eLearning for Suicide Prevention: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for eLearning for Suicide Prevention (NCT05178121), a na na study. The primary outcome is Training Acceptability - System Usability Scale for Client Bot Emily.

2. Clinical Question

3. Trial Design

NCT05178121, titled “eLearning for Suicide Prevention,” is a completed study of an eLearning approach to suicide safety planning. The official title describes a formative evaluation. The project summary places the work within Project WISE (Workplace Integrated Support & Education), which includes developmental and pilot research to create training that can be integrated into nurses’ routine workflow. The planned setting is care for patients hospitalized for medical, surgical, or traumatic injury reasons.

The registered design is single group, with allocation listed as not applicable and masking listed as none. The intervention is behavioral training: Project WISE eLearning Training in Suicide Safety Planning. There is no registered like-for-like control arm, so the study is not a randomized comparison of training against another condition. Its role is formative: to pilot an initial version and collect information about acceptability of the training and its components, as well as nurses’ engagement. The stated purpose is to inform later iterations of the training.

Enrollment is listed as 19. The study start date is 2021-11-01, primary completion is 2023-03-01, and status is completed. Phase is listed as not applicable. The registry record does not report a sample-size justification or further details about the allocation process. It also does not provide participant characteristics or explain how many participants contributed to each outcome.

The intervention description names two technology components. Client Bot Emily is a virtual patient/chat bot with the persona of a suicidal patient. Lyssn Advisor is an online platform that automatically codes transcripts of recorded role-plays and gives nurses feedback on counseling performance. The primary endpoint is acceptability of Client Bot Emily; the broader stated evaluation covers both technologies. The record lists 12 outcome measures and no recorded analyses. These design details support reading the study as a pilot assessment of a training approach, rather than a test of clinical outcomes or comparative effectiveness.

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:

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: 18 of 19 enrolled participants actually participated in the study and completed a baseline measure of demographics.

6. Primary Endpoint

The registry lists the primary outcome as Training Acceptability - System Usability Scale for Client Bot Emily, measured over Once, immediately after engaging with each of the training technologies.

The primary endpoint is titled Training Acceptability - System Usability Scale for Client Bot Emily. It uses the System Usability Scale (SUS), a self-report measure based on Likert-type ratings, to assess how acceptable or usable participants find a technology. The registered outcome is a mean score with standard deviation. The stated scale runs from 0-100, with higher scores indicating greater usability or acceptability.

Client Bot Emily is described as a virtual patient/chat bot with the persona of a suicidal patient. Nurses chat with Emily to practice asking open-ended questions and making reflections about statements Emily makes. A usability measure is relevant to a formative evaluation because an interactive training component must be usable enough for learners to engage with it. This measure concerns participants’ reported experience of the technology; it is not a direct measure of skill acquisition, performance with patients, or patient outcomes.

The timeframe is once, immediately after engaging with each training technology. Although the outcome title specifies Client Bot Emily, the description discusses acceptability assessment of both Client Bot Emily and Lyssn Advisor. The registry record does not report the mean SUS score, standard deviation, number of observations contributing to the primary score, or any interpretation against an acceptability threshold. Consequently, the endpoint definition is available, but its observed result cannot be interpreted from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the primary score represent?

The SUS is described as a self-report measure using Likert-type ratings. In general, a scale score condenses a participant’s responses into a value intended to represent a broader construct—in this case, perceived usability or acceptability. The record states that the score ranges from 0-100 and that higher scores indicate greater usability or acceptability. It does not report the score observed for Client Bot Emily, so the scale’s range and direction should not be mistaken for a study result.

The registered summary measure is the mean. In general, a mean represents the arithmetic average of the observations included in an analysis. Its interpretation depends on which observations are included and how the measure is scored. The registry record does not report the number of completed SUS assessments or the scoring details used for the primary result. Therefore, the intended summary is identifiable, but the value and analysis population behind it are not.

Why is a standard deviation listed?

The endpoint specifies standard deviation as its measure of dispersion. In general, a standard deviation describes how spread out individual observations are around their mean. It gives information about variation among ratings, whereas the mean describes their average level. Neither quantity is reported for Client Bot Emily in the registry record, so it is not possible to assess either the central tendency or the spread of the observed ratings.

A standard deviation is not the same as a confidence interval. In general, a confidence interval describes uncertainty around an estimated quantity, while a standard deviation describes variation among observations. The record does not state a confidence interval for the primary outcome. Without a reported estimate and its uncertainty, readers cannot judge how precise the primary result would be, even if the mean had been included.

What does the single-group structure allow?

This is a single-group study with allocation listed as not applicable. In general, a single-group formative study can describe participants’ experiences and identify issues for further development, but it does not provide a concurrent control condition for estimating a comparative effect. Here, the stated goals are to pilot an initial training version and assess acceptability and engagement. The design aligns with those developmental goals, but it is not a randomized test of the training against another intervention.

Masking is listed as none. In general, masking can reduce the influence of knowledge about assigned treatment on certain measurements, but the registry record does not specify any masked assessment procedures. For a self-report usability measure, participant ratings reflect participants’ own experience and judgments. The record does not provide information about how expectations, prior experience, or other influences were assessed.

How should the planning assumptions be read?

The registry information 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 that the effect to detect is a stated fraction of the observed effect. Such calculations are planning illustrations, not observed power. They do not demonstrate the probability that this completed study detected an effect, and they should not be confused with the study’s actual design, which is single group.

The record does not report a sample-size justification for the pilot or the results needed to interpret an effect-based planning illustration. The effect estimate underlying that illustration is not available in the registry information described for this study. No planning sample-size result should therefore be treated as evidence about the primary endpoint or as a description of participants actually analyzed.

In general, power calculations depend on assumptions about the design, outcome variability, target effect, and analysis. A calculation for two equally allocated arms does not match a single-group study without a comparator. The listed assumptions are useful to recognize as planning conventions, but the record does not explain their relationship to this formative evaluation. There is no basis to infer a prespecified target, interim analysis, or confirmatory testing plan.

What can recalculation add?

No recalculated primary estimate is reported. In general, recalculation from summary statistics can check or restate a simple unadjusted result when the relevant group summaries are available. Here, the primary mean and standard deviation are absent, and there is no comparison group. A recalculation cannot fill in missing outcome information or provide a comparative estimate that the design did not generate. The registry record also contains no sponsor analysis for this outcome that could be compared with a recalculated result.

The key statistical distinction is between an outcome that is defined and an outcome that is reported. The endpoint definition specifies the construct, scale, summary measure, and timeframe. Those details clarify what the study intended to assess. They do not establish what participants rated, how much ratings varied, or how precisely the underlying acceptability level was estimated.

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("Project WISE eLearning Training in Suicide Safety ")
n   <- c(16)
m   <- c(70.3)
sp  <- c(19.7)
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  Project WISE eLearning Training in Suicide Safety   16  70.300  19.700  59.803  80.797

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 12 outcome measures, but it does not report their results or a statistical analysis plan explaining how multiple outcomes were handled. In general, when several outcomes or statistical tests are considered, the chance of at least one apparently unusual result can increase if no adjustment or prespecified hierarchy is used. The record does not report whether any multiplicity strategy was planned, so no claim about adjustment, prioritization, or confirmatory interpretation is warranted.

The record identifies the SUS measure for Client Bot Emily as the primary outcome. It does not state how missing outcome data were handled, whether participants could skip items, or how incomplete questionnaires would be scored. It also does not report the number of completed assessments for the primary endpoint. Enrollment of 19 should not be assumed to equal the number included in an outcome analysis.

In general, missingness can affect both the size and representativeness of the observed data. If participants who do not complete an assessment differ from those who do, a mean calculated from available responses may not describe the full enrolled group. The registry record does not report a missing-data method, sensitivity analysis, or reasons for missing observations. It does not identify an analysis population beyond the registered enrollment information.

The record lists no analyses. Thus, there is no reported account of exclusions, scoring decisions, or handling of missing values to evaluate. These are reporting gaps, not evidence that data were missing or that any particular method was used.

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 information lists one group, Project WISE eLearning Training in Suicide Safety Planning. For that group, 18 participants are listed as at risk for serious adverse events, and 0 are listed as affected. The record also lists 18 at risk for other adverse events and 0 affected. Deaths are listed as 0. No top serious-event terms are listed.

These are registry safety counts, not a comparison with another group. Because the design is single group, there is no control group in this record against which to compare event counts. The listed at-risk count is not the same as the enrollment figure, and the registry record does not explain the difference or specify the safety analysis population.

In general, a count of zero reported events is not proof that an event is impossible, nor does it establish that all possible events were assessed or reported. The record does not provide detail about event definitions, collection procedures, observation duration, or whether any events were considered unrelated. The appropriate reading is limited to the counts recorded: no serious or other adverse events are listed as affecting participants in the stated group, and deaths are recorded as 0.

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

This study addresses a practical development question: how acceptable a new eLearning approach and its technology components are to nurses using them in training. Its primary measure, the SUS score for Client Bot Emily, is intended to capture perceived usability or acceptability shortly after engagement. That makes the endpoint relevant to refining an interactive training experience, but it is distinct from evidence about clinical effectiveness.

The registry record does not report the primary score or standard deviation. It therefore cannot establish whether ratings were high or low, whether they varied substantially, or how precisely an average rating was estimated. The absence of those results is not evidence that participants disliked the training, nor is the completed status evidence that they accepted it. The quantitative result needed to answer that question is not reported in the registry record.

Even a reported SUS result would speak to perceived usability or acceptability, not by itself to learning, skill retention, changes in nursing practice, or patient outcomes. The project description says that nurses practice communication skills with Client Bot Emily and receive feedback through Lyssn Advisor. Those are features of the training, not outcomes demonstrated by the primary endpoint. No conclusion about improved care or suicide prevention can be drawn from the registered primary measure.

The single-group design is appropriate to describe a pilot experience but cannot establish comparative effects against another training approach. No control condition is registered, and no randomized allocation is described. The record’s formative purpose is to inform future iterations, so its contribution is principally about the planned evaluation and development context. Yet because the primary outcome result is not reported, the registry information cannot show what changes the evaluation might support.

The most defensible conclusion is therefore about scope: this was a completed pilot of a behavioral eLearning training, with usability/acceptability identified as a primary outcome and engagement among the stated interests. The registry record does not provide the primary numerical findings needed to quantify acceptability or to judge the precision of that assessment.

14. Why This Trial Matters Statistically

Formative studies often address questions that arise before a larger evaluation: whether a training component can be used as intended, whether participants engage with it, and which features may warrant revision. This study’s stated purpose fits that developmental role. Project WISE aims to integrate suicide safety planning training into the routine workflow of nurses serving hospitalized patients, and the pilot is described as a way to assess acceptability and engagement while informing later iterations.

The statistical distinction between feasibility-oriented measurement and effectiveness testing matters. A self-reported SUS score can describe perceived usability, but it does not establish that a training changes professional behavior or patient outcomes. Likewise, a single-group design does not estimate a comparative treatment effect. Keeping the question and design aligned prevents a pilot from being interpreted as a controlled efficacy trial.

Clear reporting is especially important for formative work because the information is often meant to guide practical decisions about refinement. A mean and standard deviation would describe the average SUS rating and variability among ratings; a reported analysis size would clarify how many observations contributed. Those primary outcome details are not reported in the registry record. As a result, the record establishes what was intended to be measured, but not the observed acceptability findings that would help readers understand the pilot’s empirical contribution.

The record also illustrates why enrollment, analysis size, and result reporting should be distinguished. Enrollment is listed as 19, while the number contributing to the primary measure is not stated. A reader should not assume the enrollment figure is the denominator for every outcome. The listed safety counts likewise use an at-risk count that differs from the enrollment listing, without an explanation in the record.

Statistically, the study matters as a reminder that developmental aims can be valuable while still requiring transparent outcome reporting. The design and endpoint provide context for the intended work; without the primary score and its variability, however, the central acceptability question remains unanswered by 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 primary limitation for interpreting this registry entry is that the primary outcome result is not reported. Although the measure, summary type, scale direction, and timeframe are described, the record gives no mean SUS score or standard deviation for Client Bot Emily. It also does not report the number of completed assessments contributing to that endpoint. This prevents quantitative interpretation of the principal registered outcome.

The record lists enrollment of 19 but does not give participant characteristics, the number assessed at each time point, or an analysis population. The stated target is nurses serving hospitalized patients, but detailed eligibility criteria and participant descriptions are not reported in the registry record. The at-risk count in the adverse-event information is not explained relative to enrollment.

The single-group design has no registered comparator, and masking is listed as none. Consequently, the study is not structured to estimate differences against usual practice or another training program. The registry record does not report a statistical analysis plan, a sample-size justification, missing-data procedures, or a multiplicity strategy. It also lists 12 outcome measures but no analyses. These gaps make it difficult to determine how the outcome data were handled or how any future reported results should be interpreted.

The endpoint is self-reported acceptability immediately after technology engagement. It does not directly assess skill performance, sustained use, clinical practice, or patient outcomes. The record describes those broader training aims but does not report measures that would establish changes in those domains. Finally, the safety counts are limited to the recorded group and do not include event definitions or collection details. These limitations restrict interpretation to the design and planned measurements that are documented.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: eLearning for Suicide Prevention — NCT05178121.
• Registry record last updated 2023-12-18; status last verified 2023-11.
• Results first posted 2023-12-18.
• 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

NCT05178121 is a completed, single-group formative evaluation of Project WISE eLearning Training in Suicide Safety Planning. The registry lists enrollment of 19, allocation as not applicable, and masking as none. The intervention is behavioral training intended for nurses serving patients hospitalized for medical, surgical, or traumatic injury reasons.

The primary outcome is acceptability of Client Bot Emily, measured by the SUS immediately after engagement with each training technology. The stated scale ranges from 0-100, with higher scores indicating greater usability or acceptability, and the planned summary is a mean with standard deviation. The registry record does not report the primary score, its variability, or the number contributing to that outcome. It lists 12 outcome measures and no analyses.

Safety information lists 18 participants at risk for serious adverse events, 0 affected, 18 at risk for other adverse events, 0 affected, and 0 deaths. The record’s stated formative purpose is to assess acceptability and engagement and inform training iterations. The available registry information describes that purpose and design but does not report the primary outcome result.