not report the water-consumption target itself.

The primary outcome group counts differ from the safety at-risk counts, and the secondary outcome counts vary by outcome. The registry does not explain these differences, identify participants with missing measurements, or describe how missingness was handled. Without that information, it is difficult to assess whether each comparison represents the same analysis population or whether missing data could have influenced the estimates.

Only two of the five listed secondary outcomes have posted results. In particular, results are not posted for myofunction assessment, snoring intensity or snoring frequency. The record does not explain whether these outcomes were measured, analyzed or omitted from reporting. This limits assessment of the complete outcome set and makes the available secondary findings less conclusive.

The registry does not report the original sample-size justification, prespecified statistical methods, primary testing threshold, multiplicity plan, confidence level for the posted intervals, or methods for handling unusual distributions. It also does not provide participant-level data or detailed baseline characteristics. These omissions constrain evaluation of the precision and robustness of the posted summaries. They do not show that the unreported methods were absent; they mean the details are not reported in the registry record.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Novel Myofunctional Water Bottle to Reduce OSA and Snoring Study — NCT05371509.
• Registry record last updated 2025-11-10; status last verified 2025-10.
• Results first posted 2025-11-10.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

22. Record Summary

The registry record describes a completed, randomized, double-masked, parallel-group study sponsored by Mayo Clinic, with enrollment of 43. It compared daily use of a water bottle with a myofunctional therapy nozzle against a placebo nozzle. The primary endpoint was mean days meeting a daily water-consumption goal during a 60-day timeframe.

The primary posted comparison showed a mean of 18.4 days in the myofunctional therapy nozzle group and 26.1 days in the placebo nozzle group. The unadjusted mean difference was -7.7 days, with an interval that includes zero and an unadjusted p-value of 0.119. Secondary results are posted for AHI change and oxygen-saturation change; three other listed secondary outcomes have no posted results.

The registry does not report the trial's original sample-size assumptions, full statistical plan, multiplicity approach or missing-data methods. The posted summaries describe uncertain group comparisons, not definitive evidence about clinical effects.