The Esteem® Hearing Implant Post Approval Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Esteem® Hearing Implant Post Approval Study (NCT02666222), a registered phase not stated study. The primary outcome is Change From Baseline (Pre-implant Aided Condition) at Year 5 in Speech Reception Threshold (SRT).

2. Clinical Question

3. Trial Design

The record identifies NCT02666222 as the Esteem® Hearing Implant Post Approval Study. Envoy Medical Corporation is listed as the sponsor. The study is marked completed, with a recorded start of 2010-08 and primary completion of 2014-08. Its stated purpose was to evaluate long-term safety and efficacy in subjects suffering from moderate to severe hearing loss.

The listed intervention is the Esteem Hearing Implant, classified as a device. The registry record gives an enrollment of 51. That figure describes enrollment, not necessarily the number with a Year 5 measurement or the number included in a particular analysis. Follow-up participation and endpoint-specific analysis populations are not reported in the registry record.

The primary outcome is a continuous measure: change from baseline, defined as the pre-implant aided condition, in speech reception threshold at Year 5. The recorded unit is dB, and the endpoint timeframe is baseline through Year 5 of follow-up. The record also lists a secondary outcome concerning quality of life as reflected by the Abbreviated Profile of Hearing Aid Benefit questionnaire.

Allocation is not stated, and the record does not describe a randomized comparison. No like-for-like control comparison is specified. The pre-implant aided condition supplies the endpoint's baseline reference; it should not be mistaken for a concurrently assigned control arm. The registry record does not report a detailed protocol, analysis populations, or the procedures used to collect follow-up measurements.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: 5 Year Follow-up

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 Change From Baseline (Pre-implant Aided Condition) at Year 5 in Speech Reception Threshold (SRT), measured over Baseline through Year 5 of Follow Up.

The primary endpoint is change in speech reception threshold from the pre-implant aided baseline to Year 5. The registry definition calculates this as baseline SRT minus Year 5 SRT and records the measure in dB. It specifies that a positive difference, corresponding to a lower SRT with the Esteem, indicates a better outcome.

A continuous endpoint retains information about the measured value rather than reducing it to a category such as improved or not improved. That can be useful when the scientific question concerns the amount of change in a hearing-related measure. The baseline reference also makes the comparison within the endpoint explicit: the Year 5 value is interpreted relative to the pre-implant aided condition.

The registry lists the endpoint parameter as a mean and its dispersion as a standard error. In general, a mean describes the central value of a set of measurements, while a standard error describes the uncertainty around an estimated mean. These are different quantities: the standard error is not the spread of individual measurements. The registry record does not report the endpoint mean, standard error, confidence interval, or analysis result, so the magnitude and precision of any observed change cannot be assessed from the posted record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a continuous primary endpoint summarized by a mean, with standard error as the dispersion measure. That description identifies the type of outcome summary, but it does not specify the full statistical procedure used to estimate or test the endpoint. The record lists no analyses. The distinction matters: an outcome definition is not the same as a statistical analysis plan, and neither reveals a numerical result on its own.

What does a mean summarize?

For a continuous measure, a mean is an average of the observations included in an analysis. Here, the intended measure is the difference between baseline SRT and Year 5 SRT for the pre-implant aided baseline and follow-up described in the registry. If a mean change were reported, its interpretation would follow the stated subtraction direction: positive values correspond to lower SRT at Year 5 and are described as a better outcome. The registry record does not give the mean or identify the endpoint analysis population.

What does the standard error convey?

In general, the standard error describes the uncertainty in an estimated mean. It is not the same as the standard deviation, which describes variation among individual measurements. A small standard error does not mean that individual participants had similar outcomes; it indicates greater precision of the estimated mean under the statistical method used. The record names standard error but does not post its value or the method by which it was calculated.

How would a confidence interval help?

In general, a confidence interval expresses uncertainty around an estimate by presenting a range derived using a specified method. Readers can use that range to assess which effect sizes are compatible with the data and how precise the estimate is. A confidence interval does not establish that an effect is clinically important, and it does not remedy limitations in study design or missing data. The registry record does not report a confidence interval for the primary endpoint.

Why does the comparison structure matter?

The endpoint compares Year 5 with a pre-implant aided baseline. This is a within-person time reference as described by the endpoint, not evidence of a separate concurrent control group. The record states that allocation is not stated and does not describe a randomized comparison. Without a described control comparison, a change from baseline cannot isolate the contribution of the device from other influences that may occur over follow-up. This is a general limitation of interpreting pre/post change, not a claim about what caused any particular result in this study.

What role do distributional assumptions play?

General methods for continuous outcomes may rely on assumptions about the distribution of measurements or estimated effects. Those assumptions affect standard errors, confidence intervals, and tests. The registry record does not state which method was used or report diagnostic checks, so it is not possible to assess those assumptions for this endpoint. A method should not be inferred solely from the fact that the endpoint is continuous or that a mean and standard error are named.

What does over-dispersion mean in general?

Over-dispersion refers to variability greater than a statistical model expects. It is particularly relevant in models for counts or rates, where an overly restrictive variance assumption can make uncertainty estimates too small. The primary endpoint in this record is a continuous mean, not a listed count outcome, and the registry does not identify an over-dispersion model. The concept is useful generally but should not be presented as a feature of this study's primary analysis.

How should planning illustrations be read?

In general, a sample-size planning illustration based on an observed effect asks how much information a future study might need under stated assumptions. The assumptions recorded for this study's planning illustration are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the target effect is a stated fraction of the observed effect. Such an illustration is not the study's original design justification and is not observed power. The registry record does not report numerical planning estimates, and the primary endpoint result needed to interpret an observed-effect-based illustration is not posted in the record.

For sample-size planning, the distinction between participants per arm and total events is also important in general. The recorded planning description says that time-to-event outputs refer to total events, while other outputs refer to participants per arm. This primary outcome is continuous, but no numerical planning estimate for it is reported in the registry record. Planning figures, where available, should be understood as conditional illustrations rather than as evidence that the completed study had a particular probability of detecting an effect.

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("Esteem Implant")
n   <- c(49)
m   <- c(4.8)
sp  <- c(2)
sd  <- sp * sqrt(n)      # standard errors converted to SDs
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  Esteem Implant  49  4.800  14.000  0.779  8.821

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists five outcome measures and identifies speech reception threshold change at Year 5 as the primary outcome. It also names a secondary quality-of-life outcome based on the Abbreviated Profile of Hearing Aid Benefit questionnaire. The record does not provide a complete description of the other outcome measures or state how results across outcomes were handled statistically.

In general, multiplicity arises when several outcomes, time points, or statistical tests are examined. Repeated testing can increase the chance of finding an apparently notable result even when no corresponding effect exists. Analysis plans may address this through prespecification, adjustment, or a hierarchy of outcomes. The registry record does not report a multiplicity procedure, so no adjustment or hierarchy beyond the identification of the primary outcome should be assumed.

Missing data are also important for a Year 5 endpoint. Participants may lack follow-up measurements, and different approaches to incomplete data can lead to different estimates. The registry record does not state how many participants contributed endpoint data, how missing measurements were handled, or whether any sensitivity analyses were performed. Enrollment of 51 does not establish the endpoint analysis size.

The record lists no posted analyses. It does not define an intention-to-treat, per-protocol, safety, or other analysis population for the primary endpoint. Nor does it report a statistical analysis plan that could clarify these choices. These omissions limit assessment of the endpoint's estimation and of the potential influence of missingness or multiple analyses; they do not establish that any particular problem occurred.

12. 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.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: death (3.9%), sore behind ear (2.0%), exposed leads (2.0%), infected implant site (2.0%), gall bladder removal surgery (2.0%).

The registry lists an Esteem Implant group with 51 at risk for serious adverse events and 14 affected by serious adverse events. It separately lists 51 at risk for other adverse events and 42 affected. These are registry counts for the categories as recorded; the record does not explain whether the people represented in one category also appear in the other. The counts should not be added to infer a number of distinct participants.

The listed serious-event terms include Death at 3.9%, Sore behind ear at 2.0%, Exposed Leads at 2.0%, Infected Implant Site at 2.0%, Gall bladder removal surgery at 2.0%, and Multiple sclerosis at 2.0%. These are term-level entries in the safety record. The record gives deaths as null in the separate deaths field, so that field does not provide a death count. The Death term and the null deaths field should be reported as recorded rather than reconciled through speculation.

Adverse-event counts describe events recorded during the study; they do not, by themselves, establish causation. The registry record does not provide event timing, duration, severity definitions, relatedness assessments, or a comparison group. The figures therefore describe the posted safety data but do not support a causal comparison or a complete safety profile.

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

The registry record establishes the study's purpose, intervention, endpoint definition, enrollment, and selected safety figures. It does not provide the primary endpoint estimate or a statistical analysis. The key statistical result—mean change in SRT at Year 5, with its uncertainty—is therefore unavailable in the record. No conclusion about the size, direction, or precision of the primary endpoint result can be drawn from the endpoint description alone.

The endpoint's sign convention is explicit. Baseline SRT minus Year 5 SRT is the specified calculation, and a positive difference is described as a better outcome because it corresponds to a lower Year 5 SRT. This definition clarifies how a reported estimate would be read, but it does not show that a positive change occurred. The registry record does not report the estimate, standard error, confidence interval, or test result.

The study is marked completed, and the registry gives an enrollment of 51. Those details do not show how many participants reached Year 5 follow-up or contributed to the primary analysis. The record does not state the analysis population or the handling of missing follow-up data. It also does not describe a randomized comparison or a comparator group; allocation is not stated. Accordingly, the listed pre-implant aided condition is a baseline reference and should not be treated as a parallel control arm.

The safety counts and event terms provide descriptive information, not proof that an event was caused by the implant or that the device caused no other events. The record does not provide the timing and relatedness details needed for those judgments. Likewise, the secondary quality-of-life outcome is identified but its result is not reported in the registry record. The most defensible interpretation is that the record describes what the study set out to evaluate and some recorded safety data, while leaving the principal efficacy result and key analytic details unavailable.

14. Why This Trial Matters Statistically

This study is statistically informative as an example of why an endpoint definition and a result must be distinguished. The registry specifies a continuous Year 5 change in speech reception threshold, identifies the baseline reference, and explains the direction considered favorable. That level of definition helps readers understand what a reported estimate would mean. Yet without the estimate and its uncertainty, the endpoint cannot answer the study's primary statistical question.

The record also illustrates the importance of separating a pre/post comparison from a controlled comparison. The endpoint uses a pre-implant aided baseline, while the record does not describe a randomized comparison and does not state allocation. A change over time can be summarized, but that alone does not identify why the change occurred. This distinction is central when interpreting device studies and other follow-up research.

Safety records require similar care. Counts affected by serious and other adverse events, and listed event terms, are useful descriptive information. They are not automatically causal evidence, and the separate safety fields should not be combined into a count of distinct people. Event definitions, timing, relatedness, and comparison context influence interpretation, but are not reported in the available registry record.

Finally, the record identifies enrollment and completion status without stating the Year 5 analysis population, missing-data methods, or detailed statistical plan. This emphasizes why transparent reporting of estimates, uncertainty, analysis populations, and methods matters: those details let readers judge both what the data show and how strongly they support an interpretation.

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 principal limitation for statistical interpretation is that the registry record does not report a primary endpoint estimate. Although the endpoint is defined as change from pre-implant aided baseline to Year 5 and is summarized in principle by a mean and standard error, no numerical mean, standard error, confidence interval, or test result is posted. The direction and precision of the observed endpoint are therefore unknown from this record.

The record gives an enrollment of 51 but does not report the number with Year 5 data or the analysis population. It does not state how missing measurements were handled, whether follow-up differed among participants, or whether sensitivity analyses were conducted. Enrollment cannot be used as a substitute for an endpoint-specific denominator.

Study allocation is not stated, and the record does not describe a randomized comparison or a concurrent comparator. The pre-implant aided condition is the endpoint baseline reference. Without a described control group, a pre/post change cannot by itself distinguish a change associated with the intervention from other changes over time. This limits causal interpretation, irrespective of the direction of any unreported estimate.

The registry record lists five outcome measures but does not report a multiplicity strategy, a full statistical analysis plan, or posted analyses. It also does not give detail on endpoint measurement procedures, analysis assumptions, or the handling of protocol deviations. For safety, the record provides counts and event terms but not timing, duration, severity criteria, relatedness, or comparative context. These limitations concern what can be learned from the registry record; they do not establish that the study's conduct or unposted analyses were inadequate.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: The Esteem® Hearing Implant Post Approval Study — NCT02666222.
• Registry record last updated 2016-05-04; status last verified 2016-01.
• Results first posted 2016-05-04.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

NCT02666222 is the completed Esteem® Hearing Implant Post Approval Study, sponsored by Envoy Medical Corporation. The registry records enrollment of 51 and describes a study of long-term safety and efficacy in subjects suffering from moderate to severe hearing loss.

The primary outcome is mean change from the pre-implant aided baseline in speech reception threshold at Year 5, measured in dB. The endpoint is defined as baseline SRT minus Year 5 SRT, with a positive difference described as a better outcome. A quality-of-life outcome using the Abbreviated Profile of Hearing Aid Benefit questionnaire is also listed.

The record includes serious and other adverse-event counts and selected serious-event terms. It does not report the primary endpoint estimate, its uncertainty, a detailed analysis plan, or the endpoint analysis population. Allocation is not stated, and a randomized comparison is not described. Consequently, the registry record identifies the question and some safety information but does not provide the primary result needed to assess the observed change.