Lidocaine + Clonidine for Intraoral Anesthesia in Patients With Diabetes Mellitus Type 2: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Lidocaine + Clonidine for Intraoral Anesthesia in Patients With Diabetes Mellitus Type 2 (NCT02371759), a randomized phase 3 study. The primary outcome is Duration of Intraoral Local Anesthesia.

2. Clinical Question

3. Trial Design

This was a randomized, quadruple-masked, parallel-design phase 3 study sponsored by the University of Belgrade. The registry lists enrollment of 256 and a completed status. The study began in 2013-06, with primary completion in 2016-01. The title focuses on patients with diabetes mellitus type 2, but the outcome results also include healthy participants. The registry record does not explain the rationale for including healthy participants or the intended role of those groups in the primary analysis.

The interventions combine two anesthetic formulations with two administration approaches: lidocaine plus clonidine or lidocaine plus epinephrine, given as maxillary infiltration or mandibular block anesthesia. The registry describes a single dose of 2ml for each intervention. For the primary endpoint, results are separated into diabetic and healthy groups and into maxillary and mandibular procedures. The eight reported groups have different sample sizes, ranging from 24 to 32 participants.

Randomization and quadruple masking are listed, but the registry record does not report the randomization sequence method, allocation concealment process, or which roles were masked. It also does not detail how participants were assigned across the distinct population, procedure, and formulation combinations. The original sample-size justification, target effect, and allocation plan are not reported in the registry record. The enrollment listing should therefore not be taken as evidence that the primary comparisons were planned or powered in a particular way.

The registry lists 25 outcome measures and 10 analyses. A sponsor-reported Wilcoxon (Mann-Whitney) analysis is recorded across all eight primary-outcome groups, with p < 0.05 and a non-inferiority-or-equivalence analysis classification. The record does not report a test statistic, confidence interval, non-inferiority margin, or detailed interpretation for that analysis. The distinction between this overall sponsor analysis and the simple pairwise recalculations is important when interpreting the findings.

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.

Only the first 6 of 8 groups are shown.

Overall Study

Reasons for not completing this period:

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.

Only the first 6 of 9 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Duration of Intraoral Local Anesthesia, measured over Up to 6 hours after local anesthesia injection.

The primary endpoint is duration of intraoral local anesthesia, in minutes, measured as the time until soft-tissue numbness ceases. The registry specifies a measurement window of up to 6 hours after local anesthesia injection. It reports the mean and standard deviation for each of eight groups. The outcome is continuous: it can take a range of values rather than being only a yes-or-no event.

Duration is a direct measure of how long the reported local anesthetic effect persists, making it relevant to the study's stated comparison of two formulations and two administration approaches. It is not, by itself, a complete account of anesthesia quality or safety. The study summary also refers to parameters of anesthesia and stable cardiovascular measures, while the listed secondary outcomes include onset, anesthetic-field width, postoperative analgesia, and local postoperative complications. The registry record does not report the primary endpoint's measurement instrument, assessor procedures, or any threshold defining a clinically important difference.

Group means describe average duration, and standard deviations describe how much participant-level observations vary around those averages. A difference in means can be useful for describing group separation, but it does not show the distribution of individual results or establish that a difference matters clinically. Interpretation also depends on how groups were assigned and compared, the planned analysis, and the uncertainty around estimates. The posted primary results include means and standard deviations but not sponsor-reported group-specific confidence intervals.

7. Results Posted in the Registry

• Diabetics: L+C Mandibular Anesthesia: mean 173.27 versus 132.48 on control; difference 40.79 (95% CI -1.08 to 82.66), standardized effect d = 0.50; z-test p = 0.056.
• Diabetics: L+E Maxillary Anesthesia: mean 182.09 versus 132.48 on control; difference 49.61 (95% CI 10.63 to 88.59), standardized effect d = 0.65; z-test p = 0.013.
• Diabetics: L+E Mandibular Anesthesia: mean 195.35 versus 132.48 on control; difference 62.87 (95% CI 21.55 to 104.19), standardized effect d = 0.78; z-test p = 0.003.
• Healthy: L+C Maxillary Anesthesia: mean 108.82 versus 132.48 on control; difference -23.66 (95% CI -58.89 to 11.57), standardized effect d = -0.34; z-test p = 0.188.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Onset of Intraoral Local Anesthesia

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Diabetics: L+C Mandibular Anesthesia: mean 5.27 versus 1.76 on control; difference 3.51 (95% CI 2.69 to 4.33), standardized effect d = 2.15; z-test p = <0.001.
  • Diabetics: L+E Maxillary Anesthesia: mean 2.16 versus 1.76 on control; difference 0.40 (95% CI -0.09 to 0.89), standardized effect d = 0.41; z-test p = 0.110.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Diabetics: L+C Mandibular Anesthesia than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Diabetics: L+E Maxillary Anesthesia and the control. The interval gives the range of effects that remain compatible with the data.

Width of Anesthetic Field After Maxillary Infiltration Anesthesia

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Diabetics: L+E Maxillary Anesthesia: mean 35.19 versus 27.07 on control; difference 8.12 (95% CI 7.42 to 8.82), standardized effect d = 5.74; z-test p = <0.001.
  • Healthy: L+C Maxillary Anesthesia: mean 23.81 versus 27.07 on control; difference -3.26 (95% CI -3.84 to -2.68), standardized effect d = -3.06; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Diabetics: L+E Maxillary Anesthesia than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Healthy: L+C Maxillary Anesthesia than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Postoperative Analgesia

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Diabetics: L+C Mandibular Anesthesia: 50.0% (15/30) versus 37.9% (11/29) on control; risk difference 12.1 percentage points (95% CI -13.1 to 37.2), risk ratio 1.32 (0.73–2.37); unadjusted two-proportion z-test p = 0.351.
  • Diabetics: L+E Maxillary Anesthesia: 40.6% (13/32) versus 37.9% (11/29) on control; risk difference 2.7 percentage points (95% CI -21.8 to 27.2), risk ratio 1.07 (0.57–2.00); unadjusted two-proportion z-test p = 0.830.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Diabetics: L+C Mandibular Anesthesia and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Diabetics: L+E Maxillary Anesthesia and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes add several kinds of information beyond duration: onset of anesthesia, width of the anesthetic field after maxillary infiltration, postoperative analgesia, and local postoperative complications. The posted numerical results include group summaries and selected recalculated contrasts for onset, anesthetic-field width, and postoperative analgesia. The registry also reports a sponsor analysis for each of those outcomes, but does not provide complete detail for every comparison or outcome.

Across these outcomes, the posted results do not form a single, uniformly consistent pattern that resolves the primary question. Some selected recalculated contrasts are more separated than others, while some intervals include no difference. The secondary outcomes measure different aspects of the procedure and cannot be treated as substitutes for the primary duration endpoint. They can help contextualize the study's broader aims, but the registry does not report a prespecified synthesis that combines them with duration or establishes how they should affect interpretation of the primary analysis.

Secondary findings generally carry less confirmatory weight when many outcomes and comparisons are examined without a reported multiplicity plan. The registry lists 25 outcome measures and 10 analyses, but does not report which secondary hypotheses were primary to the statistical plan, how tests were ordered, or whether p-values were adjusted. The recalculated secondary p-values are unadjusted. A small p-value among several exploratory contrasts may be less persuasive than a result from a clearly prespecified, appropriately controlled primary analysis.

Several secondary details are incomplete. For example, the width outcome is reported for maxillary groups, while mandibular entries have no posted mean or standard deviation. The registry record does not report why some outcome values are absent or how missing values were handled. Overall, these secondary measures broaden the description of what was studied, but they do not remove uncertainty about the primary comparison or the statistical plan.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Onset of Intraoral Local Anesthesia
• Width of Anesthetic Field After Maxillary Infiltration Anesthesia
• Postoperative Analgesia
• Local Postoperative Complications

9. Statistical Interpretation

10. Statistical Methods Explained

The registry identifies the primary endpoint as a continuous measure summarized by its mean and standard deviation. The recalculated pairwise estimates compare each listed group mean with the diabetic lidocaine-plus-clonidine maxillary group. These calculations use posted summary statistics and are simple, unadjusted comparisons. They do not reproduce a potentially more complex sponsor analysis, account for covariates, or adjust for multiple testing.

What does a mean difference describe?

A mean difference is the estimated separation between two group averages, expressed in the outcome's units. For duration, those units are minutes. A positive estimate in the listed comparisons means the second group's posted mean is higher than the reference group's posted mean; a negative estimate means it is lower. The estimate describes average separation, not the experience of every participant. Group distributions may overlap even when their means differ, and means alone do not describe that overlap.

Standard deviation is a measure of dispersion among individual observations around a group mean. It is not the same as the uncertainty in the estimated mean. The registry reports standard deviations for the primary outcome, and they vary across groups. A large standard deviation relative to a mean difference can make the estimate less precise, particularly with modest group sizes. General statistical principle: increased variability makes it harder to distinguish a group contrast from sampling variation unless other features, such as sample size, provide more information.

What does the confidence interval add?

A confidence interval gives a range of values compatible with the estimate under the assumptions of the method. In general, a wider interval indicates less precision, while a narrower interval indicates greater precision. For a difference, an interval that includes zero is compatible with no difference as well as with values on either side of zero. An interval excluding zero is evidence against a zero difference under the interval's assumptions, but it does not establish clinical importance or account for unreported multiplicity. The recalculated primary comparisons have intervals; the sponsor-reported overall result does not have a posted confidence interval.

The reported intervals belong to the simple recalculations, not necessarily to the trial's prespecified inferential procedure. They are useful for understanding magnitude and uncertainty in the posted group summaries. They cannot resolve questions about whether the original analysis used a different model, population, endpoint definition, or adjustment. Those details are not reported in the registry record.

Why might rank-based and mean-based analyses differ?

The sponsor-reported primary test is Wilcoxon (Mann-Whitney), a rank-based procedure. In general, rank-based methods compare the ordering of observations between groups rather than relying on a comparison of means alone. They can be useful when distributional shape or extreme observations make a mean-based model less suitable, although their interpretation depends on the distributions and study design. The registry does not report individual observations, distribution plots, or the rationale for selecting this test.

The recalculated comparisons instead target differences in means using summary statistics. They answer a different question from a single rank-based test across all eight groups. A global test can assess evidence of some difference across a set of groups without identifying which particular groups differ or estimating every pairwise contrast. The record's overall test is classified as non-inferiority or equivalence, but the non-inferiority margin and detailed hypothesis are not reported. A p-value alone does not identify the size or direction of an effect, and the posted p < 0.05 does not fill in those missing details.

Why do multiple comparisons matter?

When many hypotheses are tested, the chance of obtaining at least one apparently notable result through random variation increases. General statistical practice may address this through a prespecified hierarchy, adjustment, or a clear distinction between confirmatory and exploratory analyses. The registry lists 10 analyses and 25 outcome measures, but does not report a multiplicity strategy. The pairwise p-values are explicitly unadjusted recalculations. They should therefore be read as descriptive evidence, not as a complete family-wise confirmatory analysis. The record also does not establish that these particular pairwise comparisons were prespecified.

Over-dispersion is a general issue when outcome variation is greater than a statistical model expects. It can lead to uncertainty estimates that are too small if the model does not accommodate the extra variation. The registry's summary statistics show notable differences in standard deviations among groups, but they do not by themselves establish that a particular model was over-dispersed. The underlying observations and sponsor model diagnostics are not reported, so no conclusion about model fit can be drawn.

What can summary-statistic recalculation establish?

These recalculations make the posted means, standard deviations, sample sizes, and pairwise estimates easier to interpret together. They do not recover information absent from aggregate summaries, such as participant-level distributions, missingness patterns, covariate balance, or changes to the analysis population. Nor do they verify the original randomization, masking, outcome assessment, or statistical plan. If the recalculated estimates appear to conflict with the sponsor's analysis, the sponsor's own analysis takes precedence. The discrepancy is an important reason to keep the two analyses distinct rather than treating the recalculation as a correction.

11. Confidence Intervals and Precision

Precision varies across the primary comparisons. The diabetic lidocaine-plus-clonidine mandibular comparison has a mean difference estimate of 40.79 minutes and a 95% confidence interval from -1.08 to 82.66. This interval is broad and includes zero, so the summary-statistic recalculation is compatible with a range of possibilities, including little or no difference and a larger positive difference. Its unadjusted p-value is 0.056.

The diabetic comparisons with lidocaine plus epinephrine have intervals that exclude zero: 10.63 to 88.59 minutes for the maxillary comparison, and 21.55 to 104.2 minutes for the mandibular comparison. These intervals still allow a range of effect sizes, so they do not identify a single precise duration difference. Their unadjusted p-values are 0.013 and 0.003, respectively. The healthy-participant comparisons have intervals that include zero: -58.89 to 11.57, -17.94 to 64.16, -54.62 to 19.14, and -2.909 to 83.77 minutes. They are not precise enough to rule out a range of possible differences.

These are recalculated intervals around selected pairwise mean differences, not intervals reported for the sponsor's overall rank-based analysis. The registry record does not provide a confidence interval for that overall test, or for each group mean. Confidence intervals address sampling uncertainty under their statistical assumptions. They do not account automatically for the multiplicity of outcomes and comparisons, bias, missing outcomes, or uncertainty about clinical importance. The registry does not report a clinically meaningful threshold for duration, so precision cannot be judged against such a threshold from this record.

12. 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 planning table and curve translate observed differences and variability into illustrative sample sizes under stated assumptions. For these continuous-outcome comparisons, the figures are participants per arm, not total participants or total events. The table gives estimates for planning around 100%, 75%, and 50% of the observed effect, with columns for 80% and 90% power. The curve presents the corresponding relationship between an assumed effect size and the required sample size; it should be read as a planning aid rather than a report of who was enrolled.

The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is the stated fraction of the observed effect. The original trial's own sample-size assumptions and justification are not reported in the registry record. These calculations use the observed effect as a starting point, so they are not evidence that the trial was designed around that effect.

In general, 80% power means a design with that probability of detecting the assumed effect under the specified model and assumptions if that effect is real. The 90% power column represents a higher target probability of detection, which generally requires more participants. Smaller assumed effects are harder to distinguish from random variation and therefore require more participants per arm. The table's very different estimates across comparisons reflect different observed effects and variability; they should not be treated as a recommended enrollment target without clinical and design judgment. These figures are planning illustrations, not observed power.

13. 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 = 40.790; pooled standard deviation σ = 81.667.
2. n = 2 × (1.96 + 0.842)² × 81.667² / 40.790² = 62.9, rounded up to 63 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 <- 40.79                      # observed difference in means
sigma <- 81.6671983369732                     # 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(2371759)
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 = 63 (80% power), 85 (90% power)
 75% of observed effect: n per arm = 112 (80% power), 150 (90% power)
 50% of observed effect: n per arm = 252 (80% power), 337 (90% power)
power.t.test: 63.9 
Simulated power at n = 63 per arm: 0.796 (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.

14. Analyses Reported by the Sponsor

The registry's primary analysis is attributed to the sponsor and uses a Wilcoxon (Mann-Whitney) method across all eight primary-outcome groups. It is classified as a non-inferiority-or-equivalence analysis and has a reported p-value of <0.05. The record does not give the test statistic, group-specific estimates, confidence interval, non-inferiority margin, or the detailed hypothesis and decision rule. Consequently, the p-value cannot by itself show which groups differed or by how much, nor can it establish equivalence without the relevant margin and analysis details.

The recalculations use the posted means and standard deviations to estimate unadjusted pairwise mean differences, including selected comparisons against the diabetic lidocaine-plus-clonidine maxillary group. They are not the same analysis as the sponsor's rank-based overall test. Their estimates and p-values can differ because the methods, contrasts, and information used differ. The registry flags a discrepancy, so the sponsor's own analysis takes precedence. The recalculations remain useful as transparent descriptions of the group summaries, but should not be represented as replacing or correcting the sponsor's result.

The registry record does not report enough detail to reconcile the discrepancy or determine whether the overall analysis and recalculated contrasts address the same estimand. The sponsor result should therefore be read as the reported overall analysis, with its limitations in detail, while the pairwise recalculations should be read as supplementary unadjusted summaries.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists 25 outcome measures and 10 analyses, but does not report a multiplicity strategy. It is therefore unclear whether the primary and secondary hypotheses were tested in a hierarchy, whether p-values were adjusted, or which comparisons were considered confirmatory. The recalculated pairwise p-values are unadjusted. Repeated testing can increase the chance of findings that appear notable by chance, so these pairwise results should be interpreted cautiously rather than as a set of independent confirmatory conclusions.

The sponsor's primary analysis is recorded as an overall Wilcoxon (Mann-Whitney) analysis across eight groups, with a non-inferiority-or-equivalence classification. The registry does not report a margin, a detailed hypothesis, a confidence interval, or the statistical decision rule. Without these, the non-inferiority or equivalence claim cannot be independently interpreted from the registry entry. The original analysis plan and sample-size justification are not reported in the registry record.

The registry does not describe missing-data rates or methods for handling missing observations. Some secondary outcome entries have no posted results, but whether these reflect missing measurements, non-applicability, or another reason is not reported in the registry record. The analysis population is also not specified: the entry does not say whether results were based on all randomized participants, participants who received treatment, or another population. There is no reported account of exclusions, protocol deviations, or sensitivity analyses.

Although randomization and quadruple masking are listed, supporting operational details are not reported. The record does not specify the randomization process, concealment procedures, masking roles, or whether masking was assessed. It also does not describe baseline balance or adjustment for participant characteristics. These omissions limit assessment of potential bias and the relationship between the reported overall analysis and the simpler recalculations. They do not demonstrate that a particular problem occurred; they identify information unavailable in the registry record.

16. 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.

For each of the eight reported groups, the registry lists zero serious adverse events and zero other adverse events among participants at risk. The listed at-risk group sizes range from 24 to 32. These entries describe the adverse-event counts reported in the registry; they do not establish that no unrecorded events occurred or that the groups had equivalent safety profiles.

Death counts are null for all groups, so deaths are not reported in the registry record. The record does not give an adverse-event follow-up timeframe, definitions, ascertainment procedures, or a detailed safety analysis. It also does not describe whether event reporting was complete for every participant. With groups of these sizes and no reported events, the registry entries alone cannot precisely characterize the frequency of uncommon harms or support a broad comparison of safety between formulations or populations. The study summary refers to cardiovascular stability, but the registry information summarized in the outcome results does not provide values for systolic, diastolic, or mean blood pressure or heart rate.

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

The registry describes a randomized, quadruple-masked study comparing lidocaine plus clonidine with lidocaine plus epinephrine across maxillary and mandibular anesthesia procedures, with results reported for participants with diabetes and healthy participants. The primary endpoint was duration of soft-tissue numbness. The posted group means vary, and selected unadjusted recalculations show estimated differences with differing degrees of uncertainty. The sponsor's overall analysis is reported separately and does not include enough detail in the registry entry to interpret its magnitude or direction.

These findings do not, by themselves, establish that one formulation is clinically superior, equivalent, or non-inferior. The sponsor's analysis is classified as non-inferiority or equivalence, but its margin and detailed results are not reported. The recalculated pairwise tests are unadjusted, compare selected groups, and do not substitute for the sponsor's analysis. The record also does not report a threshold for a clinically important difference in duration.

The results do not establish safety equivalence. The registry lists no serious or other adverse events in the reported groups, but it does not report deaths, the adverse-event observation period, event collection methods, or cardiovascular outcome values. Absence of events in the listed record is not proof that risks are absent.

General statistical principle: a p-value or confidence interval addresses uncertainty under an analysis and its assumptions, not the full quality or relevance of a study. The available entry does not resolve questions about missing data, analysis populations, multiplicity, or the applicability of healthy-participant findings to people with diabetes. The conclusions should remain limited to the posted outcomes and the incomplete statistical details in the registry record.

18. Why This Trial Matters Statistically

This study is statistically instructive because its registry combines an overall rank-based sponsor analysis with recalculated pairwise mean differences. Those analyses answer different questions and should not be collapsed into one result. A single overall test can indicate evidence of differences somewhere among groups, while pairwise estimates describe selected contrasts and their uncertainty. Without the sponsor's full analysis details, the registry result cannot be mapped directly onto each pairwise comparison.

The design also includes multiple dimensions: anesthetic formulation, maxillary versus mandibular procedure, and diabetic versus healthy participants. Separating those factors matters because a comparison between groups can reflect more than the formulation alone. The registry does not report a statistical model that jointly addresses those dimensions, nor does it explain the intended role of the healthy groups in the primary question.

The study highlights why estimates and intervals are more informative than p-values alone. The recalculated differences show both magnitude and uncertainty, while the sponsor's posted p-value has no accompanying estimate or interval. The listed outcomes and analyses also make multiplicity relevant, yet the record does not describe how it was addressed. Finally, the absence of event counts in the safety entries should be read alongside the limited group sizes and missing safety-method details, not as a guarantee of no risk. These issues are useful reminders to examine design, estimand, uncertainty, and reporting completeness together.

19. 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's primary outcome includes eight groups spanning participant population, formulation, and procedure. The record does not explain how those groups were allocated or whether the central intended comparison was between formulations within each procedure and population. The title focuses on diabetes, while healthy-participant results are also included. No statistical model is reported that separates these factors or estimates their interaction.

The sponsor's primary analysis is classified as non-inferiority or equivalence, but the margin, hypothesis details, test statistic, and confidence interval are absent. The record reports p < 0.05 without enough information to identify the direction or size of the overall result. The unadjusted recalculations use a single reference group for selected contrasts and do not provide a complete prespecified analysis of every clinically relevant comparison. The registry flags a discrepancy, making it especially important not to treat those calculations as a replacement for the sponsor's analysis.

There is no reported multiplicity plan despite 25 outcome measures and 10 analyses. Missing-data handling, analysis populations, exclusions, and protocol deviations are not reported. Several secondary results are incomplete, including absent values for mandibular groups in the anesthetic-field-width outcome. The registry does not report whether such entries reflect missing measurements or another reason.

The record does not report eligibility details, participant characteristics beyond population grouping, baseline balance, outcome assessment procedures, or the original sample-size justification. Cardiovascular measurements named in the study summary are not included among the posted outcome values described in the record. Safety follow-up timing and ascertainment are also not reported. These limitations restrict interpretation of both the comparative results and their applicability; they do not establish that bias or measurement problems occurred.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Lidocaine + Clonidine for Intraoral Anesthesia in Patients With Diabetes Mellitus Type 2 — NCT02371759.
• Registry record last updated 2017-05-03; status last verified 2017-03.
• Results first posted 2017-05-03.
• 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.

23. Record Summary

NCT02371759 is a completed, randomized, quadruple-masked, parallel-design phase 3 study sponsored by the University of Belgrade. It enrolled 256 participants and studied intraoral anesthesia with lidocaine plus clonidine or lidocaine plus epinephrine. The primary endpoint was duration of anesthesia, measured as time until soft-tissue numbness ceased, up to 6 hours after injection.

The registry reports primary-outcome means and standard deviations for diabetic and healthy groups, and an overall sponsor-reported Wilcoxon (Mann-Whitney) analysis with p < 0.05. Its non-inferiority-or-equivalence classification is not accompanied by a margin or detailed estimates. Pairwise mean-difference recalculations are unadjusted and should be read separately from that analysis. Multiplicity handling, missing-data methods, analysis populations, and original design assumptions are not reported in the registry record.