Suvorexant to Reduce Symptoms of Nicotine Use: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Suvorexant to Reduce Symptoms of Nicotine Use (NCT04234997), a randomized phase 2 study. The primary outcome is Stress as Assessed by a Visual Analog Scale (VAS) for Stress.

2. Clinical Question

3. Trial Design

The registry describes a phase 2, randomized, quadruple-masked, parallel study of suvorexant to reduce symptoms of nicotine use. The comparison is between suvorexant 20 mg and suvorexant 0mg. The official title calls the study placebo-controlled. The listed enrollment is 14, and the record status is completed. The study start date is 2021-08-23, and the primary completion date is 2024-08-22.

The stated purpose extends beyond the primary stress score. The brief summary describes assessing craving, withdrawal, stress reactivity, and latency to self-administration as measures related to smoking relapse risk, as well as validating a somnolent effect on sleep metrics in individuals with tobacco use disorder. These aims describe the scope of the study; the primary outcome posted for the present analysis is specifically stress measured by VAS on Day 1.

The primary endpoint is reported as a continuous measure summarized by its mean and standard deviation. The posted arm counts are 5 for suvorexant 20 mg and 6 for suvorexant 0mg. Although the registry reports enrollment of 14, it does not explain the difference between that figure and the available primary outcome counts. A reason for the difference, such as missing observations or a different analysis population, is not reported in the registry record.

The record identifies a parallel model and quadruple masking, but does not describe the randomization procedure, masking roles, allocation concealment, treatment period, or visit schedule beyond the endpoint timeframe of Day 1. Those design details are not reported in the registry record. The sponsor is The University of Texas Health Science Center, Houston.

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 14 enrolled participants, 11 were randomized and 3 withdrew from the study before randomization.

Overall Study

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Population: include all who were randomized.

6. Primary Endpoint

The registry lists the primary outcome as Stress as Assessed by a Visual Analog Scale (VAS) for Stress, measured over Day 1.

The primary endpoint is stress measured with a visual analog scale (VAS) on Day 1. The record states that the total score ranges from 1, meaning none, to 10, meaning extreme stress. A higher score indicates a worse outcome. The endpoint is reported as a mean with a standard deviation, making it a continuous measure rather than an event count or a time-to-event outcome.

A self-reported stress score can capture a participant’s rating of their experience at a specified assessment. In general, the value of a rating scale depends on the question, scoring range, timing, and consistency of administration. The registry record gives the score anchors and the assessment timeframe, but does not describe the exact VAS question, how it was administered, whether assessments were repeated, or whether the Day 1 value represents a change from another measurement. These details are not reported in the registry record.

The study’s broader stated aims include stress reactivity and other measures related to relapse risk, but those aims should not be conflated with this primary endpoint. The VAS stress result is a Day 1 score, not itself a direct measure of smoking relapse, smoking cessation, or sleep. The record does not provide a clinically meaningful threshold for interpreting a difference on this scale. Consequently, the group summaries describe the recorded scores but do not by themselves show how any contrast would relate to a meaningful change in stress or to the broader study aims.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous and summarized by a mean and standard deviation for each arm. In general, a mean describes the center of observed scores, while a standard deviation describes how dispersed those scores are around the mean. These summaries are useful for describing the recorded observations, but they do not by themselves quantify uncertainty in a between-arm contrast. The posted means are 3.4 and 3.0, and the posted standard deviations are 2.07 and 2.61, for suvorexant 20 mg and suvorexant 0mg, respectively.

A comparison between groups ordinarily focuses on an effect estimate, such as a difference in means, and its uncertainty. A confidence interval is a range of values compatible with the observed data and the statistical model at a stated confidence level. It communicates precision as well as direction and magnitude. A p-value, when reported, describes how compatible the observed data are with a specified null hypothesis under the analysis assumptions; it is not the probability that the null hypothesis is true. In this case, the registry record says that values are missing or not estimable for a two-arm comparison of the continuous endpoint. It does not report a confidence interval or p-value for that comparison, so neither significance nor precision can be assessed from the posted summaries.

In general, the standard error of a mean or contrast depends on both variability and the number of observations. Here, the primary outcome counts are 5 and 6. Those modest counts mean that estimates can be sensitive to which participants are observed, and uncertainty can be appreciable even when the arm means appear close. The record does not provide enough information to quantify that uncertainty for the contrast, and no additional inferential result should be derived from the summary statistics.

The score is bounded from 1 to 10. In general, bounded scales may have distributions that differ from the assumptions of a normal model, particularly when observations cluster near a scale boundary. The posted summaries do not reveal whether scores were symmetric, skewed, or concentrated at any values. The analysis method, any assumption checks, and any alternative modeling approach are not reported in the registry record. This matters because the appropriateness of a mean-based model depends partly on the observed distribution and analysis assumptions.

In general, over-dispersion describes variability greater than a model expects. It is particularly relevant to count outcomes, where an overly restrictive variance assumption can make uncertainty appear too small. The primary endpoint is a continuous score, not a count outcome, and the registry record does not report an over-dispersion analysis. More broadly, statistical models should match the outcome’s measurement scale and observed distribution; the specific model used for the primary comparison is not reported in the registry record.

The study is described as randomized, which means treatment assignment was intended to be assigned by chance rather than selected by participants or investigators. Randomization can support a fair comparison when allocation and follow-up are appropriately handled, but the registry record does not detail sequence generation, concealment, or the analysis used to account for the assigned groups. The record labels masking as quadruple, but does not identify which groups of people were masked. These labels alone do not reveal how successfully masking was maintained.

The record identifies the study as parallel, so the listed arms represent separate treatment groups rather than a reported crossover comparison. It does not describe the treatment duration or provide a baseline stress score for the primary endpoint. The endpoint timeframe is Day 1, but the timing of treatment relative to the assessment and the role of any baseline measurement are not reported. Therefore, the posted means should be read as arm summaries for the stated timeframe, not as changes from baseline.

Planning calculations, when based on an observed effect, are illustrations of what a future study might require under stated assumptions. They are not observed power and do not establish that the current study was adequately powered. The registry record describes a planning illustration based on the observed effect, a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect defined as a fraction of the observed effect. These assumptions are not described as the trial’s own design or sample-size justification. The record does not report the trial’s sample-size rationale. Since the primary two-arm contrast is not estimable in the registry record, any planning illustration should be understood cautiously and not as evidence that a treatment effect was established.

There are no posted inferential analyses in the record: the number of analyses is reported as 0. That limits the statistical interpretation to the descriptive endpoint summaries and the record’s explicit note that a two-arm comparison could not be estimated. No recalculated comparison is warranted from the posted information.

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("Suvorexant 20 mg", "Suvorexant 0mg")
n   <- c(5, 6)
m   <- c(3.4, 3)
sp  <- c(2.07, 2.61)
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  Suvorexant 20 mg  5  3.400  2.070  0.830  5.970
CARM  Suvorexant 0mg  6  3.000  2.610  0.261  5.739

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 36 outcome measures and reports 22 secondary outcomes posted. The secondary outcomes include stress measures and changes in stress reactivity assessed with blood pressure during the cold pressor test. The brief study summary also names craving, withdrawal, latency to self-administration, and sleep metrics among the study aims. The posted primary endpoint for this analysis remains the Day 1 stress VAS; other measures should be interpreted as separate outcomes rather than interchangeable evidence about the primary question.

When a study evaluates many outcomes, the chance of at least one apparently unusual result can increase if each outcome is tested separately without accounting for multiplicity. In general, methods to address multiplicity may define a primary outcome hierarchy, adjust significance thresholds, or treat secondary findings as exploratory. Whether any such approach was planned or used is not reported in the registry record. The record reports zero analyses, so it does not provide a set of inferential findings for which an adjustment can be assessed.

The record does not report a missing-data method, a definition of the analysis population, or whether outcomes were analyzed according to assigned treatment. For the primary endpoint, the arm counts are 5 and 6, while enrollment is reported as 14. The reason these counts differ is not reported in the registry record. It would be inappropriate to infer that all other enrolled participants had missing measurements or to assume a particular exclusion rule.

The registry record also does not describe imputation, sensitivity analyses, handling of protocol deviations, or procedures for participants who did not complete an assessment. These omissions restrict conclusions about whether the posted summaries represent all randomized participants or a subset. The available information supports description of the posted values, but not a fuller assessment of missingness, multiplicity, or population-level analysis decisions.

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 serious adverse event figures list 5 participants at risk in the suvorexant 20 mg group and 6 in the suvorexant 0mg group. The recorded serious adverse event counts are 0 in each group. The figures also list 5 and 6 participants at risk, respectively, for other adverse events, with recorded counts of 0 in both groups. Deaths are recorded as 0 in both groups.

These figures describe what the registry record reports for the listed categories. They do not establish that no adverse events of any kind occurred, and they do not show that the treatments are free of risk. The record does not report the safety observation period, the criteria used to classify events, or whether the categories include every event collected during the study. It also does not provide event-level descriptions because no serious adverse event terms are listed.

With the small group counts reported, zero recorded events should be read as an absence of reported events in these categories in this record, not as proof that the underlying risk is zero. The figures are descriptive and do not provide a comparative safety estimate or its precision. The record does not report a formal statistical analysis of adverse events.

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

The posted information establishes a narrow descriptive result: on Day 1, the mean stress VAS score was 3.4 for suvorexant 20 mg and 3.0 for suvorexant 0mg. Higher scores indicate worse stress. The corresponding standard deviations were 2.07 and 2.61, with primary outcome counts of 5 and 6. These values describe the recorded scores in each arm; they do not establish a treatment effect.

The registry record explicitly says that values are missing or not estimable for a two-arm comparison of this continuous endpoint. No inferential comparison, confidence interval, or p-value is reported. Therefore, the numerical ordering of the means cannot establish whether the observed values reflect a real group contrast, random variation, or other factors. The record does not provide a threshold for a clinically meaningful VAS change, and the posted primary value is not described as change from baseline.

The study’s broader aims concern several measures of smoking relapse risk and sleep metrics, but the Day 1 stress VAS is not itself a measure of smoking relapse, cessation, or sleep. The primary result cannot stand in for those outcomes. The registry record reports 22 secondary outcomes posted and zero analyses, so the available information does not support conclusions about the secondary endpoints either.

Nor do the results establish that suvorexant 20 mg improves or worsens stress, or that it does or does not affect any other study aim. The record’s enrollment and arm counts, lack of an estimable primary comparison, and absent analysis details limit what can be inferred. The result should be read as descriptive evidence from a small study record, with no reported estimate of the between-arm effect or its precision.

14. Why This Trial Matters Statistically

This study is statistically notable because it has a clearly defined continuous primary outcome but does not report an estimable two-arm comparison for that outcome. The posted arm means and standard deviations give a limited view of the observed scores, yet the information needed to evaluate a treatment contrast—an effect estimate and its uncertainty—is not reported. This illustrates why descriptive summaries and inferential results answer different questions.

The record also distinguishes the number enrolled from the numbers contributing to the primary outcome summaries. Enrollment is reported as 14, while the arm counts for the endpoint are 5 and 6. The reason for the difference is not reported in the registry record. Without an explanation of the analysis population and missing-data handling, readers cannot determine how the primary summaries relate to all enrolled participants.

The study’s purpose includes multiple constructs: stress, relapse-risk measures, stress reactivity, and sleep metrics. Statistically, these are not interchangeable outcomes. Each requires its own measure, analysis, and interpretation, and a large family of outcomes can raise multiplicity concerns. The record lists 36 outcome measures, reports 22 secondary outcomes posted, and reports zero analyses. It does not describe a multiplicity strategy.

Finally, the planning assumptions described in the record should be distinguished from the trial’s design and from observed power. A planning illustration can help frame future research under explicit assumptions, but it cannot replace a reported analysis of this study. The record does not report the trial’s own sample-size justification. These features make the study useful for understanding the importance of transparent reporting of endpoint data, analysis populations, uncertainty, and prespecified statistical methods.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The main trial-specific limitation in interpreting the primary endpoint is that the registry record says the values are missing or not estimable for a two-arm comparison. Although each arm has a reported mean and standard deviation, there is no reported contrast or measure of its precision. The absence of these statistics prevents an inferential assessment of the primary question.

The endpoint counts are 5 for suvorexant 20 mg and 6 for suvorexant 0mg, whereas enrollment is reported as 14. The reason for this difference is not reported in the registry record. It does not identify the analysis population or explain whether the counts reflect missing measurements, exclusions, or another process. The missing-data approach and any sensitivity analyses are also not reported.

The primary outcome is a Day 1 stress VAS score, and the record gives its range and direction. It does not report the exact question wording, administration procedures, baseline score, or a clinically meaningful threshold. It is therefore not possible to assess change from baseline or to connect a numerical contrast with a stated meaningful-change criterion.

The registry describes randomized allocation, quadruple masking, a parallel model, and a phase 2 study, but does not report the randomization procedure, allocation concealment, identities of masked roles, or the statistical model. It also does not report how multiple outcomes were handled. The record lists 36 outcome measures, 22 secondary outcomes posted, and zero analyses. These limitations leave important questions about analysis choices and secondary findings unresolved.

The small arm counts also make the descriptive summaries vulnerable to instability, while the record provides no confidence interval to quantify precision. The completed status does not resolve these reporting limitations. These are constraints on interpretation of the registry record, not evidence about the study’s conduct beyond what it reports.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Suvorexant to Reduce Symptoms of Nicotine Use — NCT04234997.
• Registry record last updated 2025-10-01; status last verified 2025-09.
• Results first posted 2025-10-01.
• 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

The registry record describes a completed, randomized, quadruple-masked, parallel, phase 2 study of suvorexant 20 mg versus suvorexant 0mg for symptoms related to nicotine use. Enrollment is reported as 14. The primary endpoint is a Day 1 stress VAS score ranging from 1 to 10, with higher scores indicating worse stress.

The posted primary summaries are a mean of 3.4 and standard deviation of 2.07 for suvorexant 20 mg, based on 5 participants, and a mean of 3.0 and standard deviation of 2.61 for suvorexant 0mg, based on 6 participants. The registry record says values are missing or not estimable for a two-arm comparison of this continuous endpoint. It reports zero analyses, and does not provide an analysis population or missing-data method.

The record lists 36 outcome measures and 22 secondary outcomes posted. Serious adverse events, other adverse events, and deaths are recorded as 0 in both groups. The reason the primary endpoint counts differ from the enrollment figure, the methods used for statistical comparisons, and the multiplicity approach are not reported in the registry record.