NeuroCovid Rehab and Recovery Related to COVID-19 Diagnosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for NeuroCovid Rehab and Recovery Related to COVID-19 Diagnosis (NCT04638673), a randomized phase 2 study. The primary outcome is Change in Score of Patient Health Questionnaire-9.

2. Clinical Question

The study addressed whether an online, wearable taVNS approach could be investigated in people described as experiencing NeuroCovid symptoms. The primary outcome was change in PHQ-9 score between baseline and the end of treatment at week 4. Since higher PHQ-9 scores indicate worse symptoms, a negative mean change represents a reduction in scores over that interval.

The treatment schedules matter to the interpretation. One group received active stimulation throughout the four weeks, while the other received sham stimulation initially and active stimulation during the final two weeks. Thus, the week-4 summaries compare two different assigned schedules; they do not compare active stimulation with sham stimulation maintained for the full treatment period. The registry record does not report a separate outcome assessment at the end of the initial two-week period.

3. Trial Design

This completed phase 2 study is recorded as randomized, triple-masked and parallel. It enrolled 13 participants. The registry record lists two groups: Active-Active Stimulation and Sham-Active Stimulation. The first group was assigned active stimulation during weeks 1&2 and weeks 3&4; the second was assigned sham stimulation during weeks 1&2 and active stimulation during weeks 3&4. Both groups therefore had active stimulation during the final two weeks.

The primary outcome is change in PHQ-9 score from baseline to week 4, the end of treatment. The posted outcome summaries list 6 participants in each group. The registry record does not explain how those outcome counts relate to the enrollment of 13, so the difference should not be interpreted as a known reason for exclusion, withdrawal or missing data.

The study summary describes the research as entirely online, with assessments completed virtually, and describes a wearable device controlled through telemedicine. The registry record does not report the roles covered by triple masking, details of the allocation process, the stimulation dose or session frequency, or adherence to the assigned schedules. It also does not report a protocol-level sample-size justification or other design details beyond the recorded phase, allocation, masking and model.

Because the sham-assigned group switched to active stimulation after the first two weeks, the week-4 outcome is not a comparison of active treatment against an ongoing sham condition. Randomization provides the design basis for comparing assigned schedules, but the small outcome groups and lack of a posted inferential comparison limit what can be concluded from the descriptive summaries alone.

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 Change in Score of Patient Health Questionnaire-9, measured over Baseline and week 4 (End of Treatment).

The primary endpoint is change in Patient Health Questionnaire-9 score from baseline to week 4, identified as the end of treatment. The PHQ-9 is a nine-question instrument used in primary care to screen for the presence and severity of depression. Its scores range from 0-27, with higher scores indicating worse symptoms. The registry describes the endpoint as a mean change and reports standard deviations for the group summaries.

A negative change means that the average follow-up score was lower than the average baseline score; given the direction of the scale, this represents a reduction in reported symptom scores over the measurement interval. The posted mean changes are -8.7 for the Active-Active group and -5.5 for the Sham-Active group. These are group-level summaries, not individual participant outcomes. Standard deviations describe the spread of observed changes within each group and are not measures of uncertainty around the group mean.

The registry also defines response categories using baseline severity: remission is a PHQ-9 score < 5; response is a decrease of 50% or greater; partial response is a decrease of 26% to 49%; and non-response is a decrease of less than 25%. These definitions do not mean that category counts were reported. The registry record does not report remission or response counts, confidence intervals for the mean changes, or individual score trajectories.

PHQ-9 change is used as a quantitative symptom measure, allowing the group averages and their variability to be described. It does not by itself identify which symptoms changed or establish the cause of any change.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a mean change describe?

A continuous outcome can be summarized by its mean, which represents the average observed value or change in a group. For this endpoint, each participant’s change concerns their PHQ-9 score between baseline and week 4; the registry reports the group mean change. A negative mean is a downward average change in scores. It does not indicate that all participants moved in the same direction, nor does it reveal the distribution of individual changes by itself.

The standard deviation describes how dispersed participant-level changes are around the group mean. A larger standard deviation indicates greater variability in the observed changes. It is different from a standard error or confidence interval: those quantify uncertainty about an estimated mean, whereas the standard deviation describes variation among observations. The registry reports standard deviations but does not report standard errors or confidence intervals for these mean changes.

What would a between-group analysis add?

A comparison of randomized groups would estimate how their average changes differ, with an uncertainty measure and a statistical test if those were part of the analysis. The registry record does not report such an analysis. It is therefore not possible to infer statistical significance, estimate the precision of a group contrast, or decide how compatible the observed summaries are with a range of possible between-group effects from the posted results alone.

A confidence interval, in general, gives a range of values that are compatible with the data and the method used to calculate it. Its width reflects precision: wider intervals indicate less precision, while narrower intervals indicate more. A confidence interval for a mean change would concern uncertainty in that group’s mean; a confidence interval for a contrast would concern uncertainty in the between-group comparison. Neither kind of interval is reported for this outcome.

Randomization is intended to support a fair comparison of assigned groups by reducing systematic differences at assignment. It does not remove uncertainty, ensure that the groups are identical in a small study, or resolve missing outcome data. The small group sizes in the posted summaries mean that estimates may be sensitive to individual observations; that is a general statistical consideration, not evidence about any particular participant’s contribution.

How should the schedule affect the comparison?

The assigned schedules define the contrast that a randomized analysis could address. The Active-Active group received active stimulation during both weeks 1&2 and weeks 3&4. The Sham-Active group received sham stimulation during weeks 1&2 and active stimulation during weeks 3&4. A comparison at the end of week 4 would therefore compare these two sequences, not active stimulation against sham stimulation continuing through the endpoint. The registry record does not report a separate outcome estimate at the end of week 2 that would isolate the initial schedule period.

The study is recorded as parallel, meaning participants were assigned to groups that follow different schedules. Although the second group changes from sham to active stimulation, the registry classifies the overall model as parallel. The reported endpoint remains a baseline-to-week-4 change for each group; no within-person treatment-period comparison is reported.

What do planning illustrations mean?

Sample-size planning illustrations are prospective calculations about the number of participants per arm that would be needed under stated assumptions to detect a specified effect with a chosen power. They are not observed results, and they are not evidence that a completed trial had that power. The registry’s described illustration uses a two-sided significance level of 0.05, equal allocation, a normal approximation and effects expressed as fractions of the observed effect. No numeric planning values are reported in the registry record.

Using an observed effect for a planning illustration has an important limitation: an effect estimated in a small study can be imprecise. Planning for a fraction of that estimate explores alternative target effects, but does not make the underlying estimate more certain. The illustrations should be understood as planning scenarios rather than confirmation of a required sample size, since the registry record does not report that they were the study’s original design justification.

In general, over-dispersion means that outcome variability is greater than a statistical model assumes. When a model underestimates variability, standard errors and intervals can be too small and tests can appear more conclusive than warranted. This is a general concept; the posted continuous summaries do not report a model or an over-dispersion assessment for this endpoint.

What can be recalculated?

The registry record does not report a recalculated two-arm comparison for this continuous endpoint. It also lists no statistical analyses. The posted group means, standard deviations and participant counts are descriptive inputs, not a replacement for a prespecified or otherwise documented analysis. In the absence of a reported model, uncertainty estimate and analysis population, no inferential result should be attributed to the registry summaries.

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("Active-Active Stimulation Group", "Sham-Active Stimulation Group")
n   <- c(6, 6)
m   <- c(-8.7, -5.5)
sp  <- c(6.3, 4.1)
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  Active-Active Stimulation Group  6  -8.700  6.300  -15.311  -2.089
CARM  Sham-Active Stimulation Group  6  -5.500  4.100  -9.803  -1.197

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and no posted secondary outcomes. A single listed primary outcome reduces the concern that many reported outcome tests are being selectively highlighted, but it does not establish whether other outcomes were measured or whether any multiplicity plan existed. The registry record does not report a multiplicity adjustment, a hierarchy of hypotheses, or an analysis plan specifying how multiple tests would be handled.

Missing-data methods are not reported in the registry record. The study enrolled 13 participants, while the primary outcome summaries list 6 participants in each group. The record does not explain the difference, identify the number of participants with missing baseline or week-4 scores, or state how any missing outcomes were handled. It is not reported in the registry record whether the summaries include all randomized participants or a subset defined by treatment completion or another criterion.

These details affect interpretation. If outcome availability is related to participants’ scores or experiences, a summary based only on those with recorded outcomes may not represent all randomized participants. This is a general concern, not a claim that missingness occurred for a particular reason in this study. Without the analysis population and missing-data approach, readers cannot assess how the reported means relate to the full randomized group.

The registry record does not report an intention-to-treat analysis, a per-protocol analysis, imputation, sensitivity analyses, or prespecified rules for handling incomplete scores. It also does not report the protocol’s statistical analysis plan. Consequently, the endpoint summaries can be read descriptively, but the effect of missing-data decisions and analytic choices cannot be evaluated from 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 5% reporting threshold.

Most frequent non-serious adverse event terms

The registry lists 0 serious adverse events among 6 participants at risk in the Active-Active Stimulation Group and 0 among 6 at risk in the Sham-Active Stimulation Group. For other adverse events, it lists 0 among 6 at risk in the Active-Active group and 2 among 6 at risk in the Sham-Active group. Deaths are listed as 0 in the Active-Active group and 2 in the Sham-Active group. These are the registry’s counts; they should not be combined or treated as mutually exclusive categories without further information.

These figures are counts within groups, not estimates of a causal effect of either schedule. The record does not report event descriptions for the other adverse events or the deaths, their timing, or an attribution to study treatment. It also does not report additional detail about follow-up duration or the method used to collect adverse-event information.

Zero reported serious adverse events does not establish that serious events could not occur; it means none are listed in these group summaries. The small numbers at risk also limit how precisely safety experience can be characterized. No medical conclusion about safety should be drawn from these counts alone, and the registry record does not explain the circumstances behind the listed deaths.

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

The primary outcome summaries document average changes in PHQ-9 scores from baseline to week 4. The Active-Active group had a mean change of -8.7, with a standard deviation of 6.3 and 6 participants in the summary. The Sham-Active group had a mean change of -5.5, with a standard deviation of 4.1 and 6 participants. As higher PHQ-9 scores indicate worse symptoms, the negative means describe decreases in scores on average in both groups.

Those observations do not establish how much the assigned schedules differed in their effects. The registry does not report a between-group statistical analysis, confidence interval, or other measure of uncertainty for a comparison. It also does not report the analysis population or explain the difference between the 13 enrolled participants and the 12 participants represented across the group summaries. The precision and representativeness of the endpoint estimates therefore cannot be fully assessed.

The treatment schedules further limit the question answered by the week-4 outcome: both groups received active stimulation during weeks 3&4, while their assignments differed during weeks 1&2. The results cannot be interpreted as a comparison of four weeks of active stimulation against four weeks of sham stimulation. Nor do the score changes alone establish that stimulation caused a change, since the posted summaries do not supply a statistical comparison or a control condition remaining on sham through the endpoint.

The registry defines remission and response categories, but does not post category counts. Mean changes cannot show how many participants met those definitions. Similarly, the group averages do not establish the experience of any individual participant, and the listed safety counts do not identify causes or treatment relationships.

Accordingly, the result supports a limited descriptive statement: average PHQ-9 scores were lower at week 4 than baseline in each group represented in the posted summaries. It does not establish a treatment effect, the statistical significance or precision of a difference between schedules, or the reason for the listed safety events.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of why a reported outcome summary and a comparative result are not the same thing. The registry gives group means, standard deviations and participant counts for a continuous endpoint. Those quantities describe the observed data, but without an inferential analysis they do not quantify uncertainty in the difference between randomized groups.

The timing of treatment is also part of the estimand—the precise comparison a study is designed to answer. Here, one group received active stimulation throughout the four weeks, and the other switched from sham to active after weeks 1&2. At week 4, the comparison is between assigned schedules, not between active stimulation and a continuing sham group. Clear interpretation depends on keeping that distinction in view.

The difference between overall enrollment and the outcome-summary counts is another statistical issue, not merely a reporting detail. Readers need to know which participants contributed outcome data and how missing data were handled to judge how well the summaries represent the randomized groups. The registry record does not report those details.

Finally, the sample-size planning illustrations are not observed power and do not establish that the completed trial was adequately powered. They are planning scenarios based on stated assumptions and the observed effect. In a small study, uncertainty in the observed effect is itself relevant to how such scenarios should be read. Together, these features make the registry a useful case for separating descriptive change, the intended randomized comparison, and the evidence actually reported.

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 primary outcome summaries include 6 participants in each group, while enrollment is listed as 13. The registry record does not explain this difference, so the outcome analysis population and the completeness of endpoint data cannot be determined from the record. Missing-data handling and sensitivity analyses are not reported in the registry record.

No statistical analysis is listed for the primary endpoint. Confidence intervals, a between-group estimate, a test result and the model used to analyze the continuous outcome are not reported in the registry record. The means and standard deviations therefore do not establish the precision or statistical significance of a group contrast.

The comparison is limited to the assigned schedules. The Sham-Active group received active stimulation in weeks 3&4, so the week-4 result does not compare active stimulation with sham maintained throughout the study. The registry record does not report a separate week-2 outcome that could describe the initial active-versus-sham period.

The registry does not report further eligibility details in the outcome record, the roles included in triple masking, adherence, or the stimulation dose and session frequency. These omissions make it difficult to assess the population represented, the implementation of the schedules, and the possible influence of treatment exposure on the observed summaries.

The safety record provides group counts but not event descriptions for the other adverse events or deaths, timing, or attribution. The registry record also does not report a protocol-based sample-size justification. These limitations do not negate the descriptive observations, but they constrain causal, precision and safety interpretations.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: NeuroCovid Rehab and Recovery Related to COVID-19 Diagnosis — NCT04638673.
• Registry record last updated 2022-07-26; status last verified 2022-07.
• Results first posted 2022-07-26.
• 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

NCT04638673 is a completed phase 2 randomized, triple-masked, parallel study sponsored by the Medical University of South Carolina. The registry lists enrollment of 13 participants and two taVNS schedules: active stimulation for weeks 1&2 and weeks 3&4, or sham for weeks 1&2 followed by active stimulation for weeks 3&4.

The primary outcome is mean change in PHQ-9 score from baseline to week 4. The posted summaries list 6 participants per group, with mean changes of -8.7 and -5.5 and standard deviations of 6.3 and 4.1, respectively. No statistical analysis of the group comparison is listed. The registry record does not explain the difference between enrollment and outcome counts or report confidence intervals, missing-data methods or the analysis population.

Serious adverse events are listed as 0 in both groups. Other adverse events are listed as 0 in the Active-Active group and 2 in the Sham-Active group; deaths are listed as 0 and 2, respectively. The registry does not provide further event context.