Using a Wireless Controller to Deliver a Lighting Intervention to Persons With Dementia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Using a Wireless Controller to Deliver a Lighting Intervention to Persons With Dementia (NCT05519137), a randomized na study. The primary outcome is Sleep Disturbance Using the Pittsburgh Sleep Quality Index (PSQI).

2. Clinical Question

The clinical question is about the comparison of two lighting conditions within a randomized crossover study. In this design, participants receive both conditions in sequence, rather than remaining in only one condition. This makes the comparison potentially informative about changes in the same participant across conditions, but the result depends on how the sequence, time, and any carryover from an earlier condition are handled in the analysis.

The study’s stated focus includes sleep and mood. The primary outcome is sleep disturbance using the PSQI; listed secondary outcomes concern depression screening, actigraphy-based sleep efficiency, and sleep burden. These measures describe different aspects of mood and sleep and should not be treated as interchangeable. The record does not report findings for any of them.

3. Trial Design

This is a randomized, double-masked crossover trial recorded as completed. The registry lists an enrollment of 14 and identifies the sponsor as Icahn School of Medicine at Mount Sinai. The recorded start date is 2022-01-06, and the primary completion date is 2023-05-01. The record lists the phase as NA.

The two study conditions are active lighting intervention and control lighting intervention. The arm descriptions specify two sequences: active lighting followed by control, and control followed by active lighting. Each lighting condition is described as lasting 8 weeks, with a 4 week washout before crossover to the opposite condition. The record does not report how participants were allocated to the sequences, beyond identifying the allocation as randomized.

In a crossover study, each participant receives both conditions. As a general statistical point, this can allow a comparison that accounts for stable differences between participants, because the same person contributes information under both conditions. The comparison still needs an analysis appropriate to the sequence and repeated measurements. The registry record does not report the planned or completed statistical model, how period effects were handled, or whether carryover was assessed.

Masking is recorded as double, but the record does not identify which people were masked or describe how masking was maintained. Further operational details, including the characteristics of the lighting conditions, are not reported in the registry record. The record describes the intervention as tailored and controlled by the RAD controller, but does not provide additional specifications that would allow the lighting exposure to be characterized.

The primary outcome is PSQI score, with a stated timeframe of baseline and post intervention (8 weeks). The registry also lists secondary outcomes involving the Cornell Scale for Depression in Dementia, actigraphy-measured sleep efficiency, and the Sleep Disorders Inventory. The registry record reports no analyses for these outcomes.

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.

First Intervention (8 Weeks)

Reasons for not completing this period:

Washout Period (4 Weeks)

Second Intervention (8 Weeks)

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 Sleep Disturbance Using the Pittsburgh Sleep Quality Index (PSQI), measured over Baseline and post intervention (8 weeks).

The primary endpoint is sleep disturbance measured using the Pittsburgh Sleep Quality Index (PSQI). The record describes the PSQI as a questionnaire comprising 19 items that generate 7 component scores. Those component scores are summed to form a global score ranging from 0 to 21. A global score >5 is described as indicating sleep disturbances, and a lower global score indicates improvement in sleep disturbance.

The endpoint is a continuous score. As a general measurement point, a continuous outcome can retain information across its scale rather than reducing each observation to a yes-or-no classification. The stated threshold provides an interpretation of scores in relation to sleep disturbance, but it does not replace the continuous score as the primary measure described in this record. A change in the score and a difference between conditions would need to be interpreted using the actual results and an analysis that accounts for the crossover design.

The recorded timeframe is baseline and post intervention (8 weeks). The record does not report the observed PSQI scores, their variability, or a condition contrast. It also does not report a clinically important difference threshold. Consequently, the endpoint description explains what was intended to be measured, but does not establish how participants’ scores changed or whether any difference was precise.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a crossover design compare?

In this trial, participants were assigned to receive both active and control lighting conditions, in opposite orders. As a general statistical explanation, a crossover comparison uses measurements collected from the same participant under different conditions. This can account for stable participant characteristics that would otherwise contribute to variation between groups. It does not remove the need to consider time, condition order, or effects that persist after a condition ends.

The registry describes each condition as 8 weeks long and a 4 week washout before crossover. A washout is intended, in general, to separate periods of exposure so that effects from an earlier condition are less likely to influence measurement under the next condition. Whether that separation is sufficient depends on the intervention and outcome. The record does not report a justification for the washout duration or an assessment of carryover.

Why does the analysis need to reflect the design?

As a general statistical point, measurements from the same person are related, so treating them as if they came from unrelated participants can misrepresent uncertainty. An analysis may account for that dependence by using a paired comparison or another suitable repeated-measures model. The particular method used in this trial is not reported in the registry record. Neither are details about adjustment for period or sequence, model assumptions, or how baseline measurements entered the analysis.

Randomization helps guard against systematic differences in assigned sequences, but it does not by itself determine the correct analysis or ensure that all possible sources of bias are absent. Double masking may help reduce some effects of expectations, depending on who is masked and how masking is implemented. The record identifies the trial as double-masked but does not say who was masked or describe the masking procedures.

How should a continuous outcome be understood?

The PSQI is recorded as a mean continuous measure with standard deviation as its dispersion measure. In general, a mean describes the central value of a set of scores, while a standard deviation describes how spread out those scores are around the mean. Neither quantity alone gives the estimated contrast between lighting conditions. For a condition comparison, the analysis would also need to state which observations are being compared and how the crossover structure is represented.

A confidence interval, in general, expresses uncertainty around an estimated effect under the assumptions of the analysis. A narrow interval indicates greater precision than a wide one, but precision does not by itself establish clinical importance. A p-value and a confidence interval answer related but different questions. No estimate, interval, or p-value for the primary outcome is reported in this record, so these concepts cannot be applied to a trial result.

What does the registry report about analysis?

The registry lists 0 analyses. It also flags the primary outcome as having several categories or time points and not being reduced to one comparison. This means the outcome description does not yield a single posted contrast to interpret. The record does not report a statistical analysis plan, an adjustment strategy, interim analyses, or the approach to multiple outcomes. These details are not reported in the registry record; their absence should not be filled in by assuming a conventional method.

Several outcomes are described, including sleep disturbance, depression screening, sleep efficiency, and sleep burden. As a general statistical point, examining multiple outcomes or contrasts can raise multiplicity concerns: when many hypotheses are tested, the chance of at least one seemingly unusual result may increase. Whether and how that concern was handled in this trial is not reported. No adjustment method or hierarchy of secondary outcomes is specified in the record.

How should planning calculations be read?

The stated sample-size assumptions describe a planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is described as a stated fraction of the observed effect. Such calculations are conditional on their assumptions and are not a report of what the trial observed. They are planning illustrations, not observed power. The trial’s own sample-size justification is not reported in the registry record.

For a general interpretation of planning values, a requested power level defines a design target under chosen assumptions; it does not tell whether the completed study found an effect. A calculation expressed as participants per arm for 80% power is a hypothetical design quantity, not the number analyzed in this crossover trial. The available record does not report a result-based estimate from which the precision of the primary comparison can be assessed.

What remains unknown?

The registry does not report the primary outcome data, the completed analysis method, outcome-specific analysis populations, missing-data procedures, protocol deviations, or an explanation for the absence of posted analyses. The details needed to evaluate model fit, assumptions, and robustness are therefore not available in the registry record. These gaps limit statistical interpretation; they do not justify assuming that a particular method was used or that missing information had no effect.

10. Multiplicity, Missing Data and Analysis Populations

The study lists a primary PSQI outcome alongside secondary outcomes concerning depression screening, sleep efficiency, and sleep burden. The registry record does not report how the primary and secondary outcomes were prioritized in analysis, whether any multiplicity adjustment was planned or applied, or whether comparisons were selected from a broader set of measures or time points. These matters are not reported in the registry record.

As a general statistical point, multiplicity arises when several hypotheses, outcomes, or time points are examined. Without a prespecified strategy, readers may have difficulty distinguishing a primary confirmatory comparison from additional exploratory findings. The record’s note that the primary outcome has several categories or time points and was not reduced to one comparison reinforces that a single interpretable primary contrast is not available in the posted results. It does not establish what analyses were performed outside the registry.

Missing-data methods and analysis populations are also not reported in the registry record. The record does not state how many PSQI observations were available, how incomplete questionnaires were handled, whether participants were analyzed according to assigned sequence, or how withdrawals and protocol deviations were treated. No assumptions about the reasons for missingness or the methods used to address it can be made.

In general, missing outcomes can affect both the estimate and its uncertainty, depending on why data are absent and how the analysis handles them. A complete-case analysis, an imputation method, or a model using repeated measurements would each rely on different assumptions. The record does not identify any such approach. It also does not report an interim analysis plan or any analysis populations that would clarify which observations contributed to the intended primary comparison.

11. 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 registry’s adverse-event entries list 0 serious adverse events and 0 other adverse events in the active lighting intervention condition, with 11 at risk. The control lighting condition likewise lists 0 serious adverse events and 0 other adverse events, with 11 at risk. The death count is 0 for each listed condition. No serious adverse-event terms are listed.

These are the counts recorded in the registry; they do not establish that no adverse experiences occurred. The at-risk figures are not the same as a complete description of exposure, and the record does not explain their relationship to the enrollment of 14 or to the crossover sequences. It also does not provide event definitions, collection methods, reporting windows, severity details beyond the serious-event category, or information about events not captured in the registry entries.

As a general point, zero recorded events in a study does not prove that an intervention has no safety risks. The ability to characterize uncommon events depends on the amount and duration of observation and on how events are collected and reported. The adverse-event entries should therefore be read narrowly as registry counts, not as a comprehensive safety evaluation or a comparison establishing that the conditions have identical safety profiles.

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

The record establishes that a randomized, double-masked crossover trial was conducted to test active versus control lighting in people with Alzheimer’s disease. It describes the sequence of conditions, the washout, the PSQI primary outcome, and other sleep and mood measures. It also records the study as completed. These details clarify the research question and planned structure.

The record does not establish the effect of active lighting on PSQI scores. No primary outcome estimate, comparison, confidence interval, or p-value is posted, and the registry lists 0 analyses. The note that the primary outcome has several categories or time points and was not reduced to one comparison further means that a specific primary contrast cannot be interpreted from the available record. Without results, there is no basis for describing the direction, magnitude, or precision of a difference.

The absence of a reported effect is not evidence that the lighting conditions are equivalent. Equivalence would require an appropriate analysis and a defined margin for interpreting differences; the registry record reports neither. Nor can the lack of a reported result be taken as evidence that the intervention improved or worsened sleep or mood. The listed secondary outcomes likewise have no posted analyses.

The recorded adverse-event counts are zero for serious and other adverse events in each condition, and zero deaths are recorded. These counts provide a limited registry snapshot, not proof that no adverse experiences occurred or a comprehensive assessment of safety. The record does not reconcile the adverse-event at-risk entries with enrollment or explain how exposure was counted across crossover periods.

Any statistical interpretation should therefore stay at the level of design and outcome definitions. The study’s completed status does not itself supply an efficacy result. A reader would need outcome data and an analysis accounting for the crossover structure, missing observations, and relevant periods to assess the intervention contrast. Those details are not reported in the registry record.

13. Why This Trial Matters Statistically

This trial is statistically notable because its crossover structure makes the comparison depend on both condition and order. Each participant was intended to receive active and control lighting, separated by a washout. In general, that structure can make within-participant comparisons useful, while also requiring analysis that respects repeated observations and considers period or carryover effects. The registry record does not report how those features were handled.

The primary measure is a continuous score with an explicit interpretation: lower PSQI global scores indicate improvement in sleep disturbance, and scores >5 are described as indicating disturbances. This makes clear how the measure is intended to be read, while leaving open the key statistical questions about the estimated contrast, its precision, and the relevance of any observed difference. No outcome result is posted to answer those questions.

The trial also illustrates why a completed status and a detailed outcome definition are not substitutes for posted analyses. The record identifies several categories or time points for the primary outcome but does not reduce them to one comparison, and it lists 0 analyses. As a result, readers can understand the planned clinical question but cannot evaluate an estimated treatment effect or its uncertainty.

Finally, the registry entries make the distinction between safety counts and a complete safety assessment important. The reported zeros should be interpreted in the context of the listed at-risk figures and the absence of further reporting detail. Overall, the statistical value of this record lies in documenting a randomized crossover design and its outcome framework, while also making clear that the evidence needed for an effect estimate is not reported.

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 main limitation for interpretation is the absence of posted outcome analyses. The registry lists 0 analyses and does not report PSQI scores, an active-versus-control contrast, or uncertainty around such a contrast. The trial’s completed status therefore cannot be used to infer what the study found.

The primary outcome is described with a baseline and post intervention (8 weeks) timeframe, but the record also notes several categories or time points and no single reduced comparison. The particular categories and the intended primary contrast are not reported in the registry record. Without a clearly stated analyzed contrast, readers cannot determine which measurements would support the main conclusion.

The crossover design raises questions that the record leaves unresolved. It does not report the statistical model, how within-participant dependence was handled, whether period and sequence were considered, or whether carryover was assessed. The 4 week washout is described, but its rationale and adequacy are not reported. The record identifies double masking without identifying who was masked or how it was maintained.

Analysis populations and missing-data handling are not reported. The registry enrollment is 14, while adverse-event entries list 11 at risk in each condition; no explanation reconciles these values. The record does not state how many outcome observations were available or how incomplete measures, withdrawals, or protocol deviations were addressed.

Additional limitations include the absence of a reported sample-size justification, analysis plan, multiplicity strategy, and outcome-specific results. The registry describes planning assumptions, but those assumptions do not supply a trial result or establish observed power. These omissions restrict assessment of precision, robustness, and the scope of any conclusions.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Using a Wireless Controller to Deliver a Lighting Intervention to Persons With Dementia — NCT05519137.
• Registry record last updated 2026-07-30; status last verified 2026-07.
• Results first posted 2026-07-30.
• 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.

18. Record Summary

The registry record describes a completed, randomized, double-masked crossover study of active and control lighting interventions for people with Alzheimer’s disease. Enrollment is recorded as 14. The study began on 2022-01-06, with primary completion on 2023-05-01, and is sponsored by Icahn School of Medicine at Mount Sinai.

Each lighting condition is described as lasting 8 weeks, with a 4 week washout before participants crossed over to the opposite condition. The primary outcome is PSQI sleep disturbance score, measured at baseline and post intervention (8 weeks). Listed secondary outcomes concern depression screening, actigraphy-measured sleep efficiency, and sleep burden.

The registry lists 0 analyses and does not report an estimated primary outcome contrast. It records 0 serious adverse events, 0 other adverse events, and 0 deaths in each listed condition, with 11 at risk in each. Analysis methods, missing-data procedures, and a trial-specific sample-size justification are not reported in the registry record.