ENgaging in Advance Care Planning Talks Group Visit Intervention for Cognitive Impairment: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for ENgaging in Advance Care Planning Talks Group Visit Intervention for Cognitive Impairment (NCT03711396), a non-randomized na study. The primary outcome is Change in Readiness to Engage in ACP (ACP Engagement Scale).

2. Clinical Question

The study concerns adapting a group-visit approach for people with aMCI and their family care partners. The registry describes the intervention as an approach to encourage conversations and documentation about advance care planning. Its primary outcome focuses on participants’ readiness to take part in specific advance care planning behaviors, rather than on a clinical health event.

Because the study is listed as a single-group, non-randomized trial, the primary question is about change over time in the participants receiving group visits. It is not a randomized comparison of the intervention with an alternative. The record does not report an outcome estimate, so it does not establish whether readiness changed, how large any change was, or how precisely a change was estimated. It also does not report a separate comparison that could distinguish change associated with the intervention from change over time or other influences.

3. Trial Design

The registry describes a completed, non-randomized, single-group behavioral intervention study. The listed enrollment is 26. The sponsor is the University of Colorado, Denver. The record gives a start date of 2019-02-01 and a primary completion date of 2020-10-31.

The intervention is called Advance Care Planning Group Visits. Participants with aMCI were to attend group visits with their study partners to discuss advance care planning. The care-partner description likewise says that care partners attend with the person with mild cognitive impairment. Visits were described as lasting up to two hours and occurring up to twice. The brief description says the approach was initially designed for people without cognitive impairment and that this study would investigate ways to adapt it for people with aMCI and their family care partners.

The design is not randomized and is not masked. No separate control condition is described. Although the record contains descriptions for participants with aMCI and care partners, it characterizes the overall model as single-group; those descriptions should not be read as evidence of a treatment-versus-control comparison. The record does not report how participants were recruited, how they were assigned to particular visit groups, or what procedures were used to ensure that the intervention was delivered consistently.

The primary outcome is a change in ACP Engagement Scale score for participants with aMCI, with the timeframe listed as 0 and 3 months. The registry lists a secondary outcome concerning change in readiness to engage in advance care planning based on care-partner report. It lists three outcome measures overall, but does not report outcome estimates or analysis entries. The record does not report further details of the statistical plan, such as a prespecified model or a method for handling repeated 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

Analysis population for the primary outcome, as defined in the registry: Participants with aMCI

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: Participants with aMCI who were enrolled to group visits with a study partner. Demographics data were not collected for the care partners.

6. Primary Endpoint

The registry lists the primary outcome as Change in Readiness to Engage in ACP (ACP Engagement Scale), measured over 0, 3 months.

The primary endpoint is change in readiness to engage in advance care planning, measured with the ACP Engagement Scale for participants with aMCI. The measure addresses readiness to take part in specific behaviors: signing official papers to name a medical decision maker, talking to that decision maker, talking to a doctor, and signing official papers to put wishes in writing. Items use a Likert scale with possible scores ranging from 1-5. Higher scores indicate greater engagement with the advance care planning behavior and are defined in the registry as a better outcome.

The record lists the outcome parameter as a mean and its dispersion as a standard deviation. It gives the timeframe as 0, 3 months. A mean describes the average score in the assessed group; a standard deviation describes how spread out individual scores are around that average. The endpoint is relevant to the study’s stated focus on readiness to have advance care planning conversations and document preferences. It is not itself a measure of whether documents were completed, whether conversations occurred, or whether a medical outcome changed.

The registry record does not report the mean scores at either time point, a change estimate, a standard deviation for change, or a confidence interval. Consequently, the size and precision of any change cannot be determined from the reported information.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary measure is continuous, and the registry specifies a mean and standard deviation. General statistical explanation: a mean gives a group’s average value, while a standard deviation describes the variability of individual values around that average. These statistics answer different questions. A mean describes the group’s central level on the measure; a standard deviation describes how similar or dispersed the participants’ scores are. Neither is reported for the primary outcome in the registry record.

What would a change estimate describe?

For a repeated measure, a change estimate describes the difference between a participant’s later and earlier scores, or an average of such differences across participants, depending on the analysis method. General statistical explanation: using the same participants at both time points can account for the fact that each person has their own starting score. A paired analysis considers within-person changes, while other approaches can model scores over time. The registry record does not report which method was planned or used, or whether the available observations were analyzed as paired measurements.

A change estimate should be interpreted alongside its uncertainty. General statistical explanation: a confidence interval gives a range of values reasonably compatible with the data under the assumptions of the analysis. A narrower interval indicates greater precision than a wider interval. A p-value, when reported, addresses how compatible the data are with a specified null model; it does not describe the size or practical importance of a change. No confidence interval or p-value for the primary outcome is reported in the registry record, so neither precision nor statistical evidence of change can be assessed.

What does the design imply for inference?

The registry identifies a single-group, non-randomized design with no masking. General statistical explanation: random assignment can help balance measured and unmeasured characteristics between comparison groups, while a concurrent control group can help account for changes that would have occurred even without the intervention. This study’s listed design does not provide that randomized comparison. If before-and-after results were available, they would describe observed change in the group; they would not, on their own, establish that the intervention caused that change.

Masking can reduce some forms of influence on how outcomes are assessed or reported. The registry lists masking as none. Since the primary outcome is a readiness measure, it is also important to know how scores were collected and whether participants knew the study’s aims when responding. Those details are not reported in the registry record. This does not show that bias occurred; it identifies information needed to evaluate potential sources of bias.

How should planning calculations be read?

The record describes a sample-size planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect, and that non-time-to-event planning quantities are participants per arm. Those assumptions describe a planning calculation, not the design of this single-group trial. The record does not report numerical planning outputs or a numerical observed effect. The illustration should not be interpreted as evidence that the study had a particular level of power, nor as observed power. A sample-size calculation is a planning aid based on assumptions; it does not substitute for an outcome estimate or its uncertainty.

General statistical explanation: power is the probability, under specified assumptions, of detecting an effect of a chosen size using a particular design and analysis. It depends on factors such as the effect being targeted, variability, sample size, and the decision threshold. When an illustration assumes two arms but the registered study is single-group, the illustration does not directly describe the enrolled design. The record does not report a trial-specific sample-size justification or a statistical analysis plan, so the planning illustration cannot establish what considerations shaped the study’s enrollment.

What can be said about distribution and model choice?

The primary endpoint is a scale score, and the registry describes it as a continuous measure summarized by a mean and standard deviation. General statistical explanation: a statistical model should be appropriate to the outcome’s scale, the pattern of repeated observations, and the data’s distribution. A mean-based summary can be useful, but its interpretation and precision depend on the observed score distribution and the chosen analysis. The registry record does not report diagnostic checks, model assumptions, or any alternative analyses. There is no basis to state that a particular model was used or that its assumptions were met.

General statistical explanation: over-dispersion refers to greater variability than a statistical model expects. When it occurs, standard errors and confidence intervals from an overly restrictive model can be misleading. It is a general consideration in model selection, but this record does not identify an over-dispersed outcome or report a model for which over-dispersion was assessed. It would be inappropriate to infer that this issue affected the study.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists three outcome measures, including the primary ACP Engagement Scale outcome and a secondary outcome on change in readiness to engage in advance care planning based on care-partner report. It does not name every outcome in the brief information, and it does not report analysis entries. No multiplicity adjustment or hierarchy for testing outcomes is reported in the registry record.

General statistical explanation: when several outcomes or several comparisons are tested, the chance of at least one apparently notable result can increase. A prespecified primary outcome and a clear testing strategy help readers distinguish the main question from secondary or exploratory analyses. Adjustments can also be used to control error across multiple tests. The record does not say whether any such strategy was planned or used. Since no outcome tests are reported, the effect of multiplicity on conclusions cannot be assessed.

Missing outcome data are not described. The record does not report the number of participants with measurements at each time point, reasons for missingness, or a method for handling incomplete data. Enrollment of 26 does not establish how many participants contributed to the primary analysis. General statistical explanation: missing data can affect both the precision and interpretation of an estimate, particularly when the likelihood of a missing measurement is related to participants’ outcomes or characteristics. Without information about completeness and handling, the direction or extent of any resulting bias cannot be evaluated.

The analysis population is also not reported. The record does not specify whether analyses included everyone enrolled, only participants who attended visits, or another defined group. These distinctions can matter when interpreting an intervention study. No analysis population or missing-data assumption should be inferred from the enrollment count alone.

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 5% reporting threshold.

The registry reports one safety group, Advance Care Planning Group Visits, with 13 participants at risk. It records 0 participants affected by serious adverse events, 0 affected by other adverse events, and 0 deaths. No leading serious adverse-event terms are listed. These are the counts entered for the reported group; they are not estimates of comparative risk because no control group is described.

A zero count means that no events of the specified type were recorded in this group in the registry results. It does not establish that an event was impossible, or that there was no risk beyond the observation captured in the record. The registry does not report the safety observation period, the methods used to collect events, or further detail about event definitions and ascertainment. The listed 13 at risk should not be replaced by the total enrollment when interpreting this safety entry, and the record does not explain the relationship between that safety denominator and the enrollment of 26.

Because no comparison group or event terms are reported, the safety information is descriptive. It cannot establish whether the intervention changed the occurrence of adverse events relative to another condition. The registry record also does not provide details that would support a broader assessment of safety beyond these recorded counts.

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

The registry record documents a study intended to adapt advance care planning group visits for people with aMCI and their care partners. It defines a primary outcome concerned with participants’ readiness to engage in advance care planning behaviors. However, it does not report the primary outcome values or an estimate of change. The central statistical result is therefore unavailable in the registry record, and no direction or size of change can be stated.

Even if a before-and-after estimate were available, the listed single-group, non-randomized design would constrain its interpretation. An observed change would describe the participants’ scores over time. Without a separate comparator, it would not by itself show that the group visits caused the change. This distinction is about what the design can establish, not a judgment about whether the intervention is useful.

The registry describes the scale’s possible scores as ranging from 1-5 and defines higher scores as indicating greater engagement with the advance care planning behavior. That helps explain what the endpoint is intended to capture, but it does not reveal participants’ actual scores. No clinical outcome, completion of advance care planning documents, or effect on care is reported as a result in the information available in the registry record.

The safety entry reports 0 serious adverse events, 0 other adverse events, and 0 deaths among 13 at risk in the listed group. Those are descriptive registry counts and do not provide a comparison with an alternative condition. The record also does not give sufficient information to characterize the duration or completeness of safety follow-up.

Accordingly, the record supports a description of the study question, intervention, design, and selected safety counts, but not a conclusion about the magnitude, precision, or cause of a change in readiness. The absence of reported outcome analyses should not be mistaken for evidence that the outcome did not change.

13. Why This Trial Matters Statistically

This study raises a statistical question that is important in intervention research: how should change in a behavioral measure be interpreted when participants are followed in a single group? The ACP Engagement Scale gives the study a defined outcome focused on readiness for particular advance care planning behaviors. The registry also distinguishes the participant-reported primary outcome from a care-partner-reported secondary outcome. Those features clarify whose perspective is being measured and what kind of change the study sought to assess.

The single-group design makes the limits of causal interpretation especially visible. General statistical explanation: measuring participants over time can describe a trajectory, but a comparator is needed to help distinguish intervention-associated change from other explanations for change. Randomization, masking, and a well-described analysis plan are elements that help readers assess how a result was generated and what inferences it supports. The registry lists the study as non-randomized and unmasked, and does not report detailed analysis methods or outcome estimates.

The record also illustrates why enrollment and results are not interchangeable. Enrollment is listed as 26, while the safety group has 13 participants at risk; the record does not report the number with complete primary-outcome data. Without analysis counts, effect estimates, and uncertainty measures, readers cannot determine how informative the outcome data are. Nor can a planning illustration, described using two-arm assumptions, stand in for the results of a single-group study.

These statistical distinctions matter for interpreting research on adapting interventions for people with cognitive impairment and their care partners. A clear outcome definition is useful, but readers also need transparent outcome data, analysis populations, missing-data information, and design details to judge what the findings can support. The registry record leaves those result and methods questions unanswered.

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.

The most important limitation for interpreting the registry record is that it contains no numerical primary-outcome results and no analysis entries. Without scores, a change estimate, or uncertainty measures, the amount and precision of any change in readiness cannot be evaluated. The listed enrollment of 26 does not show how many participants completed the outcome assessment at either time point.

The registered design is single-group, non-randomized, and unmasked, with no separate control condition described. As a result, the design does not provide a randomized comparison for attributing any observed change to the group visits. The record does not report whether participants knew the study aims when completing the readiness measure, or how outcome assessments were administered.

The record does not give details about recruitment, participant characteristics beyond the population description, visit attendance, intervention fidelity, or the handling of deviations from the intended visits. It describes visits as lasting up to two hours and occurring up to twice, but does not report how many participants attended or whether delivery varied. These omissions limit assessment of who took part and what exposure to the intervention was received.

Statistical methods are also insufficiently detailed for evaluation. The record does not report the analysis model, uncertainty estimates, analysis population, missing-data approach, or multiplicity strategy. The sample-size planning description uses equal allocation between two arms, whereas the registered study is single-group; no numerical planning outputs or trial-specific sample-size justification are reported. The safety record contains descriptive counts but does not specify the observation period or event ascertainment methods. These limitations concern what can be learned from the registry record and should not be treated as evidence that unreported procedures or analyses did not occur.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: ENgaging in Advance Care Planning Talks Group Visit Intervention for Cognitive Impairment — NCT03711396.
• Registry record last updated 2021-11-22; status last verified 2021-10.
• Results first posted 2021-11-22.
• 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

NCT03711396 is a completed, non-randomized, single-group behavioral study sponsored by the University of Colorado, Denver. The listed enrollment is 26, with a start date of 2019-02-01 and a primary completion date of 2020-10-31. The study concerns Advance Care Planning Group Visits for people with aMCI and their care partners.

The primary outcome is change in participants’ readiness to engage in advance care planning, measured with the ACP Engagement Scale at 0 and 3 months. The scale’s possible scores range from 1-5, with higher scores indicating greater engagement. A care-partner-reported readiness outcome is also listed as secondary.

The registry record does not report primary-outcome estimates, analysis entries, missing-data methods, or a detailed statistical analysis plan. Its safety entry records 0 serious adverse events, 0 other adverse events, and 0 deaths among 13 at risk in the listed group. The record therefore describes the trial’s design and intended outcome, but does not provide results sufficient to estimate change or its precision.