Efficacy And Safety Of Azithromycin SR Compared With Minocycline In Acne: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy And Safety Of Azithromycin SR Compared With Minocycline In Acne (NCT00392223), a randomized phase 3 study. The primary outcome is Change From Baseline to End of Treatment in Global Acne Grading System (GAGS) Score.

2. Clinical Question

The registry describes a randomized, parallel-group trial in outpatients with moderate to severe inflammatory acne. Its primary objective was to evaluate the clinical efficacy of azithromycin microspheres compared with minocycline after 8 weeks of therapy. The record does not provide more detail about the clinical decision context or the criteria used to characterize disease severity.

The groups received different active treatments and matching placebos, according to the treatment and placebo intervention descriptions. The official title describes a double-blind, double-dummy study. A double-dummy approach generally uses placebo versions of the different treatment forms to help maintain masking when treatments are delivered in different ways; that general explanation does not establish exactly how treatment was administered in practice. The record does not describe the masking procedures or who was masked.

The primary question is framed around the mean change in GAGS score through Week 8. The posted arm estimates are least-squares means, with 95% confidence intervals. The registry also lists secondary GAGS outcomes and acne graded by the Leeds Technique, but detailed results for those outcomes are not included in the record. The record’s status is terminated. It does not state why the trial was terminated or whether the termination affected follow-up or the analysis.

3. Trial Design

This is a Phase III, randomized, double-blind, double-dummy, parallel-group trial. The registry lists enrollment as 118 and identifies outpatients with moderate to severe inflammatory acne as the target population. Recruitment began in 2007-10, and primary completion is recorded as 2008-06. The trial status is terminated. The reason for termination and the date of termination are not reported in the registry record.

The trial compared azithromycin microspheres with minocycline capsules over 8 weeks. The official title specifies azithromycin microspheres oral powder for suspension, 2 g in one administration a week, and minocycline capsules, 100 mg daily, each for 8 weeks. The registry lists placebo interventions corresponding to both treatments. Arm descriptions are blank, so the record does not give a fuller account of the assigned regimens or how the placebo treatments were matched.

Random allocation can reduce systematic differences between treatment groups at the time of assignment, while masking is intended to reduce the influence of treatment knowledge on care or assessment. These are general design principles; the registry record does not describe the allocation sequence, concealment procedures, masking checks, or the roles of masked staff. It also does not report a planned sample-size justification, allocation ratio, or statistical analysis plan.

The primary outcome is change from baseline to Week 8 end of treatment in GAGS score. It is reported as a least-squares mean with a 95% confidence interval for each group. The registry identifies the primary analysis population as the Full Analysis Set, using Last Observation Carried Forward. The definition of that set, the handling of participants who discontinued, and the treatment of missing observations are not reported in the registry record.

The registry lists 6 outcome measures, including 3 secondary outcomes, and 2 analyses. It does not provide detailed results for the secondary outcomes in the information recorded. The design and analysis details therefore support a focused description of the posted primary outcome, but they do not allow a complete reconstruction of how the trial was conducted or how every outcome was analyzed.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set, Last Observation Carried Forward (LOCF)

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 Change From Baseline to End of Treatment in Global Acne Grading System (GAGS) Score, measured over Baseline, Week 8 End of Treatment (EOT).

The primary endpoint is change from baseline to Week 8 end of treatment in the Global Acne Grading System score. GAGS assesses 6 locations on the face, chest, and upper back. Each location is graded separately from 0 to 4, with a factor for each location based on surface area, distribution, and density of pilosebaceous units. The global score is based on summing the factored local scores.

Change is defined as the score at an observation minus the score at baseline. Consequently, a negative change indicates that the observed score was lower than the baseline score. The posted arm estimates are negative in both groups. This is a description of the direction of the score change, not by itself a conclusion about the comparative effect of the treatments or its clinical importance.

A standardized grading system can provide a structured way to track acne severity across assessed body locations and over time. That general role helps explain why a score change is used as an endpoint: it expresses how the measured score moved during the treatment period. The registry does not report a threshold for a clinically important change, a validation discussion, or a rationale for selecting Week 8 as the assessment time.

The primary analysis population is the Full Analysis Set with LOCF. Least-squares means are adjusted model-based estimates in general, but the model and included covariates are not reported in the registry record. The posted confidence intervals therefore describe the precision indicated by the registry, while the record does not provide enough detail to independently reproduce the model-based estimates.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Continuous outcomes are measurements that can take values along a scale, such as a score. GAGS is treated as a continuous measure in the registry’s primary outcome analysis. A mean summarizes the average score change in a group, while a mean difference summarizes a contrast between groups. These are general statistical descriptions; the registry reports the arm results as least-squares means and the comparison as a mean difference in final values.

What does a least-squares mean represent?

A least-squares mean is generally an estimate from a statistical model rather than a simple arithmetic average. Depending on the model, it can represent a group mean adjusted for other terms included in the analysis. The registry record does not identify the model, its covariates, or the estimation details, so the specific adjustments behind these least-squares means are not reported. The estimates should be read as the registry’s model-based arm results, not as independently reconstructable raw averages.

How should the confidence intervals be read?

A confidence interval expresses statistical uncertainty around an estimate under the assumptions of the analysis. A narrower interval indicates greater precision, while a wider interval indicates less precision. For the arm estimates, the intervals describe uncertainty around the estimated mean change. For the between-group estimate, the interval describes uncertainty around the estimated contrast. These intervals do not show the full range of individual responses and do not guarantee that the true value lies within a particular interval.

The reported 95% confidence interval for the between-group estimate extends from -2.48 to 1.54. Since it includes 0, the data are compatible with no difference as well as with differences in either direction on the analyzed scale. The interval should be considered together with the endpoint definition, analysis population, and any prespecified decision threshold. No non-inferiority margin is reported, and the record does not state a p-value for this comparison.

What is the endpoint-label issue?

The registered primary endpoint is change from baseline to Week 8 end of treatment. The comparison is labeled a mean difference in final values. Final values and changes from baseline are different quantities unless a specific analysis makes them equivalent for the purpose at hand. The record does not explain the relationship between the label on the comparison and the change endpoint, nor does it specify the model used to obtain the comparison. This limits how confidently the contrast can be interpreted as the registered primary comparison.

What does non-inferiority or equivalence require?

In general, a non-inferiority analysis asks whether the data exclude a disadvantage larger than a prespecified margin. An equivalence analysis asks whether the data are sufficiently compatible with differences confined within prespecified margins on both sides. The margin is essential: an estimate near 0 does not demonstrate either conclusion without a decision rule and an appropriate confidence interval. The registry classifies the posted analysis as non-inferiority or equivalence, but the margin, decision rule, and detailed method are not reported in the registry record. The classification alone cannot show that a criterion was satisfied.

Why can over-dispersion matter?

General statistical explanation: over-dispersion occurs when outcome variability is greater than a model assumes. When a method underestimates variability, standard errors can be too small and confidence intervals can be too narrow; methods that account for extra variability may produce more appropriate uncertainty estimates. This is a general consideration, not a finding about this trial. The registry record does not report a dispersion estimate or identify a method for assessing or addressing over-dispersion. The primary outcome is a score analyzed using least-squares means, and the model details needed to assess its variance assumptions are not available.

What can planning calculations tell a reader?

Sample-size calculations are planning illustrations based on assumptions about a future study, not observed power for a completed trial. The registry’s planning description specifies a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect defined as a stated fraction of the observed effect. Such illustrations depend on their assumptions and should not be read as evidence that the trial had a particular probability of detecting an effect. They do not replace a prespecified sample-size justification or a complete analysis plan, neither of which is reported in the registry record.

Why is the analysis population important?

The registry identifies the primary population as the Full Analysis Set with Last Observation Carried Forward. In general, LOCF carries the last available measurement forward when a later measurement is missing. This approach can preserve a value for analysis, but it relies on an assumption about the unobserved measurement and can affect estimates if the assumed value does not reflect what would have been observed. The record does not describe the missingness pattern, the number of observations carried forward, or sensitivity analyses using alternative assumptions.

The record also does not define the Full Analysis Set or describe how participants were handled if they did not follow the assigned regimen. Without those details, it is difficult to assess how closely the analyzed population corresponds to all randomized participants or to understand the impact of missing outcome data. These limitations apply to interpretation of the posted estimate, not just to attempts to reproduce it.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s between-group analysis as a mean difference in final values of -0.47, with a 95% confidence interval from -2.48 to 1.54. The analysis is categorized as non-inferiority or equivalence. The registry record does not provide a p-value, the non-inferiority or equivalence margin, the method used, or the decision rule. It also does not clarify how the final-value comparison relates to the registered primary endpoint of change from baseline.

The arm-level least-squares mean changes and their confidence intervals are posted separately. A simple unadjusted recalculation from summary statistics is not a substitute for the sponsor’s own analysis, which may use a model or other details not represented by the arm summaries. The record does not supply enough analysis detail to verify that the reported comparison can be reproduced from those summaries alone. No discrepancy is flagged in the registry record, but that does not resolve the endpoint-label and model-detail gaps.

The sponsor’s result should therefore be read as the posted comparison, not as a demonstrated non-inferiority or equivalence conclusion. Such a conclusion requires the prespecified margin and analysis criteria, which are not reported in the registry record. The interval includes 0, but that observation alone cannot determine whether a margin-based criterion was met.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 3 secondary outcomes: change from baseline in GAGS score, improvement of GAGS score, and change from baseline in acne graded by the Leeds Technique. It records 6 outcome measures and 2 analyses, but the record does not provide the detailed secondary results or describe how they were analyzed. The available information is therefore centered on the posted primary result, and it does not permit a full review of the outcome set.

When a study evaluates several outcomes or makes several comparisons, the chance of at least one apparently unusual result can increase. General statistical practice may address this through prespecification, adjustment, or a clear distinction between primary and exploratory analyses. The registry record does not report a multiplicity strategy, a hierarchy among the outcomes, or how the analyses relate to the listed outcomes. It would be inappropriate to assume that an adjustment was or was not performed.

The primary analysis population is identified as the Full Analysis Set with LOCF. The record does not define the population, state how many participants contributed outcome data, describe reasons for missing observations, or report the amount of missingness by group. It does not identify whether other populations were analyzed or provide sensitivity analyses for missing data. LOCF is an analysis choice, but without information about the pattern and handling of missing observations, its influence on the result cannot be assessed.

The registry status is terminated, but the record does not explain the reason or whether termination altered planned follow-up or analysis. The statistical plan, including any interim analyses, is not reported in the registry record. These omissions make it difficult to judge whether the posted analyses reflect a complete prespecified analysis strategy. They do not prove that the analyses were incomplete or changed; they mark issues that the record leaves unresolved.

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.

Most frequent non-serious adverse event terms

The registry reports serious adverse events affecting 0 participants in the azithromycin group, with 58 at risk, and 0 participants in the minocycline group, with 60 at risk. These are the figures recorded for serious adverse events. The record does not list serious adverse event terms, and deaths are not reported in the registry record.

The registry also records other adverse events affecting 29 participants in the azithromycin group and 21 in the minocycline group. The corresponding numbers at risk for these other events are not reported in the registry record. Without those denominators, the counts cannot be interpreted as comparative rates. The record does not provide event terms, severity, timing, relatedness, or the method used to collect these events in the information summarized.

Zero reported serious adverse events does not mean that no adverse events of any kind occurred: other adverse events are recorded for both groups. Nor does the serious-event count establish that there was no risk. These figures describe what the registry reports for the trial; they do not by themselves determine the safety profile of either treatment or support medical advice.

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

The posted results describe GAGS score changes through Week 8 for the two treatment groups. Both arm-level least-squares mean changes are negative, and the registry’s reported between-group estimate is -0.47 with a 95% confidence interval from -2.48 to 1.54. That interval includes 0, so it does not isolate a single direction of difference between the groups. Its span also indicates uncertainty about the size of the comparative estimate.

This is not enough to conclude that the treatments are equivalent or that one is non-inferior to the other. Those claims depend on a prespecified margin and a suitable analysis, and the registry record does not report the margin or decision rule. The posted analysis is labeled as a mean difference in final values, whereas the registered primary endpoint is change from baseline. The record does not explain how those quantities are connected in the reported comparison.

The result is also specific to the registered outcome, time point, analysis population, and method recorded. The primary analysis uses the Full Analysis Set with LOCF, but the record does not define that set or report missing-data details. There is no basis in the record to infer that the posted estimate represents every randomized participant under every possible analysis approach.

The registry does not report detailed results for the listed secondary outcomes, a complete statistical plan, or the reason for trial termination. The primary result should be interpreted alongside these gaps rather than as a complete account of all trial findings. The safety counts likewise have limits: serious adverse event counts are recorded, but other adverse event denominators and event details are absent.

More generally, a trial estimate is not a guarantee of an individual outcome and should not be treated as treatment advice. The evidence described by the registry is a comparison of group-level score measurements under the recorded analysis. It does not establish the clinical importance of the score change, explain the trial’s termination, or resolve questions that depend on information not reported in the registry record.

14. Why This Trial Matters Statistically

This trial is statistically informative because its registry record places a group-level estimate beside arm-level changes and confidence intervals. Those measures answer different questions: the arm estimates describe average score changes within each group, while the between-group estimate describes a contrast. Keeping those quantities distinct helps prevent an observed change in both groups from being mistaken for a clear comparative effect.

The record also illustrates why a non-inferiority or equivalence label is not a conclusion by itself. A margin and a decision rule are essential to interpreting such analyses. Without them, readers cannot tell from the posted interval whether the analysis met the intended criterion. The interval’s inclusion of 0 is relevant to uncertainty about a difference, but it does not replace a margin-based assessment.

A second statistical issue is alignment between the registered endpoint and the reported comparison. The primary outcome is defined as change from baseline, while the comparison is labeled as a mean difference in final values. Clear reporting of the target estimand, model, and endpoint helps readers understand what a contrast means and whether it answers the stated primary question.

Finally, the Full Analysis Set with LOCF, the terminated status, and limited reporting on multiplicity and missing data shape how confidently the result can be interpreted. These are not reasons to dismiss the estimate; they identify the boundaries of what can be learned from the record. A precise account of those boundaries is part of sound statistical interpretation.

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 registry record does not report why the trial was terminated or whether termination affected the planned enrollment, follow-up, or analyses. Enrollment is recorded as 118, while the posted primary outcome arm estimates list 53 for azithromycin and 59 for minocycline. The record does not explain the relationship between those figures or provide a participant flow account, so the reasons for the difference are not reported in the registry record.

The primary analysis population is called the Full Analysis Set, but its definition is absent. The record does not describe exclusions after randomization, adherence, discontinuations, missing outcome measurements, or how many values were carried forward using LOCF. Consequently, the influence of the analysis population and missing-data approach cannot be fully evaluated.

The comparison is labeled a mean difference in final values, while the primary endpoint is change from baseline. Model details, covariates, baseline handling, and the connection between the comparison and the primary endpoint are not reported in the registry record. The sponsor’s analysis is also classified as non-inferiority or equivalence, but its margin and decision criteria are absent. These omissions prevent a full assessment of the comparative claim.

The registry lists secondary outcomes but does not provide detailed results for them in the record. A multiplicity plan, full statistical analysis plan, sample-size justification, and interim-analysis details are not reported in the registry record. There is also limited safety detail: serious event counts are recorded, but serious event terms and deaths are not reported; denominators and event descriptions for other adverse events are not reported.

These limitations concern the amount of information available in the registry record. They do not establish that procedures were absent from the trial itself, and they do not determine what additional documentation may exist elsewhere. They do restrict what can be verified from the recorded results.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Efficacy And Safety Of Azithromycin SR Compared With Minocycline In Acne — NCT00392223.
• Registry record last updated 2010-01-12; status last verified 2010-01.
• Results first posted 2009-08-03.
• 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.

19. Record Summary

The registry describes a randomized, double-blind, double-dummy, parallel-group Phase III trial comparing azithromycin microspheres with minocycline in outpatients with moderate to severe inflammatory acne. The registered primary endpoint is change from baseline to Week 8 end of treatment in GAGS score. The primary analysis population is the Full Analysis Set with LOCF.

The posted least-squares mean changes are -8.69 for azithromycin and -9.16 for minocycline. The reported mean difference in final values is -0.47, with a 95% confidence interval from -2.48 to 1.54. The record does not report the non-inferiority or equivalence margin, a p-value, or the model details, and it does not explain the difference between the endpoint and comparison labels.

The registry status is terminated. Its reason is not reported in the registry record. Detailed secondary outcome results, missing-data information, and fuller safety details are also not reported in the registry record.