Pain Outcomes Following Intralesional Corticosteroid Injections: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Pain Outcomes Following Intralesional Corticosteroid Injections (NCT03630198), a randomized phase 4 study. The primary outcome is Pain Outcome: Visual Analog Scale.

2. Clinical Question

The posted group means were 5.4 for corticosteroid with lidocaine and 2.7 for corticosteroid with normal saline. The posted unadjusted mean difference, calculated as the normal-saline group minus the lidocaine group, was -2.7. This describes a lower mean score in the normal-saline group in this trial. It does not, by itself, establish how broadly the finding applies to other patients, diagnoses, injection settings, or pain assessments. The registry record does not report condition-specific comparisons or a threshold for interpreting the size of a score difference as clinically important.

3. Trial Design

This was a randomized, triple-masked, parallel-group, phase 4 trial. The registry lists Vanderbilt University Medical Center as the sponsor and records the study status as completed. The recorded study start was 2018-10-01, and the primary completion date was 2019-09-01. Enrollment was 31.

The parallel design compared two injection mixtures: corticosteroid with lidocaine and corticosteroid with normal saline. The registry describes normal saline as serving to keep volume and concentration similar to the lidocaine mixture. The masking designation is triple, but the registry record does not specify which roles or individuals were masked, or describe how masking was maintained. Allocation is listed as randomized; the method used to generate or conceal the allocation is not reported in the registry record.

The trial included a broad list of conditions, including keloid, alopecia areata, acne, hypertrophic scar, epidermal inclusion cyst, frontal fibrosing alopecia, lichen plano-pilaris, keratoacanthoma, plaque psoriasis, lichen simplex chronicus, prurigo nodularis, nummular eczema, granuloma annulare, morphea, and lichen planus. The record does not report the distribution of participants across those conditions or indicate whether the primary comparison was adjusted for diagnosis or other characteristics.

The primary outcome was pain on a visual analog scale, assessed 1 minute after injection in clinic. The registry reports outcome summaries for both groups and a simple unadjusted comparison. It does not report the original sample-size justification, a detailed statistical analysis plan, or whether interim analyses were planned or conducted. Although the record lists two outcome measures, it lists no analysis records. The detailed analysis populations and handling of missing outcome measurements 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 Pain Outcome: Visual Analog Scale, measured over Assessed 1 minute after the injection (in clinic).

The primary endpoint was pain measured with a visual analog scale 1 minute after the injection, in clinic. The registry describes the scale as running from zero, meaning no pain, to 10, meaning the worst pain ever. The endpoint is a continuous score: each participant's recorded score can take values along the scale rather than being limited to a category such as pain present or absent.

A short-interval assessment is relevant to the stated study question because the registry description focuses on pain during the injection procedure, including the possibility of a burning sensation associated with lidocaine. The measurement therefore captures pain reported soon after injection, not pain over a longer follow-up period, change in an underlying condition, or a later treatment outcome. The registry does not report the exact wording used to administer the scale, who recorded the score, or whether additional pain assessments were collected at other times.

The posted results summarize the endpoint using a mean and standard deviation for each group. A mean describes the group's average score, while the standard deviation describes how spread out individual scores were around that average. These summaries do not show the full distribution of scores or how many participants reported any particular score. They also do not establish whether the observed difference matters to patients in a practical sense; a threshold for a clinically important difference is not reported in the registry record.

7. Results Posted in the Registry

• Corticosteroid With Normal Saline: mean 2.70 versus 5.40 on control; difference -2.70 (95% CI -4.38 to -1.02), standardized effect d = -1.15; z-test p = 0.002.

8. Statistical Interpretation

9. Statistical Methods Explained

The posted comparison uses a continuous endpoint: a visual analog scale score. For a continuous measure, a group mean summarizes the average recorded value, while a standard deviation describes the dispersion of individual values around that mean. These summaries answer different questions. The mean indicates the central level of scores in a group; the standard deviation indicates how much scores varied within that group. Neither summary alone describes every participant's experience.

What does the mean difference represent?

The reported mean difference is -2.7, calculated as the normal-saline group mean minus the lidocaine group mean. The group means were 2.7 and 5.4, respectively. The negative sign indicates that the first group in that subtraction had a lower average score. Because the scale defines zero as no pain and 10 as the worst pain ever, a lower score is a lower reported pain score. The mean difference is an absolute difference on the scale, not a relative percentage change.

The comparison is described as an unadjusted recalculation from the posted summary statistics. An unadjusted comparison contrasts the group summaries without accounting for other measured characteristics in a statistical model. This is distinct from an adjusted analysis, which may estimate a group contrast after accounting for specified variables. An adjusted analysis is not reported in the registry record. The posted estimate should therefore be understood as the simple group-level contrast, rather than as an estimate adjusted for diagnosis or other characteristics.

How should the standard deviations be read?

The standard deviations were 2.4 in the lidocaine group and 2.3 in the normal-saline group. They describe spread in the observed scores, not uncertainty in the group mean and not the range of possible scores. A standard deviation is not a confidence interval. The registry does not provide a histogram or participant-level data, so the score distributions, outliers, and any differences in distribution shape cannot be examined from the posted summaries.

In general, a comparison based on means is most informative when its assumptions are reasonable for the observed data and the analysis design. The registry record does not report diagnostic checks, a model specification, or a detailed account of distributional assumptions. The simple recalculation uses the posted means and standard deviations, but it cannot recover information that is not included in those summaries.

What does the p-value say?

The unadjusted p-value is 0.002. In general, a p-value describes how unusual data at least as discrepant as those observed would be under a specified null model, assuming the model and its assumptions. It is not the probability that there is no difference, and it does not quantify the probability that the result will replicate. A small p-value is not a measure of how important the difference is to patients. The registry record does not report a prespecified significance threshold or a fuller analysis plan, so the p-value should be read as the posted unadjusted result rather than as a complete account of the trial's statistical decision process.

The comparison also reports a standardized effect, d = -1.153, and a pooled standard deviation of 2.342. A standardized effect expresses a group contrast relative to a measure of variability, which can help describe the contrast on a scale without the original score units. It does not replace the original-scale mean difference, which is directly interpretable in score units. These standardized values are recalculated summaries, not additional clinical outcomes.

Why can over-dispersion matter?

In general, over-dispersion occurs when variability in observed data is greater than a model expects. It can make standard errors too small if the analysis assumes less variability than the data contain, which can in turn make uncertainty intervals too narrow and tests too optimistic. The posted primary outcome is a continuous score, and the registry record does not report an over-dispersion assessment or a model that addresses it. Over-dispersion is therefore a general statistical consideration, not a reported problem in this trial.

The comparison uses a mean-based approach and presents an uncertainty interval from -4.383 to -1.017. The registry does not identify the interval construction method or its confidence level, so those details should not be inferred. The interval is useful for seeing the range of values represented by the posted recalculation, but it cannot resolve questions about missing data, selection, masking, or applicability. The design is randomized, but the registry record does not give enough detail to assess allocation procedures or the success of masking.

Finally, the record lists zero analysis records and does not report the original statistical analysis plan. The posted comparison can be interpreted as an unadjusted summary-based result, while choices not documented in the record—including model selection, treatment of missing scores, and multiplicity handling—remain unknown.

10. Confidence Intervals and Precision

The unadjusted mean difference was -2.7, and its reported uncertainty interval extends from -4.383 to -1.017. The interval gives a range of values compatible with the posted analysis under its calculation assumptions. Its endpoints are both below zero, which is consistent with a lower mean score in the normal-saline group for this comparison. The registry record does not identify the interval's confidence level or construction method, so neither should be assumed.

The interval is not a range containing most individual participants' pain scores. It describes uncertainty around the estimated difference between group means. Individual scores can be much more dispersed: the posted standard deviations were 2.4 with lidocaine and 2.3 with normal saline. The group counts were 13 and 18, respectively. The registry does not provide the raw scores, so the individual-level distribution and the number of people with scores above or below any threshold are not reported in the registry record.

Precision and importance are separate considerations. The interval indicates uncertainty in the estimated mean contrast, while clinical importance depends on how a score difference is interpreted by patients and clinicians. A threshold for clinical importance is not reported in the registry record. The posted p-value of 0.002 is another summary of the unadjusted comparison; it does not replace the interval or answer whether the difference is practically meaningful.

Precision also depends on analysis choices and data completeness. The registry record does not report missing outcome counts, missing-data methods, or an adjusted analysis. The interval should therefore be read as precision for the posted simple comparison, not as a complete account of uncertainty from every possible source.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size figures are planning illustrations based on the observed effect, not the original trial's design calculations. The original design assumptions are not reported in the registry record. These figures are participants per arm, not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect used for planning is the stated fraction of the observed effect.

The row for 100% of the observed effect gives 12 participants per arm for 80% power and 16 participants per arm for 90% power. The row for 75% of the observed effect gives 21 participants per arm for 80% power and 29 participants per arm for 90% power. The row for 50% of the observed effect gives 48 participants per arm for 80% power and 64 participants per arm for 90% power.

In general, power is the chance that a planned study would detect an effect of the specified size under the planning assumptions if that effect were the true one. The 80% column describes a design targeting an 80% chance under those assumptions; the 90% column targets a higher chance. The illustration is not observed power and does not describe the probability that the trial's result is correct.

Smaller effects require more participants to detect under the same assumptions, as reflected by the larger per-arm figures for the smaller fractions. The curve is another view of the planning relationship, rather than a record of trial outcomes. These projections should not be treated as a retrospective judgment about the trial's design, since the original sample-size justification and planning assumptions are not reported in the registry record.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -2.700; pooled standard deviation σ = 2.342.
2. n = 2 × (1.96 + 0.842)² × 2.342² / -2.700² = 11.8, rounded up to 12 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -2.7                      # observed difference in means
sigma <- 2.34189725620504                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(3630198)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 12 (80% power), 16 (90% power)
 75% of observed effect: n per arm = 21 (80% power), 29 (90% power)
 50% of observed effect: n per arm = 48 (80% power), 64 (90% power)
power.t.test: 12.8 
Simulated power at n = 12 per arm: 0.768 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Multiplicity, Missing Data and Analysis Populations

Multiplicity concerns the risk of obtaining apparently notable results when several outcomes, comparisons, time points, or analyses are examined. In general, testing many questions can increase the chance of at least one result appearing unusual by chance. Statistical plans sometimes address this through prespecified outcome hierarchies or adjustment procedures. The registry record does not report a multiplicity plan or an adjustment for multiple testing.

The registry lists two outcome measures but lists zero analysis records. The primary outcome discussed in the posted results is pain on the visual analog scale, assessed 1 minute after injection. The record does not specify whether other comparisons or time points were analyzed, whether the primary comparison was prespecified in an analysis plan, or whether any multiplicity procedure was used. Those details are not reported in the registry record and should not be inferred from the posted p-value.

Missing-data handling is also not described. The record provides group counts for the reported outcome summaries, but it does not state whether any measurements were missing, how missing values were handled, or whether the analysis included all randomized participants. The analysis population definition—such as whether results were based on all randomized participants or on a subset with observed outcomes—is not reported in the registry record. Without that information, the extent to which missingness or exclusions could affect the comparison cannot be assessed.

The registry record does not report an intention-to-treat analysis, a per-protocol analysis, imputation methods, sensitivity analyses, or reasons for any exclusions. These are not claims that such procedures were absent; they are details not reported in the registry record. The available results support interpretation of the posted group summaries and unadjusted comparison, while the analysis choices behind them remain incompletely documented.

More generally, a statistical analysis plan helps distinguish confirmatory questions specified before examining the results from exploratory analyses. Its availability, timing, and contents are not reported in the registry record. Interim analyses and any associated decision rules are also not reported in the registry record. These gaps limit evaluation of the full analysis process, but they do not change the numerical description of the posted outcome summaries.

14. 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 registry reports zero serious adverse events in the corticosteroid-with-lidocaine group and zero in the corticosteroid-with-normal-saline group. The number at risk for the serious adverse event summary was 13 in the lidocaine group and 18 in the normal-saline group. The registry also reports zero other adverse events in each group and zero deaths in each group.

These entries mean that no events were recorded in the posted categories for the participants included in those summaries. They do not establish that the mixtures are free of risk, or that uncommon events could not occur. When no event is observed in a study of this size, the data provide limited information about the frequency of rare events. The record does not report detailed event definitions, surveillance procedures, duration of safety follow-up, or event severity beyond the serious-versus-other categories.

The registry lists no serious adverse event terms. The safety figures should be read as descriptive counts, not as a formal comparison establishing that the groups have equivalent safety. They also do not address pain, which was the primary outcome rather than an adverse-event count.

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

The posted results show lower average visual analog pain scores in the corticosteroid-with-normal-saline group than in the corticosteroid-with-lidocaine group at the assessment 1 minute after injection. The group means were 2.7 and 5.4, and the unadjusted mean difference, normal saline minus lidocaine, was -2.7. The posted interval for that difference ran from -4.383 to -1.017, and the unadjusted p-value was 0.002. These figures describe the short-term pain scores recorded in this randomized comparison.

The findings do not establish that the same difference would occur in every setting or for every condition listed in the registry. The record does not provide condition-specific outcome summaries, participant characteristics by group, or longer-term assessments. It also does not report a threshold for a clinically important difference. The statistical contrast therefore cannot, on its own, determine how meaningful the score difference is to participants.

The results do not show that one mixture improves the underlying conditions for which corticosteroid injections were used. The primary endpoint was pain shortly after injection, not disease response or longer-term health outcomes. Nor do the results establish that all individual participants experienced less pain with one mixture: group means do not describe each person's result.

The absence of recorded adverse events in the posted categories does not prove that harms cannot occur. The safety summaries are limited to the registry's reported counts and do not establish equivalence between groups or provide detailed information about uncommon events. Likewise, the unadjusted p-value is not a probability that the finding is true, and it is not a measure of clinical value.

The most defensible interpretation is therefore narrow: for this trial's posted short-term pain assessment, the average score was lower in the normal-saline group, with an unadjusted estimate and uncertainty interval as reported. The registry record leaves important details about analysis populations, missing data, multiplicity, and the trial's original design assumptions unreported.

16. Why This Trial Matters Statistically

This trial illustrates the distinction between a measurement question and a treatment-outcome question. Its primary endpoint was pain shortly after an injection, rather than change in the conditions being treated. Keeping the endpoint in view prevents the pain comparison from being misread as evidence about longer-term clinical outcomes.

The result is also a useful example of why estimates and uncertainty should be read together. The mean difference of -2.7 summarizes the contrast in average scores, while the interval from -4.383 to -1.017 describes uncertainty around that contrast under the posted recalculation. The standard deviations show that individual scores varied within both groups. The p-value adds a test-based summary, but it does not tell readers whether the contrast is clinically important or how individual participants responded.

Another statistical issue is the distinction between posted results and a complete analysis record. The registry provides group summaries and an unadjusted comparison, but analysis populations, missing-data procedures, multiplicity handling, and the original sample-size rationale are not reported in the registry record. These details matter because they inform how much confidence to place in the generalizability and robustness of a result, beyond its arithmetic summary.

The planning illustration is useful for understanding how assumed effect size and power relate: smaller effects require more participants per arm under the stated assumptions. It is not a retrospective estimate of trial power or a substitute for the original design rationale. Taken together, the trial highlights how a clear endpoint, transparent uncertainty, and careful attention to what is not documented are all necessary for statistical interpretation.

17. 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 enrollment was 31, and the reported group counts were 13 for corticosteroid with lidocaine and 18 for corticosteroid with normal saline. These counts provide limited information for assessing uncommon outcomes or differences within subgroups. The registry record does not report results separately for the listed conditions, so the overall comparison cannot establish whether the observed pattern was similar across diagnoses.

The primary assessment was made 1 minute after injection in clinic. The record does not report pain measurements at other times or longer-term outcomes, and the result should not be extended to those unreported outcomes. It also does not report participant characteristics that might help readers judge how well the study population represents other settings.

Although the trial is listed as randomized and triple-masked, the registry record does not describe the randomization procedure, allocation concealment, which parties were masked, or whether masking was successful. The record does not provide an analysis plan, a definition of analysis populations, or the handling of missing outcome data. It lists no analysis records, so the posted summaries cannot be checked against a documented analysis protocol.

The reported comparison is unadjusted, and the registry does not report whether other relevant characteristics were included in any additional model. A threshold for a clinically important score difference is not reported. The confidence level and construction method for the reported interval are also not identified in the registry record. Finally, the original sample-size justification, interim analysis plans, and multiplicity procedures are not reported. These are limits of the available record, rather than evidence that any particular method was or was not used.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Pain Outcomes Following Intralesional Corticosteroid Injections — NCT03630198.
• Registry record last updated 2021-03-11; status last verified 2021-02.
• Results first posted 2021-03-11.
• 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.

21. Record Summary

The registry record describes a completed, randomized, triple-masked, parallel-group, phase 4 trial sponsored by Vanderbilt University Medical Center. It compared intralesional corticosteroid mixed with lidocaine against corticosteroid mixed with normal saline, with enrollment of 31. The primary endpoint was visual analog pain score assessed 1 minute after injection in clinic.

The posted mean scores were 5.4 with lidocaine and 2.7 with normal saline. The unadjusted mean difference, normal saline minus lidocaine, was -2.7, with a reported interval from -4.383 to -1.017 and an unadjusted p-value of 0.002. The record reports zero serious adverse events, zero other adverse events, and zero deaths in each group.

The registry does not report the original sample-size rationale, detailed analysis populations, missing-data methods, or multiplicity procedures. The comparison is best read as an unadjusted summary of pain scores at the specified short-term assessment, with the record's reporting limitations kept in mind.