Personal Sound Amplification Smartphone Application Feasibility: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Personal Sound Amplification Smartphone Application Feasibility (NCT03652909), a registered phase not stated study. The primary outcome is Sentence Perception in Noise Fine-tuned v Unamplified.

2. Clinical Question

3. Trial Design

The registry identifies NCT03652909 as a completed feasibility study titled “Personal Sound Amplification Smartphone Application Feasibility.” The sponsor is the Medical College of Wisconsin. The recorded study start date is 2021-02-26, and the primary completion date is 2021-09-20. Enrollment is listed as 32, and the condition is hearing loss.

The intervention is a device named Ascending Hearing Technologies device. The arm description concerns patients listening to sounds with and without the personal sound amplification smartphone application. The primary outcome title compares sentence perception in noise in a fine-tuned condition with an unamplified condition. These descriptions identify listening conditions, but the registry record does not report a randomized allocation, and allocation is stated as not reported. The comparison should not be read as a randomized, like-for-like treatment contrast.

The primary outcome is a continuous measure: the percentage of words heard correctly. Its dispersion is specified as the standard deviation, and the stated timeframe is that the patient will wear the Personal Sound Amplification Device for approximately 30 minutes. The registry lists five outcome measures and three secondary outcome names: Words Clear, Sentences Easy to Understand, and Sounds Are Distorted. It lists zero analyses.

Information about the detailed study protocol, recruitment procedures, allocation process, masking, planned statistical analysis, and sample-size justification is not reported in the registry record. The enrollment figure is not an analysis denominator and does not show how many participants completed the listening assessment or contributed outcome data.

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: Not applicable. Enrollment and subject participation in the experiment occurred sequentially within the same study visit.

Overall Study

Analysis population for the primary outcome, as defined in the registry: All subjects

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 Sentence Perception in Noise Fine-tuned v Unamplified, measured over The patient will wear the Personal Sound Amplification Device for approximately 30 minutes.

The primary endpoint is sentence perception in noise, expressed as the percentage of words heard correctly. It is intended to capture speech understanding under the listening conditions named in the registry: fine-tuned personal sound amplification compared with an unamplified condition. The stated timeframe is a listening period of approximately 30 minutes wearing the device.

Word accuracy is a continuous outcome: participants can have different measured percentages rather than being assigned only to a yes-or-no category. A mean can describe the average performance in a condition, while a standard deviation describes how spread out individual measurements are around that mean. Those summaries can help readers understand both typical performance and variation between participants, provided the values and denominators are reported.

The endpoint is relevant to the stated question because it measures recognition of words in sentences against background noise. The registry’s outcome description says the fine-tuned device output will show a speech-perception benefit, but this is a stated expectation, not evidence that the endpoint changed. The registry record does not report the condition means, standard deviations, difference estimate, confidence interval, or test result. Without those results, the observed performance and the precision of the comparison cannot be evaluated.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary endpoint as a continuous measure summarized by a mean, with standard deviation as the dispersion measure. The outcome is the percentage of words heard correctly. In general, a mean describes the average observed performance, while a standard deviation describes variation among individual measurements. Reporting both can convey average performance and how consistent or dispersed the observations are. The registry record does not report either value for the listening conditions.

What would a condition contrast represent?

A comparison of the fine-tuned and unamplified conditions would estimate how word accuracy differs between those conditions in the assessed participants. The estimated difference would need to be accompanied by information about uncertainty, such as a confidence interval. In general, an interval helps distinguish a relatively precise estimate from one that remains compatible with a broad range of effects. The interval and the estimate are not reported in the registry record, so neither the size nor precision of a contrast can be described.

The registry’s title and description specify a fine-tuned-versus-unamplified question, while the arm description says patients listen with and without the application. However, the record explicitly characterizes the study as not randomized and says allocation is not stated. These details matter because random allocation, when used and properly implemented, can help balance other influences on a comparison. The record does not establish that such allocation occurred. It also does not report the ordering of listening conditions, so possible order or learning effects cannot be assessed from the registry entry.

What does the planning illustration assume?

The stated sample-size planning approach is an illustration based on the observed effect, not the study’s own design. It specifies a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is expressed as a stated fraction of the observed effect. Such planning scenarios describe the participants per arm that would be needed under their assumptions; they are not observed power and do not describe how many participants actually completed the study.

Planning calculations depend on an effect estimate and other assumptions. Because the registry record does not report the primary outcome estimate or its analysis, the numerical basis for an observed-effect planning illustration cannot be independently judged from this record. The stated planning assumptions should not be mistaken for a registered statistical analysis plan, or taken as evidence that the study was designed around those assumptions. The sample-size justification and the study’s statistical plan are not reported in the registry record.

Why does the nonrandomized comparison matter?

In general, results from repeated or paired listening conditions can be analyzed in ways that account for measurements from the same participant, while results from separate groups require methods suited to independent observations. The registry description does not establish the exact data structure, allocation process, or analysis method. It is therefore not possible to identify an appropriate analysis from the record alone or to say whether a within-participant comparison was used. The fact that the arm description refers to listening with and without the application does not by itself document pairing, order, or a statistical model.

For continuous outcomes, assumptions about the distribution and variability of measurements can affect uncertainty estimates and tests. If observations are more variable than a chosen model allows, uncertainty may be understated; general methods may need to account for that over-dispersion. The registry does not report the distribution of the endpoint, diagnostics, model, or any adjustment for unusual variation. This is a general methodological consideration, not a claim about the data in this study.

What analysis details are available?

The registry lists zero analyses. It does not report a test statistic, p-value, estimated effect, confidence interval, covariate adjustment, handling of repeated observations, or analysis population beyond the primary outcome label “All subjects.” That label does not establish how the endpoint was analyzed or how many participants had complete measurements. The record also does not report whether any interim analyses were planned or conducted. These omissions limit what can be inferred about the conduct and interpretation of the statistical analysis.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Personal Amplification")
n   <- c(32)
m   <- c(78)
sp  <- c(20)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Personal Amplification  32  78.000  20.000  70.789  85.211

11. Multiplicity, Missing Data and Analysis Populations

The registry lists five outcome measures, including the primary endpoint and three named secondary outcomes: Words Clear, Sentences Easy to Understand, and Sounds Are Distorted. It reports zero analyses. The record does not state how many comparisons were planned, whether additional outcomes were assessed, or whether a strategy was specified to address multiplicity. When several outcomes or contrasts are examined, the chance of finding a seemingly notable result can increase; in general, a prespecified analysis strategy helps readers understand how such results should be interpreted. No such strategy is reported in the registry record.

Missing-data handling is also not reported in the registry record. The entry does not give the number of participants with primary endpoint measurements, the reasons observations may be unavailable, or the method used to handle missing values. Enrollment of 32 does not establish the endpoint denominator. Without those details, it is not possible to determine whether the analyzed data represent all enrolled participants or to assess the potential effect of missing observations.

The primary outcome identifies its population as “All subjects.” This wording alone does not define an analysis population, confirm that all enrolled participants were included, or explain how incomplete measurements were treated. The statistical analysis plan, analysis populations, and missing-data procedures are not reported in the registry record.

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 lists a PSAD safety group with 32 at risk for serious adverse events and 0 affected. It also lists 32 at risk for other adverse events and 0 affected, with 0 deaths. No top serious adverse event terms are listed. These are the event counts recorded in the registry entry; they do not establish that adverse events were impossible or that none occurred outside the categories or reporting captured by the record.

Counts should be read in the context of the recorded group and the available follow-up. The entry does not describe the safety surveillance procedures, duration of safety follow-up, completeness of event reporting, or whether the at-risk counts represent everyone who received the device. The primary outcome timeframe concerns approximately 30 minutes of device use, but that endpoint timeframe alone does not define the safety follow-up period.

Zero recorded events should therefore be interpreted as no events reported in these registry categories, rather than proof of no risk. The registry record does not report further safety analyses or a detailed account of non-serious events.

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

The registry record documents a completed feasibility study of the Ascending Hearing Technologies device in adults with difficulty hearing in some daily listening situations. It describes a primary endpoint based on the percentage of words heard correctly during sentence perception in noise, comparing fine-tuned device output with an unamplified condition. This makes the intended measurement and listening contrast clear.

The record does not report results for that endpoint. It therefore cannot show whether word accuracy differed between conditions, the size or direction of any difference, or how precisely an effect was estimated. The outcome description’s expectation of a speech-perception benefit is not a reported finding. No statistical analysis is listed, and the methods used to analyze the outcome are not reported in the registry record.

The entry also states that the comparison was not randomized and that allocation is not stated. Consequently, even if a contrast were available from another source, this registry record would not support interpreting it as a randomized comparison. The record does not provide enough detail about the condition sequence or analysis to evaluate potential influences on a contrast.

The enrollment figure describes the registry’s enrollment, not the number with complete primary outcome data. The number analyzed and the handling of missing observations are not reported. Similarly, the recorded safety counts describe events listed in the registry categories and should not be taken as proof that no risk existed.

In statistical terms, the entry establishes the study question and selected outcome but not the evidence needed to estimate an outcome effect. It cannot support a conclusion about whether amplification changed sentence perception, nor about the clinical importance or certainty of any change. Those questions require outcome estimates, uncertainty measures, and transparent analysis details, none of which are reported in the registry record.

14. Why This Trial Matters Statistically

This study raises a useful measurement question: how to assess speech perception in noise when a personal sound amplification device is fine-tuned for a listener. The endpoint is expressed as the percentage of words heard correctly, a continuous measure that can preserve differences in performance rather than reducing the task to a simple pass-or-fail outcome. The stated use of a mean and standard deviation also signals an intention to describe both average performance and variability.

The record highlights why the design and analysis context matter alongside the endpoint. It describes listening with and without the application but explicitly says the study was not randomized and that allocation is not stated. A comparison between conditions therefore needs careful interpretation; the condition contrast alone does not establish that other influences were controlled. Details such as condition order, participant-level pairing, and the analysis method are not reported in the registry record.

The record also illustrates the difference between a feasibility study’s stated objective and evidence about an outcome. A completed study and a defined primary endpoint do not substitute for reported estimates and uncertainty. Without those results, readers cannot assess the magnitude, direction, or precision of a difference in word accuracy.

Finally, the entry names secondary measures and records safety counts, but provides no statistical analyses. This makes clear why transparent reporting of analysis populations, missing data, outcome estimates, and uncertainty is important: those details allow readers to distinguish what was planned, what was measured, and what the data support. The record identifies the topic and measurement framework, while leaving the statistical evidence unavailable.

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 main limitation for interpreting this trial record is the absence of reported primary outcome results. The registry identifies the measure and comparison but gives no condition summaries, estimated contrast, uncertainty interval, or test result. The record therefore cannot establish the observed speech-perception performance or its precision.

The study is explicitly described as not randomized, with allocation not stated. The registry does not explain how listening conditions were assigned or ordered, whether the same participants contributed measurements in both conditions, or how these features were handled analytically. This prevents assessment of possible order effects and the suitability of any comparison method.

The record lists enrollment of 32, but does not report the number with usable primary endpoint data or the reasons for any missing observations. It identifies the primary outcome population as “All subjects,” but does not define the analyzed population or report missing-data procedures. The statistical analysis plan and sample-size justification are also not reported in the registry record.

Five outcome measures are listed, with three secondary outcome names, but the record reports zero analyses. It does not explain how multiple outcomes or comparisons were handled. Safety entries list zero serious and other adverse events in the recorded categories and zero deaths; the duration and completeness of safety monitoring are not described. These gaps limit interpretation of both the effectiveness-related endpoint and the recorded safety information.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Personal Sound Amplification Smartphone Application Feasibility — NCT03652909.
• Registry record last updated 2023-02-03; status last verified 2023-01.
• Results first posted 2023-02-03.
• 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.

19. Record Summary

NCT03652909 is a completed feasibility study sponsored by the Medical College of Wisconsin. The registry lists hearing loss as the condition, enrollment of 32, a start date of 2021-02-26, and a primary completion date of 2021-09-20. The intervention is the Ascending Hearing Technologies device.

The primary endpoint is sentence perception in noise, measured as the percentage of words heard correctly, with standard deviation specified as the dispersion measure. The title contrasts fine-tuned sound with an unamplified condition, and the stated timeframe is approximately 30 minutes of device use. The study is identified as nonrandomized, with allocation not stated.

The registry lists five outcome measures, three secondary outcome names, and zero analyses. Primary outcome estimates, analysis details, missing-data methods, and the statistical plan are not reported in the registry record. The listed PSAD safety counts are 0 serious adverse events, 0 other adverse events, and 0 deaths.