Comprehensive Cardiac Rehabilitation Feasibility After Stroke: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Comprehensive Cardiac Rehabilitation Feasibility After Stroke (NCT03944668), a na na study. The primary outcome is Attendance Rate.

2. Clinical Question

The study’s stated purpose is to evaluate whether stroke patients can be enrolled in a comprehensive cardiovascular rehabilitation program and to examine feasibility and safety. The summary also identifies recurrence of stroke, myocardial infarction, readmission, and mortality as clinical outcomes of interest. These aims should be distinguished from evidence of comparative benefit: the study has no control arm, and the posted record contains no inferential analyses. The primary question is therefore about feasibility as operationalized through attendance, rather than whether the program improves outcomes relative to another treatment or usual care.

The record lists enrollment as 17, while the primary outcome description refers to 14 enrolled and consenting stroke patients. It does not explain the relationship between those figures. The primary outcome population should be read as described in the outcome record, without assuming that the broader enrollment figure is the analyzed population or that all enrolled participants contributed attendance information.

3. Trial Design

This is a completed, single-group study registered as NCT03944668, with the title Comprehensive Cardiac Rehabilitation Feasibility After Stroke. The registry lists the phase as not applicable, allocation as not applicable, and masking as none. These entries are consistent with a feasibility study without a randomized treatment comparison; they do not establish that every other aspect of conduct was unmasked or explain how outcomes were assessed.

The registry lists HealthPartners Institute as the sponsor. The study start date is 2019-04-29, and primary completion is recorded as 2020-12-31. Status is completed. Enrollment is listed as 17. The primary outcome description separately identifies 14 stroke patients who enrolled and consented; the record does not explain the difference or specify how many contributed to each outcome.

The intervention is labeled Exercise, with an arm description of exercise intervention. The brief summary describes comprehensive cardiovascular rehabilitation as aerobic exercise and patient education about risk factors and medication compliance. It frames the study as assessing feasibility and safety in stroke patients while examining clinical outcomes, including stroke recurrence, myocardial infarction, readmission, and mortality. The registry does not give further details about session frequency, exercise intensity, program delivery, or adherence support.

Attendance Rate is the primary outcome, with a 12-week timeframe and a description specifying 75% attendance at comprehensive cardiovascular rehabilitation sessions. The listed outcome unit is participants. Secondary outcomes include recurrent stroke, myocardial infarction, hospital readmission, silent stroke, and death-related status. The record lists 6 outcome measures and 0 analyses. It does not report a statistical analysis plan, a sample-size justification, interim analyses, or procedures for handling missing outcomes.

Because there is no control group, the design can describe what was recorded among participants in the intervention group, but it cannot estimate a treatment contrast against a concurrent comparator. Feasibility observations and safety counts should be interpreted within that single-group design.

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

Analysis population for the primary outcome, as defined in the registry: 14 Stroke patients who enrolled and consented in 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.

Population: 14 Enrolled and consented stroke patients

6. Primary Endpoint

The registry lists the primary outcome as Attendance Rate, measured over 12 weeks.

The primary endpoint is titled Attendance Rate. Its timeframe is 12 weeks, and its description defines the attendance criterion as 75% attendance at comprehensive cardiovascular rehabilitation sessions. The record identifies the outcome unit as participants and describes the population as 14 stroke patients who enrolled and consented in the study. It does not report the observed attendance count, the number meeting the criterion, or a numerical attendance rate.

Attendance is relevant to a feasibility question because it describes participation in the rehabilitation program. In general, attendance can indicate whether participants engage with scheduled sessions, but it does not by itself establish the program’s clinical effect or explain why a participant attended or missed sessions. The registry does not provide a fuller endpoint definition, such as how missed sessions were treated or how attendance was verified.

The distinction between the stated criterion and an observed result is important. The description of 75% attendance identifies the criterion associated with the endpoint; it is not a reported finding that participants achieved that level. Without an observed count or rate, the primary outcome cannot be evaluated from the posted record. The record also does not report uncertainty around attendance, such as a confidence interval, or a comparison with another group.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation depends on matching each number to the question it answers. In this study, the registry identifies attendance as the primary outcome and describes a 75% attendance criterion over 12 weeks. That criterion is a definition of the target associated with the outcome, not an observed result. Since no attendance count or rate is reported, there is no primary estimate to interpret. The registry’s listing of 0 analyses reinforces that it does not post an inferential result for this outcome.

What does a single-group design allow?

A single-group design follows participants who receive an intervention without a concurrent control arm. It can describe participation and outcomes recorded in that group. It cannot, on its own, estimate what would have happened to comparable participants under a different intervention or without the program. That distinction matters for the clinical outcomes mentioned in the study summary: a count of events in the intervention group would remain descriptive unless an appropriate comparison and analysis were available. In this record, those analyses are not reported.

Allocation is listed as not applicable, masking as none, and the model as single group. There is therefore no randomized comparison from which to interpret a between-group difference. Lack of a comparator does not make attendance information uninformative for feasibility, but it limits claims about clinical benefit and comparative safety. The record does not report an analysis plan that would permit additional conclusions.

How should the attendance criterion be read?

The endpoint title is Attendance Rate, the unit is participants, and the description refers to 75% attendance at rehabilitation sessions. These entries suggest an attendance-based outcome, but the registry does not give an observed result or further operational detail. It does not say how session attendance was recorded, how the criterion was applied to individual participants, or how missing attendance records were treated. Those details should not be inferred from the endpoint title alone.

In general, a proportion or rate is easier to interpret when the numerator, denominator, observation period, and handling of missing information are clear. Here, the primary outcome population is described as 14 stroke patients who enrolled and consented, but no count of participants meeting the attendance criterion is posted. The record also lists total enrollment as 17 and does not explain how that figure relates to the primary outcome population. Therefore, no attendance proportion should be reconstructed from the available entries.

What do the event counts mean?

The outcome type is described as binary, with the meaning specified as participants with an event, expressed as counts. For an outcome represented this way, the count identifies how many participants were recorded with the event; interpretation also depends on the corresponding population at risk and on the event definition. The registry lists secondary outcomes involving recurrent stroke, myocardial infarction, readmission, silent stroke, and death-related status, but does not post their analyzed counts or estimates in the record summarized for this study.

For safety, the record gives counts at risk and counts affected for serious and other adverse events, as well as deaths. These are descriptive observations, not estimates of a comparative risk. In general, zero observed events do not establish that the underlying event risk is zero. With limited event information, uncertainty can remain substantial, and an estimate’s precision depends on the amount and completeness of observed data. The registry does not post an interval for these counts.

What does a confidence interval contribute?

In general, a confidence interval expresses the statistical uncertainty around an estimate under a specified method and its assumptions. A narrow interval indicates greater precision than a wide interval, while neither interval guarantees that an estimate is free from bias. For a single-group feasibility measure, an interval could help show the uncertainty around an observed attendance proportion. No such estimate or interval is reported for this study, so its precision cannot be described from the registry record.

More generally, event outcomes may be sparse, especially in feasibility studies. When counts are low, normal approximations can be unreliable; methods suited to the outcome and data structure may be needed. Over-dispersion is a general concern when observed variability exceeds what a chosen model expects, potentially making standard errors too small if the model is not appropriate. The record does not report model details or analyses that would permit assessment of these issues for this trial.

How should planning illustrations be interpreted?

The sample-size assumptions describe a planning illustration based on the observed effect, not the study’s own design. They specify a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. For non-time-to-event outcomes, results are expressed as participants per arm; time-to-event illustrations use total events. These are generic planning assumptions, not evidence that this single-group trial was designed or analyzed as a two-arm comparison.

A planning illustration asks what sample size might be required under specified assumptions. It is not observed power, and it does not demonstrate that the study was adequately sized. The registry does not report a sample-size justification for this trial, and the attendance result or observed effect needed to interpret an effect-based illustration is not reported. No numerical sample-size implication can therefore be drawn from the record. The underlying design remains a single-group feasibility study, regardless of a hypothetical planning framework for a future comparison.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Intervention")
n      <- c(14)
events <- c(8)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Intervention  14  8  57.1  28.9  82.3  32.6  78.6  32.3  78.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 6 outcome measures and 0 analyses. It identifies Attendance Rate as the primary outcome and lists secondary outcomes involving recurrent stroke, myocardial infarction, hospital readmission, silent stroke, and death-related status. A list of outcomes does not reveal which analyses were conducted or whether any were designated as primary analyses beyond the outcome label.

When a study examines multiple outcomes, the chance of at least one apparently notable finding can increase if many statistical tests are performed. General approaches to this issue include prespecifying a primary outcome, adjusting for multiple comparisons, or treating secondary findings as exploratory. The registry record does not report a multiplicity strategy, a hierarchy of tests, or analyses, so it is not possible to assess whether multiplicity was addressed.

The record does not report how missing attendance or clinical outcome data were handled, whether any participants withdrew, or what analysis populations were used. The primary endpoint description refers to 14 stroke patients who enrolled and consented, while total enrollment is listed as 17; the relationship between these entries is not explained. These figures should not be used to infer how many observations were missing or excluded.

Rules for handling missing data, exclusions, and analysis populations are important because different choices can affect estimates. In general, an analysis population might include all enrolled participants, participants meeting specified criteria, or participants with observed outcome data. The registry does not state which approach applied. It also does not report interim analyses, a statistical analysis plan, or a sample-size justification. Those elements 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 adverse-event record lists 14 participants at risk for serious adverse events and 0 affected. It also lists 14 at risk for other adverse events and 0 affected, with 0 deaths. These are the recorded counts for the intervention group. No serious adverse-event terms are listed.

These entries describe what the registry reports; they do not establish that the intervention carries no risk. In general, a zero count can reflect no observed events during the recorded follow-up, but its interpretation depends on surveillance, event definitions, completeness of reporting, and follow-up. The registry does not provide detailed information on these procedures or a statistical interval around the counts. It also does not present a comparison group, so the counts cannot be used to estimate a comparative safety effect.

The primary outcome timeframe is 12 weeks, but the adverse-event record does not specify its own follow-up window. It should not be assumed that the safety counts cover exactly the same period as the attendance outcome. These data are best read as descriptive registry counts, not as proof of absence of harm.

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

This trial record addresses whether stroke patients can be enrolled in a comprehensive cardiovascular rehabilitation program and whether their participation can be assessed through attendance. The registry describes an attendance criterion of 75% over 12 weeks. It does not report the observed attendance rate or the number of participants who met the criterion. The central feasibility result is therefore unavailable in the posted record, and the criterion cannot be treated as an achieved outcome.

The record reports 0 serious adverse events among 14 at risk, 0 other adverse events among 14 at risk, and 0 deaths. These counts describe the recorded safety data. They do not establish that no risk exists, and the registry does not give enough detail to assess completeness of event surveillance or precision.

The study does not include a control group, and the registry lists 0 analyses. It does not report estimates or tests for the clinical outcomes named in the summary, including stroke recurrence, myocardial infarction, readmission, and mortality. Consequently, the record cannot establish that the intervention improves these outcomes, nor can it quantify an effect relative to another approach. It also cannot establish that outcomes would have differed without the intervention.

What the record does establish is the study’s stated feasibility and safety focus, its single-group design, its attendance criterion, and its posted safety counts. The relationship between total enrollment of 17 and the primary outcome population of 14 is not explained. Details on missing data, analysis populations, and the statistical plan are not reported. These limits mean that interpretation should remain descriptive and should not extend beyond the information recorded.

14. Why This Trial Matters Statistically

Feasibility studies address practical questions that precede or accompany evaluations of clinical outcomes. Attendance is one such measure: it concerns whether participants engage with a rehabilitation program, rather than directly measuring whether the program changes health outcomes. In this record, attendance is the primary outcome and the criterion is 75% over 12 weeks, but the observed attendance result is not reported. This distinction illustrates why a well-defined target and a measured result are not interchangeable.

The study is also a useful example of how design constrains statistical interpretation. A single-group study can provide descriptive information about participants receiving the intervention, but it cannot supply a randomized comparison with a control group. The registry’s clinical aims include important outcomes, yet the posted record contains 0 analyses. Without reported estimates and an appropriate comparator, no treatment contrast or precision assessment can be made.

The safety entries show why counts need context. Zero recorded events are informative as descriptions of what was captured, but they do not prove that risk is absent. Follow-up, event definitions, and data completeness shape the meaning of an event count, and those details are not fully reported in the registry.

Finally, the record distinguishes total enrollment from the population named in the primary outcome description without explaining the relationship. That makes transparent reporting of analysis populations and missing-data procedures especially relevant. The example reinforces a general statistical principle: interpretation depends not only on an endpoint label, but also on the observed data, the population contributing those data, the design, and the analysis plan. Several of those elements are not reported in the registry record.

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 the primary outcome is that the registry defines an attendance criterion but does not report the observed attendance count or rate. The 75% criterion is not evidence that the criterion was achieved. No confidence interval or other measure of uncertainty is reported for attendance.

The design is single-group, with no concurrent comparator. Thus, even if descriptive clinical outcomes were available, they could not establish a comparative effect. The record lists 0 analyses, and does not report estimates for the secondary outcomes named in the study summary or outcome list.

Enrollment is listed as 17, whereas the primary outcome description refers to 14 stroke patients who enrolled and consented. The registry does not explain the relationship between these entries. It does not report participant flow, withdrawals, completeness of outcome data, or the analysis populations. Missing-data methods are not reported in the registry record.

The brief summary describes aerobic exercise and education about risk factors and medication compliance, but the record gives limited detail about program delivery, session attendance recording, or the definition and verification of attendance. The adverse-event counts are reported, but the record does not specify the safety follow-up window or provide detailed event-monitoring procedures. A statistical analysis plan, sample-size justification, and multiplicity approach are also not reported. These gaps limit assessment of both the feasibility result and the completeness and precision of the safety findings.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Comprehensive Cardiac Rehabilitation Feasibility After Stroke — NCT03944668.
• Registry record last updated 2023-05-16; status last verified 2020-09.
• Results first posted 2021-02-24.
• 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

NCT03944668 is a completed, single-group study of comprehensive cardiac rehabilitation feasibility after stroke, sponsored by HealthPartners Institute. The registry lists enrollment as 17 and describes the primary outcome population as 14 stroke patients who enrolled and consented; the relationship between these entries is not explained.

The primary outcome is Attendance Rate over 12 weeks, with a criterion of 75% attendance. The observed attendance result is not reported in the registry record. The adverse-event entries report 0 serious adverse events among 14 at risk, 0 other adverse events among 14 at risk, and 0 deaths. The record lists 6 outcome measures and 0 analyses. It does not report a comparator, inferential results, missing-data procedures, or a statistical analysis plan.