This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Study of Lemborexant for Irregular Sleep-Wake Rhythm Disorder and Mild to Moderate Alzheimer's Disease Dementia (NCT03001557), a randomized phase 2 study. The primary outcome is Core Phase: Change From Baseline in Mean Actigraphy Sleep Efficiency (aSE) With Lemborexant Compared to Placebo During Week 1 of Treatment.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT03001557 |
| Phase | Phase 2 |
| Condition | Irregular Sleep-Wake Rhythm Disorder |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Quadruple |
| Enrollment | 63 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Eisai Inc. |
| Results posted | Yes |
2. Clinical Question
Population
Participants with irregular sleep-wake rhythm disorder and mild to moderate Alzheimer’s disease dementia. The registry record does not report further eligibility details in the information available for this study.
Intervention
Nightly lemborexant at 2.5 mg, 5 mg, 10 mg, or 15 mg during the 28-night core treatment period.
Comparator
Lemborexant-matched placebo, taken nightly during the 28-night core treatment period.
Primary question
How did mean actigraphy-derived sleep efficiency change from baseline during Week 1 for participants assigned to lemborexant, compared with those assigned to placebo? The registry record does not report the comparative endpoint estimates.
The study was designed to examine dose response across four lemborexant doses, with placebo as the comparator. The primary measure was the change from baseline in mean actigraphy sleep efficiency (aSE) during Week 1. aSE describes the proportion of a predefined nocturnal time in bed that was recorded as sleep. Actigraphy captured movement using a wrist-worn accelerometer.
The registry record describes a randomized, double-blind, placebo-controlled, parallel-group core phase. The stated primary endpoint concerns average measurements over the first 7 nights of treatment, rather than a single night or the full 28-night core phase. A follow-up period and an optional open-label extension were also part of the study, but they are distinct from the primary Week 1 comparison.
The main question is therefore about a short-term, measured sleep outcome in the specified participant group. The registry record does not report a numerical estimate of change for any treatment group, a between-group contrast, or a statistical test for this primary comparison. It is not possible to characterize the direction, size, or precision of the primary comparison from the registry information.
3. Trial Design
This was a Phase 2, randomized, quadruple-masked, parallel-group study sponsored by Eisai Inc. The study title identifies irregular sleep-wake rhythm disorder and mild to moderate Alzheimer’s disease dementia as the clinical setting. The registry record lists total enrollment as 63. It does not report the number randomized to each core-phase group in the information available for this study.
The core phase compared four lemborexant doses—2.5 mg, 5 mg, 10 mg, and 15 mg—with lemborexant-matched placebo. Participants took their assigned tablets orally each night for 28 consecutive nights, immediately before the time they intended to try to sleep. For the 15 mg regimen, the description specifies one 5 mg tablet and one 10 mg tablet; descriptions of the other active regimens include a matched placebo tablet alongside the active dose. The placebo group took two matched placebo tablets.
The registry describes screening before random assignment. Following core treatment, participants had a 2-week follow-up period. Eligible participants could then enter an open-label extension lasting up to 30 months or until program discontinuation. Extension participation was optional and restricted to eligible participants, so extension observations do not represent the same randomized comparison as the core phase.
The study start date was 2016-12-20, and primary completion was 2018-07-26. Its status is completed. Although the record gives the masking classification and parallel-group model, the specific roles masked, randomization procedure, allocation ratio, and site count are not reported in the registry record. The record also does not report the rationale for the planned enrollment or additional design details such as stratification factors.
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: In Core phase, a total of 214 participants were screened, of which 151 were screen failures and 63 were randomized and enrolled in to the study. Of these 63 participants, 62 received the study treatment (1 participant was inadvertently randomized but did not receive any study drug). In Extension phase, a total of 25 participants who completed the Core Phase, gave consent to join Extension phase were enrolled and treated.
Only the first 6 of 8 groups are shown.
Core Phase
| Stage | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Extension Phase: Lemborexant 5 mg |
|---|---|---|---|---|---|---|
| STARTED | 12 | 12 | 14 | 13 | 12 | 0 |
| Treated | 12 | 12 | 13 | 13 | 12 | 0 |
| COMPLETED | 12 | 12 | 13 | 13 | 12 | 0 |
| NOT COMPLETED | 0 | 0 | 1 | 0 | 0 | 0 |
Reasons for not completing this period:
| Reason | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Extension Phase: Lemborexant 5 mg |
|---|---|---|---|---|---|---|
| Randomized but not treated | 0 | 0 | 1 | 0 | 0 | 0 |
Extension Phase
| Stage | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Extension Phase: Lemborexant 5 mg |
|---|---|---|---|---|---|---|
| STARTED | 0 | 0 | 0 | 0 | 0 | 5 |
| COMPLETED | 0 | 0 | 0 | 0 | 0 | 0 |
| NOT COMPLETED | 0 | 0 | 0 | 0 | 0 | 5 |
Reasons for not completing this period:
| Reason | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Extension Phase: Lemborexant 5 mg |
|---|---|---|---|---|---|---|
| Adverse Event | 0 | 0 | 0 | 0 | 0 | 2 |
| Withdrawal by Subject | 0 | 0 | 0 | 0 | 0 | 1 |
| Lost to Follow-up | 0 | 0 | 0 | 0 | 0 | 0 |
| Administrative Reason | 0 | 0 | 0 | 0 | 0 | 1 |
| Loss of caregiver | 0 | 0 | 0 | 0 | 0 | 0 |
| Others | 0 | 0 | 0 | 0 | 0 | 1 |
Analysis population for the primary outcome, as defined in the registry: The full analysis set (FAS) included group of randomized participants who received at least 1 dose of randomized study drug and had at least 1 postdose efficacy measurement. Participants who were evaluable for this measure at given time point were included for the assessment.
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: The safety analysis set included the group of randomized participants who received at least 1 dose of randomized study drug and had at least 1 postdose safety assessment.
| Characteristic | Unit | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Total |
|---|---|---|---|---|---|---|---|
| Participants analysed | 12 | 12 | 13 | 13 | 12 | 62 | |
| Age, Continuous | years | 75.3 (SD 6.15) | 76.5 (SD 6.32) | 76.9 (SD 7.98) | 71.8 (SD 7.05) | 71.9 (SD 6.11) | 74.5 (SD 6.94) |
| Sex: Female, Male: Female | Participants | 7 | 6 | 8 | 6 | 10 | 37 |
| Sex: Female, Male: Male | Participants | 5 | 6 | 5 | 7 | 2 | 25 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 4 | 2 | 4 | 6 | 8 | 24 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 8 | 10 | 9 | 7 | 4 | 38 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 | 0 | 0 | 0 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 | 0 | 0 | 0 | 0 | 0 |
| Race (NIH/OMB): Asian | Participants | 2 | 2 | 2 | 3 | 2 | 11 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 | 0 | 0 | 0 | 0 | 0 |
| Race (NIH/OMB): Black or African American | Participants | 2 | 1 | 2 | 1 | 1 | 7 |
| Race (NIH/OMB): White | Participants | 8 | 9 | 8 | 9 | 9 | 43 |
| Race (NIH/OMB): More than one race | Participants | 0 | 0 | 0 | 0 | 0 | 0 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 1 | 0 | 0 | 1 |
6. Primary Endpoint
The registry lists the primary outcome as Core Phase: Change From Baseline in Mean Actigraphy Sleep Efficiency (aSE) With Lemborexant Compared to Placebo During Week 1 of Treatment, measured over Baseline, Week 1.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | percentage of sleep time |
| Endpoint classification | Continuous Endpoint |
The primary endpoint was change from baseline in mean actigraphy sleep efficiency (aSE) during Week 1 of treatment. The registry defines aSE as the percentage of time spent in bed sleeping during the predefined 8-hour nocturnal sleep period. It was calculated from the duration of sleep epochs relative to that period. Higher values were defined as better.
Actigraphy used a wrist-worn accelerometer programmed to monitor the degree and intensity of movement. This provides a movement-based measure of sleep and wake patterns, rather than a participant’s direct report of sleep. For the primary endpoint, the reported change was from baseline to the average of the first 7 treatment nights. The stated timeframe is Baseline, Week 1.
A change-from-baseline outcome focuses on how the measure differs from its starting value over the specified treatment period. Comparing changes between randomized groups can help distinguish the observed treatment-group pattern from changes also seen in the placebo group. The registry record does not report baseline or Week 1 group means, the change estimates, or the between-group comparison, so the observed endpoint pattern and its precision cannot be described.
Actigraphy-derived sleep efficiency is one sleep-related parameter within a broader outcome set: the study summary also describes sleep-related, wake-related, and circadian-rhythm-related measures. The primary endpoint is therefore a specific operational measure, not a complete account of sleep or circadian function. Its interpretation depends on the recorded measurement, the defined nocturnal interval, and the analysis population.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record identifies the primary outcome and its measurement but does not report the primary result. No group-specific baseline values, Week 1 values, changes from baseline, treatment contrasts, confidence intervals, or p-values for mean aSE are reported in the registry record. Without these results, the observed direction and magnitude of the primary comparison cannot be assessed, and its statistical precision cannot be described.
The study had four active dose groups and a placebo group in its core phase. This design can address patterns across doses, but the presence of multiple groups does not itself establish a dose-response relationship. That conclusion would depend on the endpoint estimates and the analysis used to compare them. The registry record’s stated objective was to determine dose response for sleep-, wake-, and circadian-rhythm-related actigraphy measures. The numerical results needed to evaluate that objective are not reported in the registry record.
Enrollment was 63, but the record does not provide the primary-outcome analysis counts by treatment group. The FAS definition says it includes randomized participants who received at least 1 dose of randomized study drug and had at least 1 postdose efficacy measurement; participants evaluable at a given time point were included for that assessment. The number contributing to the primary Week 1 result is not reported in the registry record. Thus, the overall enrollment should not be taken as the number with a usable primary endpoint measurement.
The registry lists 53 outcome measures and 48 analyses. This indicates a broad collection of registered outcome and analysis entries, but those counts alone do not establish which results were prespecified as confirmatory, how comparisons were prioritized, or whether adjustment for multiple testing was used. Those aspects of the statistical plan are not reported in the registry record.
There is also no reported primary-outcome confidence interval from which to judge whether the estimated effect is tightly or loosely determined. In general, a confidence interval expresses the uncertainty around an estimate under the analysis assumptions; it is not a guarantee that the true value lies within a particular interval. Here, because the estimate and interval are not reported in the registry record, no inference about the precision of the primary comparison can be made.
The adverse-event counts are separate safety summaries and do not supply evidence about the primary sleep-efficiency endpoint. Likewise, the optional extension differs in design from the randomized core phase and cannot substitute for the core comparison. The registry record supports describing the study design and intended endpoint, but not a conclusion about the comparative primary result.
9. Statistical Methods Explained
The primary outcome is a continuous measure, and the registry specifies that results are expressed as a mean with standard deviation. A mean describes the central value of observations in a group. The standard deviation describes how dispersed individual observations are around that mean. These statistics answer different questions: the mean summarizes the group’s average, while the standard deviation describes variation among participants.
What does change from baseline represent?
A change-from-baseline measure compares an observation after treatment begins with a participant’s starting measurement. The trial’s primary outcome uses the change from baseline to the average of the first 7 treatment nights. This defines the time window and the summary being evaluated. It does not mean that every participant had a measurement on every night; the registry record does not report the completeness of nightly actigraphy data or how missing nights were handled.
For a randomized comparison, treatment groups can be compared through their changes, or through a model that accounts for baseline and follow-up measurements. These are general analytical approaches; the particular model used for the primary endpoint is not reported in the registry record. The record also does not report whether covariates, repeated-measure structures, or other adjustments were included.
Why is the standard deviation not the uncertainty in a treatment effect?
The standard deviation measures spread in participant-level values. The uncertainty of a group mean or between-group contrast is generally represented by a standard error or confidence interval, which depends on the data and analysis. A standard deviation alone is not a confidence interval and cannot establish whether a difference between groups is statistically compatible with no difference. Since the primary comparison estimates and their uncertainty are not reported in the registry record, the endpoint’s statistical precision cannot be assessed.
What does randomization contribute?
In general, random allocation is intended to make treatment groups comparable, on average, with respect to measured and unmeasured characteristics at the time of assignment. It does not ensure that every feature will be balanced in a study, particularly when group sizes are limited. The registry reports randomized allocation, but the procedure used to generate or conceal the sequence is not reported in the registry record. The actual baseline distributions by treatment group are also not reported in the information available for this study.
Masking can reduce the influence of expectations on participant experience, care, measurement, and analysis. The registry classifies the study as quadruple-masked but does not report which roles were masked or the procedures used to maintain masking. Actigraphy provides an instrument-based measure, but measurement and analysis choices can still matter. The registry does not report details such as the scoring algorithm, rules for defining valid nights, or handling of device non-wear.
How should dose comparisons be considered?
The core design included four lemborexant doses and placebo. A dose-response assessment can be conducted in several ways, such as comparing each dose with placebo or evaluating a trend across dose levels. These methods address different questions. The specific primary statistical model, planned contrasts, and criteria for interpreting a dose-response pattern are not reported in the registry record. No conclusion about a dose trend can be drawn without the numerical results and analysis details.
When several doses and many outcomes are examined, the chance of at least one apparently unusual result can rise if each comparison is treated as an independent test without adjustment. This is a general multiplicity concern. Adjustment methods and a hierarchy for interpreting outcomes can address it, but the registry record does not report whether such methods were used. The listed counts of 53 outcome measures and 48 analyses do not reveal how the analysis family was defined or which results were designated as primary for inference.
What do planning calculations mean?
General sample-size planning asks how many participants may be needed to detect a specified effect with a chosen error rate and power under stated assumptions. The registry record’s sample-size illustration assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the assumed effect is a stated fraction of the observed effect. Such an illustration is not the trial’s original design justification, and it is not observed power. It is a planning exercise conditional on its assumptions and the effect used. The trial’s own sample-size justification is not reported in the registry record. No numerical planning estimates are reported in the information available for this study.
These distinctions matter because planned sample size, observed enrollment, and the number analyzed for a particular endpoint are not interchangeable. Enrollment was 63. The registry record’s FAS definition requires receipt of at least 1 dose and at least 1 postdose efficacy measurement, with participants evaluable at the specific time point included for that assessment. The actual primary endpoint analysis count is not reported in the registry record.
10. Multiplicity, Missing Data and Analysis Populations
The registry record lists 53 outcome measures and 48 analyses, while the primary endpoint is aSE change from baseline during Week 1. A broad set of outcomes and comparisons raises a general multiplicity issue: when many hypotheses are tested, some results may appear notable by chance. The registry record does not report a statistical testing hierarchy, a family of comparisons, or a method for controlling multiplicity. It is therefore not possible to tell how the primary comparison was distinguished from other analyses for inferential purposes.
The record also does not report whether interim analyses were planned or conducted, whether the primary analysis was adjusted for baseline or other covariates, or how treatment effects were modeled. These details should not be inferred from the randomized, parallel-group description. The primary endpoint’s numerical results and inferential statistics are not reported in the registry record.
For the primary measure, the FAS included randomized participants who received at least 1 dose of randomized study drug and had at least 1 postdose efficacy measurement. Participants evaluable for the measure at a given time point were included for that assessment. The registry record does not report how many participants were included in the Week 1 analysis, the extent or pattern of missing actigraphy data, or the method used to address missing data. It also does not report sensitivity analyses assessing the effect of missing observations.
These points limit assessment of the analysis population and robustness. Overall enrollment cannot be assumed to equal the number analyzed for the primary endpoint. Nor can the FAS definition, by itself, establish how participants with incomplete measurements affected the estimates. The statistical analysis plan and further details of missing-data handling are not reported in the registry record.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Core Phase: Lemborexant-matched Placebo | 0 | 12 | 0.0% |
| Core Phase: Lemborexant 2.5 mg | 0 | 12 | 0.0% |
| Core Phase: Lemborexant 5 mg | 0 | 13 | 0.0% |
| Core Phase: Lemborexant 10 mg | 0 | 13 | 0.0% |
| Core Phase: Lemborexant 15 mg | 0 | 12 | 0.0% |
| Extension Phase: Lemborexant 5 mg | 1 | 5 | 20.0% |
| Extension Phase: Lemborexant 10 mg | 2 | 14 | 14.3% |
| Extension Phase: Lemborexant 15 mg | 1 | 6 | 16.7% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Core Phase: Lemborexant-matched Placebo | 0 of 12 |
| Core Phase: Lemborexant 2.5 mg | 0 of 12 |
| Core Phase: Lemborexant 5 mg | 0 of 13 |
| Core Phase: Lemborexant 10 mg | 0 of 13 |
| Core Phase: Lemborexant 15 mg | 0 of 12 |
| Extension Phase: Lemborexant 5 mg | 0 of 5 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Core Phase: Lemborexant-matched Placebo | 4 of 12 |
| Core Phase: Lemborexant 2.5 mg | 3 of 12 |
| Core Phase: Lemborexant 5 mg | 3 of 13 |
| Core Phase: Lemborexant 10 mg | 4 of 13 |
| Core Phase: Lemborexant 15 mg | 6 of 12 |
| Extension Phase: Lemborexant 5 mg | 4 of 5 |
Most frequent serious adverse event terms
| Event term | Organ system | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Extension Phase: Lemborexant 5 mg |
|---|---|---|---|---|---|---|---|
| Ischaemic stroke | Nervous system disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 0 of 12 | 1 of 5 |
| Asthenia | General disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
| Ilium fracture | Injury, poisoning and procedural complications | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
| Hypercapnia | Respiratory, thoracic and mediastinal disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
| Hypoxia | Respiratory, thoracic and mediastinal disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
| Orthostatic hypotension | Vascular disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Core Phase: Lemborexant-matched Placebo | Core Phase: Lemborexant 2.5 mg | Core Phase: Lemborexant 5 mg | Core Phase: Lemborexant 10 mg | Core Phase: Lemborexant 15 mg | Extension Phase: Lemborexant 5 mg |
|---|---|---|---|---|---|---|---|
| Somnolence | Nervous system disorders | 0 of 12 | 0 of 12 | 0 of 13 | 1 of 13 | 2 of 12 | 3 of 5 |
| Constipation | Gastrointestinal disorders | 0 of 12 | 0 of 12 | 0 of 13 | 1 of 13 | 2 of 12 | 0 of 5 |
| Bradycardia | Cardiac disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 1 of 12 | 1 of 5 |
| Diarrhoea | Gastrointestinal disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 1 of 12 | 1 of 5 |
| Nasopharyngitis | Infections and infestations | 1 of 12 | 0 of 12 | 1 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
| Arthralgia | Musculoskeletal and connective tissue disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 2 of 12 | 0 of 5 |
| Headache | Nervous system disorders | 0 of 12 | 0 of 12 | 0 of 13 | 0 of 13 | 2 of 12 | 0 of 5 |
| Sedation | Nervous system disorders | 0 of 12 | 0 of 12 | 1 of 13 | 0 of 13 | 0 of 12 | 1 of 5 |
| Nightmare | Psychiatric disorders | 0 of 12 | 0 of 12 | 0 of 13 | 2 of 13 | 0 of 12 | 0 of 5 |
| Atrioventricular block first degree | Cardiac disorders | 0 of 12 | 0 of 12 | 1 of 13 | 0 of 13 | 0 of 12 | 0 of 5 |
Serious events with the highest arm-level rate: ischaemic stroke (20.0%), ilium fracture (16.7%), asthenia (7.1%), hypercapnia (7.1%), hypoxia (7.1%).
The core-phase safety summaries list participants at risk for serious adverse events and for other adverse events, along with affected counts. In the placebo group, 12 participants were at risk for serious events and 0 were affected; 12 were at risk for other events and 4 were affected. For lemborexant 2.5 mg, the corresponding counts were 12 and 0 for serious events, and 12 and 3 for other events. At 5 mg, they were 13 and 0 for serious events, and 13 and 3 for other events. At 10 mg, they were 13 and 0 for serious events, and 13 and 4 for other events. At 15 mg, they were 12 and 0 for serious events, and 12 and 6 for other events. Deaths were 0 in each core-phase group.
Extension-phase counts are separate: at 5 mg, 5 participants were at risk for serious events and 1 was affected; 5 were at risk for other events and 4 were affected. At 10 mg, those counts were 14 and 2 for serious events, and 14 and 10 for other events. At 15 mg, they were 6 and 1 for serious events, and 6 and 5 for other events. Deaths were 0 in each listed extension group.
The registry also lists serious-event terms with percentages, including Ischaemic stroke at 20.0% and Ilium fracture at 16.7%; the denominator for these percentages is not reported in the registry record. These counts describe events in the reported groups and are not adjusted comparisons. Core and extension groups should not be combined as if they were one randomized comparison.
12. What the Result Does, and Does Not, Mean
The registry record establishes that a randomized, masked, placebo-controlled study was conducted and identifies the primary endpoint as change in mean actigraphy sleep efficiency during Week 1. It also records four lemborexant dose groups, a placebo group, and an optional open-label extension. These details clarify what the study was designed to examine, but they do not establish what the primary comparison found.
The primary endpoint estimates, between-group differences, uncertainty intervals, and p-values are not reported in the registry record. Consequently, the posted information does not show whether aSE increased or decreased in any group, how the groups compared, or how precisely any comparison was estimated. The record cannot support a statistical conclusion about the primary endpoint’s result.
More generally, an outcome is a defined measurement, not a complete representation of a clinical condition. Here, the primary measure captures actigraphy-derived sleep efficiency over a defined nocturnal period. It does not, by itself, describe every dimension of sleep, wakefulness, circadian rhythm, or participant experience. The study summary describes broader sleep-, wake-, and circadian-related objectives, but the primary endpoint remains a specific measurement collected over a short treatment window.
Safety counts provide another type of information. They report affected participants in specified core and extension groups, but do not constitute a randomized efficacy comparison and should not be read as comparative estimates adjusted for other factors. The extension was open-label and optional, which also distinguishes it from the masked randomized core phase.
The record gives design and endpoint definitions, total enrollment, and safety counts. It does not report the primary outcome findings or enough analysis detail to evaluate multiplicity, missing-data sensitivity, or the model used. A statistically careful interpretation therefore separates the study’s intended question from evidence about its answer. No claim about whether lemborexant changed sleep efficiency relative to placebo can be drawn from the primary results reported in the registry record.
13. Why This Trial Matters Statistically
This study is statistically notable for combining a placebo-controlled randomized core phase with four active dose groups and a continuous actigraphy-derived endpoint. The design targets a dose-response question rather than a single active-versus-placebo contrast alone. Interpreting such a design requires clarity about which comparisons were planned, how a dose pattern was defined, and how multiple endpoints and treatment contrasts were handled. Those statistical-plan details are not reported in the registry record.
The endpoint also illustrates how operational definitions shape clinical measurement. Sleep efficiency was defined using sleep epochs during a predefined 8-hour nocturnal period and measured with a wrist-worn accelerometer. The primary summary averaged the first 7 treatment nights and compared that with baseline. These choices identify precisely what the outcome represents, while also making clear that it is not a general measure of all sleep-related experience.
Enrollment was 63, and the registry’s FAS definition depends on treatment receipt and availability of a postdose efficacy measurement. The number analyzed for the primary time point is not reported in the registry record. This highlights why enrollment alone is not enough to judge information available for a continuous endpoint: time-point-specific measurement availability and missing-data handling also matter.
Finally, the optional open-label extension sits alongside, but is analytically distinct from, the randomized core comparison. Its safety observations have different design context and should not be treated as additional randomized evidence. Since the primary efficacy estimates and analysis details are not reported in the registry record, the trial’s statistical importance lies in its design and measurement framework, rather than in a demonstrated result.
14. 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 efficacy results are not reported in the registry record. Without group-level endpoint values, comparative estimates, or uncertainty measures, the direction, magnitude, and precision of the primary comparison cannot be evaluated. The record identifies aSE as the primary endpoint but does not provide the analysis count for that time point.
The participant-level flow from enrollment through randomization, treatment, and endpoint analysis is not reported in the information available for this study. Total enrollment was 63, but group sizes for the primary analysis cannot be inferred from that total. The FAS definition includes randomized participants who received at least 1 dose and had at least 1 postdose efficacy measurement; actual endpoint-specific inclusion counts are not reported.
Actigraphy data quality and missingness are also not described. The registry record does not report how valid nights were determined, how device non-wear was handled, or how incomplete measurement sequences were analyzed. Such details can affect a mean based on repeated nightly observations.
Other limitations for interpretation include the absence of reported details on randomization procedures, allocation ratio, masking roles, primary statistical model, prespecified contrasts, and multiplicity control. The record also does not report a sample-size justification or interim-analysis plan. These omissions do not establish that the procedures were inadequate; they mean the relevant information is not reported in the registry record.
The extension was open-label and optional, and its safety groups are not equivalent to the randomized core comparison. The registry’s safety counts should therefore be read in their phase-specific context. The available information does not permit a full assessment of longer-term efficacy or comparative safety.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Study of Lemborexant for Irregular Sleep-Wake Rhythm Disorder and Mild to Moderate Alzheimer's Disease Dementia — NCT03001557.
- Registry record last updated 2021-05-17; status last verified 2021-04.
- Results first posted 2020-01-14.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
NCT03001557 is a completed Phase 2 randomized, quadruple-masked, parallel-group study sponsored by Eisai Inc. It enrolled 63 participants and examined lemborexant at 2.5 mg, 5 mg, 10 mg, and 15 mg against matched placebo in participants with irregular sleep-wake rhythm disorder and mild to moderate Alzheimer’s disease dementia. Core treatment lasted 28 consecutive nights, followed by a 2-week follow-up; eligible participants could enter an optional open-label extension.
The primary endpoint was change from baseline in mean actigraphy sleep efficiency during Week 1, based on the average of the first 7 treatment nights. The registry record does not report the primary endpoint estimates or their statistical uncertainty. It lists safety counts separately for core and extension phases, with 0 deaths in every listed group. Additional details on the primary analysis model, multiplicity, missing-data handling, and sample-size justification are not reported in the registry record.