A Study to Assess the Efficacy and Safety of XP23829 in Subjects With Moderate-to-Severe Chronic Plaque-Type Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Assess the Efficacy and Safety of XP23829 in Subjects With Moderate-to-Severe Chronic Plaque-Type Psoriasis (NCT02173301), a randomized phase 2 study. The primary outcome is • The Percent Change in PASI (Psoriasis Area and Severity Index) Score From Baseline.

2. Clinical Question

The registry describes a Phase 2 study of XP23829 in subjects with moderate-to-severe chronic plaque-type psoriasis. The primary endpoint was the percent change in Psoriasis Area and Severity Index (PASI) score from baseline at 12 weeks. PASI combines ratings of lesion redness, thickness, and scaliness with the area of involvement. A more negative percentage change represents a larger reduction in the score from baseline; the registry describes a lower score at the end of the study as improvement in the measured condition.

The posted primary results give a least-squares mean for each arm, with standard errors, rather than individual participant results. Comparisons with placebo are available for all three regimens. The registry also lists two secondary outcomes: the proportion achieving PASI-75 and the proportion with a Static Physician’s Global Assessment score of clear or almost clear. Numerical results for those secondary outcomes are not included in the registry record presented for this analysis, so their findings are not reported in the registry record available for this account.

The clinical question is therefore about the difference in the measured PASI change between each XP23829 regimen and placebo at the stated endpoint time. It is not, by itself, a complete account of safety, durability, or other outcomes. The registry’s summary also names safety, tolerability, and pharmacodynamic assessment as study objectives; the posted primary endpoint results address only the PASI measure.

3. Trial Design

The registry characterizes this as a Phase 2, randomized, double-blind, multicenter, parallel-group, placebo-controlled study. The listed enrollment is 200. The study is marked completed. Its stated objectives were to evaluate the efficacy of three XP23829 doses compared with placebo, assess safety and tolerability, and assess pharmacodynamics through immunological analysis of peripheral blood samples.

There were four arms: XP23829 400 mg once daily, XP23829 800 mg once daily, XP23829 400 mg twice daily, and placebo. The arm descriptions state that eligible subjects entered a 12-week treatment period after a 4-week screening period. The XP23829 treatment descriptions include a titration period within those 12 weeks; the placebo description specifies 12 weeks of placebo. The record identifies the overall design as double-blind but does not report further details about the blinding procedures.

The primary endpoint analysis population is described as the modified Intent-to-Treat population, using observed cases. The posted arm-level counts for the primary analysis are 48 for 400 mg once daily, 53 for 800 mg once daily, 46 for 400 mg twice daily, and 47 for placebo. These arm-level analysis counts should not be treated as a replacement for the overall enrollment figure: they refer to the stated primary analysis, while the registry lists enrollment separately.

The registry gives sponsor-reported mixed models analyses comparing each XP23829 arm with placebo. It does not report the full model specification, the randomization procedure, allocation ratios, details of concealment, or the original sample-size justification in the registry record. The record also does not report whether there were interim analyses. Those omissions limit what can be said about design choices and analysis procedures beyond the information explicitly stated.

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: modified Intent-to-Treat population Observed cases analysis

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as • The Percent Change in PASI (Psoriasis Area and Severity Index) Score From Baseline, measured over 12 Weeks.

The primary endpoint was percent change in PASI score from baseline at 12 weeks. PASI is a continuous measure of psoriasis severity that combines ratings of lesion redness, thickness, and scaliness with the area of involvement. Each of the three lesion features is graded on a 0–4 scale, and the resulting score is weighted by affected area. The registry describes the scale as ranging from 0 to 72, with lower scores at the end of the study indicating improvement in the measured condition.

Using percentage change expresses the endpoint relative to the participant’s baseline score rather than only reporting an endpoint score. In general, a continuous outcome can retain information across its range, rather than reducing each person’s result to a yes-or-no category. That can make it useful for comparing the average degree of change between randomized groups. This general explanation does not establish how the trial selected or justified PASI as its primary endpoint; that rationale is not reported in the registry record.

The registry reports least-squares means for the primary endpoint, with standard errors, for a modified Intent-to-Treat population using observed cases. The negative arm means indicate decreases from baseline in the analyzed groups. Those group averages do not describe every participant’s result, and they do not by themselves establish how outcomes were distributed within an arm. PASI-75 and static global assessment are listed as secondary outcomes, but numerical findings for them are not reported in the registry record available for this account.

7. Results Posted in the Registry

• XP23829 400 mg QD (Once Daily): mean -38.10 versus -25.00 on control; difference -13.10 (95% CI -27.14 to 0.94), standardized effect d = -0.38; z-test p = 0.067.
• XP23829 800 mg QD (Once Daily): mean -48.20 versus -25.00 on control; difference -23.20 (95% CI -37.23 to -9.17), standardized effect d = -0.65; z-test p = 0.001.
• XP23829 400 mg BID (Twice Daily): mean -50.70 versus -25.00 on control; difference -25.70 (95% CI -40.35 to -11.05), standardized effect d = -0.71; z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

The registry reports least-squares means for a continuous endpoint and sponsor-reported mixed models analyses comparing each XP23829 regimen with placebo. The additional pairwise estimates described as recalculated are simple, unadjusted comparisons based on posted summary statistics. They should be read as a separate statistical view, not as a replacement for the sponsor’s model-based analysis. Because a discrepancy is flagged, the sponsor’s own analysis takes precedence for its comparison results.

What does a least-squares mean represent?

In general, a least-squares mean is a model-based estimate of a group mean. It may account for features of the analysis model rather than simply being the arithmetic average of the observed values. The registry gives the endpoint parameter as a least-squares mean and identifies the dispersion as a standard error. It does not report the model terms, covariates, covariance structure, estimation details, or whether the estimates were adjusted for baseline or other characteristics. Therefore the estimates can be described as reported, but the exact model-based interpretation cannot be reconstructed from the registry record.

The posted least-squares means are -38.1, -48.2, -50.7, and -25.0 for the 400 mg once-daily, 800 mg once-daily, 400 mg twice-daily, and placebo arms, respectively. A standard error describes the uncertainty in an estimated mean under the analysis used; it is not the spread of individual participant outcomes. The standard errors are 5.07, 5.06, 5.5, and 5.06 in that same arm order. They give information about precision of the arm estimates, but a standard error alone does not provide the full distribution of participant responses.

How do the recalculated comparisons work?

For each regimen, the simple recalculation contrasts its posted arm mean with the posted placebo mean. The estimates are -13.1 for 400 mg once daily, -23.2 for 800 mg once daily, and -25.7 for 400 mg twice daily. Negative differences correspond to a more negative mean percentage change in the XP23829 group than in placebo. These are unadjusted differences calculated from summary statistics and are not a reanalysis of individual participant data.

The recalculated confidence intervals use an approximate pooled standard deviation derived from the posted standard errors and sample sizes. The registry analysis includes an explicit indication that this standard deviation is approximate. Such a reconstruction relies on assumptions that may not match the sponsor’s mixed models analysis. The registry does not provide individual observations or the full model specification needed to reproduce that analysis. For this reason, the recalculated estimates and p-values are useful as an independent summary-statistic comparison, but they should not be presented as the trial’s primary inferential procedure.

In general, a confidence interval is a range of values compatible with the data and the assumptions of the method. An interval for a mean difference that includes zero does not rule out a difference in either direction, while an interval entirely below zero supports a negative difference under that method. These interval statements apply to the recalculated, unadjusted comparisons only. They are not a substitute for the sponsor’s reported mixed models p-values, and the registry does not give sponsor-reported confidence intervals for those comparisons.

Why can the analyses differ?

In general, model-based analyses can differ from simple comparisons because they may use the outcome data and study design in a different way. A mixed model may account for repeated measurements, correlations, or other model terms, depending on its specification. The registry identifies the method as mixed models analysis but does not report enough details to say which features were included or how they were handled. It would therefore be speculation to attribute the difference between the sponsor’s p-values and the recalculated values to a particular model choice.

The sponsor’s reported p-values are 0.066, 0.001, and <0.001 for the 400 mg once-daily, 800 mg once-daily, and 400 mg twice-daily comparisons, respectively. The corresponding recalculated p-values are 0.067, 0.001, and <0.001. The close numerical agreement in these entries does not make the methods identical; one set comes from the reported mixed models analyses and the other from simple unadjusted recalculations. The discrepancy flag means the sponsor’s own analysis should be treated as the primary reported analysis.

What does observed-cases analysis mean?

The primary population is described as modified Intent-to-Treat, with observed cases. In general, an observed-cases approach analyzes available outcome observations rather than filling in missing values through an imputation procedure. This can make results dependent on which participants have measurements at the relevant time and on why other measurements are absent. The registry does not report the number of missing outcomes, reasons for missingness, imputation methods, or sensitivity analyses. It is therefore not possible to determine from the record whether missing data could have changed the estimates or how the analysis addressed that possibility.

The term modified Intent-to-Treat is given, but the registry does not specify the exact modifications or eligibility rules for this population. The primary analysis counts are 48, 53, 46, and 47 across the three active regimens and placebo. They differ from the total enrollment figure of 200, and the registry’s population description does not provide a full participant-flow account that explains every difference between enrollment and analysis counts.

Why do dispersion and over-dispersion matter?

In general, dispersion describes how much participant outcomes vary around a group estimate. When data vary more than a statistical model expects, uncertainty can be understated if the model does not allow for that extra variation; this is often described as over-dispersion. For a continuous endpoint such as percentage change in PASI, the registry provides standard errors for the least-squares means and approximate pooled standard deviations for the recalculated comparisons. It does not report raw outcome variability, a formal over-dispersion assessment, or diagnostics for the sponsor’s model. Any claim that over-dispersion was or was not present would go beyond the registry record.

Finally, the registry does not report the original sample-size assumptions, the planned treatment effect used in the design, or the planned analysis framework in sufficient detail to reconstruct them. The separate planning illustrations use the observed effects and stated hypothetical assumptions. They are not evidence about the trial’s original design rationale and are not observed power calculations.

10. Confidence Intervals and Precision

The recalculated intervals quantify uncertainty around the unadjusted mean differences using the posted arm summaries and an approximate pooled standard deviation. For XP23829 400 mg once daily versus placebo, the estimate is -13.1 and the interval is -27.14 to 0.939. This range includes zero, so the recalculation does not pin down the direction of the difference with the same clarity as the other two intervals. It remains compatible with a more negative average change under XP23829 and with a value close to, or slightly on the other side of, no difference.

For 800 mg once daily, the estimate is -23.2 and the interval is -37.23 to -9.175. For 400 mg twice daily, the estimate is -25.7 and the interval is -40.35 to -11.05. Both intervals are below zero. Their widths also show that the exact magnitude is uncertain: the data are compatible with a range of negative differences, not a single fixed effect. The estimates should not be read as precise predictions for a future study or for an individual participant.

In general, confidence intervals reflect both the amount of information and the variability in the data, as well as the assumptions of the method used to construct them. Here, the recalculations use summary statistics and an approximate pooled standard deviation, while the sponsor’s analysis is identified as a mixed models analysis. The registry does not provide sponsor-reported confidence intervals for the comparisons. The intervals above therefore describe the recalculated comparisons and do not directly quantify uncertainty under the sponsor’s model.

Precision is also distinct from clinical importance. The registry record does not state a threshold for a clinically important PASI difference, so the intervals cannot be classified against such a threshold from the reported information. They also do not address multiplicity across the three comparisons. The sponsor-reported p-values and the recalculated intervals are best interpreted alongside the analysis population, endpoint definition, and missing-data limitations.

11. Planning a Similar Trial: Sample Size

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

The sample-size illustrations show how many participants per arm would be needed under stated planning assumptions for different fractions of the observed effect. The figures are participants per arm, not total participants across both arms and not total event counts. The latter distinction matters because time-to-event illustrations can use total events, but these comparisons concern a continuous outcome and the figures are per arm.

The assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning scenario uses the stated fraction of the observed effect as the effect to detect. For example, the rows labeled 100% of the observed effect use the full observed estimate; the rows labeled 75% and 50% use smaller assumed effects. These are planning illustrations based on the observed comparison, not the original trial’s design assumptions. The original sample-size justification and design assumptions are not reported in the registry record.

The 80% power column gives the planned number of participants per arm for an illustrative design that would have an 80% chance of detecting the assumed effect under the stated statistical assumptions, if that effect and those assumptions were correct. The 90% power column describes the corresponding planning target for a 90% chance. Power is a property of a proposed design under assumptions, not a statement about the probability that the trial result is true.

For each comparison, the required number rises as the assumed effect becomes smaller: detecting a smaller difference generally takes more information, all else held equal. The curve should be read in the same planning spirit, as a representation of how the required sample size changes with the assumed effect. It does not show a count of participants actually enrolled or analyzed. These illustrations are not observed power; they do not establish whether the completed trial had adequate power for its true effect or whether its original design was justified.

12. How the Sample Size Is Derived

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

Formula

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

Worked calculation for this trial

1. Observed difference Δ = -13.100; pooled standard deviation σ = 34.911.
2. n = 2 × (1.96 + 0.842)² × 34.911² / -13.100² = 111.5, rounded up to 112 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 <- -13.1                      # observed difference in means
sigma <- 34.9108292038291                     # 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(2173301)
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 = 112 (80% power), 150 (90% power)
 75% of observed effect: n per arm = 199 (80% power), 266 (90% power)
 50% of observed effect: n per arm = 446 (80% power), 597 (90% power)
power.t.test: 112.5 
Simulated power at n = 112 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.

13. Analyses Reported by the Sponsor

The registry reports sponsor analyses using mixed models for each XP23829 regimen versus placebo. The sponsor-reported p-values are 0.066 for 400 mg once daily, 0.001 for 800 mg once daily, and <0.001 for 400 mg twice daily. The registry describes these as superiority analyses. No sponsor-reported effect estimates or confidence intervals for these comparisons are included in the record presented for this analysis.

The separate recalculations are simple, unadjusted comparisons derived from the posted summary statistics. They estimate mean differences of -13.1, -23.2, and -25.7, respectively, and yield p-values of 0.067, 0.001, and <0.001. These figures may be useful for seeing the approximate scale and uncertainty of the comparisons, but they are not the sponsor’s mixed models results. They use summary data and an approximate pooled standard deviation rather than the sponsor’s full model.

A discrepancy is flagged between the two sources of analysis. Accordingly, the sponsor’s own analysis takes precedence for reporting the trial’s inferential results. The recalculations should be identified as recalculations and should not be used to replace or reinterpret the sponsor’s model-based analysis. The registry does not provide sufficient details of the mixed model to reproduce it or explain the precise source of any difference.

14. Multiplicity, Missing Data and Analysis Populations

The study has one listed primary endpoint and three sponsor-reported comparisons of active regimens with placebo. The registry reports a p-value for each comparison, but a multiplicity adjustment is not reported in the registry record. Without that information, the p-values should be read as reported for their individual analyses, not described as adjusted for the set of comparisons. The record also does not state whether a hierarchy, gatekeeping strategy, or other prespecified testing sequence was used.

The registry lists two secondary outcomes: the proportion of subjects achieving PASI-75 and the proportion with a static Physician’s Global Assessment score of clear or almost clear. It reports three outcome measures and nine analyses overall in the registry record presented, but numerical results for the secondary outcomes and their analysis details are not reported in the registry record. It is therefore not possible to assess the full multiplicity of testing across primary and secondary outcomes or to say how the secondary analyses were handled.

The primary population is described as modified Intent-to-Treat, observed cases. In general, an observed-cases analysis uses data available for analysis and does not, by that label alone, explain how missing outcome measurements were handled. The registry does not report the number of participants with missing 12-week PASI data, the reasons for missingness, any imputation approach, or sensitivity analyses. It also does not provide a participant-flow account sufficient to trace all enrolled participants through analysis.

These gaps affect interpretation because missing outcomes and multiple comparisons can influence how confidently a result is generalized. They do not show that the analysis was necessarily inappropriate; they mean the registry record does not contain enough information to evaluate these issues fully. The record also does not report the complete statistical analysis plan, model specification, interim analyses, or original sample-size justification. No assumptions about those procedures should be inferred from the reported endpoint estimates or p-values.

15. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: enterocolitis (2.1%), abdominal adhesions (2.0%), abdominal hernia (2.0%), small intestinal obstruction (2.0%), cholecystitis acute (1.8%).

The registry lists serious adverse events in the three XP23829 arms and placebo. One participant is recorded as having a serious adverse event in each XP23829 group: among 49 at risk in the 400 mg once-daily arm, among 55 at risk in the 800 mg once-daily arm, and among 48 at risk in the 400 mg twice-daily arm. No serious adverse events are listed among 48 at risk in the placebo group. The death count is 0 in each arm.

The registry also records other adverse events in 36 of 49 participants in the 400 mg once-daily arm, 42 of 55 in the 800 mg once-daily arm, 37 of 48 in the 400 mg twice-daily arm, and 29 of 48 in placebo. These are counts from the posted safety results; they do not by themselves establish causation, severity distribution, or comparative risk. The registry record does not give enough detail to describe event duration, recurrence, treatment relatedness, or the full adverse-event coding rules.

Several serious-event terms are listed with percentages: Enterocolitis, 2.1%; Abdominal Adhesions, 2.0%; Abdominal hernia, 2.0%; Small intestinal obstruction, 2.0%; and Cholecystitis acute, 1.8%. The record information presented does not assign these terms to particular arms, so they should not be attributed to a regimen. Small counts and the absence of further context limit conclusions from these listings. These figures summarize reported events, not a complete assessment of safety or tolerability.

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

The posted results describe average PASI change over the 12-week treatment period in the analyzed population. The three XP23829 arms have more negative least-squares mean percentage changes than placebo: -38.1, -48.2, and -50.7 compared with -25.0. In the sponsor’s mixed models analyses, the reported p-values are 0.066 for 400 mg once daily, 0.001 for 800 mg once daily, and <0.001 for 400 mg twice daily. These results distinguish the reported statistical evidence for each regimen-versus-placebo comparison; they do not establish a direct difference between XP23829 regimens.

The primary endpoint is a continuous average measure. An average group change does not show how many individuals improved, how much responses varied, or whether every participant changed in the same direction. The two secondary outcome types could address responder proportions, but their numerical results are not reported in the registry record available for this account. The primary result should not be treated as a substitute for those outcomes.

Statistical evidence is not the same as clinical importance. The registry record does not report a threshold for a clinically important PASI difference, so the results cannot be categorized against such a threshold using the available information. The findings also do not show the duration of any change beyond 12 weeks, and the record does not provide longer-term results. Generalization beyond the studied subjects and study conditions requires information not contained in the primary endpoint values alone.

The comparisons are subject to important interpretive limits. The sponsor’s model specification and multiplicity procedure are not reported. The primary analysis is described as modified Intent-to-Treat and observed cases, while missing-data counts and sensitivity analyses are not reported. Simple recalculations from the arm summaries are unadjusted and approximate; because a discrepancy is flagged, the sponsor’s analysis takes precedence. The safety counts likewise describe posted events but do not, by themselves, establish comparative safety or causation.

Accordingly, the registry supports a statistical description of the reported group averages and sponsor p-values, with the 800 mg once-daily and 400 mg twice-daily comparisons having smaller reported p-values than the 400 mg once-daily comparison. It does not establish that any regimen is effective or ineffective in a broader clinical sense, nor does it resolve clinical importance, long-term outcomes, individual benefit, or a complete benefit-risk assessment.

17. Why This Trial Matters Statistically

This trial is statistically informative because it places three XP23829 regimens against a placebo group within a randomized, double-blind, parallel-group design and reports a continuous primary outcome at a defined treatment time. The arm-level least-squares means allow readers to see both the average percentage change within each group and the direction of the contrasts with placebo. Reporting the standard errors also gives a measure of uncertainty around the arm estimates.

The comparisons illustrate why effect estimates, confidence intervals, and p-values answer different questions. The recalculated mean differences describe the estimated scale and direction of the contrast; their intervals show the range of uncertainty under the recalculation assumptions; and the sponsor’s p-values summarize the model-based tests. For the 400 mg once-daily regimen, the interval includes zero and the sponsor p-value is 0.066, while the other two sponsor p-values are 0.001 and <0.001. No single statistic tells the full story.

The record also highlights the importance of distinguishing a sponsor’s prespecified analysis from an analyst’s reconstruction from summary results. The sponsor used mixed models, while the recalculations are unadjusted and use an approximate pooled standard deviation. The registry lacks model details and does not report multiplicity handling, making transparent labeling essential. The sample-size illustrations likewise answer a planning question based on observed effects, not whether the original design was adequately justified.

Finally, the endpoint, population, and missing-data approach shape what the results mean. A 12-week mean change in PASI among observed cases is not the same as a responder outcome, a long-term result, or an estimate for all enrolled participants regardless of observed data. The study is useful for examining these statistical distinctions, while its registry record also shows why unreported analysis details should remain uncertainties rather than being filled in by assumption.

18. 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 record identifies the study as randomized and double-blind, but the randomization sequence, allocation concealment, and practical blinding procedures are not reported in the registry record. The multicenter designation is given, but the number or location of centers is not reported. The arm descriptions specify treatment periods, but the registry does not provide adherence, discontinuation, or participant-flow details that would clarify exposure and follow-up.

The primary endpoint analysis is described as modified Intent-to-Treat and observed cases. The exact definition of the modified population is not reported, nor are the numbers and reasons for missing 12-week PASI measurements. No imputation method or missing-data sensitivity analysis is reported. As a result, the impact of incomplete observations on the estimates cannot be assessed from the available record.

The sponsor’s comparison method is identified as mixed models analysis, but the model specification, covariates, repeated-measures structure, and other analysis details are not reported. The registry also does not report whether the three comparisons were adjusted for multiplicity or whether a testing sequence was planned. A discrepancy is flagged between sponsor results and simple recalculations; the sponsor’s own analysis takes precedence, while the summary-statistic recalculations remain approximate and unadjusted.

The registry lists two secondary outcomes, but their numerical results are not reported in the information available for this account. The original sample-size rationale and design assumptions are not reported; the planning illustrations are based on observed effects under stated assumptions and cannot reconstruct the original design. Interim analyses are not reported. In addition, the posted primary endpoint covers 12 weeks, and the information presented does not establish longer-term outcomes. These limitations concern the completeness of the registry record and the scope of the reported results; they do not supply evidence about unreported analyses or outcomes.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Study to Assess the Efficacy and Safety of XP23829 in Subjects With Moderate-to-Severe Chronic Plaque-Type Psoriasis — NCT02173301.
• Registry record last updated 2022-04-12; status last verified 2017-11.
• Results first posted 2022-04-12.
• 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.

22. Record Summary

The registry describes a completed Phase 2 randomized, double-blind, multicenter, parallel-group, placebo-controlled study of XP23829 in subjects with moderate-to-severe chronic plaque-type psoriasis. Listed enrollment is 200. The four arms were XP23829 400 mg once daily, 800 mg once daily, 400 mg twice daily, and placebo; the treatment period was 12 weeks after a 4-week screening period.

The primary endpoint was percent change in PASI score from baseline at 12 weeks, analyzed in a modified Intent-to-Treat population using observed cases. Sponsor-reported mixed models p-values for the three comparisons with placebo were 0.066, 0.001, and <0.001, respectively. Simple unadjusted recalculations give mean differences of -13.1, -23.2, and -25.7; because a discrepancy is flagged, the sponsor’s analysis takes precedence.

The record lists serious adverse events and other adverse events by arm, with no deaths recorded. Multiplicity procedures, detailed model specifications, missing-data handling, secondary-outcome results, and the original sample-size justification are not reported in the registry record available for this account.