Cognitive Behavioral Therapy for Insomnia for Gulf War Illness: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Cognitive Behavioral Therapy for Insomnia for Gulf War Illness (NCT02782780), a randomized na study. The primary outcome is Gulf War Illness Symptom Severity Index.

2. Clinical Question

The trial asks whether telephone-delivered Cognitive Behavioral Therapy for Insomnia (CBTi) is associated with changes in Gulf War Illness (GWI) symptom severity among Veterans with GWI and insomnia. The registry describes a comparison between CBTi and a Monitor Only control group, with usual care continued in the control group during the 8-week period.

3. Trial Design

This is a randomized, single-masked, parallel-group pilot trial. The registry lists an enrollment of 165 and describes two groups: CBTi and Monitor Only. The planned behavioral intervention consisted of 8 weekly individual CBTi sessions. The Monitor Only group was followed for 8 weeks of usual care, with participants advised to continue their existing approach to managing GWI and insomnia without changing treatment dosage or frequency.

The study is marked completed, with a start date of 2016-10-24 and a primary completion date of 2020-01-31. Its phase is listed as NA. The sponsor is the VA Office of Research and Development. The masking field says single, but the registry record does not identify who was masked or describe how masking was maintained. Details of random-sequence generation, allocation concealment, and the exact randomization procedures are not reported in the registry record.

The primary outcome is the Gulf War Illness Symptom Severity Index, assessed at baseline and after 8 weeks of study participation. The record also lists a 6-month assessment among participants randomized to CBTi. It reports that 32 of 39 participants randomized to CBTi completed treatment, and that only 28 of those participants completed the 6-month follow-up assessment. This account does not establish the status of every participant at each outcome visit.

Other listed outcomes include fatigue, pain, self-reported abilities, anxiety, depression, sleep quality, and sleep efficiency. The registry does not state a single analysis population, specify the primary statistical model, or explain how the listed outcomes and assessment times were handled analytically. Those details 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: During the first phase of screening, veterans participated in a brief telephone interview to inquire about inclusion/exclusion criteria and to determine probable GWI/CMI and insomnia diagnoses. Only participants who passed the initial telephone eligibility screening were invited to undergo a second round of clinical screening to assess for mental health disorders and other exclusionary conditions (e.g., untreated sleep apnea and restless legs syndrome).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: 32 of 39 participants randomized to CBTi completed treatment; only 28 of these participants completed the 6-month follow-up 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.

6. Primary Endpoint

The registry lists the primary outcome as Gulf War Illness Symptom Severity Index, measured over At baseline, after 8 weeks of study participation in all subjects, in subjects randomized to CBTi, 6 months after study participation.

The primary endpoint is the Gulf War Illness Symptom Severity Index, a score based on the symptom portion of the Kansas Gulf War Military History and Health Questionnaire. The measure covers fatigue and sleep problems, somatic pain, skin abnormalities, gastrointestinal and respiratory symptoms, and neurologic, cognitive, and mood symptoms. Participants report whether symptoms were absent, present at mild severity, moderate severity, or severe over the past 2 weeks.

The stated score range is 0-87, with higher scores indicating more symptoms and/or more severe symptoms. The registry explains that no single measure of severity addresses every presentation of GWI, given its novelty, complexity, and variability. This index brings a range of reported symptoms into one measure, allowing symptom burden to be described across several domains rather than by a sleep measure alone.

The endpoint is listed at baseline and after 8 weeks of study participation in all subjects, with a 6-month assessment among subjects randomized to CBTi. The registry specifies the median and inter-quartile range as the summary format. A median describes the middle of the observed scores, while the inter-quartile range describes the spread of the middle portion of those scores; these are general statistical interpretations. The numerical endpoint summaries and a single defined primary contrast are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a randomized, parallel-group study with single masking. Randomization is a method for assigning participants to groups by chance; in general, it is intended to reduce systematic differences between groups at the start of a trial. A parallel-group design means the groups are followed as separate treatment groups rather than participants crossing from one intervention to another. The registry does not describe the sequence-generation method, allocation concealment, or who was masked, so those implementation details are not reported in the registry record.

What does the endpoint summary describe?

The primary measure is summarized using a median and an inter-quartile range. In general, the median is the middle value after observations are ordered. It is often useful when data are skewed or when a typical value is better represented by the center of the observed scores than by an arithmetic average. The inter-quartile range describes the spread from the lower to the upper quartile. Together, these summaries describe location and variability without requiring the scores to follow a normal distribution. They do not, by themselves, quantify a between-group effect or establish whether a difference is statistically distinguishable from chance.

The endpoint is a symptom score ranging from 0-87, with higher scores indicating more symptoms and/or greater severity. Its component symptoms are rated as absent, mild, moderate, or severe over the past 2 weeks. The outcome description explains why a composite symptom measure was used: GWI has varied presentations, and no single measure of severity covers every possible presentation. A composite can represent several domains, but interpretation still depends on the exact scoring and analysis choices. Those choices beyond the stated score and summary format are not reported in the registry record.

What does the assessment schedule imply?

The primary outcome is listed at baseline and after 8 weeks of study participation, with a 6-month assessment among participants randomized to CBTi. In general, repeated measurements can be analyzed in several ways, including comparisons of change from baseline, comparisons of follow-up scores adjusted for baseline, or models that use measurements across visits. These approaches can answer related but not identical questions and may make different assumptions. The statistical model, the contrast used, and whether baseline was incorporated into the analysis are not reported in the registry record. The stated schedule alone does not establish which method was used.

The registry does not specify one primary comparison across its listed outcome categories and time points. Without a defined contrast, it is not possible to identify one numerical estimate as the decisive primary effect. A comparison at 8 weeks between groups would address a different question from a change within one group over time or from a 6-month follow-up within CBTi. These are general distinctions; the registry record does not state which of them was used for a formal primary analysis.

How should uncertainty and significance be understood?

In general, an effect estimate describes the size and direction of a contrast, while an uncertainty interval indicates how precisely it is estimated under the chosen analysis. A p-value, if reported, addresses how compatible the observed data are with a specified null hypothesis under a statistical model; it is not the probability that the null hypothesis is true. Statistical significance alone would not describe clinical importance, and a non-significant result would not establish that groups are equivalent. The registry record does not report the primary effect estimate, uncertainty interval, or p-value, so none of these interpretations can be made for the primary endpoint.

The record lists a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. It describes planning scenarios for stated shares of the observed effect. These are design illustrations, not observed power and not evidence that the trial was planned using those assumptions. The actual sample-size justification and the trial’s own design assumptions are not reported in the registry record. No specific planning sample-size results are stated in the registry record.

Why can outcome counts and analyses matter?

The registry lists 12 outcome measures and 24 analyses. In general, testing or estimating many outcomes can raise multiplicity concerns: when many hypotheses are examined, the chance of at least one apparently notable result can increase if no adjustment or prespecified hierarchy is used. A multiplicity strategy may include a primary-outcome hierarchy, adjusted significance thresholds, or emphasis on estimation rather than isolated tests. The registry record does not state whether any such strategy was planned or used. The count of outcomes and analyses alone does not establish that an adjustment was or was not appropriate.

For count outcomes, over-dispersion is a general concern when variability exceeds what a simple statistical model assumes. This trial’s stated primary outcome is a bounded symptom score summarized by median and inter-quartile range; the registry does not identify a count model for it. More broadly, the appropriate analysis depends on the outcome scale, distribution, missingness, and target comparison. The record does not report enough analysis detail to determine which model assumptions were checked or how they were addressed.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists multiple outcomes and assessment times, including the Gulf War Illness Symptom Severity Index and measures of fatigue, pain, abilities, anxiety, depression, sleep quality, and sleep efficiency. It also records 12 outcome measures and 24 analyses. These features make it important to know which outcome and time point were prespecified as primary, and whether any adjustment or hierarchy was used for multiple comparisons. The registry record does not report a multiplicity plan or identify a single primary comparison; its outcome record is not reduced to one comparison.

Missing-data handling is also not described. The primary outcome entry says 32 of 39 participants randomized to CBTi completed treatment and only 28 of those participants completed the 6-month follow-up assessment. This identifies incomplete follow-up in that group, but does not say whether missing scores were imputed, excluded, modeled, or addressed through sensitivity analyses. Outcome completion for Monitor Only is not described in the primary outcome population statement.

In general, missing observations can affect estimates if the participants with observed data differ systematically from those without them. Statistical methods may rely on assumptions about the process that led to missing data; different assumptions can lead to different interpretations. The registry record does not state the assumptions or methods used. It also does not identify whether the primary analysis was intention-to-treat, based on treatment received, or based on participants with available data. The analysis population and missing-data approach are not reported in the registry record.

Enrollment is listed as 165, while the adverse-event record gives groups of 46 in Monitor Only and 39 in CBTi. The record does not explain how those counts relate to enrollment or to the primary-outcome analysis population. No reconciliation should be inferred from those entries.

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 adverse-event record lists 46 participants at risk in Monitor Only and 39 in CBTi. It reports zero serious adverse events in each group and zero deaths in each group. It also reports zero other adverse events in each group. These are the event counts recorded for the groups and participants at risk listed in the adverse-event entry.

Such counts describe what the registry record reports; they do not, on their own, show that no adverse events occurred outside the registry’s definitions, reporting period, or recorded population. The record does not provide further detail about event collection, attribution, severity grading, or the period over which events were monitored. It also does not explain how the adverse-event group counts relate to the listed enrollment of 165.

In general, a zero count in a trial does not establish that a risk is absent. The ability to detect uncommon events depends on the number of participants observed, duration of observation, and completeness of reporting. The posted figures should therefore be read as recorded counts, not as proof of safety or a comparison of risk between groups. No medical advice or treatment conclusion follows from these figures.

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

The registry record establishes that a randomized, parallel-group pilot trial compared telephone-delivered CBTi with a Monitor Only group among Veterans with GWI and insomnia. It identifies a broad primary symptom index, a post-treatment assessment after 8 weeks, and a 6-month assessment among participants randomized to CBTi. It also reports treatment and follow-up completion counts for the CBTi group and adverse-event counts for both groups.

It does not report numerical primary-outcome scores, a between-group estimate, an uncertainty interval, or a p-value. It does not identify one primary contrast across the outcome categories and assessment times. Therefore, the posted record does not show how large or precise any primary-outcome difference was. It also does not support a conclusion that CBTi did or did not change GWI symptom severity relative to Monitor Only.

The planned treatment and comparison can be described from the record, but the numerical outcome evidence needed to evaluate the primary question is absent. Likewise, the listed secondary outcomes identify domains of interest, but without their results they cannot establish whether those domains changed or differed between groups. The fact that the study is marked completed does not itself report an outcome.

General statistical interpretation distinguishes absence of evidence from evidence of no effect. Without estimates and their uncertainty, it is not possible to determine whether results are compatible with a range of effects, whether any estimated effect is precise, or whether groups can be considered similar. The registry does not report an equivalence or non-inferiority framework.

The adverse-event entry records zero serious events and zero deaths in the listed groups, but those counts are not a comprehensive demonstration that the intervention has no risks. They are a description of recorded events in the registry entry. Overall, the record gives useful information about the trial question, design, endpoint, follow-up, and some completion and safety counts, while leaving the principal efficacy results and key analysis details unreported.

13. Why This Trial Matters Statistically

This trial raises several important statistical issues common to clinical research. First, GWI is described as variable and multidimensional, and the primary score combines symptoms from several domains. Composite measures can capture a broader picture than a single symptom, but interpretation depends on how the score is constructed and on which comparison is used. The record provides the score range and direction but does not report the numerical results or a single primary contrast.

Second, the assessment schedule includes a baseline, an 8-week post-treatment assessment, and a 6-month assessment among CBTi participants. Different comparisons across these time points answer different questions. Clear specification of the target comparison is important for separating between-group effects from changes within a group and for understanding what longer-term follow-up represents. The registry record does not specify the statistical contrast or model.

Third, missing follow-up is relevant to interpretation. The CBTi completion figures show that not all participants randomized to that group completed treatment or the later assessment. Statistical methods can account for incomplete observations under stated assumptions, but the registry record does not describe the analysis population or missing-data method. This limits assessment of how missingness may affect the findings.

Finally, the registry lists numerous outcome measures and analyses. A prespecified primary outcome and multiplicity strategy help readers understand how to interpret results across many tests. Neither is detailed as a single primary comparison. The record’s value is therefore in documenting the planned clinical question and trial structure, while its missing numerical findings and analysis details limit statistical evaluation.

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 central limitation for interpretation is that no numerical primary-outcome results are reported in the registry record. The median and inter-quartile range for the Gulf War Illness Symptom Severity Index are not given, and there is no reported effect estimate, uncertainty interval, or p-value for a defined contrast. The record also does not reduce the several categories and time points to one comparison.

The follow-up statement identifies treatment completion for 32 of 39 participants randomized to CBTi and 6-month assessment completion for only 28 of those participants. It does not describe the corresponding primary-outcome completion pattern in Monitor Only, nor does it report how missing data were handled. Without those details, the possible influence of incomplete outcome data cannot be evaluated.

Important design and analysis details are also absent. The record does not identify who was masked, how randomization and allocation concealment were conducted, which analysis population was used, what statistical model was fitted, or whether multiplicity adjustments were applied. The actual sample-size justification and protocol-specific statistical plan are not reported in the registry record. The planning illustration is not a substitute for those details.

The registry lists an enrollment of 165, whereas the adverse-event entry lists 46 participants at risk in Monitor Only and 39 in CBTi. It does not explain the difference or connect these counts to the outcome analysis population. These entries cannot be reconciled from the information in the record.

Finally, the listed adverse-event counts do not include detail about monitoring periods, event definitions, or attribution. The counts can be reported as recorded, but they cannot establish the absence of unrecorded events or fully characterize safety.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Cognitive Behavioral Therapy for Insomnia for Gulf War Illness — NCT02782780.
• Registry record last updated 2021-02-02; status last verified 2021-01.
• Results first posted 2021-01-11.
• 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, single-masked, parallel-group pilot trial of telephone-delivered CBTi for Veterans with GWI and insomnia. Enrollment is listed as 165. CBTi involved 8 weekly individual sessions; Monitor Only participants continued usual care over 8 weeks.

The primary outcome was the Gulf War Illness Symptom Severity Index, summarized as a median and inter-quartile range, with assessment at baseline and after 8 weeks and a 6-month assessment among participants randomized to CBTi. The registry reports that 32 of 39 CBTi participants completed treatment and 28 of those participants completed 6-month follow-up.

Numerical primary-outcome results and a single primary comparison are not reported in the registry record. The record lists multiple secondary outcomes but does not report their numerical results or the statistical analysis and missing-data plans. The adverse-event entry records zero serious adverse events and zero deaths in each listed group.