A Study of TAK-994 in Adults With Narcolepsy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of TAK-994 in Adults With Narcolepsy (NCT04820842), a randomized phase 2 study. The primary outcome is Number of Participants With at Least One Treatment Emergent Adverse Event (TEAE) During the Active Drug Extension Period.

2. Clinical Question

The registry describes the study as a dose-blind extension with a double-blind, placebo-controlled, randomized withdrawal period. Its main stated aim was to check for side effects from TAK-994; the official title also describes evaluating safety and exploring pharmacokinetics and pharmacodynamics. The primary endpoint is a safety count from the extension, rather than a measure of symptom benefit or a direct estimate of a treatment effect against placebo.

3. Trial Design

This was a phase 2, randomized, quadruple-masked, parallel study of TAK-994 in adults with narcolepsy type 1. The registry records an enrollment of 26 and a terminated status. The recorded start date is 2021-04-30, and the primary completion date is 2021-11-03. The registry record does not report why the study was terminated.

Participation was limited to adults who had completed the TAK-994-1501 study. The active drug extension assigned participants to TAK-994 30 mg, 90 mg, or 180 mg twice daily, orally, from Day 1 through Day 56. The record describes Day 1 as Day 57 of the previous study. This extension period lasted up to 8 weeks.

After the extension, participants meeting eligibility specifications entered a double-blind randomized withdrawal period. They either continued their existing TAK-994 dose or received placebo-matching tablets from Day 57 to Day 84. The brief summary describes this as a 4-week period, followed by a clinic visit for a final check-up 2 weeks after the last dose. It also says participants continued recording narcolepsy symptoms as in Part B of the earlier study, while study doctors checked for side effects throughout.

The primary outcome concerns treatment-emergent adverse events during the active extension, not the later withdrawal period. The record also lists four secondary safety outcomes for the withdrawal period: participants with at least one treatment-emergent adverse event, and participants with at least one post-dose maximum abnormal value for laboratory tests, vital signs, or ECG parameters. The registry record does not report the randomized withdrawal outcome results in the registry record for this analysis.

The record identifies randomization and masking but does not report the sequence-generation method, allocation concealment procedures, or which roles were masked. Details of the eligibility criteria beyond prior-study completion and the withdrawal-period eligibility specification 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: Participants with narcolepsy type 1 (NT 1) who completed Part B of TAK-994-1501(NCT04096560) were enrolled in this study to receive TAK-994 or placebo.

Only the first 6 of 7 groups are shown.

Active Drug Extension Period (8 Weeks)

Reasons for not completing this period:

Randomized Withdrawal Period (4 Weeks)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Safety Analysis Set for the Active Drug Extension Period included all participants who were randomized and received at least 1 dose of study drug in the Active Drug Extension 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: Safety Analysis Set for the Active Drug Extension Period included all participants who were randomized and received at least 1 dose of study drug in the Active Drug Extension Period.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With at Least One Treatment Emergent Adverse Event (TEAE) During the Active Drug Extension Period, measured over Up to 8 weeks in the Active Drug Extension Period (Weeks 1 to 8).

The primary endpoint is the number of participants with at least one treatment-emergent adverse event during the active drug extension period, up to 8 weeks. The registry defines an adverse event as an untoward medical occurrence in a participant receiving a drug in a clinical investigation. It need not be considered related to treatment. An event can include an unfavorable sign, symptom, disease, or clinically significant abnormal laboratory finding that occurs in temporal association with drug use. A treatment-emergent adverse event is one whose onset occurs after study drug is received.

This endpoint is used to describe the observed safety experience during treatment. Counting participants with at least one event gives a simple measure of how many people had any recorded treatment-emergent event, while avoiding treating multiple events in one participant as if they came from separate people. It does not convey how many events each participant experienced, how long events lasted, their severity, or whether investigators judged them related to TAK-994.

The posted counts are 5 of 8 participants in the 30 mg group, 4 of 9 in the 90 mg group, and 3 of 9 in the 180 mg group. These are descriptive counts for the active extension. Without a reported statistical comparison or a placebo group in this period, they should not be interpreted as a test of differences among doses or as evidence about causation. The registry record does not report a confidence interval or a formal analysis for this primary count.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The main outcome is binary at the participant level: each participant either had at least one treatment-emergent adverse event during the active extension or did not. The registry presents the outcome as a count of participants. This is a direct descriptive summary, not a model-based estimate of a treatment effect. It is useful for communicating how many people in each dose group had one or more events during the specified period.

What does a participant count capture?

A count of participants with at least one event collapses each participant’s event history into an indicator. A participant with one event and a participant with multiple events both contribute one to the count. That makes the measure easy to interpret, but it leaves out event frequency and recurrence. It also does not distinguish event types, seriousness, duration, or investigator assessment of relatedness unless those features are reported separately.

The observed counts are 5 of 8 at 30 mg, 4 of 9 at 90 mg, and 3 of 9 at 180 mg. The endpoint timeframe is up to 8 weeks in the active drug extension, identified as Weeks 1 to 8 in the registry. The analysis population is the safety analysis set for that period: participants randomized and given at least one dose in the extension. That population definition matters because a safety count based on treated participants is not necessarily the same as a count based on everyone enrolled or randomized.

Why are there no formal two-group comparisons?

The registry record lists no analyses for the posted outcomes. It also notes that values are missing or not estimable for a two-arm comparison of this binary endpoint. The primary results are instead presented across three active dose groups. There is no placebo arm in the active extension outcome, so the primary endpoint does not directly compare active treatment with placebo. The record does not report a statistical test, confidence interval, or adjusted analysis for the primary count.

General statistical context: a confidence interval describes uncertainty around an estimate under the assumptions of the method used. For a binary participant outcome, estimates can be imprecise when group sizes are small, especially when the event count is low. Because the registry record does not report confidence intervals for the primary outcome, the precision of the observed counts cannot be quantified from this result alone. It is not appropriate to infer statistical significance from the counts or from their ordering across dose groups.

How should adverse-event classifications be understood?

The primary endpoint includes treatment-emergent adverse events, defined by timing after receipt of study drug and not necessarily by a causal relationship. Serious adverse events are a separate classification reported in the safety data. A serious event count therefore should not be substituted for the primary endpoint count, and the primary endpoint count should not be described as a count of serious events. Likewise, the adverse event term listings provide labels for reported events but do not, by themselves, establish the cause of an event.

General statistical context: safety summaries commonly report participant counts because they indicate the number of people affected. Event counts can answer a different question by including repeated events in one person. Neither measure alone captures all aspects of safety. Interpretation also depends on the observation period, the population included, event definitions, completeness of follow-up, and how events were collected and classified. The registry record describes the endpoint definition and period, but several further analytic details are not reported.

What is known about the design and analysis plan?

The study is described as randomized, quadruple-masked, and parallel, with a double-blind randomized withdrawal period after an active drug extension. The registry record does not report the randomization sequence, allocation concealment, masking roles, prespecified statistical analysis plan, sample-size justification, or interim analyses. It also does not explain the termination. These items should not be inferred from the study label or from the presence of dose groups.

General statistical context: randomization can support fair comparisons when treatment groups are analyzed as planned and follow-up is sufficiently complete. Masking can reduce some forms of bias in treatment delivery and outcome assessment. Those design features do not remove uncertainty, and they do not make a descriptive safety count a randomized comparison unless the relevant groups and analysis are reported. The randomized withdrawal design could support comparison of continued treatment with placebo among participants eligible for that period, but the withdrawal outcome results are not reported in the information available for this analysis.

The record contains planning assumptions for sample-size illustrations based on an observed effect, two-sided significance level 0.05, equal allocation, and a normal approximation. Such illustrations are planning calculations, not observed trial results or observed power. No resulting participant-per-arm values are stated in the record details for this analysis, and no design justification is reported. The posted primary safety counts should therefore be interpreted on their own terms, without treating them as evidence of planned power or as a substitute for an analysis of the randomized withdrawal period.

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("Active Drug Extension Period: TAK-994 30 mg", "Active Drug Extension Period: TAK-994 90 mg", "Active Drug Extension Period: TAK-994 180 mg")
n      <- c(8, 9, 9)
events <- c(5, 4, 3)
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  Active Drug Extension Period: TAK-994 30 mg  8  5  62.5  24.5  91.5  30.6  86.3  29.9  86.3
ARM  Active Drug Extension Period: TAK-994 90 mg  9  4  44.4  13.7  78.8  18.9  73.3  18.7  73.8
ARM  Active Drug Extension Period: TAK-994 180 mg  9  3  33.3  7.5  70.1  12.1  64.6  12.2  65.2

11. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary safety outcome and four secondary outcomes for the double-blind randomized withdrawal period. The secondary outcomes cover participants with at least one treatment-emergent adverse event and participants with at least one post-dose maximum abnormal value for laboratory tests, vital signs, or ECG parameters. The registry record does not report results for those secondary outcomes in the information available for this analysis.

When several outcomes or comparisons are assessed, the chance of at least one apparently notable result can increase. General statistical context: multiplicity procedures can address that issue by adjusting how evidence is evaluated across a family of tests, or by defining a hierarchy of outcomes in advance. The registry record does not report a multiplicity adjustment, a hierarchy among the outcomes, or a statistical analysis plan. It is therefore not possible to determine how multiple outcomes were intended to be interpreted.

Missing-data methods and completeness of follow-up are also not reported in the registry record. The primary safety population is defined as randomized participants who received at least one dose in the active extension, but the record does not describe how participants with incomplete observation, discontinuation, or missing event assessments were handled. It also does not report an imputation method or sensitivity analysis. The termination reason and its relationship, if any, to outcome collection or missingness are not reported in the registry record.

The analysis population specified for the primary endpoint is a safety population, not a stated intention-to-treat population. The registry record does not report an intention-to-treat analysis or explain whether other analysis populations were used. These omissions limit assessment of the analysis choices and of whether the posted counts reflect all eligible randomized participants. The available primary result can be read as a descriptive account for the stated safety population, but it does not resolve missing-data or multiplicity concerns.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: hepatitis (11.1%), hepatitis acute (11.1%).

The serious adverse event figures are participant counts within the listed treatment-period groups. In Period 1, the record reports 0 of 8 participants with a serious event in the TAK-994 30 mg group, 1 of 9 in the 90 mg group, and 1 of 9 in the 180 mg group. The registry lists “Hepatitis” and “Hepatitis acute” among the top serious-event terms, each at 11.1%. These are registry-listed event terms; the record does not establish that either event was caused by TAK-994.

For Period 2, serious adverse events were recorded for 0 of 3 participants continuing 30 mg, 0 of 1 continuing 90 mg, 0 of 1 continuing 180 mg, and 0 of 3 receiving placebo. These period-specific groups are small, so zero recorded serious events should be understood as an observation in those groups, not evidence that the risk is absent. No deaths are reported among the listed groups.

Serious events are distinct from the primary endpoint, which counts participants with any treatment-emergent adverse event during the active extension. The non-serious event counts are also listed separately. The serious-event information is descriptive; the registry record does not report a formal comparison, uncertainty interval, causal assessment, or detailed event narratives in the registry record for this analysis.

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

The posted primary result describes the number of participants in each active extension dose group who experienced at least one treatment-emergent adverse event during up to 8 weeks of treatment. It gives a safety snapshot for participants in the registry-defined safety analysis set. It does not measure whether narcolepsy symptoms improved, and it does not compare the active extension doses with placebo.

The outcome definition is based on event timing after study drug was received, not on a determination that the drug caused the event. Therefore, an event counted as treatment-emergent should not automatically be described as drug-related. The count also does not tell how many total events occurred, whether events recurred, how severe they were, or how long they lasted. Separate serious-event information adds some detail but does not answer those questions for every event.

The results do not establish that one dose is safer than another. The registry does not report a formal dose comparison or uncertainty intervals for the primary counts, and the group sizes are limited. Differences in the displayed counts may reflect chance, the participants included, event ascertainment, or other factors; the registry record does not allow those possibilities to be separated.

The withdrawal phase has a randomized placebo comparison in its design, but its outcome results are not reported in the registry record for this analysis. Consequently, the primary extension result cannot be used to estimate the effect of continuing TAK-994 versus switching to placebo. Nor does it establish an effect on narcolepsy symptoms or provide a full assessment of safety across longer follow-up.

The record states that the study was terminated, but does not report the reason. That status is important context, yet it does not on its own show that the results are invalid, that a safety concern caused termination, or that treatment was beneficial or harmful. The appropriate interpretation is limited to the recorded study design, outcome definition, and observed counts.

14. Why This Trial Matters Statistically

This study raises several useful statistical issues in clinical safety reporting. First, the primary endpoint is a participant-level binary outcome, making its meaning straightforward: it records whether each person had at least one treatment-emergent adverse event during the active extension. The measure is accessible, but it compresses potentially varied event histories into a single count for each participant.

Second, the study has two distinct treatment periods with different interpretive roles. The extension includes three TAK-994 dose groups and supplies the primary safety counts. The later randomized withdrawal period includes continued dose and placebo groups, but the corresponding results are not reported in the registry record. Keeping those periods separate prevents a descriptive extension count from being mistaken for a placebo-controlled effect estimate.

Third, safety results require careful attention to the analysis population and event definition. The primary population includes participants randomized and treated in the active extension, while treatment-emergent refers to event onset after study drug receipt. Neither feature means that events were caused by treatment. The distinction between any adverse event and a serious adverse event also matters: the primary outcome counts participants with any qualifying event, whereas serious-event counts are reported separately.

Finally, the registry’s terminated status and limited analysis reporting frame the uncertainty. The record does not state why the study ended, give a formal analysis for the primary endpoint, or report the withdrawal outcomes. This is a setting where precise description is more informative than an unsupported treatment-effect claim. The key statistical lesson is that observed counts can describe what was recorded in a defined group and period, while remaining insufficient to establish comparative safety, causation, or a clinical effect.

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 outcome is reported as participant counts without a formal comparison, confidence intervals, or other uncertainty estimates. This prevents assessment of the precision of the observed counts and limits comparisons among the dose groups. The registry record lists no analyses for the posted outcomes.

The active extension result has no placebo comparator. Although the study includes a randomized withdrawal period, its outcome results are not reported in the information available for this analysis. The primary endpoint therefore cannot answer the randomized continuation-versus-placebo question. The registry record also does not report a formal analysis comparing the doses.

The population was restricted to adults who had completed the TAK-994-1501 study. The primary safety analysis set further includes those randomized and given at least one dose in the active extension. This selected population and treatment-period definition should be kept in mind when considering how broadly the counts may apply. Detailed eligibility criteria and the extent of follow-up by participant are not reported in the registry record.

The endpoint captures whether participants had at least one treatment-emergent adverse event, but does not provide the total number of events, duration, severity distribution, or event-level causal assessments in the primary result. The registry lists serious-event counts separately, but does not provide detailed narratives or a formal comparison for those events in the information.

The study is listed as terminated, and the reason is not reported in the registry record. The record also does not report the statistical analysis plan, sample-size justification, interim analyses, multiplicity handling, missing-data methods, or results for the listed withdrawal-period secondary outcomes. These gaps limit evaluation of the intended analysis and the completeness of the overall safety picture.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study of TAK-994 in Adults With Narcolepsy — NCT04820842.
• Registry record last updated 2023-12-26; status last verified 2023-12.
• Results first posted 2023-12-26.
• 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 phase 2 randomized, quadruple-masked, parallel study of TAK-994 in adults with narcolepsy type 1 who had completed the TAK-994-1501 study. Enrollment is listed as 26; the study is terminated. The recorded start date is 2021-04-30, and primary completion is recorded as 2021-11-03.

Participants received TAK-994 30 mg, 90 mg, or 180 mg twice daily during an active extension lasting up to 8 weeks. Eligible participants then entered a 4-week double-blind randomized withdrawal period, continuing their dose or receiving placebo. The primary outcome was the number with at least one treatment-emergent adverse event during the active extension.

The registry reports counts of 5 of 8, 4 of 9, and 3 of 9 in the 30 mg, 90 mg, and 180 mg groups, respectively. It also lists serious adverse event counts by period and four secondary withdrawal-period safety outcomes. The withdrawal outcome results, formal analyses, termination reason, and several statistical planning and missing-data details are not reported in the registry record.