Feasibility Trial of a Single Session of Crisis Response Planning for Youth at High Risk for Suicide: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Feasibility Trial of a Single Session of Crisis Response Planning for Youth at High Risk for Suicide (NCT06164106), a randomized na study. The primary outcome is Number of Participants With Self-reported Use of the Treatment Plan in the Crisis Response Planning (CRP) Treatment Arms.

2. Clinical Question

3. Trial Design

This was a completed, randomized, parallel-group trial sponsored by Ohio State University. The registry lists an enrollment of 57 and three behavioral intervention arms: virtual crisis response planning, in-person crisis response planning, and virtual crisis risk counseling. Masking is recorded as none. The phase is recorded as NA. The registry lists Suicide Prevention as the condition.

The trial summary describes male and female adolescents with current suicidal intent being assigned to a one-hour session in one of the three arms. The intervention descriptions give a session duration between 30 minutes and 1 hour. Virtual crisis response planning was conducted through doxy.me with a trained study therapist and was primarily text-based. In-person crisis response planning used the same protocol and treatment components face-to-face. The virtual counseling arm included supportive listening, crisis resources, and referral to a mental health professional, as described in the registry.

The planned assessment of feasibility and acceptability was 14 days after treatment. The registry summary also describes daily assessments of mood, behavior, and suicidality for 14 days after treatment. The primary posted endpoint is different in scope: it records whether participants in either crisis response planning arm reported using their plan during the two weeks after the intervention. Participants in the counseling arm did not complete that use form, so the primary result does not compare all three arms.

The registry records the study start as 2023-11-01, primary completion as 2025-01-22, and status as completed. Further details of the randomization procedure and the trial's original statistical design assumptions are not reported in the registry record.

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.

Before assignment: Of the 57 enrolled participants, 55 were randomized to treatment.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Participants who were randomized to one of the CRP arms and completed the post-treatment use form were included in the analyses.

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 Number of Participants With Self-reported Use of the Treatment Plan in the Crisis Response Planning (CRP) Treatment Arms, measured over Two weeks after the intervention session.

The primary endpoint is the number of participants who self-reported using their crisis response plan in the two weeks after the intervention. The assessment was made at the end of the trial through a form asking whether the participant used the plan, with yes or no response options. The reported values are counts: 14 of 16 participants in virtual crisis response planning and 8 of 17 participants in in-person crisis response planning.

This endpoint is relevant to a feasibility study because it records whether participants say they used the intervention's plan during the specified follow-up period. It is a behavioral measure of reported plan utilization, rather than a measure of whether the plan changed mood, suicidal thoughts, suicidal behavior, or other clinical outcomes. Self-report also means the endpoint reflects participants' reports on the form; the registry does not describe independent verification of use.

The analysis population was participants randomized to a crisis response planning arm who completed the post-treatment use form. The virtual counseling group did not complete the form. Its absence from this endpoint is not a zero count and does not support a three-arm comparison of plan use. The registry record does not report the number of randomized participants in either crisis response planning arm who did not complete the form, or further details about how incomplete forms were handled.

7. Results Posted in the Registry

• In-Person Crisis Response Planning: 47.1% (8/17) versus 87.5% (14/16) on control; risk difference -40.4 percentage points (95% CI -69.2 to -11.7), risk ratio 0.54 (0.31–0.92); unadjusted two-proportion z-test p = 0.014.

8. Statistical Interpretation

9. Statistical Methods Explained

What kind of endpoint is this? The endpoint is binary at the participant level: each completed form records whether a participant reported using the plan or not. The registry reports the number answering yes in each crisis response planning arm and the number included in each arm's analysis. Counts are useful for understanding the observed data, while a comparison of proportions places the counts in the context of the analyzed group sizes. The counseling arm is not part of this endpoint analysis because its participants did not complete the plan-use form.

What does the risk difference express? A risk difference subtracts one group's proportion with the recorded outcome from the other group's proportion. In the recalculation, the contrast is in-person minus virtual. Its estimate is -0.404, so the direction favors a higher observed proportion of reported plan use in the virtual arm for this specific measure. This is an absolute contrast in proportions, not a relative effect. It does not identify a mechanism for the difference, and it does not convert self-reported plan use into a clinical outcome.

What does the confidence interval add? A confidence interval gives a range of values compatible with the observed data under the statistical method used. The recalculated 95% interval for the risk difference is -0.692 to -0.117. In general, a wider interval signals less precision, while a narrower interval signals greater precision. The interval describes sampling uncertainty under its assumptions; it does not account automatically for every source of bias, such as missing forms or inaccurate self-report. It should be read alongside the endpoint definition and analysis population.

How should the p-value be understood? The recalculated unadjusted p-value is 0.014. In general, a p-value measures how unusual data at least as incompatible with a specified null model would be if that model and the analysis assumptions held. It is not the probability that the null hypothesis is true, and it does not measure the size or importance of an effect. The registry's sponsor analysis reports p = .014. Neither value explains the reason for the observed difference or establishes its reproducibility.

What does the sponsor's method indicate? The sponsor reports a chi-squared analysis for a difference in proportions. In general, a chi-squared test assesses whether observed categorical outcome counts are compatible with no association or difference under its assumptions. The registry lists a value of 6.07 and p = .014, but does not report a confidence interval for that analysis. The recalculation uses the posted summary counts to estimate an unadjusted risk difference and interval. These are different ways of presenting evidence from the same two-arm endpoint, and the sponsor's own analysis remains the reported trial analysis.

Why might over-dispersion matter in other settings? General explanation: over-dispersion means observed variability exceeds what a chosen statistical model expects. It can make model-based uncertainty too small if it is ignored. The primary endpoint is a binary count rather than a count rate with an over-dispersion estimate; the registry does not report an over-dispersion analysis for this endpoint. No additional model details are reported in the registry record.

What does randomization contribute? General explanation: random assignment is intended to make intervention groups comparable on average, including for characteristics that may not be measured. It does not guarantee balance in a small trial, and it does not remove limitations caused by missing outcome data or measurement error. The registry identifies the allocation as randomized but does not report the sequence-generation method, concealment procedures, or any stratification factors. Masking is recorded as none, so masking should not be assumed for participants or study staff.

Which population does the result describe? The registry says the primary analysis included participants randomized to a crisis response planning arm who completed the post-treatment use form. This is a completer-based analysis as described, not a stated analysis of every randomized participant. The record does not report the number of incomplete forms, a missing-data method, or an intention-to-treat analysis for this endpoint. General explanation: if form completion is related to treatment assignment or to plan use, restricting analysis to completers can affect the comparison. The direction or extent of any such effect cannot be determined from the reported information.

10. Confidence Intervals and Precision

The recalculated risk difference is -0.404, with a 95% confidence interval from -0.692 to -0.117. The contrast is in-person minus virtual, so negative values indicate a lower observed proportion reporting plan use in the in-person arm. The interval excludes zero, but it spans a range of possible difference magnitudes. The point estimate is therefore not a precise statement of the exact size of a population difference.

In general, a confidence interval represents uncertainty from sampling under the method's assumptions. It is not a guarantee that the true effect lies in the interval, and it does not account for every possible source of error. Here, the endpoint is self-reported, the analysis includes participants who completed the use form, and the registry does not report details about missing forms. These features matter when considering how much confidence to place in the estimate beyond the analyzed participants.

The sponsor's reported chi-squared analysis gives p = .014 but does not include a confidence interval. The recalculation supplies an interval for an unadjusted risk difference based on the posted summary statistics; it is not an adjusted estimate. The relative risk interval is 0.314 to 0.920, and the odds ratio interval is 0.022 to 0.739. These relative measures express the contrast on different scales and should not be mistaken for the absolute risk-difference interval.

The analyzed group sizes, 16 and 17, are modest. That context helps explain why the observed contrast should be interpreted with caution, even though the recalculated interval does not include zero. Precision is about uncertainty in the estimate, not whether the result is clinically important or whether it applies to other populations or settings.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm for 80% power and participants per arm for 90% power. They concern a two-arm comparison of virtual and in-person crisis response planning, not the virtual counseling arm. The registry record's planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The target effect is set to a stated fraction of the observed effect.

For planning at 100% of the observed effect, the figures are 20 participants per arm for 80% power and 27 participants per arm for 90% power. At 75% of the observed effect, the figures are 33 participants per arm for 80% power and 44 participants per arm for 90% power. At 50% of the observed effect, the figures are 66 participants per arm for 80% power and 88 participants per arm for 90% power. The planning display and curve illustrate that detecting smaller effects requires more participants under these assumptions.

In general, power is the chance that a specified analysis would detect an effect of a chosen size if that effect were present and the assumptions held. The 80% and 90% columns describe different target chances of detection for a future planning scenario; the higher target is associated with larger required group sizes. These figures are planning illustrations calculated from the observed effect, not the trial's original design assumptions. The registry does not report the trial's own sample-size justification or original design assumptions. This is not observed power.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.875; treatment proportion p₁ = 0.471; average p̄ = 0.673.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6635 = 1.3005.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5988 = 0.5039.
4. n = (1.3005 + 0.5039)² / (-0.4044)² = 19.9, rounded up to 20 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
p0 <- 0.875                          # control proportion
p1 <- 0.470588235294118                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(6164106)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 20 (80% power), 27 (90% power)
 75% of observed effect: n per arm = 33 (80% power), 44 (90% power)
 50% of observed effect: n per arm = 66 (80% power), 88 (90% power)
power.prop.test: 19.9 
Simulated power at n = 20 per arm: 0.826 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Analyses Reported by the Sponsor

The sponsor's posted result compares virtual with in-person crisis response planning for the primary plan-use endpoint. It lists a chi-squared method, a difference in proportions, a value of 6.07, and p = .014. The registry does not list a confidence interval alongside that result.

The recalculation uses the posted counts and analyzed group sizes to estimate an unadjusted risk difference of -0.404, with a 95% confidence interval from -0.692 to -0.117, and an unadjusted p-value of 0.014. The direction is expressed as in-person minus virtual. The recalculated p-value matches the sponsor's reported p-value, and the record does not flag a discrepancy.

The recalculation is a supplementary, unadjusted calculation from the posted summary statistics; it does not replace the sponsor's analysis or supply details that the registry does not report. When the sponsor's analysis and a recalculation conflict, the sponsor's own analysis takes precedence. No such discrepancy is indicated for this result. The two presentations should still be distinguished: the sponsor reports its chi-squared result, while the recalculation adds an absolute risk-difference estimate and interval. Neither presentation resolves limitations related to self-report, form completion, or the restricted endpoint population.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists four outcome measures and three analyses, but does not report a multiplicity adjustment or a prespecified hierarchy for interpreting multiple outcomes. The primary plan-use result is identified as primary. Without a stated testing plan, the record does not establish how the sponsor intended to control the chance of false-positive findings across outcomes or analyses. The reported p-value should therefore be read as the result for this comparison, not as evidence that all outcome testing was accounted for.

The primary analysis population consisted of participants randomized to either crisis response planning arm who completed the post-treatment use form. The virtual crisis risk counseling group did not complete that form, so it is not represented in this endpoint comparison. The posted results give 16 analyzed participants for virtual crisis response planning and 17 for in-person crisis response planning. The registry does not report how many randomized participants in those arms failed to complete the form, why forms were not completed, or whether any forms were partially incomplete.

The record does not report a missing-data method, sensitivity analysis, or an intention-to-treat analysis for this endpoint. General explanation: missing outcome data can affect a group comparison if completion is related to treatment assignment or the outcome. The available information does not show whether this occurred or how it might have changed the estimate.

Randomization is recorded, but the registry does not describe sequence generation, allocation concealment, or stratification. Masking is recorded as none. These omissions limit assessment of the analysis and its safeguards, but they do not establish that a particular bias occurred. Additional secondary posted results are not reported in the registry record, so the other listed outcome measures cannot be interpreted from this endpoint result.

15. 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 1% reporting threshold.

The adverse-event figures list no serious adverse events in the virtual crisis response planning group, no serious adverse events in the in-person crisis response planning group, and no serious adverse events in the virtual crisis risk counseling group. Deaths are listed as 0 in each group. The registry lists 18 participants at risk for serious adverse events and other adverse events in the virtual crisis response planning group, 19 in the in-person group, and 18 in the counseling group.

These figures describe the posted adverse-event record for the groups and participants listed. They do not show that no non-serious adverse events occurred: the affected-participant count for other adverse events is 0 in each group, but the registry record does not provide additional event descriptions or a list of reported terms. It also does not give further details about the observation period or how events were assessed.

Zero recorded serious events or deaths in these groups is not proof that an intervention has no safety risks. The trial's size and the registry's limited event detail restrict what can be inferred about uncommon events or safety beyond the recorded follow-up. These are descriptive safety counts, not a comparison establishing safety or harm.

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

The primary posted result concerns self-reported use of a crisis response plan during the two weeks after an intervention session. Among participants who completed the form, the recorded counts were 14 of 16 for virtual crisis response planning and 8 of 17 for in-person crisis response planning. The recalculated unadjusted risk difference was -0.404 for in-person minus virtual, with a 95% confidence interval from -0.692 to -0.117. The sponsor's analysis reports p = .014.

This finding means that reported plan use differed between the two analyzed crisis response planning groups in the registry result. It does not establish that one format caused the difference, explain why participants reported different use, or show that either format changed suicidal thoughts or behavior. Use of a plan is not interchangeable with a clinical outcome. The posted endpoint also cannot compare crisis response planning with virtual crisis risk counseling, because that arm did not complete the plan-use form.

The result is limited to the participants who completed the form and to the follow-up period specified. The registry does not report the number of missing forms or a method for accounting for them. The study was randomized, but allocation and analysis details are limited in the registry record, and masking is recorded as none. The estimate has uncertainty, and the population and setting to which it may apply cannot be determined from this result alone.

The trial summary describes broader goals involving feasibility, acceptability, mood, behavior, and suicidality. The registry lists four outcome measures, but additional secondary posted results are not reported in the registry record. The plan-use result therefore should not be treated as a summary of all trial outcomes. It is one behavioral report from a feasibility trial, and it does not by itself establish clinical benefit, lack of benefit, or safety.

17. Why This Trial Matters Statistically

This trial raises a statistical question that is easy to overlook: whether the endpoint actually represents the comparison a reader may assume it represents. The primary measure is use of a crisis response plan, and only participants in the two crisis response planning arms completed the relevant form. The counseling group is not a zero-use group; it is outside this endpoint's analysis. Clear attention to the endpoint population prevents an unsupported three-arm interpretation.

The result also shows why counts and comparative estimates should be read together. Counts describe the observed responses, while a risk difference presents the contrast on an absolute scale and a confidence interval conveys uncertainty. The sponsor's chi-squared result and the recalculated estimate offer complementary presentations, but neither removes the limits of a small completer-based endpoint or self-reported measurement.

Planning illustrations based on an observed effect can help readers understand how required group sizes change when a future study targets smaller effects or a higher power. They are not evidence that the current trial had a particular power, and they do not substitute for the trial's original design rationale, which is not reported in the registry record. Keeping planning calculations distinct from observed results is important for interpreting feasibility research.

Finally, registry transparency matters for assessing evidence. Details about missing forms, multiplicity, randomization procedures, and other outcome results are not reported in the registry record. Their absence does not prove that the study lacked those procedures or analyses, but it limits independent evaluation of how the primary result should be interpreted.

18. 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 is self-reported plan use rather than a direct clinical outcome. The registry describes a yes-or-no form at the end of the trial, but does not report independent confirmation of use, further validation details, or whether participants interpreted the question in the same way. Recall and reporting can therefore be relevant measurement considerations, although the record does not establish that either affected the results.

The analysis includes participants in the two crisis response planning arms who completed the form. The number and characteristics of participants who did not complete it, and the reasons for noncompletion, are not reported in the registry record. The counseling group did not complete the form, preventing a direct comparison of plan use across all randomized arms. No missing-data procedure or sensitivity analysis is reported for this endpoint.

The analyzed group sizes are 16 and 17. That limited base makes the estimate vulnerable to imprecision and means individual responses can have substantial influence. The recalculated interval reflects sampling uncertainty under its assumptions, not all possible sources of bias. Masking is recorded as none, and details of allocation procedures are not reported in the registry record.

The registry does not report a multiplicity strategy, the original sample-size justification, or further posted secondary results. The planning calculations are illustrations based on the observed effect and cannot establish what the original design targeted. The study summary describes broader feasibility and clinical measures, but those aims cannot be assessed from the primary plan-use result alone. These limitations narrow the conclusions to the reported endpoint and analyzed participants.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Feasibility Trial of a Single Session of Crisis Response Planning for Youth at High Risk for Suicide — NCT06164106.
• Registry record last updated 2026-03-18; status last verified 2026-02.
• Results first posted 2026-03-18.
• 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.

22. Record Summary

NCT06164106 is a completed randomized, parallel-group feasibility trial sponsored by Ohio State University. The registry lists enrollment of 57 and three behavioral arms: virtual crisis response planning, in-person crisis response planning, and virtual crisis risk counseling. The study population is described as male and female adolescents with current suicidal intent. Masking is recorded as none, and phase is recorded as NA.

The primary posted endpoint is self-reported use of a crisis response plan during the two weeks after the intervention, among participants in the crisis response planning arms who completed the form. The recorded counts are 14 of 16 in the virtual arm and 8 of 17 in the in-person arm. The recalculated unadjusted risk difference is -0.404, with a 95% confidence interval from -0.692 to -0.117; the sponsor reports p = .014.

The record lists study start as 2023-11-01, primary completion as 2025-01-22, and status as completed. The posted endpoint does not include the counseling arm, and additional secondary posted results are not reported in the registry record.