Study of Epidural Steroid Injection (ESI) Versus Minimally Invasive Lumbar Decompression (Mild®) in Patients With Symptomatic Lumbar Central Canal Stenosis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Epidural Steroid Injection (ESI) Versus Minimally Invasive Lumbar Decompression (Mild®) in Patients With Symptomatic Lumbar Central Canal Stenosis (NCT00995371), a randomized phase 4 study. The primary outcome is Mean Change in VAS.

2. Clinical Question

The clinical comparison is framed around pain reported on a validated 10-point scale, where 10 is the worst possible pain and zero represents complete lack of pain. The registry defines change as baseline value minus the 6-week value. Under that direction of subtraction, a positive change means the reported VAS value was lower at Week 6 than at baseline.

The posted primary outcome gives a mean and 95% confidence interval for each arm. Those arm-specific estimates describe change within each treatment group; they are not, by themselves, an estimate of the difference in change between randomized groups. The registry record does not report a direct between-arm estimate for this endpoint. Accordingly, the central statistical question is what the arm-level results say about pain change and its uncertainty, while recognizing that they do not establish the size or precision of a comparative treatment effect.

3. Trial Design

This was a randomized, prospective, double-blind, parallel-group, Phase 4 study. The registry describes it as a single-center study of MILD® devices versus epidural steroid injection in patients with symptomatic moderate to severe central canal spinal stenosis. The listed condition is lumbar spinal stenosis, and the record is marked completed.

The registry reports enrollment of 38. The primary outcome population is described as all 38 participants with Week 6 VAS data: 21 assigned to Vertos Mild® Minimally-Invasive Lumbar Decompression and 17 assigned to ESI. The outcome timeframe is baseline and 6 weeks prior to cross-over. The ESI measurements are explicitly described as having occurred before participants crossed over to the mild procedure. The registry also lists an ESI cross-over group in the safety results.

The intervention descriptions state that both procedures were to be performed by appropriately trained physicians in accordance with product labeling and indications for use. The registry identifies one intervention as a device and the other as a drug. It does not report further detail about the randomization sequence, concealment, or how masking was maintained; those features are not reported in the registry record.

The registry lists four outcome measures and eight analyses, but reports zero secondary posted outcomes. The record does not describe the reason for that difference or provide further secondary outcome results. Details of the sample-size justification and the trial’s prespecified statistical analysis plan are not reported in the registry record, so the design features should not be inferred beyond those explicitly described.

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: Randomization occurred in blocks of four. After Week 6 post-treatment and prior to 4 months, ESI arm participants were allowed to cross over to mild if they chose to have it.

Prior to ESI Cross-over, 6 Weeks

After ESI Cross-over to Mild, 26 Weeks

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All 38 participants (21 in mild and 17 in ESI arm) reported VAS at Week 6 post-treatment. All measurements for the ESI group occurred prior to cross-over to the mild procedure. This is Intent to Treat (ITT) analysis.

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.

Population: ITT analysis includes all patients at weeks 6 post-treatment. Week 26 cohort analysis includes 16 mild patients who reported outcomes at Week 26 and the 12 ESI patients who reported outcomes at Week 26 after cross-over to mild.

6. Primary Endpoint

The registry lists the primary outcome as Mean Change in VAS, measured over Baseline and 6 weeks prior to cross-over.

The primary endpoint is mean change in VAS from baseline to 6 weeks, before cross-over. VAS is described as a validated 10-point scale: 10 represents the worst possible pain and zero represents complete lack of pain. The registry defines the change as baseline VAS minus Week 6 VAS, so positive values indicate that the Week 6 score was lower than the baseline score.

A mean change summarizes the average within-arm change in a continuous measure. It is useful for describing the direction and average size of change, while a confidence interval conveys uncertainty around that average. Neither summary shows how individual participants’ scores were distributed, and the mean does not imply that every participant experienced the same change.

The outcome is clinically interpretable as a change in reported pain, but the registry record does not provide a threshold for deciding whether a particular change is important to participants. Nor does it report a direct randomized between-arm contrast for this endpoint. Therefore, arm-level mean changes can describe what was observed in each group, but they do not alone quantify the comparative difference between the procedures.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a mean change represent?

A mean change is an average of participants’ changes in a continuous measure. Here, the registry defines each change using baseline VAS minus the Week 6 VAS. Positive values therefore correspond to lower Week 6 scores on average, while negative values correspond to higher Week 6 scores on average. This direction depends on the registry’s stated subtraction convention; it should not be reversed by interpreting the result as Week 6 minus baseline.

An average is a concise summary, but it can conceal variation among participants. The registry does not report the spread of individual VAS changes, such as a standard deviation or a distribution of individual outcomes. Consequently, the mean and its confidence interval do not tell readers how many participants improved, remained unchanged, or had a higher score.

How should the confidence intervals be read?

A confidence interval expresses uncertainty around an estimated mean under the analysis that produced it. It is not a range containing a stated proportion of individual participants’ changes. The mild arm’s 95% confidence interval is 1.09 to 3.96; the ESI arm’s is -1.43 to 1.55. The interval for the mild arm lies above zero, whereas the interval for ESI includes zero. This helps describe the evidence about each arm’s mean change relative to zero, but does not test whether the arm means differ from each other.

Interval width is also relevant: a wider interval indicates less precision about the mean than a narrower interval, under the same general interpretation. Precision depends on the variability in the data and the analysis, not only on the point estimate. The registry does not report enough distributional detail to examine the variation in individual changes independently.

What do the reported tests address?

The reported analyses are two-sided t-tests, each listing one arm and a mean difference in final values. The mild analysis reports 2.52 with a 95% confidence interval from 1.09 to 3.96 and p <0.05. The ESI analysis reports 0.06 with a 95% confidence interval from -1.43 to 1.55 and p >0.05. These results concern the listed arm-level analysis; they should not be read as a reported test of a randomized between-arm contrast.

In general, a two-sided test assesses evidence against a null value in either direction. A p-value is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. The registry record does not provide additional detail about the exact null hypothesis, model assumptions, or whether the analysis adjusted for other variables.

Why is a direct comparison important?

In a randomized parallel-group trial, the comparative question is typically represented by a contrast between outcomes in the assigned groups. For a change endpoint, that could be a difference between the group mean changes, accompanied by an uncertainty interval and an appropriate test. The posted primary results give arm-wise means and intervals, but the registry record does not report that direct contrast. A reader cannot recover its uncertainty from the separate intervals alone without making assumptions and performing an analysis not reported in the record.

The term “final values” appears in the descriptions of the reported tests, while the primary outcome description defines a baseline-to-Week 6 change. The record does not explain the relationship between that test label and the stated change measure. This is a reporting detail to keep in view rather than a basis for assuming a different endpoint.

What can planning illustrations tell readers?

Sample-size planning is different from describing observed results. The stated planning assumptions use a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect to detect expressed as a fraction of the observed effect. Such illustrations are hypothetical planning calculations, not observed power and not evidence that the trial was designed around those assumptions. The registry record does not report the trial’s own sample-size justification, so planning illustrations should not be treated as the protocol’s rationale.

In general, over-dispersion means that the observed variation is greater than a model assumes. If a model understates variation, uncertainty can appear too small and tests can be too optimistic. The registry record does not report an over-dispersion assessment for this continuous endpoint, and there is no basis to assert that over-dispersion occurred. More generally, any statistical model depends on assumptions; clear reporting of the model and diagnostics helps readers judge how well those assumptions fit the data.

Finally, statistical significance and clinical importance answer different questions. A test and confidence interval describe evidence and precision relative to a statistical reference value; clinical importance requires an interpretable benchmark. No such benchmark for change in VAS is reported in the registry record.

10. Analyses Reported by the Sponsor

The registry lists separate sponsor-reported analyses for the mild and ESI groups. Each is a two-sided t-test described as a mean difference in final values. The arm-level estimates and 95% confidence intervals correspond to the figures reported for the primary outcome: 2.52 with 1.09 to 3.96 for mild, and 0.06 with -1.43 to 1.55 for ESI. The reported p-values are p <0.05 and p >0.05, respectively.

These analyses do not present a direct comparison between randomized arms. The record does not report a recalculated two-arm estimate for the primary outcome; values are missing or not estimable for that comparison. Thus, there is no recalculated between-arm result to set against the sponsor’s own analysis. The registry does not identify a discrepancy between the reported arm summaries and its recalculated results, but the arm summaries should not be mistaken for a comparative treatment-effect estimate.

The description of the primary outcome defines change as baseline minus Week 6, while the sponsor analyses are labeled as mean differences in final values. The registry does not explain this wording, so interpretation should retain the outcome definition and the analysis label as reported rather than assuming additional details about the calculation.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists four outcome measures and eight analyses, but the posted secondary outcome count is zero. The primary endpoint described in the record is mean change in VAS at 6 weeks before cross-over. The registry does not report results for secondary outcomes, nor does it explain why secondary results are absent.

When a study examines multiple outcomes, time points, or analyses, the chance of at least one apparently unusual result can increase. Multiplicity procedures are sometimes used to address this issue, but the registry record does not report whether an adjustment was planned or used. It also does not describe a hierarchy among outcomes, a prespecified testing sequence, or which analyses were designated as primary beyond identifying the primary outcome. No adjustment should be assumed from the information reported.

The primary outcome population is described as an intent-to-treat analysis, with all 38 participants reporting VAS at Week 6. The registry states that all ESI measurements occurred before cross-over to the mild procedure. These details identify the population and timing as reported, but do not give a complete account of data handling. The method used to address missing data, if any, is not reported in the registry record. Although the population description says all participants reported the outcome, that alone does not establish how other records, protocol deviations, or analysis-set decisions were handled.

The record does not report interim analyses, stopping rules, or the statistical plan. Those details should not be inferred from the completion status or from the reported p-values. Without a multiplicity plan, complete secondary results, and fuller missing-data methods, readers have limited information for evaluating the full analysis process. These omissions do not change the arm-level numbers reported for the primary outcome, but they constrain assessment of how comprehensively the analysis was specified and reported.

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 0% reporting threshold.

The safety record lists zero serious adverse events among the 21 participants at risk in the mild group and zero among the 17 participants at risk in the ESI group. It also lists zero other adverse events among the participants at risk in each of those groups. A separate ESI cross-over to lumbar decompression with Mild group is listed with 17 at risk and zero serious and zero other adverse events.

These are reported event counts for the groups and categories recorded; they should not be read as proof that no adverse events of any kind occurred beyond the registry’s reporting. The record lists no serious-event terms. Death counts are not reported in the registry record.

The cross-over group is a separate safety listing. The registry does not explain how its safety observation period relates to the original ESI group or whether the populations overlap. The group counts should therefore be read as recorded, without adding them together or treating the cross-over listing as an independent randomized comparison. The safety figures are descriptive and do not establish a comparative safety difference.

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

The primary results describe mean VAS change within each randomized group from baseline to 6 weeks before cross-over. The mild group’s mean change is positive, and its 95% confidence interval lies above zero. The ESI group’s mean is close to zero, and its interval includes zero. These summaries convey the direction and uncertainty of each arm’s reported average change using the registry’s stated subtraction convention.

They do not establish the size of a difference between the randomized groups. A direct between-arm estimate and its uncertainty are not reported in the registry record. Comparing which arm has a p-value below a threshold, or whether one arm’s interval includes zero, is not a substitute for that contrast. The arm-specific results also do not indicate how individual participants changed or whether a given amount of change is important to patients.

The findings are bounded by the trial description: a single-center randomized study, with 38 enrolled participants, and a Week 6 primary outcome measured before ESI cross-over. The record describes an intent-to-treat analysis and says all participants reported VAS at Week 6. It does not give a detailed missing-data method, an account of masking procedures, or a direct randomized estimate for the primary outcome.

Accordingly, the posted results support a cautious description of the reported within-arm means and their precision. They do not, on their own, answer how much one procedure differed from the other on mean VAS change, establish clinical importance, or provide a complete account of longer-term outcomes. No treatment recommendation follows from these registry summaries.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of the distinction between within-group change and a randomized comparison. The primary outcome is presented as a mean change in each arm, with confidence intervals and arm-specific tests. Those summaries can describe change relative to baseline, but the comparative question created by random assignment requires a direct between-arm estimate. Without that estimate, readers should avoid treating different within-arm significance results as evidence that the treatments differ.

The record also makes the outcome timing salient. ESI measurements were obtained before cross-over to the mild procedure, so the reported primary endpoint concerns the initial treatment period rather than a later comparison after cross-over. The safety listing includes a separate cross-over group, reinforcing the need to interpret outcomes in relation to their stated observation period.

Precision matters alongside the point estimates. The intervals show that the degree of uncertainty differs in how each arm’s mean is positioned relative to zero, but they do not supply the uncertainty for the between-arm contrast. This illustrates why an interval around each group mean is not interchangeable with an interval around a treatment effect.

Finally, the registry’s limited statistical detail matters for reproducibility. It does not report the trial’s sample-size justification, a full analysis plan, multiplicity handling, or missing-data methods. These gaps do not erase the reported results, but they narrow what can be assessed about the analysis and what conclusions can be drawn from the posted summaries.

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 most important limitation for comparative interpretation is that the registry reports arm-specific mean changes but no direct between-arm estimate or interval for the primary endpoint. The reported p-values address analyses listed for individual groups, not a randomized contrast. Consequently, the comparative effect and its precision cannot be read from the posted primary results.

The record labels the primary outcome as change from baseline to Week 6, with change defined as baseline minus Week 6, while the sponsor analyses are described as mean differences in final values. The registry does not explain the relationship between these descriptions. It also does not report the spread of individual changes, which limits assessment of variability and the distribution of responses.

The study is described as single-center, and enrollment is 38. The record does not provide a sample-size justification, so it is not possible to assess from the registry whether the study was planned to estimate a particular effect with a particular precision. It also does not describe how randomization was implemented, how double-blinding was maintained, or the statistical model details and assumptions.

Only the primary outcome is described in detail, while the registry lists four outcome measures and zero secondary posted outcomes. Multiplicity procedures, interim analyses, and the prespecified statistical analysis plan are not reported. The primary population description says all participants reported VAS at Week 6, but data-handling procedures and missing-data methods are not reported. The record also provides no clinical-importance threshold for change in VAS and no death counts. These reporting limitations constrain interpretation without changing the numbers that are posted.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study of Epidural Steroid Injection (ESI) Versus Minimally Invasive Lumbar Decompression (Mild®) in Patients With Symptomatic Lumbar Central Canal Stenosis — NCT00995371.
• Registry record last updated 2013-11-15; status last verified 2013-09.
• Results first posted 2013-11-15.
• 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

NCT00995371 is a completed, randomized, prospective, double-blind, parallel-group Phase 4 study of Vertos Mild® Minimally-Invasive Lumbar Decompression versus epidural steroid injection in symptomatic lumbar central canal stenosis. The registry describes a single-center study and reports enrollment of 38.

The primary outcome is mean VAS change from baseline to 6 weeks before cross-over, defined as baseline score minus Week 6 score. The reported arm-level means are 2.52 for mild and 0.06 for ESI, with 95% confidence intervals of 1.09 to 3.96 and -1.43 to 1.55, respectively. The registry does not report a direct between-arm estimate for this endpoint.

The safety record reports zero serious and zero other adverse events in the listed treatment and cross-over groups. Further details about the statistical plan, sample-size justification, missing-data methods, multiplicity, and death counts are not reported in the registry record.