Combination Therapy for Atopic Dermatitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Combination Therapy for Atopic Dermatitis (NCT00119158), a randomized phase 4 study. The primary outcome is Change From Baseline in the m-EASI (Eczema Area Severity Index) Score..

2. Clinical Question

3. Trial Design

The registry describes a completed, randomized, double-blind, phase 4 trial with parallel groups. Enrollment was 90, with 45.0 participants listed in each primary-results arm. The record gives a start of 2004-10 and primary completion of 2005-06. These dates describe the registry timeline, not the timing of each participant’s treatment or follow-up.

The official title calls the study exploratory and paired, whereas the registered model is parallel and the posted results list two arms. The record does not explain this difference. It also does not clearly reconcile the trial’s stated combination-therapy hypothesis with the intervention and arm descriptions: the intervention list names a pimecrolimus–fluticasone combination and pimecrolimus, while the arm descriptions name placebo cream and pimecrolimus cream. The labels in the primary outcome results are Active Therapy and Placebo Arm. Those differences limit how specifically the treatment contrast can be described.

The trial summary says the hypothesis was that combination treatment would lead to faster clearance than topical corticosteroid treatment alone. That is the stated rationale, not a result. The registry lists time to clearance as a secondary outcome and change in m-EASI as the primary endpoint. It does not report the original sample-size justification, planned enrollment rationale, randomization details, allocation concealment, treatment duration, or the complete protocol. Those details are not reported in the registry record.

The primary endpoint population is described as per protocol, using last observation carried forward. A participant flow, exclusions from that analysis, and the count analyzed by arm are not reported in the registry record. The registry lists the trial status as completed.

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: Patients are self controls. Equivalent areas of eczema were compared

Active Treatment

Placebo Treatment

Analysis population for the primary outcome, as defined in the registry: Analysis was per protocol, last observation carried forward

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 in the m-EASI (Eczema Area Severity Index) Score., measured over up to 15 days.

The primary endpoint is change from baseline in the m-EASI score, reported in units of a 0-12 scale and assessed up to 15 days. The registry describes EASI as a composite based on the area of eczema involved and four atopic dermatitis symptoms: erythema, infiltration or population, excoriation, and lichenification. Symptom scores range from 0, mild, to 3, severe; the listed total score ranges from 0-12.

A change score represents the difference between a follow-up measurement and a baseline measurement, but the registry record does not specify whether positive values indicate improvement or worsening. That convention matters for interpreting the direction of the reported arm means. The posted means are 5.04 for Active Therapy and 4.77 for Placebo Arm, but without the sign convention and baseline detail, those values alone do not establish which arm had a more favorable change.

In general, a symptom-and-area composite can summarize several aspects of disease severity in a single outcome. It is used as the primary measure, while clearance time and other target-area assessments are listed as secondary outcomes. The registry does not give further detail about how the m-EASI components were combined, how assessors were trained, or whether the measure was evaluated at every visit.

7. Results Posted in the Registry

• Active Therapy: mean 5.04 versus 4.77 on control; difference 0.27 (95% CI -0.79 to 1.33), standardized effect d = 0.11; z-test p = 0.616.

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.

The Time to Clearance of the Disease

• 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 errors.
• Result:
  • Active Therapy: mean 9.22 versus 7.88 on control; difference 1.34 (95% CI -10.31 to 12.99), standardized effect d = 0.05; z-test p = 0.822.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Active Therapy and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes cover several related dimensions: time to clearance, time to reach a low m-EASI score, target-area global assessment thresholds, improvement in target-area global assessment, target-area m-EASI thresholds, and patient self-assessment. The registry states that seven outcome measures were recorded, while six secondary outcomes are posted. Results are available for time to clearance; results for the other listed secondary outcomes are not reported in the registry record.

The recalculated time-to-clearance comparison has a mean difference of 1.34 days, an interval from -10.31 to 12.99, and p = 0.822. That estimate is uncertain and the interval includes zero. Its direction also cannot be translated into a clinical interpretation without the record’s definition of the contrast and further outcome details. The secondary outcome does not provide an independent resolution of the primary result.

In general, secondary endpoints can add context by measuring different aspects of the condition or assessing a primary finding through related outcomes. Their meaning depends on their definitions, timing, analysis population, and prespecified status. The posted outcome list includes measures assessed over different periods, but detailed results and analysis methods are incomplete.

Unadjusted secondary results generally carry less weight than a clearly specified primary analysis because testing many outcomes creates more opportunities for chance findings. In general, multiplicity procedures can control the increased risk of false-positive conclusions across several tests. The registry does not report whether any adjustment was planned or used. The secondary analyses should therefore be read as exploratory unless the protocol establishes otherwise; a multiplicity plan is not reported in the registry record.

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

• The Time to Clearance of the Disease
• The Time to the First Day When m-EASI is Scored by the Investigator as 2 or Less
• The Percentage of Target Areas Reaching a l-IGA (Localized Investigator Global Assessment (l-IGA) or 0 or 1)
• The Percentage of Target Areas Improved (i.e., Decrease in Localized Investigator Global Assessmet (l-IGA) Score From Baseline)
• The Percentage of Target Areas Reaching a m-EASI (Modifed-Eczema Area Severity Index) Score of 2 or Less
• Change From Baseline in Patients' Self Assessment of Disease Severity (PSA) of Target Areas

9. Statistical Interpretation

10. Statistical Methods Explained

What does the mean difference describe?

The endpoint is continuous: each participant has a score change measured in units of the m-EASI scale. A mean summarizes the average score change among participants in an arm. The posted arm means are 5.04 for Active Therapy and 4.77 for Placebo Arm. The unadjusted recalculation compares those means and reports a mean difference of 0.27. In general, a mean difference expresses the contrast between two group averages in the original measurement units. It does not show the range of individual participant responses or how many participants improved.

The registry does not state the sign convention for the change score. Thus, the arithmetic direction of the difference is known, but whether that direction represents greater improvement cannot be inferred from the record alone. The record also does not post baseline and follow-up means separately.

What does an unadjusted recalculation mean?

The recalculated comparison uses posted summary statistics for the two arms rather than participant-level observations or a model adjusted for other variables. It is therefore a simple, unadjusted comparison. The reported estimate is 0.27, with p = 0.616. The recalculated interval crosses zero. In general, zero is the no-difference value for a mean difference, so an interval that crosses zero is compatible with both directions of contrast at the interval’s stated confidence level. The confidence level for this recalculated interval is not reported in the registry record.

Unadjusted summary-statistic calculations can be useful as a check on the scale and broad uncertainty of a contrast. They cannot reproduce a participant-level analysis that may account for paired observations, covariates, repeated measurements, protocol rules, or a particular missing-data method. The record’s title refers to a paired study, but its model is listed as parallel; it does not state whether the posted means or sponsor analysis account for pairing. The recalculation should not be treated as a reconstruction of the sponsor’s full analysis.

How should the p-value be read?

In general, a p-value measures how incompatible the observed data are with a specified statistical model in which the tested difference is zero. It is not the probability that the null hypothesis is true, nor does it quantify clinical importance. The recalculated p-value is 0.616. On its own, that value does not show that the arms are identical or that any particular effect is absent. It must be read alongside the estimate, uncertainty, outcome definition, and analysis plan.

The registry also reports a sponsor two-sided t-test with p <0.05, classified as a non-inferiority or equivalence analysis. It supplies no estimate, interval, test margin, or clear account of the contrast for that result. A conventional difference test and a non-inferiority or equivalence test answer different questions. In general, the latter depends on a prespecified margin describing what difference would be considered acceptably small. That margin and the sponsor’s full analysis are not reported in the registry record. Since the record marks a discrepancy, the sponsor’s own analysis takes precedence over the recalculation.

Why does the analysis population matter?

The primary endpoint population is described as per protocol with last observation carried forward. In general, a per-protocol analysis includes participants who meet specified protocol requirements; the registry does not state those requirements or how many participants qualified. Last observation carried forward assigns a participant’s last recorded value to later missing measurements. This method can make strong assumptions about what would have happened after the last observation, and its suitability depends on the context and reasons for missingness. The amount and pattern of missing data, the number carried forward, and any sensitivity analyses are not reported in the registry record.

The registry does not provide an intention-to-treat result, participant flow, or the number included in the primary analysis by arm. Those omissions make it difficult to assess whether the posted outcome summaries represent all randomized participants or a selected subset. They also limit comparison of the registry result with analyses that use a different population or missing-data approach.

What does dispersion tell the reader?

In general, the standard deviation describes how much participant measurements vary around an arm mean. The primary arm standard deviations are 2.7 and 2.4. Variation among participants is distinct from uncertainty about the mean: the latter also depends on the amount of information in the analysis. The registry reports 45.0 participants per arm in the primary results, but the analysis population count is not separately stated.

The secondary time-to-clearance outcome is listed with standard errors of 4.5 and 3.88, rather than standard deviations. In general, a standard error describes uncertainty in an estimated mean, whereas a standard deviation describes variation among individual observations. The posted difference for that outcome is 1.34 days, with p = 0.822. The registry does not explain the apparent dispersion convention or give participant-level data, so that secondary calculation should be interpreted cautiously.

In general, over-dispersion occurs when observed variability exceeds what a statistical model assumes. It can make model-based standard errors too small if the model does not accommodate the extra variation, leading to intervals that are too narrow and tests that appear more decisive than warranted. The registry does not report a model for over-dispersion, and there is not enough information to assess whether it is relevant to these outcomes.

What can and cannot be inferred from the analysis?

The recalculation is informative as an unadjusted reading of posted arm summaries, but it cannot verify the sponsor’s analysis or resolve inconsistencies in the trial descriptions. The record does not report the detailed statistical plan, the sponsor’s effect estimate, the equivalence or non-inferiority margin, interim analyses, or multiplicity procedures. These elements should not be assumed. In general, a statistical result is best interpreted in light of the prespecified question, population, outcome, assumptions, and handling of missing data. Several of those details are not reported in the registry record.

11. Confidence Intervals and Precision

The recalculated primary mean difference is 0.27. Its interval extends below zero and above zero, so it includes the no-difference value. The lower endpoint is not repeated because the posted value has more than three decimal places. The interval is wide enough to accommodate contrasts in either direction, and the registry record does not specify the confidence level for this recalculated interval. The sponsor’s own analysis separately reports p <0.05, but no estimate or interval accompanies it.

In general, a confidence interval gives a range of effect estimates compatible with the data and the assumptions of the calculation at a stated confidence level. A narrow interval indicates greater precision; a wide interval indicates less precision. An interval that includes zero does not prove equivalence, and an interval that excludes zero does not by itself establish clinical importance. The width and location of an interval matter alongside the endpoint’s meaning and the analysis plan.

The secondary time-to-clearance recalculation gives a mean difference of 1.34 days and an interval from -10.31 to 12.99. This interval includes zero and is broad relative to the estimate. The associated p-value is 0.822. The registry labels the arm dispersion as standard error for this outcome, but the recalculated comparison’s assumptions and confidence level are not described in the record.

Precision is limited by the reported amount of information and by missing analysis details. The registry lists 45.0 participants in each primary-results arm, but does not report the number analyzed per arm, missingness, or exclusions. The sponsor’s estimate and interval are also unavailable. Consequently, the recalculated interval should be read as an unadjusted summary-based measure of uncertainty, not as a substitute for the sponsor’s complete statistical analysis.

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 sample-size illustrations are planning calculations based on the observed effect, not the trial’s original design assumptions. For this continuous outcome, the displayed figures mean participants per arm, not a total number of events. The stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect defined as the stated fraction of the observed effect. The trial’s own original sample-size justification and design assumptions are not reported in the registry record.

The 80% power column gives the number of participants per arm that the illustration estimates would be needed for an 80% chance of detecting the specified effect under those planning assumptions. The 90% power column gives the corresponding number for a 90% chance. In general, power is the probability of detecting an effect of a specified size if that effect is present and the assumptions hold. These are planning illustrations, not observed power.

The rows consider planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. For example, planning for 100% of the observed effect gives 1,406 participants per arm for 80% power and 1,881 participants per arm for 90% power. Planning for 75% gives 2,498 and 3,344 participants per arm, respectively; planning for 50% gives 5,621 and 7,524. Smaller effects need more participants to detect, all else being equal.

These values are not a recommendation for a future study and do not establish that the trial was underpowered. They depend on the observed estimate, which is uncertain, and on assumptions that may not match the original protocol. Because the sponsor analysis and the recalculation differ, the illustrations should not be taken as a reconstruction of the sponsor’s planning process.

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 = 0.270; pooled standard deviation σ = 2.554.
2. n = 2 × (1.96 + 0.842)² × 2.554² / 0.270² = 1,405.0, rounded up to 1,406 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 <- 0.27                      # observed difference in means
sigma <- 2.55440795488896                     # 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(119158)
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 = 1,406 (80% power), 1,881 (90% power)
 75% of observed effect: n per arm = 2,498 (80% power), 3,344 (90% power)
 50% of observed effect: n per arm = 5,621 (80% power), 7,524 (90% power)
power.t.test: 1406 
Simulated power at n = 1,406 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 sponsor analysis is reported as a two-sided t-test for the Active Therapy group, with p <0.05, and is categorized as non-inferiority or equivalence. The record does not provide the sponsor’s effect estimate, confidence interval, test margin, or enough detail to determine precisely what comparison that test represents. A p-value alone does not show the size or direction of a treatment contrast.

The unadjusted recalculation compares the posted means of 5.04 and 4.77 and gives a mean difference of 0.27, with p = 0.616. This differs from the sponsor’s reported result. The recalculation uses posted summary statistics and does not recreate an analysis that might use participant-level data, pairing, protocol criteria, or other design features. The registry record itself marks the results as discrepant.

For that reason, the sponsor’s own analysis takes precedence. The recalculated result can still help readers understand the posted arm summaries and their apparent uncertainty, but it cannot be used to overrule or validate the sponsor’s analysis. Without the sponsor’s full estimate, interval, margin, and methods, the source of the discrepancy is not reported in the registry record.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary endpoint and lists multiple secondary outcomes, but the full statistical analysis plan is not reported in the registry record. In particular, it does not state whether testing of secondary outcomes was adjusted for multiplicity, whether outcomes were ordered in a testing hierarchy, or whether any secondary analysis was intended to be confirmatory. In general, when several hypotheses are tested, the chance of at least one apparently significant result can increase. Adjustment or a prespecified testing sequence can address that issue, but neither should be assumed.

Only one analysis is listed in the registry’s reported analyses, and its result is described as a two-sided t-test with p <0.05 for the Active Therapy group. The record does not supply a full set of sponsor analyses or explain how that test relates to the posted arm summaries. The unadjusted recalculation is not a substitute for a prespecified multiplicity strategy.

The primary analysis is described as per protocol with last observation carried forward. The registry does not report the criteria for inclusion in the per-protocol population, the number analyzed in each arm, the amount or reasons for missing data, or sensitivity analyses. In general, last observation carried forward assumes that the last recorded value is an adequate stand-in for later unobserved outcomes. This may not reflect the true course after withdrawal or missed visits. The record does not provide enough information to evaluate that assumption.

An intention-to-treat analysis, participant flow, and handling of missing data for secondary outcomes are not reported in the registry record. Nor does the record explain whether results were adjusted for baseline scores, repeated measurements, or the apparent paired-study wording in the official title. These gaps prevent a full assessment of the analysis population, missing-data bias, and consistency between the planned and reported methods.

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 5% reporting threshold.

The posted safety counts list 45 participants at risk for serious adverse events in each arm. The registry reports zero serious adverse events affecting participants in Active Therapy and zero in Placebo Arm. These are counts for the recorded study groups; they do not by themselves establish that no event occurred outside the recorded period or under a different event definition.

The registry also lists zero participants with other adverse events in each arm, with 45 participants at risk in each. Death counts are not reported in the registry record. The record does not provide serious-event terms, event definitions, follow-up duration for safety, or detail on how events were collected. The absence of a listed event in these counts should therefore be interpreted as a feature of the posted safety record, not as proof that an event is impossible or that risk is absent.

In general, safety counts are interpreted with attention to the number exposed, duration of observation, event definitions, and completeness of reporting. With the available counts alone, no comparative safety rate or broader conclusion should be inferred.

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

The posted primary results show arm means of 5.04 and 4.77 for change from baseline in m-EASI, with a recalculated unadjusted mean difference of 0.27 and p = 0.616. The associated interval extends across zero. These summaries indicate that the recalculation does not give a clear between-arm difference, while also leaving uncertainty about effects in either direction. They do not demonstrate that the arms are equivalent.

The score change’s sign convention is not stated, so the numerical direction cannot be translated confidently into greater or lesser severity. The record’s stated hypothesis concerns faster clearance with combination therapy, but the posted primary measure is change in m-EASI. The available outcome summaries do not establish that one regimen caused faster clearance or a particular improvement.

The sponsor’s own reported analysis differs from the recalculation and is not reported with an estimate, interval, or non-inferiority or equivalence margin. The sponsor’s analysis takes precedence, but the registry record lacks the detail needed to evaluate its result independently. The recalculation is a limited check based on group-level summaries, not a definitive adjudication of the discrepancy.

General statistical interpretation distinguishes absence of clear evidence from evidence of no meaningful effect. A study can produce an uncertain estimate because of limited information or variability. Demonstrating equivalence requires an appropriate margin and a suitable analysis, neither of which is available in the record. Likewise, a non-significant unadjusted comparison is not proof that outcomes are the same.

The trial record also has limitations in endpoint reporting, analysis-population detail, missing-data methods, multiplicity, and treatment-arm descriptions. Those gaps matter to the interpretation of both efficacy and safety. The appropriate conclusion is bounded: the posted summaries permit a basic, unadjusted comparison, but they do not support a complete reconstruction of the study’s intended or sponsor-reported analysis.

18. Why This Trial Matters Statistically

This trial is statistically interesting because its registry record contains both a posted two-arm summary and a separate sponsor analysis that do not align. The recalculation from arm-level results yields a mean difference of 0.27 and p = 0.616, while the sponsor analysis reports p <0.05. When estimates and tests differ, readers need the analysis definition, estimand, population, and assumptions before treating the results as comparable. Those details are incomplete.

The record also illustrates why labels such as randomized, double-blind, and exploratory do not by themselves resolve questions about analysis. The official title describes a paired study, the registered model is parallel, and the intervention and arm descriptions do not fully correspond. These are not small statistical details: the structure of the comparison determines which uncertainty calculation and interpretation are appropriate. The registry does not explain the inconsistency.

There is also a useful distinction between a non-significant difference test and an equivalence or non-inferiority conclusion. The sponsor analysis is classified as non-inferiority or equivalence, but the margin and effect estimate are not posted. The recalculation cannot supply those missing elements. A claim about similarity requires more than a failure to find a difference.

Finally, the record links a per-protocol, last-observation-carried-forward primary analysis to a set of secondary outcomes, yet gives limited information about missingness and multiplicity. These omissions show how analysis populations, outcome selection, and reporting completeness shape the strength of statistical conclusions. The numerical results are only part of the evidence needed to understand a trial.

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.

Several limitations are specific to the available record. First, the treatment descriptions are not fully aligned. The trial summary describes a combination-versus-single-agent hypothesis, the intervention list names a pimecrolimus–fluticasone combination and pimecrolimus, and the arm descriptions list placebo cream and pimecrolimus cream. The primary results instead label the groups Active Therapy and Placebo Arm. The exact regimens and contrast cannot be reconstructed confidently.

Second, the official title refers to a paired study, but the registered model is parallel and the results are organized into two arms. The record does not explain whether pairing influenced randomization, measurement, or analysis. That uncertainty limits interpretation of the recalculated standard error and comparison.

Third, the primary analysis is per protocol with last observation carried forward, but the number analyzed, reasons for exclusions, extent of missingness, and sensitivity analyses are not reported. The baseline and follow-up score summaries and the direction convention for change are also absent. The registry lists a 0-12 scale, but gives no further detail on assessment timing within the primary timeframe.

Fourth, the sponsor’s p-value is not accompanied by an effect estimate, interval, or non-inferiority/equivalence margin. The registry marks a discrepancy with the summary-based recalculation but does not explain it. Secondary outcome results are incomplete: six are posted while seven outcome measures are listed, and most secondary results are not reported. The multiplicity approach and original sample-size justification are not reported in the registry record.

Finally, safety reporting is limited to group counts. Event definitions, collection details, and deaths are not reported. These record-level limitations do not establish that the methods were inadequate; they limit what can be verified from the registry entry.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Combination Therapy for Atopic Dermatitis — NCT00119158.
• Registry record last updated 2010-07-27; status last verified 2010-07.
• Results first posted 2010-07-22.
• 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

The registry record describes a completed, randomized, double-blind, phase 4 trial with 90 participants and a parallel model. The primary endpoint was change from baseline in m-EASI, assessed up to 15 days, with a per-protocol population and last observation carried forward. The posted arm means were 5.04 for Active Therapy and 4.77 for Placebo Arm.

The unadjusted recalculation gives a mean difference of 0.27 and p = 0.616, with an interval that includes zero. The sponsor’s reported two-sided test gives p <0.05 but lacks an estimate, interval, and stated margin; the registry marks a discrepancy, so the sponsor’s own analysis takes precedence. Treatment descriptions, analysis populations, missing-data detail, and multiplicity procedures remain unclear or unreported. Serious adverse events and other adverse events are listed as zero in both groups, while deaths are not reported in the registry record.