Cochlear Implantation for Treatment of Single-sided Deafness: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Cochlear Implantation for Treatment of Single-sided Deafness (NCT02532972), a na na study. The primary outcome is Sound Detection Via Pure-tone Threshold Audiometry (PTA).

2. Clinical Question

The central question was whether postoperative sound-field thresholds would change following cochlear implantation in participants with deafness in one ear. This is a within-group question about measured hearing thresholds over follow-up, not a randomized comparison of the implant against another treatment or a control condition. The record also identifies subjective tinnitus change measured by the Tinnitus Handicap Index as a secondary outcome.

The registry describes the study objective as determining whether the cochlear implant device can improve hearing in people with single-sided deafness. That description gives the motivation for the study, but it is not itself evidence of an outcome. Because the record does not report the primary measurements or an analysis of change, it cannot establish what threshold values participants had or how they changed after surgery.

3. Trial Design

This was a single-group interventional study of cochlear implant surgery. The registry lists enrollment of 11 and describes all subjects as belonging to one arm involving placement of the Med-El MAESTRO Cochlear Implant with Flex 28 electrode array. There was no separate control arm, so the study design does not support a like-for-like treatment comparison.

Allocation is recorded as not specified, and masking is listed as none. The phase is listed as not applicable. The registry gives a start date of 2015-09 and a primary completion date of 2019-02-27. Its status is terminated. The reason for termination is not reported in the registry record, so no conclusion about why the study stopped is warranted.

The primary outcome was sound detection via pure-tone threshold audiometry, measured in dB HL at 3, 6 and 12 months post-operatively. The record also lists subjective change in tinnitus measured by the Tinnitus Handicap Index as a secondary outcome. It reports 3 outcome measures overall, but does not describe all of them in the information available for interpretation.

The record says that 11 participants had surgery. One participant opted out of additional follow-up after the 6 month visit, and one did not return for the one-year follow-up visit following activation. As a result, the 12 month time point has data analyzed for 9 participants. These follow-up details do not tell readers how many observations were available at each earlier visit or how the analyses handled missing observations.

The registry does not report a control-group procedure, a randomization process, a masking procedure, or a statistical analysis plan. These omissions should not be filled in by assuming practices used in other studies.

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: 11 participants had surgery, but one subject opted out of additional follow-up after the 6 month visit one subject did not return for his one year followup visit following activation. As such,12 month time points only have 9 participants' data analyzed.

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 Sound Detection Via Pure-tone Threshold Audiometry (PTA), measured over 3, 6 and 12 months post-operatively.

The primary endpoint is sound detection measured using sound-field pure-tone threshold audiometry. The measurement unit is dB HL, or decibels hearing level. In this endpoint, a lower threshold means more sensitive hearing, while a higher threshold means less sensitive hearing. The registry specifies the mean as the outcome parameter and the full range as the measure of dispersion.

A threshold is used to describe the sound level at which a person detects a tone under the measurement conditions. Repeated measurements at 3, 6 and 12 months post-operatively can describe hearing thresholds at those follow-up times. In general, audiometric thresholds provide a standardized way to characterize sound detection; they do not, by themselves, describe every aspect of hearing or daily listening experience.

The endpoint is relevant to the stated research question because the study sought to assess hearing following cochlear implantation. However, the record provides the endpoint definition and time points, not the actual threshold values. It therefore does not show the mean, full range, or pattern of measurements at any visit. Nor does it report a statistical estimate comparing follow-up with a baseline value. The result of the primary endpoint is not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a mean outcome, a full-range dispersion measure, repeated postoperative time points, and a single-group design. These features shape what statistical summaries could communicate, but the record does not report the analysis methods used or any primary outcome estimates. The explanations below are general statistical context, not claims about analyses performed in this study.

What does a mean describe?

A mean is a summary of the central level of the observed measurements. For a hearing-threshold outcome, it would describe the average threshold among the participants included in a particular summary. The mean alone does not show how widely individual measurements vary, whether observations cluster, or whether an unusual value has a strong influence. The record names the mean as the parameter but does not report its value at any follow-up time.

The full range describes the span between the lowest and highest observed values. It gives readers a sense of the extremes in the observed data, but it is sensitive to individual extreme values and does not show the distribution of measurements between those extremes. A range also does not quantify the uncertainty in an estimated mean. The registry specifies full range as the dispersion measure, but does not provide the range values.

How should repeated measurements be understood?

Measurements from the same participant across follow-up are related rather than independent. A statistical analysis of change over time generally needs to account for that within-participant relationship. Describing each visit separately can show the distribution at each time, while an analysis of change can estimate how measurements differ across visits or relative to a baseline. Those are distinct summaries. The registry gives postoperative time points but does not describe a baseline measurement or a model for longitudinal change.

General longitudinal methods can use the available observations in different ways and rely on assumptions about the pattern of missingness. The suitability of a method depends on the study data and its prespecified analysis plan. No such plan is reported in the registry record, so it is not possible to determine whether the analysis accounted for repeated measurements, adjusted for participant characteristics, or made assumptions about missing follow-up.

What does a confidence interval contribute?

In general, a confidence interval expresses uncertainty around an estimated quantity under the assumptions of the statistical method. A narrower interval indicates greater precision for that estimate, while a wider interval indicates less precision. It does not guarantee that an estimate is free from bias, and it does not resolve limitations caused by the lack of a comparison group or missing observations. The registry does not report a confidence interval for the primary outcome.

A hypothesis test and a confidence interval answer related but different questions. A test evaluates data relative to a specified null hypothesis and model; a confidence interval conveys a range of estimates compatible with the data and method. Neither can be reconstructed from the endpoint description alone. No test results or inferential estimates are reported in the registry record.

Why does the single-group design matter?

With one group, postoperative observations can describe the participants’ measured outcomes, but there is no concurrent randomized control group to help distinguish an intervention-associated change from other influences. A pre-post comparison, if reported, would still be a comparison within the same group, not a randomized treatment contrast. The record does not provide such a comparison or the measurements required to assess one.

Allocation is listed as not specified, and masking as none. The registry does not describe methods to reduce measurement or assessment bias. This does not establish that a particular bias occurred; it means that the record does not provide information to assess those safeguards. Similarly, the registry does not report a statistical analysis plan, a sample-size justification, or interim analyses.

How should planning illustrations be read?

Any sample-size planning illustrations are hypothetical planning calculations, not observed power and not evidence about the trial's findings. The stated illustration assumptions are a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect expressed as a fraction of the observed effect. For time-to-event outcomes, the illustrations concern the total number of events; for other outcomes, they concern participants per arm.

Those assumptions do not describe this study's recorded single-group design, which enrolled 11 participants. A calculation that assumes two arms is not a reconstruction of this trial's design, nor does it establish that the study was planned or conducted using those assumptions. The registry does not report its own sample-size justification. Any planning illustration should therefore be kept separate from the observed enrollment and from claims about statistical power or results.

Over-dispersion is a general concern when data vary more than a statistical model expects; if unaccounted for, estimated uncertainty can be too small. It is relevant to methods whose distributional assumptions are violated, but the endpoint description alone does not establish whether over-dispersion is relevant to this audiometry analysis. The registry does not describe a model or diagnostic checks, so no claim can be made about whether this issue arose.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 3 outcome measures, identifies sound detection by pure-tone threshold audiometry as the primary outcome, and names subjective tinnitus change measured by the Tinnitus Handicap Index as a secondary outcome. When a study assesses multiple outcomes or multiple time points, there can be more than one opportunity to find an apparently notable result. General statistical approaches can address this multiplicity, but the registry does not report a multiplicity strategy or the analyses performed. It is not possible to tell whether any adjustment or hierarchy among outcomes was planned.

The primary endpoint is specified at 3, 6 and 12 months post-operatively. The record says that 11 participants had surgery, one opted out of additional follow-up after the 6 month visit, and one did not return for the one-year follow-up visit following activation. The 12 month time point therefore has data analyzed for 9 participants. The registry does not state how many observations were available at each earlier time point or how missing observations were treated in any analysis.

In general, missing data can affect interpretation when participants with observed measurements differ systematically from those without them. The record does not report reasons beyond the two follow-up details, methods for handling missingness, or sensitivity analyses. It also does not define analysis populations beyond the statement about the participants whose 12 month data were analyzed. Whether the primary analyses included all participants who had surgery, only participants with available measurements, or another population is not reported in the registry record.

The registry reports 0 analyses. Without reported outcome estimates, missing-data methods, or multiplicity procedures, readers cannot assess how these issues affected statistical inference.

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.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pneumonia (9.1%), hip replacement (9.1%).

The registry lists 11 at risk for serious adverse events and 2 affected. For other adverse events, it lists 11 at risk and 9 affected. It records 0 deaths. These are safety counts in the registry record; they should be read separately from the primary hearing-threshold endpoint.

Pneumonia and hip replacement are listed among the serious adverse event terms, each at 9.1%. Those terms do not establish that the events were caused by the implant or surgery. The registry information does not specify the timing, clinical context, or causal assessment for these terms. It also does not clarify whether the terms refer to distinct participants or whether any participant appears in more than one category, so the percentages should not be added together or treated as a count of unique people.

The single-group design provides no concurrent control group for comparing adverse-event counts. The figures therefore describe reported events among those at risk in this study, rather than a comparative estimate of excess risk. The registry record does not provide enough detail to assess event duration, severity beyond the serious classification, or the investigators’ attribution of each event.

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

The registry record establishes that a single-group cochlear implant study enrolled 11 participants and defined postoperative sound detection by pure-tone threshold audiometry as its primary outcome. It specifies the unit, the direction of the scale, and follow-up at 3, 6 and 12 months post-operatively. These details identify what the study intended to measure, but they do not report the measurements themselves.

As a result, the record cannot show whether thresholds changed, how large any change was, how variable the measurements were, or how precisely a change was estimated. There is no reported estimate or statistical test from which to judge the strength of evidence. The absence of reported results should not be interpreted as a finding of no change, just as the stated research objective should not be treated as proof of improvement.

The study also cannot provide a randomized comparison because it has one group and no separate comparator. Even with complete follow-up and reported changes, a within-group pattern would not establish what would have happened to the same participants under another condition. The follow-up record notes that 12 month data were analyzed for 9 participants, which further limits what can be inferred about the full group at that time point.

The safety counts describe serious and other adverse events recorded in the registry, including 0 deaths. They do not establish causation or comparative safety. The record does not report enough contextual detail to interpret the listed serious terms as treatment effects.

The most defensible conclusion is therefore about the registry record itself: it documents the design, endpoint definition, follow-up limitations and adverse-event counts, while leaving the primary outcome results and analyses unreported. Claims that the implant did or did not improve hearing would exceed what these data show.

13. Why This Trial Matters Statistically

This study illustrates a basic distinction in clinical statistics: an outcome definition is not an outcome result. The registry identifies a measurable endpoint, explains its unit and direction, and specifies follow-up times. Without the observed values or an analysis, however, readers cannot assess the magnitude, variability or precision of the hearing measurements. Clear endpoint specification is useful, but it cannot substitute for reported results.

The single-group design also makes the estimand important. A description of participants’ thresholds after surgery would concern their observed postoperative measurements. A claim about an intervention effect requires a counterfactual comparison: what would have happened to comparable participants without the intervention or under an alternative. This registry record has no separate control arm, so it cannot directly estimate that randomized contrast.

Follow-up completeness is another central statistical issue. The record says 12 month data were analyzed for 9 participants after reporting two follow-up issues. A late follow-up summary based on those with available data may not represent every participant who had surgery, particularly if missingness is related to outcomes. The record does not report methods to address or examine that possibility.

Finally, planning calculations should not be mistaken for trial findings or for evidence that the design had adequate power. The stated planning assumptions involve equal allocation between two arms, whereas the recorded study was single-group. The registry does not report its own sample-size justification. Keeping design, planning assumptions and observed results distinct is essential to a statistically sound reading of the record.

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.

Several trial-specific limitations restrict interpretation. The study is recorded as single-group, with no separate control arm. Allocation is not specified and masking is listed as none. These features prevent a randomized comparison and leave the record unable to show how postoperative measurements compare with an alternative condition.

The primary outcome values and statistical analyses are not reported in the registry record. The registry defines the mean and full range as the summary measures, but supplies no measurement summaries, estimate of change, uncertainty interval, or test result. The reason for the terminated status is not reported in the registry record, and no explanation should be inferred from that status alone.

Although 11 participants had surgery, the record says that the 12 month time point has data analyzed for 9 participants. One participant opted out of additional follow-up after the 6 month visit, while another did not return for the one-year follow-up visit following activation. The record does not report the missing-data analysis, the number observed at each earlier visit, or whether those with and without late measurements differed.

The registry does not report the study's sample-size justification, interim analyses, or statistical analysis plan. It lists 3 outcome measures but does not provide 0-analysis results. The adverse-event counts also lack a concurrent comparator and detailed event context. These gaps limit interpretation of both efficacy-related outcomes and safety; they do not establish that an unreported effect or analysis had a particular result.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Cochlear Implantation for Treatment of Single-sided Deafness — NCT02532972.
• Registry record last updated 2020-05-05; status last verified 2020-04.
• Results first posted 2020-03-11.
• 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

NCT02532972, titled Cochlear Implantation for Treatment of Single-sided Deafness, is recorded as a terminated, single-group interventional study. The listed intervention was cochlear implant surgery using the Med-El MAESTRO Cochlear Implant with Flex 28 electrode array. Enrollment was 11. The registry gives a start date of 2015-09 and a primary completion date of 2019-02-27.

The primary outcome was sound detection via pure-tone threshold audiometry, measured in dB HL at 3, 6 and 12 months post-operatively. The record says 12 month data were analyzed for 9 participants. It also lists subjective tinnitus change measured by the Tinnitus Handicap Index as a secondary outcome.

The registry reports adverse-event counts, including 2 affected for serious events, 9 affected for other events, and 0 deaths. It reports 0 analyses and does not include primary outcome results. The reason for termination and the study's statistical analysis plan are not reported in the registry record.