Rapid Non-Invasive Brain Stimulation for OCD (oTMS): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Rapid Non-Invasive Brain Stimulation for OCD (oTMS) (NCT03404609), a na na study. The primary outcome is Number of Patients Who Met and Exceeded Response Criteria of Yale-Brown Obsessive-Compulsive Scale..

2. Clinical Question

The question is descriptive: it asks how many participants crossed a prespecified symptom-change threshold after receiving the stimulation course. The record does not state a separate causal comparison, such as whether the response rate differed from a control condition. Without a control group, any observed change would also need to be interpreted in light of possible changes over time, expectations, measurement variability, and other influences that this design does not separate from the intervention.

The registry identifies OCD as the condition and says the study’s purpose is to understand how cortical stimulation affects OCD symptoms. It does not report additional research questions, eligibility criteria, or participant characteristics. The result needed to answer the primary question—the count of participants who met the response criterion—is not reported in the registry record.

3. Trial Design

This is a completed, single-group study sponsored by Stanford University. The registry lists enrollment of 7 participants, allocation as NA, and masking as none. It does not describe a randomized allocation or a concurrent control group; the registry specifically cautions that the study is not a randomized comparison and that its arms are not a like-for-like control comparison. There is one described treatment course rather than a set of comparative treatment groups.

Participants received an accelerated course of modified continuous theta-burst stimulation (cTBSmod) to the right frontal pole. The intervention description specifies 5 consecutive days. Each session comprised 1800 pulses, delivered in a continuous train of 600 bursts; each burst contained 3 pulses at 30 Hz and was repeated at 6 Hz. The description states that 10 sessions were applied per day and gives 18,000 pulses per day. The device is identified as the MagPro X100 by MagVenture.

The record lists the study as completed, with a start date of 2018-08-25 and primary completion date of 2019-07-01. Phase is listed as NA. The registry does not report further details about recruitment, eligibility, study-site procedures, treatment adherence, or the timing of individual assessments beyond the primary outcome timeframe of baseline and up to two weeks.

Only one outcome measure is listed, and the registry lists 0 analyses. These entries describe what is recorded, not necessarily every activity conducted during the study. The protocol’s statistical analysis plan, sample-size justification, interim analyses, and methods for handling departures from the intended treatment course 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 Number of Patients Who Met and Exceeded Response Criteria of Yale-Brown Obsessive-Compulsive Scale., measured over Baseline and up to two weeks.

The primary endpoint counts participants who met the YBOCS response criterion. The YBOCS is described in the registry as a measure of obsessions and compulsions, with total scores ranging from 0 to 40. Higher scores indicate more severe symptoms. Response is defined as at least a 35% reduction on the YBOCS. The stated timeframe is baseline and up to two weeks.

This threshold turns a change in a symptom scale into a binary classification for each participant: meeting the response criterion or not meeting it. The endpoint then reports a count of participants in the response category. Such a threshold can make a result easier to describe in terms of how many participants crossed a defined level of change. It does not show the full distribution of scores or how close participants who did not meet the threshold came to it.

The registry does not report the responder count, baseline or follow-up scores, or individual changes. It also does not give further detail about the assessment schedule within the stated timeframe or how scores were handled if an assessment was missing. As a result, the endpoint’s definition is available, but its observed value and the data underlying it are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a count of participants meeting a binary response definition. Each participant is classified according to whether the YBOCS reduction from baseline met the threshold of at least a 35% reduction. The outcome count is the number classified as responders; interpreting that count fully would also require knowing how many participants had usable assessments. The registry lists 7 enrolled participants, but does not state how many contributed data to this endpoint.

What does a binary endpoint capture?

A binary endpoint compresses a potentially detailed measurement into two categories. That can make a response rule straightforward to communicate, but it also discards information about the amount of change within each category. Participants just below and well below a threshold share the same classification, as do participants who meet the threshold by different amounts. Reporting the underlying scale scores and their changes can complement a threshold-based count, but those values are not reported in the registry record.

The YBOCS is described as having a total-score range from 0 to 40, with higher scores indicating greater symptom severity. The endpoint uses change from baseline, so both a baseline measure and a later measure are relevant to classifying response. The registry gives the timeframe as baseline and up to two weeks, but does not report the specific assessment schedule, score summaries, or the procedure used to handle an unavailable score.

How should uncertainty be understood?

In general, a confidence interval expresses the statistical uncertainty around an estimate under the assumptions of the method used. For a response proportion, an interval would help show how imprecisely the observed response frequency is estimated, particularly when the number of participants is small. It would not eliminate limitations from the study design, missing outcome data, or systematic differences between a study group and a control group. The registry record does not report a response estimate or confidence interval for this endpoint.

In general, a p-value evaluates how compatible the observed data are with a specified statistical model or null hypothesis. It is not a measure of clinical importance and does not by itself describe the size or precision of an effect. No p-value or hypothesis test for the primary endpoint is reported in the registry record. The listed count of 0 analyses means no outcome analysis is recorded there; it does not supply evidence for or against a treatment effect.

What do the planning assumptions mean?

The planning description refers to a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It also describes planning for a stated fraction of an observed effect. These are assumptions for a hypothetical two-arm sample-size illustration, rather than a report of the design actually used: this study is single-group and has no randomized control comparison. The registry does not report the study’s own sample-size justification.

A sample-size illustration asks how many participants per arm for 80% power would be needed under its stated assumptions. If additional illustrations use another target power, that remains a planning scenario rather than an observed feature of the trial. Such values are not observed power and do not establish that the completed study was adequately powered. An illustration based on an observed effect also depends on having an observed effect estimate. The primary response result is not reported in the registry record, so the registered information does not provide a basis for judging an observed effect’s stability or precision.

Normal approximations are general mathematical shortcuts that can be useful under suitable conditions. With small samples or sparse binary outcomes, the approximation used can affect the accuracy of interval or test results. The registry does not report which method, if any, was used for the primary endpoint, so no method-specific conclusion can be made. The stated normal approximation belongs to the planning description and should not be mistaken for a documented analysis of the trial results.

Why does the design matter for analysis?

Because the study has a single group, the primary endpoint is not a randomized between-group contrast. The response classification relates a participant’s later measurement to that participant’s baseline measurement, but the resulting group count does not provide a concurrent estimate of what would have happened without the intervention. General statistical adjustment cannot create a control group that the design did not include. The registry does not report a model or adjustment strategy.

The treatment schedule includes repeated stimulation sessions, but those sessions are part of the intervention. They are not additional independent participants for the outcome count. Treating sessions as though they increased the number of independent people would misstate the amount of information in the study. The registry’s primary endpoint is explicitly a count of participants, and no separate session-level outcome analysis is reported.

In general, over-dispersion is a concern in certain count-data models when observed variability exceeds the variability assumed by a simpler model. It is not a general adjustment that can be inferred from a binary participant count, and the registry does not report a count model or dispersion estimate. No over-dispersion assessment is reported. The relevant methodological limits for this endpoint are instead the small enrolled group, unreported outcome count and analysis, and absence of a control group.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("rTMS")
n      <- c(7)
events <- c(4)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  rTMS  7  4  57.1  18.4  90.1  25.0  84.2  24.5  84.3

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one outcome measure and 0 analyses. That identifies the outcome count recorded in the registry, but it does not describe whether additional comparisons, exploratory analyses, or outcome measures were planned or conducted. A multiplicity strategy—how to interpret the risk of false-positive findings when many hypotheses are tested—is not reported in the registry record. With no primary result or analysis reported, there is no set of reported tests for which the adjustment approach can be assessed.

Missing-data handling is also not reported. The record gives enrollment of 7 participants, but does not state how many had a baseline YBOCS score, how many had an assessment in the follow-up window, or how unavailable measurements affected the response count. It does not specify whether missing assessments were excluded, imputed, or handled in another way. Those details matter because the response count depends on classifying participants using measurements at the relevant times.

The analysis population is not reported in the registry record. In particular, the record does not say whether the endpoint was evaluated among all enrolled participants, only those who completed the intervention, or a different group. Enrollment should not automatically be treated as the endpoint denominator. No interim analyses, prespecified analysis plan, or sensitivity analyses are reported, so their existence and methods cannot be inferred.

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 non-serious adverse event terms

The registry lists 7 participants at risk for serious adverse events and 0 affected by serious adverse events; deaths are listed as 0. For other adverse events, 7 participants are listed at risk and 4 affected. The record does not provide terms for serious adverse events. These are the posted safety counts and should be read as counts, not as evidence that an event was or was not caused by the intervention.

The safety information does not describe event types, severity details beyond the serious-event category, timing, duration, or how events were assessed. It also does not explain whether the other adverse-event count overlaps with the serious-event category. The record’s group label is “rTMS,” while the intervention description identifies an accelerated cTBSmod course; the safety figures are reported under the registry’s listed group label.

Zero recorded serious adverse events in this group does not establish that serious events cannot occur, and the other-event count alone does not describe the clinical significance of those events. The limited group size and the absence of event terms and detail constrain interpretation. No further safety conclusion is supported by the counts alone.

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

The record establishes that a completed, single-group study enrolled 7 participants with OCD and assessed a YBOCS response criterion over a timeframe of baseline and up to two weeks. It also describes the stimulation course and lists safety counts. However, it does not report the number of participants who met the primary response criterion, their YBOCS scores, or an analysis of the outcome. The central efficacy result is therefore unavailable in the registry record.

Even if a responder count were available, a single-group result would describe what happened in the observed group rather than isolate the effect of stimulation from other possible explanations for change. Without a concurrent control group, the design cannot estimate a treatment contrast against an untreated or alternative-treatment group. The registry itself cautions that the study is not a randomized comparison.

The response threshold is one way to classify change, not a complete account of participants’ symptom trajectories. It does not show the distribution of baseline scores, follow-up scores, or individual changes. The registry also does not report outcome completeness, the analysis population, or longer-term results. These absences limit both the assessment of precision and the scope of any interpretation.

The study record is not a basis for medical advice or for concluding that the intervention does or does not work. Its statistical contribution, as recorded, is a defined outcome and a description of a small single-group study, without the primary outcome result needed to quantify response. The safety counts likewise do not establish causation or rule out risks.

14. Why This Trial Matters Statistically

Statistically, this study illustrates why an outcome definition and an outcome result are different kinds of information. The record precisely describes a YBOCS response threshold, but does not report how many participants crossed it. A clear endpoint makes the target of measurement interpretable; it cannot substitute for the observed data needed to estimate the result.

The design also highlights the distinction between observing change and estimating a comparative effect. A single-group baseline-to-follow-up question can describe change within the enrolled participants, but it does not provide the randomized control contrast needed to separate intervention-related change from other influences. The registry explicitly identifies the absence of a randomized comparison, which is central to the scope of the statistical question.

The small enrolled group makes transparent reporting of the outcome denominator, missing assessments, and uncertainty especially important. The record lists enrollment but not the number analyzed, response estimate, or confidence interval. Those omissions prevent a reader from assessing the result’s precision or the extent to which incomplete outcome data might matter.

Finally, the planning assumptions emphasize that sample-size calculations depend on design choices and effect assumptions. The stated illustration uses two arms and equal allocation, unlike this single-group study. It should therefore be understood as a hypothetical planning exercise rather than a retrospective measure of study success. The record is a useful reminder that design, analysis, and reporting each shape what a trial can answer.

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 main limitation for interpreting the primary endpoint is that its observed result is not reported. The registry defines response as at least a 35% reduction on the YBOCS, but gives no responder count, score summary, confidence interval, or analysis. Consequently, neither the magnitude nor precision of the primary outcome can be described from the registry record.

The study is single-group, with no randomized or concurrent control group. This prevents a like-for-like comparison and limits causal interpretation of any change from baseline. The registry lists 7 participants enrolled, but does not report how many completed treatment or had usable outcome assessments. The endpoint denominator and analysis population are therefore unclear.

The assessment timeframe is baseline and up to two weeks, with no longer-term outcome information reported. The record also does not provide participant characteristics, detailed eligibility criteria, adherence information, a missing-data approach, or the statistical analysis plan. It does not report whether additional analyses or interim analyses were conducted. These details should not be inferred from the completed status or the intervention description.

The safety record gives counts but no event terms for serious adverse events and limited context for other events. Finally, the sample-size assumptions describe a hypothetical two-arm planning calculation, not the study’s single-group design; the trial’s own sample-size justification is not reported in the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Rapid Non-Invasive Brain Stimulation for OCD (oTMS) — NCT03404609.
• Registry record last updated 2021-05-14; status last verified 2021-04.
• Results first posted 2021-05-14.
• 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.

19. Record Summary

NCT03404609 is a completed, single-group study sponsored by Stanford University, with 7 participants enrolled. It evaluated an accelerated course of modified continuous theta-burst stimulation to the right frontal pole. The primary outcome was the number of participants meeting a YBOCS response definition of at least a 35% reduction, assessed from baseline and up to two weeks.

The registry does not report the responder count, a primary outcome analysis, or the analysis population. It lists 0 analyses. Safety counts include 0 participants with serious adverse events among 7 at risk, 4 with other adverse events among 7 at risk, and 0 deaths. The absence of a control group, outcome result, and key analysis details limits interpretation of both efficacy and precision.