Messy Memories: Mobile Application Therapy Following Critical Illness: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Messy Memories: Mobile Application Therapy Following Critical Illness (NCT05849454), a na na study. The primary outcome is Percentage of Screened Participants Who Screen Eligible for the Study.

2. Clinical Question

The central question is about whether the study could recruit eligible people for a future investigation, not whether the application reduces distress compared with another treatment or with no intervention. The registry also describes interest in whether participants would be willing to use the application and satisfied with it. Those aims concern feasibility and acceptability; the registry record does not report numerical results for them.

The listed secondary outcomes cover psychological symptoms and health behaviors, including scores for post-traumatic stress, depression, anxiety, and anxiety sensitivity, as well as physical activity, sleep duration, sleep medication use, and sleep quality. These outcomes indicate areas the study intended to assess. Without reported outcome estimates, they do not establish the direction or size of any change.

3. Trial Design

This is a completed, single-group feasibility study of the Messy Memories intervention, registered as NCT05849454. The registry lists an enrollment of 29 and identifies Columbia University as the sponsor. The study began on 2023-10-31, reached primary completion on 2024-07-15, and has a completed status.

All enrolled participants were assigned to the experimental arm. The registry lists allocation as NA and masking as NONE. It does not describe a randomized comparison, and the record explicitly flags that the arms are not a like-for-like control comparison. In practical terms, the registered design does not support a controlled estimate of how the intervention compares with an alternative.

The intervention was a mobile application intended to help users process a distressing memory related to their ICU hospitalization. The planned use was 6 weeks, at least 3 times each week, for 30 or more minutes per session. Questionnaires were planned over a 12-week period. The population was restricted to English-speaking adults discharged from an ICU at least one month earlier who experienced some distress related to that experience and had the technology needed to use the application.

The stated primary outcome was the percentage of screened participants who screened eligible, measured at baseline before the intervention. This is a recruitment-feasibility measure, rather than a clinical outcome. The registry lists 17 outcome measures and names secondary measures spanning psychological symptoms and health behaviors. Detailed adherence, retention, questionnaire completion, and participant satisfaction results are not reported in the registry record. The registry record also does not report a statistical analysis plan or describe the rationale for the enrollment target.

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: Because this was a feasibility study, we were interested in examining how many individuals needed to be screened to reach the target sample. Therefore, one of our primary outcome measures was the proportion of screened participants who screened eligible for the study. This would necessarily make the overall number of participants analyzed for this measure greater than the number of participants assigned to the arms or groups in the Participant Flow.

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: Baseline characteristics of the 29 participants who consented to study enrollment are reported below

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Screened Participants Who Screen Eligible for the Study, measured over Baseline (pre-intervention).

The primary endpoint is the percentage of screened participants who screened eligible for the study, assessed at baseline before the intervention. The registry describes it as a measure of the feasibility of recruitment. This endpoint addresses an early practical question: among people screened for a study, what proportion meet the criteria required to enroll?

As a proportion, this outcome depends on both the number of screened people found eligible and the total number screened. Those counts, the observed percentage, and the reported 95% confidence interval are not reported in the registry record. The enrollment of 29 does not supply the screening denominator: enrollment refers to participants enrolled, while the endpoint concerns people screened. These quantities should not be treated as interchangeable.

A confidence interval communicates uncertainty around an estimate. In general, a wider interval indicates less precision, while a narrower interval indicates greater precision, under the assumptions of the method used. The registry names a 95% confidence interval for the primary outcome, but the method used to calculate it is not reported in the registry record. Without the estimate and interval, the registry record cannot show how precisely recruitment eligibility was measured.

This endpoint can inform planning for a larger study by describing the screening-to-eligibility process. It does not measure change in psychological distress, prove that the application is acceptable to participants, or establish an intervention effect. Those questions require their own reported outcomes and appropriate analyses.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes the primary outcome as a percentage of screened participants who were eligible, with a 95% confidence interval. It does not name the statistical procedure used to estimate the percentage or construct the interval. That distinction matters: a measure can be described in the registry while the calculation method remains unspecified.

What does a percentage estimate represent?

For a binary outcome such as eligible versus not eligible, the percentage is based on the eligible count relative to the number screened. The denominator must be the screened population relevant to that outcome. Enrollment is a different quantity, because people may be screened without enrolling. Since the screening count and eligible count are not reported in the registry record, the primary estimate cannot be reconstructed from the listed enrollment.

In general, a confidence interval gives a range of values compatible with the observed data under a stated statistical method. It describes uncertainty in an estimate; it is not a guarantee that the true value lies in the interval, and it does not describe variation among individual participants. The registry specifies a 95% confidence interval, but the interval itself and the calculation method are not reported in the registry record. It is therefore not possible to assess the interval’s width or evaluate the method used.

Why does the single-group design matter?

All enrolled participants were assigned to the Messy Memories intervention, and the registry does not describe a separate control group. A single-group study can describe recruitment, use, and outcomes within the enrolled group. However, it cannot make a direct randomized comparison with another group. In general, when measurements change over time in one group, the change may have more than one explanation. Without a suitable comparison, the intervention’s contribution cannot be separated from other influences using a between-group contrast.

The registry lists the masking status as NONE and allocation as NA. It does not report additional details about outcome assessment or the statistical plan. No particular adjustment method, model, or testing procedure should be assumed from the outcome descriptions alone.

How should the secondary outcomes be read?

The registry names 17 outcome measures and identifies secondary measures covering symptom questionnaires and health behaviors. A score or behavior measured repeatedly could be summarized in different ways, depending on the prespecified estimand, measurement schedule, and analysis method. The registry record does not report those details or numerical results. In general, an outcome’s name alone is not enough to determine whether the analysis concerns change from baseline, a value at a particular assessment, or another summary.

Multiplicity is a general concern when many outcomes are examined: the chance of at least one apparently notable result can rise when multiple statistical tests are performed. Whether and how to address that concern depends on the analysis plan and the purpose of the outcomes. The registry record does not report the testing hierarchy, multiplicity adjustment, or an analysis plan, so no claim about such procedures is justified.

Missing-data methods are also important for questionnaire outcomes. In general, an analysis can be affected if participants do not complete assessments, particularly when missingness is related to symptoms, intervention use, or other characteristics. The registry record does not report completion counts, reasons for missing data, imputation, or sensitivity analyses. It also does not define the analysis population for the listed outcomes.

Sample-size calculations, when used in planning, are not observed effects or evidence of achieved power. The registry record does not report its own sample-size justification. Any planning illustration associated with the posted results should be understood as a hypothetical calculation under its stated assumptions, rather than as the design rationale or an observed result from this feasibility study.

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("Messy Memories Intervention")
n      <- c(69)
events <- c(45)
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  Messy Memories Intervention  69  45  65.2  52.8  76.3  53.4  75.4  53.4  75.4

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 17 outcome measures, including the primary recruitment-feasibility endpoint and secondary measures of symptoms and health behaviors. The record does not report a statistical analysis plan, identify a testing hierarchy, or state whether any adjustment for multiple comparisons was planned or used. In general, examining many outcomes can increase the chance of obtaining at least one apparently notable result by chance. Without the analysis plan and results, the implications of multiplicity for this study cannot be assessed.

Missing-data information is not reported in the registry record. The record does not give questionnaire completion counts, outcome-specific denominators, reasons for missing assessments, or methods for handling missing values. These details are relevant because the people with completed measurements may differ from those without them. No assumptions about completeness or the effect of missingness are warranted from the enrollment figure alone.

The record also does not define analysis populations for the primary or secondary outcomes. It does not say whether analyses included all enrolled participants, only participants who completed particular assessments, or another group. For the primary endpoint, the number screened and the number eligible are not reported, so its denominator cannot be verified from the record.

Although a 95% confidence interval is specified for the primary endpoint, the numerical estimate and interval are not reported. The registry record does not report the method used to calculate that interval. These omissions limit evaluation of both the precision of the recruitment estimate and the handling of uncertainty across the broader set of outcomes.

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 registry’s adverse-event information lists 29 participants at risk in the Messy Memories Intervention group, with 0 serious adverse events and 0 deaths. The other-event category also lists 29 at risk and 0 affected. These are the recorded counts for the categories shown in the registry record.

A zero count means that no events in that category were recorded in the registry entry; it does not demonstrate that the intervention is free of risk. Serious events are only one part of safety reporting, and the registry record does not give a detailed description of how adverse events were solicited, monitored, defined, or followed over time. It also does not report a fuller account of non-serious experiences.

The listed count should not be read as a comparison with another group, because the study is single-group and has no separate control arm. The registry record also does not provide the information needed to assess whether all participants contributed equally to safety follow-up. The appropriate reading is therefore limited: the registry reports 0 serious adverse events and 0 deaths among the participants listed as at risk, without establishing an absence of all adverse experiences.

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

The study addresses a practical question about recruiting people who have experienced critical illness into a study involving a mobile application. The registered primary outcome, the percentage of screened participants who were eligible, is relevant to planning recruitment for further research. However, the registry record does not report that percentage, its denominator, or its 95% confidence interval. The recruitment result and its precision therefore cannot be judged from the posted record.

The study also planned to assess use of the application, questionnaire outcomes, and satisfaction-related aims. The registry record describes the intervention schedule and lists psychological and health-behavior measures, but it does not report numerical results for those outcomes or participant satisfaction. Listing an outcome does not establish that it changed or that participants found the intervention acceptable.

Because the study has one intervention group and no like-for-like control comparison, the registered design does not provide a randomized estimate of the intervention’s effect relative to an alternative. General changes over time in a single group cannot, on their own, isolate the cause of those changes. The registry record also does not report analyses that would quantify changes or their uncertainty.

The recorded safety figures are limited to the listed categories and show 0 serious adverse events and 0 deaths. They do not establish that no adverse experiences occurred. More broadly, the completed status indicates that the study reached its registered completion status; it does not supply missing outcome results or answer questions about effectiveness.

The record can therefore be read as documenting a feasibility study’s rationale, design, intervention schedule, and registered outcome domains. It does not provide the reported results required to judge recruitment yield, adherence, acceptability, symptom changes, health-behavior changes, or intervention effectiveness.

14. Why This Trial Matters Statistically

Feasibility studies address whether a larger investigation can be conducted and what practical issues it may need to resolve. This study’s primary endpoint focuses on the proportion of screened people who met eligibility criteria. That is a distinct question from whether an intervention changes a clinical outcome. Separating these aims helps readers avoid treating a recruitment measure as evidence of clinical benefit.

The registry describes a population with distress related to an ICU experience and an application intended to help users process a difficult memory at their own pace. It also describes a planned schedule of app use and questionnaires. Those details identify an approach and a research context, but the registry does not report results on recruitment, actual use, or satisfaction. Reporting such feasibility outcomes would help clarify whether the study procedures were workable in practice.

The single-group design is statistically relevant because it can describe outcomes within the intervention group but does not supply a direct randomized comparison. A future study intended to estimate comparative effects would need an appropriate design and a clearly reported analysis. The registry record says the investigators hoped this feasibility work would inform the design of a larger trial; it does not report that larger trial’s design or results.

Finally, confidence intervals and transparent denominators matter for interpreting feasibility estimates. A percentage without its screened denominator is difficult to assess, while an interval helps convey uncertainty when reported with the estimate. Here, the primary estimate and interval are not reported in the registry record. The distinction between registered aims and reported results is therefore central: the record explains what the study set out to evaluate, but does not provide the numerical findings needed to evaluate those aims.

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 registry record contains limited reported outcome information. In particular, it does not report the primary eligibility percentage, the number screened, the eligible count, or the 95% confidence interval named for that outcome. This prevents assessment of recruitment yield and precision.

The study is single-group, with all enrolled participants assigned to the intervention and no like-for-like control comparison. This limits what can be inferred about the cause of any change over time. In addition, the registry record does not report numerical results for the listed secondary measures, including the psychological and health-behavior outcomes.

Important feasibility details are also not reported in the registry record: actual application use, adherence to the requested schedule, questionnaire completion, retention, and participant satisfaction. These details would help distinguish planned participation from participation achieved in practice. The record does not state the analysis populations, missing-data methods, or the statistical procedures used for the primary confidence interval and secondary outcomes.

The registry lists 17 outcome measures, but does not report a testing hierarchy or multiplicity approach. It also does not report its own sample-size justification. Finally, the serious-event information is limited to the listed counts and does not describe event-monitoring procedures or provide a fuller account of non-serious events. These limitations concern what can be learned from the registry record; they do not establish that the study did or did not collect additional information.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Messy Memories: Mobile Application Therapy Following Critical Illness — NCT05849454.
• Registry record last updated 2025-09-22; status last verified 2025-09.
• Results first posted 2025-09-22.
• 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.

19. Record Summary

NCT05849454 is a completed, single-group feasibility study of the Messy Memories mobile application following critical illness, sponsored by Columbia University. The registry lists an enrollment of 29, with study dates from 2023-10-31 to primary completion on 2024-07-15. All enrolled participants were assigned to the intervention; allocation is listed as NA and masking as NONE.

The primary outcome was the percentage of screened participants who screened eligible, with a 95% confidence interval specified. The observed percentage, screening denominator, eligible count, and interval are not reported in the registry record. The record lists 17 outcome measures, including secondary symptom and health-behavior outcomes, but does not report their numerical results or analysis methods. The adverse-event entry lists 0 serious adverse events and 0 deaths among 29 participants at risk.