Non Invasive Ventilation as Airway Clearance in Patients With Cystic Fibrosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Non Invasive Ventilation as Airway Clearance in Patients With Cystic Fibrosis (NCT02083263), a randomized na study. The primary outcome is Lung Function: Lung Clearance Index.

2. Clinical Question

The registry describes the study as examining non-invasive ventilation as an airway-clearance technique. Its brief summary says the intended focus was lung function (FEV1), while the named primary outcome is lung clearance index. The registry record does not explain this difference in outcome wording, so the posted primary result should be interpreted as a comparison of lung clearance index, not as a reported FEV1 result.

The question is about a group-level difference in a continuous measure. It does not, by itself, answer whether either technique changed an individual participant’s outcome, or whether any observed difference would be important to patients. The registry record does not report a threshold for a clinically meaningful difference or a separate interpretation of the endpoint’s clinical importance.

3. Trial Design

This was a randomized, parallel-group study with no masking reported. The registry lists 32 participants and shows 16 in the Bilevel group and 16 in the PEP Mask group. The study status is completed. The recorded study start was 2012-10, and primary completion was 2013-09.

Both groups were assigned a device-based airway-clearance approach for 3 months. The Bilevel description specifies treatment twice a day, 1 hour each time. The PEP mask description specifies the same schedule. The registry identifies Karolinska University Hospital as the sponsor. The phase is listed as NA.

Random allocation is stated, but the method used to generate the allocation sequence, whether allocation was concealed, and any procedures to maintain adherence are not reported in the registry record. Masking is listed as none; further details about who was aware of group assignment are not reported. The eligibility criteria and the precise recruitment setting are also not reported in the registry record, beyond the title’s description of adults with cystic fibrosis.

The named primary outcome was lung clearance index, measured through up to 3 months. A secondary outcome is listed as blood gases, in kPa, 1 month after chest physiotherapy. The registry records two outcome measures but posts no analysis records. The available group results therefore describe the posted primary outcome, while the registry record does not provide a detailed account of the analysis population or of results for the secondary outcome.

4. Participant Flow and Accounting

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

Overall Study

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Lung Function: Lung Clearance Index, measured over up to 3 months.

The primary endpoint is lung clearance index, a continuous measure reported as a mean with a standard deviation for each group. The registry defines it as the number of lung volume turnovers needed to reduce end-tidal nitrogen concentration to 1/40th of its starting value. Lung volume turnovers are calculated as cumulative expired volume divided by functional residual capacity. The stated timeframe is up to 3 months.

In general, a continuous endpoint retains information about the measured value across participants, rather than reducing the outcome to a category such as improved or not improved. Reporting a group mean describes the average observed value, while the standard deviation describes the spread of individual values around that mean. Those summaries answer different questions: a group mean is not a description of every participant, and a standard deviation is not an uncertainty interval for the mean.

The registry’s brief summary refers to better lung function (FEV1), but the named primary endpoint and posted numerical results are for lung clearance index. FEV1 results are not reported in the registry record. The record does not state why lung clearance index was selected, how it was expected to relate to the study’s stated aim, or what size of difference would be clinically important. Those omissions limit interpretation of the endpoint’s clinical meaning, even though its calculation is described.

7. Results Posted in the Registry

• PEP Mask: mean 9.70 versus 9.00 on control; difference 0.70 (95% CI -1.38 to 2.78), standardized effect d = 0.23; z-test p = 0.509.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous, and the registry reports a mean and standard deviation for each group. In general, the mean is the arithmetic average of measured values. It provides a concise description of the group’s central value, but it can conceal variation between participants and does not show the shape of the underlying distribution. The standard deviation describes how dispersed the observations are around the group mean. It is not the same as a confidence interval, which addresses uncertainty about an estimate.

What does the mean difference represent?

The reported contrast is PEP Mask relative to Bilevel. The PEP Mask mean is 9.7 and the Bilevel mean is 9.0; the reported mean difference is 0.7. In general, a difference between group means describes the observed separation in their averages on the endpoint’s original scale. Its sign depends on the order of the groups in the contrast. Here, a positive value corresponds to a higher posted mean in PEP Mask than in Bilevel. This description is about the direction of the numerical comparison, not whether the direction is beneficial.

The standard deviation is 3.0 in each group. Equal reported standard deviations do not imply that every participant had the same value or that the distributions were identical. The registry does not post participant-level data, so the shape, outliers, and any clustering of values cannot be assessed. Nor does the record explain whether the chosen analysis accounted for any features of the data beyond the group summaries.

How should the interval and p-value be understood?

A confidence interval expresses uncertainty around an estimate under the method used to construct it. In general, a narrower interval indicates greater precision, while a wider interval leaves a broader range of values compatible with the data and method. The interval reported for the mean difference extends from -1.379 to 2.779. It includes zero and values of either sign. The confidence level and the exact interval method are not reported in the registry record, so they should not be inferred from the displayed endpoints.

The unadjusted p-value is 0.509. In general, a p-value is calculated under a statistical model that represents a specified null hypothesis. It measures how compatible the observed data are with that model, using a test statistic and its reference distribution. It is not a measure of effect size, the probability that the null hypothesis is true, or a measure of clinical importance. The exact test, its assumptions, and the significance threshold used for the trial’s primary analysis are not reported in the registry record. The planning illustration separately states a two-sided significance level of 0.05; that planning assumption does not establish the trial’s original analysis plan.

What does the standardized effect add?

The comparison record gives a standardized effect value of 0.233 and a pooled standard deviation of 3.0. In general, standardizing a mean difference expresses it in units of variability rather than in the endpoint’s original units. This can help describe relative magnitude, but it does not itself indicate clinical importance. The record does not provide a threshold for interpreting the standardized value, and it should not be treated as a clinical decision rule.

Why might variation matter?

General statistical explanation: when observations vary more widely, a group mean can be estimated less precisely for a fixed amount of information. Some outcomes can also show more variation than a simple model assumes, a property often called over-dispersion. If a method fails to account for excess variation, its uncertainty estimates may be too narrow. That general concern cannot be assessed from the registry summaries alone. The endpoint is presented as a continuous measure, and the registry does not report whether the investigators checked distributional assumptions, assessed over-dispersion, or used a method designed for unusual distributional features.

The record reports no analysis records, and it does not detail adjustment variables, handling of missing outcomes, or analysis populations. The displayed group comparison can be described as posted, but its full analytical provenance is not available in the registry record. In general, an unadjusted group comparison estimates a contrast without accounting for covariates; whether that description exactly matches the trial’s original model is not reported. No additional model details should be inferred from the means, standard deviations, interval, or p-value alone.

10. Confidence Intervals and Precision

The reported mean difference is 0.7 for PEP Mask relative to Bilevel, with a confidence interval from -1.379 to 2.779. That interval is wide enough to include a range of possibilities on both sides of zero. It therefore conveys uncertainty about both the direction and magnitude of the group contrast. The point estimate is only one value within that broader range of values compatible with the reported interval method.

In general, a confidence interval is a way to express precision: it shows how much uncertainty surrounds an estimate under the statistical method used. It does not mean that every value in the interval is equally plausible, and it is not a range containing individual participant outcomes. The confidence level and construction method are not reported in the registry record, so no confidence percentage should be assigned to these endpoints without further information.

The number of participants reported in each arm is 16. The registry provides no participant-level data, outcome-completion counts, or account of exclusions from the analysis. Consequently, it is not possible to assess how missing observations, if any, affected the estimated precision. The equal group standard deviations of 3.0 describe observed spread, not the precision of the estimated difference by themselves.

The interval’s inclusion of zero means the posted estimate does not distinguish a positive contrast from a negative one at the level represented by that interval. The record does not report a clinically important difference threshold, so it is also not possible to determine whether parts of the interval would represent negligible or important differences. Precision and clinical importance are separate considerations: even a precisely estimated difference would need a clinical benchmark for interpretation, and this record does not give one.

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 planning illustrations based on fractions of the observed effect, rather than the trial’s original design calculations. The assumptions stated for the illustration are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is the stated fraction of the observed effect. The trial’s own original sample-size assumptions and justification are not reported in the registry record.

For planning at 100% of the observed effect, the illustration gives 289 participants per arm for 80% power and 386 participants per arm for 90% power. At 75% of the observed effect, it gives 513 participants per arm for 80% power and 687 participants per arm for 90% power. At 50% of the observed effect, it gives 1,154 participants per arm for 80% power and 1,544 participants per arm for 90% power.

In general, power is the probability that a study will detect an effect of a specified size under the assumed model and design, if that effect is present. The 80% and 90% columns describe different planning targets: the higher target requires more participants for the same assumed effect. Smaller effects are harder to distinguish from random variation, so the illustration requires more participants as the target effect becomes smaller.

These figures are not observed power. They are prospective planning illustrations using the observed effect as their starting point. Because the observed estimate itself is uncertain, the resulting participant counts depend on that estimate and the stated assumptions. They should not be read as evidence about the trial’s actual design intent or as a retrospective measure of the trial’s success.

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 = 0.700; pooled standard deviation σ = 3.000.
2. n = 2 × (1.96 + 0.842)² × 3.000² / 0.700² = 288.3, rounded up to 289 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 <- 0.699999999999999                      # observed difference in means
sigma <- 3                     # 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(2083263)
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 = 289 (80% power), 386 (90% power)
 75% of observed effect: n per arm = 513 (80% power), 687 (90% power)
 50% of observed effect: n per arm = 1,154 (80% power), 1,544 (90% power)
power.t.test: 289.3 
Simulated power at n = 289 per arm: 0.794 (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 lists two outcome measures: the primary lung clearance index outcome and a secondary blood-gases outcome. The named secondary measure is blood gases in kPa, 1 month after chest physiotherapy. Numerical results for that secondary outcome are not reported in the registry record. The registry lists no analysis records, so it does not give a complete account of which outcomes were analyzed or how results were handled.

Multiplicity arises in general when investigators make several statistical comparisons or assess several outcomes. Repeated testing can increase the chance of obtaining at least one apparently notable result by chance. A planned approach may control or otherwise address that issue, but the registry record does not report whether any multiplicity strategy was specified or used. The unadjusted p-value for the primary comparison is 0.509; the record does not state whether it was part of a broader testing procedure.

Missing-data methods are not reported in the registry record. The group counts are 16 for Bilevel and 16 for PEP Mask, but those counts alone do not establish whether all participants had primary outcome measurements or whether any values were excluded. The record does not describe imputation, complete-case analysis, sensitivity analyses, or reasons for missing measurements. It also does not state whether the analysis followed an intention-to-treat principle or another population definition.

In general, the analysis population matters because the estimated contrast can depend on which randomized participants are included and how missing outcomes are handled. Without these details, the posted summary statistics cannot establish the exact population represented by the comparison. The registry record also does not report protocol deviations or how they were treated analytically. These omissions limit assessment of the analysis process; they do not establish that any particular problem occurred.

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 figures list 16 participants at risk in each group and zero participants affected by serious adverse events in each group. The other adverse event figures likewise list 16 at risk and zero affected in each group. No serious adverse event terms are listed.

These figures describe the counts recorded in the registry. They should be read as counts of affected participants, not as proof that no event of any kind occurred. The registry record does not provide further detail on event definitions, collection procedures, severity categories beyond the serious-event label, or follow-up completeness. Death counts are not reported in the registry record.

Zero recorded affected participants in these categories does not allow a precise comparison of safety between groups, particularly with 16 participants in each arm. The record also does not provide event-level descriptions or an account of whether events were judged related to a device or treatment. The posted counts therefore summarize the safety information available in the record without establishing a broader safety conclusion.

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

The result is a comparison of mean lung clearance index between the Bilevel and PEP Mask groups through up to 3 months. The posted means were 9.0 and 9.7, respectively, and the reported mean difference was 0.7 for PEP Mask relative to Bilevel. The confidence interval, -1.379 to 2.779, includes both negative and positive values. The unadjusted p-value was 0.509. Together, these statistics show an estimate with substantial uncertainty about the direction and magnitude of the difference.

The result does not establish that the two approaches are equivalent. Equivalence requires a prespecified margin and an analysis designed to assess whether the difference lies within that margin; neither is reported in the registry record. Nor does the result establish that one approach is superior. The record does not report a clinically meaningful difference threshold, so statistical summaries cannot determine whether the estimated contrast matters to patients.

The numerical outcome is lung clearance index, not FEV1, despite the reference to FEV1 in the brief summary. The registry does not report numerical FEV1 results. Blood gases are listed as a secondary outcome, but their results are also not reported in the registry record. Thus, the posted primary comparison cannot answer questions about those other measures.

The record describes a randomized, parallel-group study with no masking, but key details of randomization, outcome completeness, analysis populations, and statistical methods are not reported. The available summaries do not show individual measurements or trajectories. The results should therefore be understood as a limited statistical description of the posted group comparison, rather than as a complete assessment of treatment effects, clinical benefit, or safety.

16. Why This Trial Matters Statistically

This trial illustrates how the endpoint named in a registry record can differ from the outcome emphasized in a brief summary. The stated primary outcome is lung clearance index, while the brief summary mentions FEV1. Keeping those measures distinct is important: a numerical result for one cannot be taken as a result for the other. The registry record does not explain the difference, and it does not post FEV1 results.

The comparison also demonstrates why an estimate and its uncertainty should be read together. The mean difference is 0.7, but the interval runs from -1.379 to 2.779. The estimate’s direction alone gives an incomplete picture; the interval indicates that the data do not tightly determine the direction or size of the group contrast. The unadjusted p-value adds a test summary, but does not replace the effect estimate, interval, or assessment of clinical importance.

Reporting the group means, standard deviations, group counts, and contrast makes several basic features of the primary result visible. At the same time, the record leaves important statistical questions unanswered, including the confidence interval method, analysis population, missing-data approach, and multiplicity plan. Recognizing those limits helps prevent a concise registry result from being treated as a complete statistical report.

The planning illustration further shows how sample-size calculations depend on the assumed effect size and target power. Its figures are not the trial’s original design assumptions or a retrospective measure of power. This distinction is useful when interpreting small studies: planning quantities are conditional on assumptions, while observed results carry uncertainty of their own.

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 record identifies randomized allocation and no masking, but does not report how the random sequence was generated or whether allocation was concealed. It also does not describe participant eligibility criteria in detail, recruitment procedures, adherence, or deviations from the assigned treatment schedules. These details are relevant to judging how the comparison was implemented, but their absence from the record does not establish that procedures were inadequate.

The primary outcome description gives a timeframe of up to 3 months, while the treatment schedules specify 3 months. The registry does not further explain when measurements were taken within that timeframe or whether repeated measurements were collected. It also does not provide a protocol-level explanation for emphasizing FEV1 in the brief summary while naming lung clearance index as the primary outcome. Numerical FEV1 results are not reported.

The posted comparison includes 16 participants per group, but the record does not state the number with observed primary outcomes, the analysis population, or how missing data were handled. It does not report the confidence level or method for the interval, the exact test behind the p-value, or any prespecified adjustment for covariates or multiple testing. Because no analysis records are listed, the statistical plan and the relationship between the posted summaries and the original analysis are not detailed.

The registry lists blood gases as a secondary outcome but does not report numerical results for it. The adverse-event summaries report zero affected participants in the listed categories, while death counts and further event details are not reported in the registry record. Finally, no clinically meaningful difference threshold is stated. These limitations constrain interpretation of the posted estimates and their relevance; they do not by themselves show that the study’s conduct or results were invalid.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Non Invasive Ventilation as Airway Clearance in Patients With Cystic Fibrosis — NCT02083263.
• Registry record last updated 2014-07-16; status last verified 2014-07.
• Results first posted 2014-07-03.
• 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

NCT02083263 is a completed randomized, parallel-group study sponsored by Karolinska University Hospital. The registry lists 32 participants, with 16 in each group, and no masking. Bilevel and PEP mask were each used for 3 months, twice a day for 1 hour each treatment.

The primary outcome is lung clearance index through up to 3 months. The reported mean was 9.0 for Bilevel and 9.7 for PEP Mask, with a mean difference of 0.7 for PEP Mask relative to Bilevel. The confidence interval was -1.379 to 2.779, and the unadjusted p-value was 0.509. The registry lists blood gases as a secondary outcome but does not report its numerical results.

Serious and other adverse-event summaries each list zero affected participants in both groups; death counts are not reported in the registry record. The registry does not report the detailed statistical plan, analysis population, missing-data methods, or clinical-importance threshold.