TMS for Suicidal Crisis in Active Duty SMs: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for TMS for Suicidal Crisis in Active Duty SMs (NCT03014362), a randomized na study. The primary outcome is Change in Suicidal Ideation (Acute).

2. Clinical Question

3. Trial Design

The registry describes a randomized, single-masked, parallel-group trial. Its enrollment is 120, and its status is completed. The sponsor is Eisenhower Army Medical Center. The record lists the study start as 2017-06-12 and primary completion as 2020-01-10. Phase is recorded as NA. The record does not report who was masked or provide a fuller account of the randomization procedure, allocation concealment, or site structure.

Participants were assigned to TMS Active or TMSsham. Active treatment used the Neuronetics NeuroStar XPLOR magnetic stimulator. The description specifies localization at the left prefrontal dorsolateral neocortex and stimulation with a figure-8 solid core coil at 120% motor threshold, 10 Hz, a 4 second train duration, and a 10 second interval for 30 minutes. The active course is described as 3 days. The sham intervention used the same named stimulator, with a blocking insert rendering the coil inert and zero pulses; its description records 9 sessions, 3/day for 3 consecutive days over and above SOC.

The primary outcome is change in suicidal ideation over the active treatment course, specified as the 3 days of active treatment. The registry describes a 6 months follow-up period in the study summary, intended to assess ongoing and lasting effects, but the posted primary outcome is acute. Follow-up outcome results are not reported in the registry record. The record lists one outcome measure and no secondary outcome measures posted. Further details about the trial's conduct, adherence, participant flow, analysis populations, and statistical plan 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.

Overall Study

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Change in Suicidal Ideation (Acute), measured over Change over the active treatment course ie. the 3 days of active treatment.

The primary outcome is titled “Change in Suicidal Ideation (Acute).” It measures the Beck Scale for Suicidal Ideation, identified as SSI-T, over the active treatment course, described as 3 days. The registry says SSI-T is a clinician-administered, 19-item scale that measures current suicide ideation (SSI-C), suicide ideation at its worst point in the patient's life (SSI-W), and degree of hopelessness. Its score range is 0-38, with higher scores indicating greater suicide risk.

A change score is useful for asking whether participants' measured symptom levels shifted during a specified treatment period. Comparing change between randomized arms focuses the question on whether the recorded trajectory differed between the active and sham groups, rather than treating the final score alone as the only relevant measure. The registry describes the scale as well validated. That is the registry's characterization; details of validation, scoring procedures, and the handling of incomplete item responses are not reported in the registry record.

The posted outcome is continuous and summarized as a mean with standard error. The active and sham arm means are each 0.12. The clinical meaning of a difference of 0.0 depends on the scale, the direction and coding of the change score, and an appropriate threshold for meaningful change. A threshold for clinical importance is not reported in the registry record. Therefore, the posted numerical comparison can be described, but it cannot by itself establish the clinical importance of a change.

7. Results Posted in the Registry

• TMS Active: mean 0.12 versus 0.12 on control; difference 0.00 (95% CI -0.17 to 0.17), standardized effect d = 0.00; z-test p = 1.000.

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary outcome as continuous and reports a mean and standard error for each arm. It also posts a mean difference, a confidence interval, and an unadjusted p-value. These summaries answer related but distinct questions: the means describe the recorded average in each arm, the mean difference expresses the contrast, the confidence interval conveys uncertainty around that contrast, and the p-value describes compatibility with a statistical null under a test's assumptions.

What does the mean describe?

A mean is an average across the observations included in an analysis. For a change outcome, it summarizes the average recorded change, not the path of every participant. Participants can have different individual changes while sharing the same group mean. The active and sham means are both posted as 0.12. The record does not give a distribution of individual scores or changes, so the means alone cannot describe variation in participant experience or reveal whether changes were concentrated in a subset of participants.

What does the standard error describe?

The standard error describes uncertainty in an estimated mean, rather than the spread of individual observations itself. The arm summaries report a standard error of 0.06 for each arm. A smaller standard error generally indicates a more precisely estimated mean, while a larger one indicates more sampling uncertainty, all else being equal. The underlying standard deviations and the full outcome distributions are not reported in the registry record. It would therefore be inappropriate to treat the standard error as the standard deviation of participant-level scores.

General statistical explanation: the uncertainty of a difference between arm means depends on the uncertainty in each arm and on the analysis structure. A comparison can be estimated with greater or lesser precision even when its point estimate is the same. The posted record gives the mean difference and its interval, but does not describe the complete calculation or modeling choices behind them.

How should the mean difference and p-value be read?

The posted mean difference is 0.0. It represents the estimated contrast between the arm means as reported, with no difference at the displayed precision. The unadjusted p-value is 1.0. General statistical explanation: a p-value is calculated under a null hypothesis and a statistical model; it indicates how compatible the observed result is with that null and model. It is not the probability that the null is true, and it does not quantify the size or clinical importance of an effect. The registry does not report a test name, covariate adjustment, or full analysis specification, so the result should not be attributed to an unreported method.

The word “unadjusted” matters because it distinguishes the posted p-value from a value adjusted for other analyses or comparisons. The registry lists one primary outcome measure and no secondary outcome measures posted, but does not report a multiplicity strategy. It is not possible to infer from the available record whether other outcomes, time points, or analyses were examined.

Why do intervals matter?

A confidence interval expresses uncertainty about the estimated contrast under a specified statistical procedure. In general, it indicates a range of effect values reasonably compatible with the data and model; it is not a guarantee that the true effect lies within the realized interval. The posted interval for the mean difference extends to both sides of zero. This means the summaries do not rule out a difference favoring either arm, as well as values near no difference. Its exact endpoints are not repeated in this explanation because the registry's displayed endpoints exceed the permitted decimal precision for this discussion.

Confidence intervals are useful alongside p-values because they show the range and direction of uncertainty rather than reducing the result to a threshold decision. Their clinical interpretation still depends on scale meaning and a threshold for importance. Neither a minimally important difference nor an equivalence margin is reported in the registry record.

What does randomization contribute?

Random assignment is intended to create groups that are comparable, on average, with respect to factors known and unknown at assignment. A sham comparator can help distinguish effects associated with the active stimulation from effects associated with trial participation or the treatment procedure. These are general design principles, not proof that every potential source of bias was eliminated in this study. The registry records randomized allocation and single masking, but does not report the masking role, allocation concealment, adherence, or balance of baseline characteristics.

A parallel design assigns participants to an arm and compares outcomes between those arms. The record does not provide enough detail to characterize all analysis choices, including whether baseline scores were incorporated, how repeated or incomplete measurements were handled, or which participants were included in the final analysis. Those details are not reported in the registry record.

Why is over-dispersion relevant?

General statistical explanation: over-dispersion arises when observed variability is greater than a statistical model expects. It can make standard errors too small if the model does not account for that extra variability, leading to intervals that are too narrow and p-values that are too optimistic. This issue is most directly associated with models for count or categorical data; the primary outcome is recorded as a continuous measure summarized by means and standard errors. The registry does not report diagnostics or a model specification that would establish whether over-dispersion was considered, and it is not appropriate to assume that it affected this analysis.

The record does not report a protocol-based statistical analysis plan, sample-size justification, interim analyses, or rules for selecting the analysis population. Planning calculations based on an observed effect, if considered, are illustrations rather than evidence of the trial's original design rationale or observed power. The sponsor's analysis does not have a stated discrepancy with the posted summary in the registry record; further analysis details are not reported there.

10. Confidence Intervals and Precision

The posted estimate of the mean difference is 0.0, and the confidence interval extends below and above zero. That pattern indicates uncertainty about the direction of the underlying difference: the interval includes values favoring either arm as well as the possibility of no difference. The interval is the main guide to the range of effects compatible with the reported estimate and its statistical assumptions. Its endpoints are not repeated in this discussion because the registry displays them with more than 3 decimal places.

Precision is not the same as statistical significance or clinical importance. An estimate can be centered at zero while its interval still permits nonzero effects. Conversely, an interval's inclusion of zero does not prove that there is no meaningful effect. To judge whether the uncertainty is clinically acceptable, a reader would need a justified threshold for important change or an equivalence margin. Neither is reported in the registry record.

The arm standard errors are both 0.06. General statistical explanation: standard errors reflect uncertainty in estimated averages and contribute to the precision of a contrast. They do not show the range of individual participant responses. The registry does not report standard deviations or individual-level results, so the extent of participant-to-participant variation cannot be assessed from these summaries alone.

The p-value of 1.0 is consistent with the posted estimate being at the null value, but it does not replace the interval. The interval communicates that the evidence does not tightly pin down one nonzero direction; the p-value provides a test-based summary under a specified null and analysis. Because details of the analysis are not reported in the registry record, the confidence interval and p-value should be interpreted as the posted results rather than as a fully documented independent analysis.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and no secondary outcome measures posted. This indicates what results are represented in the registry record; it does not establish that the study assessed no other outcomes or analyses. The record does not report a multiplicity adjustment, a hierarchy of outcomes, or rules for choosing which analyses to report. Without those details, the degree to which the posted p-value reflects a broader set of statistical comparisons is unknown.

Missing-data handling is not reported in the registry record. The outcome summaries do not explain how participants without a measurement at the acute assessment were treated, whether any scores were imputed, or whether sensitivity analyses were performed. A participant-flow account and analysis population definition are also not reported. Consequently, the posted means cannot be assumed to represent every randomized participant.

The registry records 120 enrollment and arm summaries of 59.0 for TMS Active and 61.0 for TMSsham. Those entries do not by themselves establish how many participants contributed data to the acute endpoint, whether all assigned participants were analyzed, or whether the groups remained intact through follow-up. Those details are not reported in the registry record.

The registry does not report a statistical analysis plan, interim analyses, covariate adjustment, or prespecified procedures for handling multiple time points. The primary endpoint concerns change over the active treatment course, while the study summary also describes 6 months of follow-up. Results and analysis details for that follow-up are not reported in the registry record. These omissions limit assessment of how complete and selective the posted result is, without establishing that any particular problem occurred.

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: suicidal ideation (3.4%).

The registry lists serious adverse event counts for both arms. TMS Active has 2 serious events among 59 at risk, and TMS Sham has 2 among 61 at risk. The record lists zero deaths in each arm. These are the posted counts and risk-group entries; they do not show event timing, duration, severity beyond the serious classification, or the number of participants with multiple events. Those details are not reported in the registry record.

The serious-event term listed among the top serious terms is suicidal ideation, at 3.4%. The record does not assign that term to a particular arm in the summary of top terms, so it should not be interpreted as an arm-specific percentage. The other adverse-event counts are 18 for TMS Active among 59 at risk and 7 for TMS Sham among 61 at risk. The registry does not give further detail in this summary about the event types, severity, relatedness, or overlap among events.

These descriptive safety entries are not a substitute for a complete safety analysis. Differences in counts alone do not establish that an intervention caused an event or that one arm is safer. Exposure, event definitions, follow-up completeness, and adjudication details are not reported in the registry record. The zero deaths recorded should be read as the posted death counts, not as proof that all possible safety concerns were absent.

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

The primary acute result is straightforward at the level of the posted summaries: mean change in suicidal ideation is 0.12 in each arm, and the mean difference is 0.0. The unadjusted p-value is 1.0. The confidence interval extends on both sides of zero, so the comparison does not isolate a direction of difference. These statistics describe the recorded acute outcome over the 3 days of active treatment.

The result does not demonstrate equivalence. Equivalence requires a prespecified margin defining differences small enough to be considered clinically unimportant and an analysis designed to assess that claim. Neither an equivalence margin nor such an analysis is reported in the registry record. The result also does not establish non-inferiority, because a non-inferiority margin and analysis are not reported.

The arm means do not indicate the number of participants who improved, worsened, or remained unchanged. A group average can conceal variation among individual outcomes, and the registry does not post individual-level data or a distribution of changes. The scale's higher scores indicate greater suicide risk, but the clinical importance of the posted mean change cannot be judged without a meaningful-change threshold and clear interpretation of the change-score coding. Such information is not reported in the registry record.

The outcome is acute. The study summary describes 6 months of follow-up, but no corresponding longer-term results are posted in the registry record. The acute comparison therefore should not be read as evidence about sustained outcomes. Nor should the result be generalized to populations beyond those described in the registry's study title and summary.

The posted safety counts are descriptive, with 2 serious adverse events in each arm and zero deaths recorded in each arm. Other adverse-event counts differ between arms, but the summary lacks detail needed to interpret causes, severity, exposure, or participant overlap. Overall, the registry supports a narrow description of the reported acute means, uncertainty, and event counts. It does not resolve broader clinical or causal claims.

14. Why This Trial Matters Statistically

This trial poses a statistically important comparison: whether active stimulation is associated with a different short-term change in suicidal ideation than a sham procedure among the study population described in the registry. Randomized allocation and a sham comparator are relevant design features because they create a structured between-arm comparison rather than relying on change within a single group. The single-masked designation is also relevant, although the registry does not identify who was masked.

The posted result illustrates why an estimate, interval, and p-value should be read together. The point estimate is 0.0 and the unadjusted p-value is 1.0, but the confidence interval extends in both directions around zero. These summaries do not demonstrate equivalence or rule out potentially meaningful differences. A clinical threshold for meaningful change and an analysis designed to test equivalence are not reported in the registry record.

The outcome's timing is another key statistical feature. It measures change over the 3 days of active treatment, while the study summary describes 6 months of follow-up. An acute outcome and a longer-term outcome answer different questions. The latter results are not reported in the registry record, so the acute comparison cannot address durability.

Finally, the limited analysis detail matters. Missing-data procedures, analysis populations, the statistical plan, and multiplicity handling are not reported in the registry record. These details affect how readers assess precision and the scope of a reported result. The trial is therefore informative as a posted acute randomized comparison, while important questions about analysis conduct, clinical meaning, and follow-up remain unresolved in the record.

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 registry record does not provide detailed eligibility criteria, baseline characteristics, participant flow, or an account of which participants contributed data to the primary outcome. Although enrollment is recorded as 120 and the arm summaries list their respective group sizes, the number contributing to the acute analysis is not separately reported. This limits assessment of missing outcome data and comparability of the analyzed groups.

Statistical methods are incompletely documented. The record does not report a formal analysis plan, the test or model used for the primary comparison, covariate adjustment, missing-data procedures, or sensitivity analyses. Multiplicity handling is also not reported. The unadjusted result can therefore be described, but its relationship to any broader analysis strategy is unclear.

The outcome is an acute change score over the active treatment course, described as 3 days. The registry summary mentions 6 months of follow-up, but longer-term outcome results are not reported in the registry record. The scale's score range and interpretation are stated, but the record does not specify a threshold for clinically important change or provide enough detail to assess the direction and clinical meaning of the posted change score.

Additional limitations concern treatment delivery and masking. The registry describes active and sham procedures and labels the study single-masked, but does not report who was masked, adherence, treatment fidelity, or whether masking was maintained. The safety summary does not provide event timing, detailed event descriptions, or relatedness assessments. These absences restrict interpretation; they do not establish that a particular bias, missingness problem, or safety issue occurred.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: TMS for Suicidal Crisis in Active Duty SMs — NCT03014362.
• Registry record last updated 2022-09-28; status last verified 2022-09.
• Results first posted 2022-09-28.
• 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

NCT03014362 is a completed, randomized, single-masked, parallel-group trial sponsored by Eisenhower Army Medical Center. It compares active and sham Neuronetics NeuroStar XPLOR magnetic stimulation in a study of suicidal crisis in military service members. Recorded enrollment is 120; the registry lists a start date of 2017-06-12 and primary completion date of 2020-01-10.

The acute primary outcome is change in suicidal ideation over the 3 days of active treatment, measured using the Beck Scale for Suicidal Ideation. Both arms have a posted mean of 0.12, with standard error 0.06. The mean difference is 0.0 and the unadjusted p-value is 1.0; the confidence interval extends below and above zero. Follow-up results, detailed analysis methods, and missing-data procedures are not reported in the registry record.