Fitting Strategy Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Fitting Strategy Study (NCT04972162), a randomized na study. The primary outcome is Abbreviated Profile of Hearing Aid Benefit (APHAB).

2. Clinical Question

3. Trial Design

The Fitting Strategy Study was a randomized, double-masked crossover device study. The registry lists an enrollment of 28 and the condition as sensorineural hearing loss. The study status is completed; the listed start date is 2021-07-26 and the primary completion date is 2021-11-12. The phase is listed as not applicable.

A crossover design means that participants receive each of the fitting strategies in sequence, rather than being assigned to only one strategy throughout the study. The registry describes two sequences: Web-App fitting followed by standard-of-care fitting, and standard-of-care fitting followed by Web-App fitting. Participants had a 14-day home trial for each fitting type, with a 5-day washout period between them. This arrangement allows the within-participant comparison to account for some stable differences between people, while making the interpretation dependent on the sequence and timing of measurements.

Randomization assigned participants to the order of the fitting strategies. Double masking is listed, but the registry record does not specify which people were masked or how masking was maintained in a study where one fitting involved self-fitting and the other involved a hearing care professional. The record also does not report details of sequence allocation, adherence, period effects, or how the analysis handled the crossover structure.

The sponsor is WSAUD A/S. The registry describes the study as validating the Web App fitting strategy by measuring participants’ perceived hearing-aid benefit under both fitting approaches. The trial’s design and stated objective are reported, but the posted record does not contain a single numerical primary endpoint comparison that would support a summary of the observed contrast.

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.

First Intervention (14 Days)

Washout Period (5 Days)

Reasons for not completing this period:

Second Intervention (14 Days)

Analysis population for the primary outcome, as defined in the registry: All participants who completed the study visits were included in the efficacy analysis. The intention to treat (ITT) population includes 2 subjects who withdrew from study. It was concluded that their primary endpoint data was missing for cause and their APHAB benefit scores (change from baseline) was imputed as 0 for each subscale

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 Abbreviated Profile of Hearing Aid Benefit (APHAB), measured over 14-17 Days hearing aid wearing time per fitting type.

The primary endpoint is the Abbreviated Profile of Hearing Aid Benefit, or APHAB. It is a self-reported measure of hearing difficulties in daily situations. The instrument has 24 questions across four subscales: Ease of Communication, Background Noise, Reverberation, and Aversiveness. Responses describe the percentage of problems, with 100% representing the highest number of problems.

For each subscale, the benefit score is calculated by subtracting the reported percentage of problems with a hearing aid from the percentage without a hearing aid. The resulting score ranges from 0, indicating no benefit, to 100, indicating maximum benefit. The study focuses on the communication subscales: Ease of Communication, Background Noise, and Reverberation. It compares benefit scores after Web-App fitting and standard-of-care fitting.

The registry describes the difference-in-benefit scores as ranging from -100 to 100. Negative values indicate greater benefit with Web-App-fitted hearing aids, zero indicates identical benefit, and positive values indicate greater benefit with standard-of-care fitting. This direction is important when interpreting any reported estimate. The registry record does not provide the numerical scores or a single primary comparison, so the size and precision of the observed difference cannot be described.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a continuous endpoint summarized as a mean with standard deviation. A mean represents the average score in a group or condition, while the standard deviation describes how spread out participant scores are around that mean. These are descriptive summaries. On their own, they do not show the uncertainty in a comparison between fitting strategies or establish whether a difference is compatible with no difference or with a clinically relevant margin.

What does a confidence interval add?

General explanation: a confidence interval expresses the uncertainty around an estimated comparison under the statistical model used. A narrower interval indicates greater precision, while a wider interval indicates less precision. For a non-inferiority question, the estimate and its interval are interpreted relative to a prespecified margin and the endpoint’s direction. The registry record does not report the primary estimate, its confidence interval, or the specific non-inferiority margins, so those interpretations cannot be made for this trial from the reported details.

Why does the crossover structure matter?

General explanation: in a crossover study, each participant experiences more than one condition. A suitable comparison may account for the pairing of observations within a participant, because measurements from the same person are generally not independent. The order of treatment periods and possible period or carryover effects can also matter. A washout period is intended to separate periods, but its presence alone does not demonstrate that carryover is absent. The registry reports randomized order and a 5-day washout, but does not report the statistical model or the results of checks for sequence, period, or carryover effects.

The registry record lists six analyses, but the registry entries do not describe their specifications or identify which analysis produced a primary estimate. It would therefore be inappropriate to infer whether the analysis used a paired comparison, adjusted for sequence, accounted for repeated measures, or used another approach. The statistical plan is not reported in the registry record.

What does over-dispersion mean?

General explanation: over-dispersion occurs when observed variability is greater than a statistical model assumes. It is especially relevant for some count outcomes, where a model that understates variability can make uncertainty appear too small. The APHAB endpoint is continuous and summarized by a mean and standard deviation. The registry entries do not report whether any model diagnostics or alternative variance assumptions were used, and over-dispersion should not be presumed to be an issue for this endpoint.

How should non-inferiority be assessed?

General explanation: a non-inferiority analysis evaluates whether the data are sufficiently compatible with a prespecified acceptable loss relative to a comparator. The interpretation depends on the scale and direction of the endpoint, the margin, the estimated contrast, and the uncertainty around that contrast. The endpoint description states that difference-in-benefit scores below zero favor the Web-App fitting strategy and scores above zero favor standard-of-care fitting. However, the numerical margins and inferential results are not reported in the registry record. Consequently, the record’s mention of margins does not establish whether a non-inferiority criterion was met.

The outcome is reported as a mean of a continuous measure, but the record does not specify whether the main comparison was based on raw scores, change from baseline, or another quantity. The population description mentions APHAB benefit scores and change from baseline, but is truncated before fully describing the analysis. No additional analytical details should be inferred from that incomplete statement.

What can be concluded from the posted methods information?

The study design, measurement instrument, endpoint direction, and general analysis population descriptions are available. The numerical primary comparison and the statistical methods needed to assess precision and non-inferiority are not reported in the registry record. General statistical principles can clarify what those missing elements would mean, but cannot substitute for the trial’s analysis results.

10. Multiplicity, Missing Data and Analysis Populations

The registry describes the primary outcome across three communication subscales and notes that the outcome involves several categories or time points, rather than one comparison reduced to a single result. It also lists six analyses. The registry entries do not specify which analyses correspond to which subscales or time points, whether any analyses were primary or secondary, or whether the results were adjusted for multiple comparisons. A multiplicity procedure or hierarchy is not reported in the registry record.

General explanation: when several outcomes or comparisons are tested, the chance of at least one apparently notable result can increase if each is evaluated independently. Procedures such as prespecified hierarchies or adjustments can address that issue, but the approach must be stated to interpret the evidence. No such approach is described in the available the registry entries, so it should not be assumed that an adjustment was or was not used.

The population description says that all participants who completed study visits were included in the efficacy analysis. It also states that the intention-to-treat population included 2 participants who withdrew and that their primary endpoint data were missing for cause. The registry statement ends before fully describing the handling of their APHAB benefit scores. Details about imputation, exclusion, sensitivity analyses, and the relationship between the efficacy and intention-to-treat populations are not reported in the registry record.

Missing-data assumptions can affect interpretation, particularly when the reason for missingness or the values that would have been observed are uncertain. General explanation: an analysis using only available endpoint data relies on assumptions about how those observed data relate to missing outcomes; different assumptions can lead to different estimates. The registry entries do not identify the assumptions or methods used. Thus neither the impact of missingness nor the robustness of the analysis can be assessed from the record.

11. 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 reports no serious adverse events and no deaths in either fitting group. For the Web App Fitted Hearing Aids group, the number at risk for serious events is 28 and the number affected is 0; the number at risk for other events is 28 and the number affected is 0; deaths are 0. For the Standard-of-care Fitted Hearing Aids group, the corresponding reported values are 28 at risk and 0 affected for serious events, 28 at risk and 0 affected for other events, and 0 deaths.

These are the posted safety counts for the two fitting groups. A zero count means that no event was recorded in that category in the registry results; it does not establish that an event is impossible or that the fitting strategies have identical safety profiles. The record does not report further detail about event definitions, event collection, duration of observation for safety, or statistical comparisons. Because the study uses a crossover design, the group labels refer to fitting types rather than necessarily representing separate sets of participants throughout the study. The registry record does not provide more detail about how safety exposure was handled across periods.

The counts should therefore be read as descriptive registry results, not as a formal estimate of comparative risk. The registry entries do not support a broader safety conclusion.

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

The registry record describes a study designed to compare participants’ perceived hearing-aid benefit after Web-App fitting and standard-of-care fitting. It identifies a randomized, double-masked crossover design, an APHAB-based endpoint focused on communication subscales, and the direction in which a difference-in-benefit score would be interpreted. It also reports the safety counts and selected details about the study population and fitting periods.

Those details explain what the study set out to measure, but they are not a substitute for the numerical efficacy result. The registry record does not report a single primary endpoint estimate, confidence interval, p-value, or the specific non-inferiority margins. It is therefore not possible to state which fitting approach had greater observed benefit, how large any observed difference was, how precise that difference was, or whether a non-inferiority criterion was satisfied.

The endpoint description also does not establish that results were the same across the Ease of Communication, Background Noise, and Reverberation subscales. The record indicates that the outcome has multiple categories or time points, but does not give the corresponding numerical results. The six analyses listed in the record are not described in enough detail to determine their relationship to a primary comparison or to assess multiplicity.

General explanation: a study’s objective and design describe the question and how it was approached; an estimate and its uncertainty describe what the observed data say about that question. In this record, the design and measurement description are available, whereas the numerical primary comparison is not. The absence of that comparison in the registry record should not be interpreted as evidence for either fitting strategy.

The safety counts show zero recorded serious adverse events, other adverse events, and deaths in the listed groups. These counts are descriptive and do not establish equal risk or rule out events beyond the recorded study experience. The study’s reported information should be read within these limits.

13. Why This Trial Matters Statistically

This study raises a useful statistical question about comparing two fitting strategies when participants can experience both. A randomized crossover design can support a within-participant comparison, which may reduce the influence of stable differences between participants. At the same time, the design requires attention to treatment order, period effects, and possible carryover. The registry reports randomized sequences and a washout, but does not report the analysis details needed to see how those features were handled.

The endpoint also illustrates that a clinical outcome may be represented by several related subscales rather than one simple score. Here, the study focuses on communication-related APHAB subscales and describes a direction-specific difference in benefit. The specific subscale results and a single primary comparison are not reported in the registry record, making it important to distinguish an endpoint definition from an observed result.

Non-inferiority questions require especially clear reporting. A reader needs the margin, the estimate, its uncertainty, and the analysis approach to understand whether the data support the stated comparison. The registry describes the use of margins but does not report their numerical values or the result. That gap prevents a statistical assessment of the non-inferiority question.

The record also mentions withdrawals and missing endpoint data, while leaving the handling details incomplete. This highlights the importance of explaining analysis populations and missing-data methods, particularly when a trial’s primary outcome is based on participant-reported measures. Clear reporting of the comparison, uncertainty, multiplicity approach, and missing-data handling would help readers assess the evidence without having to infer how the analysis was conducted.

14. 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 central limitation for interpreting efficacy is that the registry record does not report a single numerical primary endpoint comparison. The endpoint is described across several communication subscales, but their estimates and uncertainty are not reported in the registry record for this account. The record therefore does not support a conclusion about the direction or magnitude of the observed difference.

The registry mentions non-inferiority margins but does not report their values, the primary estimate, or its confidence interval. It also does not state the statistical model or other inferential methods used. These omissions prevent an evaluation of whether the result met a non-inferiority criterion and how precise the estimate was.

The trial’s crossover design makes information about sequence, period, and carryover effects relevant. Randomization, the two treatment sequences, and a washout period are described, but period-specific results and the approach to accounting for these design features are not reported in the registry record. The record also does not describe which individuals were masked or how masking was implemented.

The analysis population description is incomplete. It says that participants completing study visits were included in the efficacy analysis and that the intention-to-treat population included 2 withdrawals with primary endpoint data missing for cause. The available description ends before explaining how those missing values were handled. The record does not report a missing-data method or sensitivity analyses.

Finally, the record lists six analyses and identifies multiple outcome categories or time points, but does not describe the analysis hierarchy or any multiplicity adjustment. These reporting gaps limit assessment of the results and the robustness of the statistical interpretation.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Fitting Strategy Study — NCT04972162.
• Registry record last updated 2025-09-30; status last verified 2025-09.
• Results first posted 2025-09-30.
• 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.

18. Record Summary

The Fitting Strategy Study is a completed randomized, double-masked crossover device study sponsored by WSAUD A/S. The registry lists enrollment of 28 and describes adults with mild-to-moderate sensorineural hearing loss using Web-App-fitted and standard-of-care-fitted hearing aids in randomized order. Each fitting period included a 14-day home trial, with a 5-day washout between periods.

The primary endpoint is APHAB benefit, focused on Ease of Communication, Background Noise, and Reverberation. The record defines the direction of the difference-in-benefit score but does not report a single numerical primary comparison, its precision, or the stated non-inferiority margins. It notes 2 withdrawals in the intention-to-treat population, with primary endpoint data missing for cause; further handling details are not reported in the registry record. The listed safety results report no serious adverse events, other adverse events, or deaths in either fitting group.