Peripheral Nerve Stimulation Registry for Intractable Migraine Headache: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Peripheral Nerve Stimulation Registry for Intractable Migraine Headache (NCT02227758), a registered phase not stated study. The primary outcome is Migraine Disability.

2. Clinical Question

3. Trial Design

This completed registry study concerns peripheral nerve stimulation for intractable chronic migraine. Abbott Medical Devices is listed as the sponsor. The record gives a start date of 2012-09 and a primary completion date of 2015-12, with enrollment of 112. Its stated purpose was to assess long-term safety and performance and to detect infrequent complications or problems that may appear in real-world practice.

The described group consists of patients diagnosed with chronic migraine who had failed 3 or more preventative drugs, had at least moderate disability, and were implanted with a St. Jude Medical Conformité Européenne approved implantable neurostimulation system. The registry does not describe a randomized allocation. Allocation is not stated, and the arm descriptions do not constitute a like-for-like control comparison. The record therefore does not support a randomized between-group estimate of treatment effect.

The primary outcome is migraine disability, expressed as percentage change in MIDAS score from baseline to 3 months. The outcome is defined as a mean with standard deviation. The record lists 8 outcome measures, but reports no analyses. A 3-month disability assessment is one part of the record’s broader safety and performance purpose; it does not by itself answer every long-term question described in the study purpose.

The registry status is COMPLETED. That status indicates the record marks the study as completed; it does not supply the results needed to judge the size or precision of the primary outcome. The numeric mean change and standard deviation are not reported in the registry record. Details such as the full analysis plan, the rationale for enrollment, and any interim analyses are also 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 Migraine Disability, measured over 3 months.

The primary endpoint is the percentage change in MIDAS score from baseline to 3 months. MIDAS is a patient questionnaire about the effect of headache on everyday activity. Three questions address days missed in school or paid work, household work, and family, social, or leisure activities. The other two address additional days when productivity was substantially limited in employment or household work. The total score sums the days entered for the five questions. Its stated range is 0 to 21+, with higher values indicating greater disability.

This endpoint is used to describe disability rather than simply counting headache episodes. It captures lost days as well as days with significant activity limitation, so it reflects functional impact in several areas. A change from baseline can describe whether the measured disability score shifted over the stated follow-up interval. The registry calls for a mean percentage change and standard deviation, but does not report either numeric value.

Interpretation depends on the actual change, its variability, and the completeness of questionnaire data. The record reports that 63 patients had data for all 5 MIDAS questions at the 3-month visit. It also reports that 59 patients had available data excluding outliers, without describing the outlier rule. These counts identify the data available for the endpoint but do not reveal the mean change, its direction, or how precisely it was estimated. The clinical importance of a measured change is not established by the endpoint definition alone.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous because it is a numeric score-derived measure that can take a range of values. The registry specifies the mean and standard deviation as its summary statistics. The mean describes the average value in the analyzed observations. The standard deviation describes how dispersed individual observations are around that average. A mean on its own does not show whether individual responses were closely clustered or widely spread, and a standard deviation is not itself a measure of uncertainty in the mean.

What does percentage change describe?

Percentage change expresses a change relative to a baseline value rather than reporting only a raw score difference. Here, the registry defines the endpoint as percentage change in MIDAS score from baseline to 3 months. The record does not state the sign convention used for the percentage change or give the actual mean. It is therefore not possible to infer from the endpoint description whether the posted mean, if available elsewhere, would represent improvement or worsening. The score definition does establish that higher MIDAS values indicate greater disability.

What does the standard deviation tell the reader?

In general, standard deviation describes variation among the observed values. A larger standard deviation indicates greater spread in those values, while a smaller one indicates that values are more concentrated around the mean. It does not, by itself, show the precision of the mean estimate. Precision also depends on the amount of usable information and on the analysis. The registry identifies 63 patients with all five questionnaire responses at follow-up and 59 with available data excluding outliers, but does not report the standard deviation or explain how those counts relate to the final analysis.

How would a confidence interval help?

In general, a confidence interval gives a range of estimates compatible with the observed data under the analysis assumptions. It can help readers judge how precisely an effect has been estimated, rather than relying only on a point estimate. The numeric mean change and a confidence interval for it are not reported in the registry record. The available information therefore does not establish whether the estimate is precise or whether a broad range of effects remains plausible.

What would a significance test answer?

In general, a significance test evaluates how compatible the data are with a specified statistical null hypothesis under a chosen model. A p-value does not state the probability that a treatment works, and it does not quantify clinical importance. No p-value for the primary outcome is reported in the registry record. The record lists no analyses, so there is no reported test to interpret. Even a reported test would need to be considered alongside the effect estimate and its uncertainty.

Why do missing observations and outliers matter?

In general, missing outcome data can affect an estimate if the people with available measurements differ systematically from those without them. The registry reports the number with complete MIDAS responses at follow-up and a separate number excluding outliers, but does not describe why some observations are unavailable, how missing values were treated, or how outliers were identified. An outlier can substantially influence a mean, especially when a distribution has a small number of extreme values. Excluding observations can also change the estimate. Without the rule and supporting analysis, readers cannot assess the effect of that decision.

How should planning calculations be read?

In general, a sample-size calculation uses assumptions about the effect to detect, variability, significance level, allocation, and statistical model to illustrate how much information a future study might need. The planning assumptions associated with this record use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They describe planning illustrations based on fractions of an observed effect, not the design of this registry study. The record describes implanted patients and does not report a randomized comparison, so those hypothetical two-arm assumptions should not be mistaken for the study’s actual allocation or protocol. Such calculations are planning illustrations, never observed power. The registry does not report its own sample-size justification or the statistical plan.

Overall, the statistical methods needed to reproduce or fully assess the primary estimate—including the specific calculation of percentage change, handling of missing responses, outlier criteria, and inferential procedure—are not reported in the registry record. The endpoint definition and data counts are useful for understanding what was intended, but they cannot replace the missing numerical estimate and its uncertainty.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Midas Score Including 4 Outliers", "Midas Score Excluding 4 Outliers")
n   <- c(63, 59)
m   <- c(74, -37)
sp  <- c(6.2, 0.4)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Midas Score Including 4 Outliers  63  74.000  6.200  72.439  75.561
CARM  Midas Score Excluding 4 Outliers  59  -37.000  0.400  -37.104  -36.896

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 8 outcome measures and reports no analyses. When several outcomes are examined, the chance of finding an apparently notable result by chance can increase if each is tested separately. Statistical approaches can account for that multiplicity, or an analysis plan can distinguish primary from secondary questions in advance. The registry record does not report a multiplicity adjustment, a hierarchy for interpreting outcomes, or the details of a prespecified analysis plan. No test results are listed to evaluate in relation to the multiple outcomes.

For the primary MIDAS outcome, the record reports that 63 patients had data for all 5 questions at the 3-month follow-up visit. It also reports that 59 patients had available data excluding outliers. The outlier rule and the relationship between these counts and the analysis population are not reported in the registry record. The record does not describe whether incomplete questionnaires were excluded, how partially completed questionnaires were handled, or whether any missing values were imputed.

In general, missing-data methods rely on assumptions about why measurements are absent. If availability is related to the outcome, an analysis limited to observed data may not represent the full enrolled group. The registry provides no information with which to assess that possibility. It also does not name an intention-to-treat, per-protocol, or other analysis population. Reasons for unavailable follow-up data and the use of any sensitivity analyses are not reported in the registry record.

These gaps limit reproducibility and make it difficult to assess whether the reported endpoint, if analyzed, would be sensitive to decisions about missing observations, outliers, or multiple outcomes. They do not establish that a particular method was or was not used outside what the registry reports.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

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: lead migration (7.1%), infection: lead site only (2.7%), wound site complications (2.7%), breakage/facture of the extension (1.8%), device malfunction (1.8%).

The registry reports 26 patients affected by serious adverse events among 112 at risk, and 7 affected by other adverse events among 112 at risk. These are separate reported categories; the record does not explain whether individuals could appear in both. The counts should not be added together or treated as mutually exclusive. Deaths are not reported in the registry record.

The listed serious adverse event terms and percentages are Lead migration, 7.1%; Infection: lead site only, 2.7%; Wound site complications, 2.7%; Breakage/facture of the extension, 1.8%; Device Malfunction, 1.8%; and IPG migration, 1.8%. These entries identify reported event terms, but the record does not give the detailed event-level definitions or explain how repeated events in one patient were handled. It also does not establish from these figures alone whether an event was caused by the device or procedure.

Adverse-event summaries describe events recorded in the registry, not a controlled comparison of risk. With no like-for-like control comparison reported, the figures cannot establish how the observed event experience compares with another treatment or with no intervention. They should be read as safety counts within the registry population, not as proof of causation or as a complete measure of long-term safety.

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

The record identifies a completed registry study of implanted neurostimulation for intractable chronic migraine and defines a primary disability outcome at 3 months. It also gives safety-event counts and identifies several serious adverse event terms. These registry entries describe the study’s focus and some of the observations recorded; they do not provide the numeric primary outcome estimate.

The registry does not report the mean percentage change in MIDAS score, its standard deviation, a confidence interval, or a p-value. Consequently, the direction and size of the measured disability change, and the precision of any estimate, cannot be determined from the registry record. The available questionnaire counts do not substitute for an outcome estimate. Nor do the safety counts answer whether disability changed.

The design description does not include a randomized, like-for-like control comparison. An observed change in a group over time, even if its value were reported, would not on its own show that the intervention caused that change. Other explanations cannot be separated without an appropriate comparative design or sufficiently detailed analysis. The record does not report such an analysis.

The registry’s stated interest in long-term safety and infrequent real-world complications is important context, but the primary disability endpoint is measured at 3 months. The event summaries should be understood as recorded safety information, not as a causal comparison or a complete account of long-term device performance. The registry also does not report enough information about missing data, outlier handling, or the analysis population to establish how representative the endpoint data are of all enrolled patients.

Accordingly, the record supports describing the population, endpoint definition, available-data counts, and recorded adverse-event figures. It does not support a conclusion about the magnitude or certainty of a disability effect, comparative benefit or harm, or whether the intervention caused a change. Those questions require results and methods that are not reported in the registry record.

14. Why This Trial Matters Statistically

This registry is statistically informative in part because it makes the distinction between a study purpose and a reportable treatment-effect estimate visible. The stated purpose includes long-term safety and performance and the detection of infrequent complications in real-world practice. The primary outcome, however, is a defined measure of migraine-related disability at 3 months. A study can collect different kinds of information for these aims, and each requires its own interpretation.

The outcome definition also illustrates the value and limits of patient-reported measures. MIDAS covers missed activity and days of substantially reduced productivity in work, household, and social domains. That breadth can make the score relevant to lived disability, while the numerical result still depends on complete and interpretable responses. The record’s counts for complete responses and for data excluding outliers make data availability an explicit consideration, but the reasons for exclusions and missingness are not described.

Safety records can identify complications that warrant attention, including lead migration, infection at the lead site, and wound-site complications. Yet counts in an uncontrolled registry do not by themselves establish causation or comparative risk. Clear denominators and event definitions help orient readers, while a suitable comparator and transparent analysis are needed for stronger comparative conclusions.

Finally, the registry illustrates why numerical endpoint estimates, uncertainty measures, and analysis methods matter. A completed status and a detailed outcome definition do not reveal the magnitude or precision of a result. Reporting the mean change, variability, missing-data approach, and analysis population would allow readers to assess what the data show and how confidently they support an interpretation. The record’s limitations are therefore not merely technical: they determine which questions can be answered from the reported information.

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 central limitation for interpreting the primary outcome is that its numeric mean percentage change and standard deviation are not reported in the registry record. Without the estimate, its direction and magnitude are unknown; without an uncertainty measure, its precision cannot be assessed. The record also gives no confidence interval or p-value for the primary outcome.

The primary outcome data are described through two counts: 63 patients had all 5 MIDAS responses at the 3-month visit, and 59 had available data excluding outliers. The record does not explain the outlier definition, the relation between those counts, or the reasons data were unavailable. Missing-data procedures, sensitivity analyses, and the analysis population are not reported. These omissions prevent assessment of how data selection may have affected the result.

The registry does not report randomized allocation, and the listed arms are not a like-for-like control comparison. This limits causal and comparative interpretation. The registry also does not provide the statistical plan, sample-size justification, or any interim-analysis information. It lists 8 outcome measures and reports no analyses, leaving no results with which to evaluate multiplicity or the relationship between the primary and other outcomes.

The study purpose includes long-term safety and the detection of infrequent complications, while the primary disability endpoint is at 3 months. The record gives adverse-event counts and selected event terms but does not establish causation or describe all event-level details. Deaths are not reported in the registry record. These limitations mean that the listed safety information should not be treated as a complete or comparative account of long-term risk.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Peripheral Nerve Stimulation Registry for Intractable Migraine Headache — NCT02227758.
• Registry record last updated 2019-02-04; status last verified 2019-01.
• Results first posted 2018-12-31.
• 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

The registry record describes a completed study of peripheral nerve stimulation in people with intractable chronic migraine. Abbott Medical Devices is the sponsor. Enrollment is 112, with a start date of 2012-09 and primary completion date of 2015-12. The described patients had chronic migraine, had failed 3 or more preventative drugs, had at least moderate disability, and received an implanted neurostimulation system.

The primary outcome is mean percentage change in MIDAS score from baseline to 3 months, with standard deviation specified as the measure of dispersion. The record reports 63 patients with complete responses to all 5 questions at follow-up and 59 with available data excluding outliers. The numeric mean change and standard deviation are not reported in the registry record.

The record reports serious adverse events in 26 of 112 at risk and other adverse events in 7 of 112 at risk. It lists several serious event terms, but does not establish causation. Allocation is not stated, no like-for-like control comparison is described, and the record reports no analyses.