A Study to Evaluate the Efficacy, Safety, and Tolerability of NDI-034858 in Participants With Active Psoriatic Arthritis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Efficacy, Safety, and Tolerability of NDI-034858 in Participants With Active Psoriatic Arthritis (NCT05153148), a randomized phase 2 study. The primary outcome is Percentage of Participants Who Achieved at Least an American College of Rheumatology 20 (ACR20) Response at Week 12.

2. Clinical Question

3. Trial Design

This was a randomized, multicenter, double-blind, placebo-controlled, parallel-group Phase 2b study of NDI-034858 in participants with active psoriatic arthritis. The registry lists the study phase as Phase 2 and the official title describes it as Phase 2b. Its stated purpose was to evaluate efficacy, safety, and tolerability.

Four groups received placebo or NDI-034858 at low, medium, or high dose. Capsules were taken orally once daily for 12 weeks. The primary endpoint was assessed at Week 12. Randomized allocation and double masking are recorded, but the allocation ratio, details of how randomization was conducted, and the specific masking procedures are not reported in the registry record.

The registry reports enrollment of 305. For the primary endpoint, the arm-level denominators were 72 for placebo, 71 for low dose, 75 for medium dose, and 72 for high dose. These are the analysis denominators reported for that endpoint, not a substitute for a complete account of participant flow. The primary analysis population included randomized participants who received at least one dose of study drug.

The study start date was 2022-01-06, primary completion was 2023-05-04, and the study status is completed. The registry record does not report the original sample-size justification, the planned allocation ratio, or whether interim analyses were conducted. These details should not be inferred from the enrollment or endpoint results.

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: A total of 305 participants with a diagnosis of psoriatic arthritis were enrolled in a 1:1:1:1 ratio to receive either one of the 3 doses of NDI-034858 or placebo.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set included all randomized participants who received at least one dose of study drug.

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.

Population: Full Analysis Set included all randomized participants who received at least one dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Who Achieved at Least an American College of Rheumatology 20 (ACR20) Response at Week 12, measured over Week 12.

The primary endpoint was the percentage of participants who achieved at least an American College of Rheumatology 20 (ACR20) response at Week 12. ACR20 is a composite response definition: it requires improvement of 20% from baseline in both tender joint count and swollen joint count, together with improvement of 20% in at least three of five other criteria.

Those additional criteria include patient and physician global assessments of psoriatic arthritis, patient assessment of psoriatic arthritis pain, the Health Assessment Questionnaire-Disability Index, and an acute-phase reactant such as high-sensitivity C-reactive protein. The assessments combine joint findings with patient-reported, clinician-assessed, functional, and laboratory information. The registry describes scales for the global assessments and HAQ-DI, but the endpoint is ultimately reported as a percentage meeting the composite definition.

A responder endpoint is useful for expressing the proportion of participants who meet a prespecified level of improvement rather than only reporting an average change. It also makes clear that the result depends on the full composite definition: a participant must satisfy the joint-count criteria and enough of the additional criteria. ACR20 is the primary endpoint in this trial; ACR50 and ACR70 are listed as secondary response outcomes. The reported percentages describe responses in the analysis population and do not by themselves explain individual variation or establish the result for people outside the study population.

7. Results Posted in the Registry

• NDI-034858 Low Dose: 35.2% (25/71) versus 29.2% (21/72) on control; risk difference 6.0 percentage points (95% CI -9.2 to 21.3), risk ratio 1.21 (0.75–1.95); unadjusted two-proportion z-test p = 0.439.
• NDI-034858 Medium Dose: 53.3% (40/75) versus 29.2% (21/72) on control; risk difference 24.2 percentage points (95% CI 8.7 to 39.6), risk ratio 1.83 (1.20–2.78); unadjusted two-proportion z-test p = 0.003.
• NDI-034858 High Dose: 54.2% (39/72) versus 29.2% (21/72) on control; risk difference 25.0 percentage points (95% CI 9.4 to 40.6), risk ratio 1.86 (1.22–2.82); unadjusted two-proportion z-test p = 0.002.

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.

Percentage of Participants Who Achieved at Least an ACR-50 Response at Week 12

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • NDI-034858 Low Dose: 15.5% (11/71) versus 9.7% (7/72) on control; risk difference 5.8 percentage points (95% CI -5.1 to 16.6), risk ratio 1.59 (0.65–3.88); unadjusted two-proportion z-test p = 0.298.
  • NDI-034858 Medium Dose: 26.7% (20/75) versus 9.7% (7/72) on control; risk difference 16.9 percentage points (95% CI 4.8 to 29.1), risk ratio 2.74 (1.24–6.09); unadjusted two-proportion z-test p = 0.008.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NDI-034858 Low Dose and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for NDI-034858 Medium Dose than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Who Achieved at Least an ACR-70 Response at Week 12

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • NDI-034858 Low Dose: 8.5% (6/71) versus 5.6% (4/72) on control; risk difference 2.9 percentage points (95% CI -5.5 to 11.3), risk ratio 1.52 (0.45–5.16); unadjusted two-proportion z-test p = 0.497.
  • NDI-034858 Medium Dose: 14.7% (11/75) versus 5.6% (4/72) on control; risk difference 9.1 percentage points (95% CI -0.5 to 18.7), risk ratio 2.64 (0.88–7.91); unadjusted two-proportion z-test p = 0.068.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NDI-034858 Low Dose and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NDI-034858 Medium Dose and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Tender Joint Count (TJC) at Week 12

• 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:
  • NDI-034858 Low Dose: mean -7.60 versus -5.90 on control; difference -1.70 (95% CI -4.80 to 1.40), standardized effect d = -0.19; z-test p = 0.283.
  • NDI-034858 Medium Dose: mean -8.90 versus -5.90 on control; difference -3.00 (95% CI -6.10 to 0.10), standardized effect d = -0.33; z-test p = 0.058.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NDI-034858 Low Dose and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NDI-034858 Medium Dose and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes include ACR50 and ACR70 response rates, changes in tender and swollen joint counts, global assessments, pain assessment, and HAQ-DI. The posted secondary results include response proportions for ACR50 and ACR70 and change from baseline in tender joint count. The broader endpoint list shows that the study examined several related aspects of disease activity and function. Numerical results for the remaining listed secondary outcomes are not reported in the registry record information used for this analysis.

Across the response outcomes with posted figures, the descriptive pattern is generally consistent with the primary endpoint: the medium- and high-dose groups had higher response percentages than placebo, while the low-dose group’s percentages were closer to placebo. The tender-joint-count results also show changes from baseline in each group, with the reported treatment comparisons requiring attention to their confidence intervals and analysis method. These secondary measures provide context for the primary composite, but they do not replace it.

Secondary outcomes are usually interpreted more cautiously when multiple outcomes, doses, or comparisons are examined. If many statistical tests are conducted, the chance of finding a nominally notable result by chance can increase unless a suitable multiplicity strategy is used. The registry record does not report such a strategy or a complete statistical analysis plan. Therefore, unadjusted secondary p-values carry less weight than a prespecified, multiplicity-controlled result, and they should be viewed as supportive or exploratory rather than as independent confirmation.

Differences in endpoint definition and analysis also matter. ACR50 and ACR70 require more stringent response levels than ACR20, whereas joint-count changes measure a continuous change rather than the proportion meeting a composite threshold. Results across these measures can add perspective, but they answer different questions and should not be combined into a single claim. The secondary findings are best read alongside the primary endpoint, its sponsor-reported comparison, and the uncertainty in all estimates.

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

• Percentage of Participants Who Achieved at Least an ACR-50 Response at Week 12
• Percentage of Participants Who Achieved at Least an ACR-70 Response at Week 12
• Change From Baseline in Tender Joint Count (TJC) at Week 12
• Change From Baseline in Swollen Joint Count (SJC) at Week 12
• Change From Baseline in PGA-PsA at Week 12
• Change From Baseline in PGAAP at Week 12
• Change From Baseline in PhGA-PsA at Week 12
• Change From Baseline in HAQ-DI Total Score at Week 12

9. Statistical Interpretation

10. Statistical Methods Explained

The registry reports percentages of participants achieving the primary response, with 95% confidence intervals. It also reports sponsor comparisons as risk differences, using the Cochran-Mantel-Haenszel method. The posted recalculations are unadjusted comparisons based on arm-level summary statistics. These methods address related questions, but they need not yield identical estimates or uncertainty intervals.

What does a response percentage describe?

A response percentage is the proportion of participants in an analysis group who met the ACR20 definition. The endpoint is binary at the participant level: each participant either met the composite response definition or did not. The group percentage then describes the observed frequency of response in that group. It does not measure the size of improvement among responders, and it does not say which component of the composite was responsible for meeting the response definition.

The reported arm percentages are rounded to the nearest decimal, as stated in the endpoint description. Their confidence intervals express uncertainty about the underlying response percentage, given the observed data and the method used. A wider interval indicates less precision than a narrower interval. The confidence interval is not a prediction interval for individual responses, and its interpretation depends on the statistical procedure used to construct it.

How should a risk difference be read?

A risk difference subtracts the event percentage in the comparator group from the event percentage in the group being compared. For this binary endpoint, the event is achieving ACR20. A positive risk difference therefore corresponds to a higher observed response proportion in the NDI-034858 group than in placebo. The sponsor reports this contrast in percentage points. Its confidence interval indicates the range of differences compatible with the data under the analysis assumptions. An interval crossing zero includes no difference as a possibility under that interval procedure; an interval entirely above zero does not.

The Cochran-Mantel-Haenszel method is the sponsor’s stated method for the primary comparisons. In general, this method can combine comparisons across strata while accounting for the stratification used in an analysis. The registry record does not specify the strata or give enough detail to reconstruct the complete model. It is therefore not possible to describe which variables were used for stratification or to reproduce the sponsor’s adjusted analysis from the arm-level percentages alone.

Why can recalculations differ from the reported analysis?

A recalculation from arm-level response percentages and denominators is a simple, unadjusted comparison. The sponsor’s analysis is identified as Cochran-Mantel-Haenszel. Differences can arise because an adjusted, stratified analysis does not necessarily equal a direct comparison of pooled group summaries. Rounding of the displayed percentages can also affect attempts to reproduce a result. The registry record flags a discrepancy, so the sponsor’s own analysis takes precedence when describing the trial’s reported comparisons. Recalculated estimates are useful as a transparent check, but they should not be presented as the official analysis.

A p-value describes how unusual data at least as incompatible with a specified null hypothesis would be under the model and assumptions used. It is not the probability that the null hypothesis is true, nor is it a measure of effect size or clinical importance. A smaller p-value does not remove uncertainty in the estimated effect, which is why the risk difference and its confidence interval should be read alongside it. The registry record does not report enough detail to establish whether the posted p-values account for all planned comparisons.

What is not described about the analysis?

The record identifies the Full Analysis Set as randomized participants who received at least one dose of study drug. It does not report the handling of missing Week 12 responses, the imputation method if any, or sensitivity analyses for missing data. It also does not report the trial’s full statistical analysis plan, multiplicity strategy, or whether interim analyses occurred. Those omissions limit what can be concluded about how robust the reported comparisons are to analysis choices.

General statistical interpretation: estimates, confidence intervals, and p-values answer different questions. The estimate gives the direction and magnitude of the observed contrast; the interval communicates its precision under the stated method; and the p-value evaluates compatibility with a null comparison under model assumptions. None alone establishes a complete account of efficacy, safety, or the relevance of the result to every patient or setting.

11. Confidence Intervals and Precision

The arm-level 95% confidence intervals for ACR20 show uncertainty around each group’s response percentage. Placebo was 29.2%, with an interval from 18.7% to 39.7%; low dose was 35.2%, with an interval from 24.1% to 46.3%; medium dose was 53.3%, with an interval from 42.0% to 64.6%; and high dose was 54.2%, with an interval from 42.7% to 65.7%. These intervals should be read as estimates with uncertainty, rather than as exact values.

For direct comparison, the sponsor reports 95% confidence intervals for risk differences. The low-dose comparison ranges from -9.3 to 21.1 percentage points, spanning zero. The medium-dose comparison ranges from 8.6 to 39.6, and the high-dose comparison ranges from 9.0 to 39.9. The latter intervals lie above zero under the sponsor’s reported analysis. Their breadth still matters: each interval includes a range of possible effect sizes, not just the point estimate.

Confidence intervals do not describe the distribution of responses among individual participants, and overlap between separate arm-level intervals is not by itself the formal test of a between-group difference. The sponsor’s risk-difference intervals are the more direct uncertainty summaries for those comparisons. The registry record does not provide a detailed explanation of interval construction beyond the reported method and confidence level, so more specific claims about the procedure are not warranted.

In general, precision is affected by the amount of information in the data, the frequency of the outcome, and the analysis method. The study’s endpoint denominators are those reported for the analysis; the confidence intervals help show the uncertainty remaining despite the observed data. Intervals should be considered together with the point estimates, the stated analysis method, and the unreported details of missing-data and multiplicity handling.

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 translate an observed effect into planning scenarios for a future comparison. For these binary outcomes, the displayed counts are participants per arm, not total participants across the trial. The assumptions stated for the illustration are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the specified effect if that effect is the true one and the assumptions hold. The 90% power column gives the corresponding planning figure for a design with a 90% chance under those same conditions. These are design calculations, not guarantees that a future study will produce a statistically significant result.

Each comparison has scenarios for planning around the full observed effect, 75% of the observed effect, and 50% of the observed effect. The smaller the effect the study is designed to detect, the more participants are generally needed to distinguish that effect from random variation under the stated assumptions. Accordingly, the illustrated counts rise as the assumed fraction of the observed effect gets smaller.

The accompanying curve should be read as a visual representation of how the planning requirement varies with the assumed effect, not as additional trial evidence. The calculations are planning illustrations based on the observed effect, not observed power. They do not report the power achieved by this completed trial, and they do not establish that the observed effect will recur in another study.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.292; treatment proportion p₁ = 0.352; average p̄ = 0.322.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6607 = 1.2950.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6593 = 0.5549.
4. n = (1.2950 + 0.5549)² / (0.0604)² = 936.6, rounded up to 937 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
p0 <- 0.291666666666667                          # control proportion
p1 <- 0.352112676056338                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(5153148)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 937 (80% power), 1,254 (90% power)
 75% of observed effect: n per arm = 1,646 (80% power), 2,202 (90% power)
 50% of observed effect: n per arm = 3,654 (80% power), 4,891 (90% power)
power.prop.test: 936.6 
Simulated power at n = 937 per arm: 0.802 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 sponsor’s reported primary comparisons use the Cochran-Mantel-Haenszel method and give risk differences with 95% confidence intervals and p-values. The posted recalculations use a simple, unadjusted approach based on arm-level summary statistics. Because these are not the same analysis, small differences in estimates, intervals, or p-values are possible.

The registry record explicitly flags a discrepancy between the recalculated summaries and the sponsor’s results. Under that circumstance, the sponsor’s own analysis takes precedence when reporting the trial’s primary comparisons. The sponsor’s reported results are a risk difference of 5.9 percentage points for low dose versus placebo, with a 95% confidence interval from -9.3 to 21.1 and p=0.446; 24.1 for medium dose, with an interval from 8.6 to 39.6 and p=0.002; and 24.5 for high dose, with an interval from 9.0 to 39.9 and p=0.002.

The recalculations are still useful as independent, unadjusted checks of the posted arm summaries. They should not be substituted for the sponsor’s analysis or treated as a correction to it. The registry record does not report the full analysis specification or stratification details needed to reproduce the sponsor’s method from the summary data alone.

15. Multiplicity, Missing Data and Analysis Populations

The trial has a primary endpoint and multiple secondary outcomes, with comparisons across placebo and three NDI-034858 dose groups. This creates a multiplicity issue: examining several outcomes and dose comparisons can make isolated nominal p-values more likely even when the underlying effects are absent. A prespecified testing hierarchy, adjustment procedure, or other statistical strategy can control how such results are interpreted.

The registry record does not report whether multiplicity was controlled, which outcomes were included in any hierarchy, or whether the secondary analyses were intended as confirmatory or exploratory. It also does not provide the complete statistical analysis plan. Consequently, the reported p-values should be understood as results of their stated comparisons, not assumed to be adjusted for all endpoints and doses. The primary result is central to the trial question, while secondary findings require more cautious interpretation when the multiplicity approach is unknown.

The primary analysis population is described as the Full Analysis Set, consisting of randomized participants who received at least one dose of study drug. This description identifies who was eligible for that analysis, but it does not explain how missing Week 12 outcome data were handled. The registry record does not report whether missing responses were treated as nonresponses, imputed, analyzed using another method, or examined in sensitivity analyses. It also does not report details about exclusions after randomization or the degree of missingness by group.

Missing-data methods can matter because the estimate may depend on what is assumed about participants whose outcomes are unavailable. Without the method and missingness information, the sensitivity of the primary and secondary results to those assumptions cannot be assessed from the registry record. The record also does not report interim analyses or the original statistical plan, so the timing and prespecification of the reported comparisons cannot be evaluated. These are limits on interpretation, not evidence that any particular analysis choice was made.

16. 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: atrial fibrillation (1.4%), cellulitis (1.4%), coronary artery disease (1.4%), respiratory tract infection (1.4%), arthritis (1.4%).

The posted serious-adverse-event figures report 4 participants in the placebo group, 4 in the low-dose group, 3 in the medium-dose group, and 2 in the high-dose group as having a serious adverse event. The corresponding at-risk denominators were 72, 71, 75, and 72. No deaths were reported in any of the four groups. These are counts within the registry’s safety reporting, not an assessment of whether an event was caused by study treatment.

The record also reports other adverse events in 13 placebo participants, 19 low-dose participants, 27 medium-dose participants, and 35 high-dose participants, using the same group-specific at-risk denominators. The listed top serious-event terms are atrial fibrillation, cellulitis, coronary artery disease, respiratory tract infection, arthritis, and Bell’s palsy, each reported as 1.4%. The record does not specify in the information available whether these terms occurred across groups or give a treatment-relatedness assessment for each.

These figures are descriptive and should be read with the trial’s group sizes, follow-up period, event definitions, and reporting methods in mind. The registry record does not provide a detailed account of event severity, timing, exposure-adjusted rates, or causal attribution. Counts alone do not establish comparative safety, particularly for uncommon events, and they do not support medical advice about an individual’s treatment.

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

The primary endpoint describes the percentage of participants meeting the ACR20 composite response definition at Week 12. The posted percentages were higher in the medium- and high-dose groups than in placebo, while the low-dose percentage was closer to placebo. The sponsor’s reported risk-difference analyses likewise show positive estimates for the medium- and high-dose comparisons, with their 95% confidence intervals above zero; the low-dose interval includes zero. These statements describe the reported trial data and analysis.

The result does not establish what any individual participant would experience, nor does it guarantee that a similar result would occur in another population or setting. A group response percentage does not reveal the full range of individual outcomes, the contribution of each ACR20 component, or the duration of any response beyond the endpoint time reported. The primary endpoint is measured at Week 12; longer-term outcomes are not described in the registry record for this analysis.

The findings also do not settle questions that depend on details not reported in the registry record. These include the original sample-size rationale, missing-data handling, full multiplicity strategy, interim analyses, and complete statistical analysis plan. The sponsor’s stated method should be distinguished from the unadjusted recalculations, and the sponsor analysis takes precedence because the registry record flags a discrepancy.

Safety counts are likewise descriptive. They record serious and other adverse events in the reported groups, but the available information does not establish causality or provide all the detail needed for a comprehensive safety assessment. The study’s stated purpose included efficacy, safety, and tolerability; the endpoint percentages and event counts are components of that assessment, not a complete answer to every clinical question.

In general, a trial result is one source of evidence about a defined population, intervention, comparator, outcome, and follow-up time. The estimates and their confidence intervals should be considered together, and conclusions should remain within the scope of the design and reporting. No treatment recommendation follows from these statistics alone.

18. Why This Trial Matters Statistically

This trial is statistically informative because it uses a randomized, double-blind, placebo-controlled, parallel-group design and reports a prespecified primary response outcome at a defined follow-up time. Comparing three dose groups with placebo provides a view of how the observed ACR20 response percentages vary across assigned groups, while the confidence intervals make uncertainty visible rather than leaving interpretation to point estimates alone.

The composite endpoint brings together joint counts and other clinical, patient-reported, functional, and laboratory criteria. That breadth makes the response definition relevant to multiple dimensions of psoriatic arthritis assessment, but it also means that the endpoint depends on meeting several conditions. The secondary response and joint-count outcomes offer related perspectives, while differing in what they measure.

The contrast between the sponsor’s Cochran-Mantel-Haenszel analysis and simple unadjusted recalculations illustrates a practical lesson: estimates from summary data need not reproduce an analysis that accounts for features of the original analysis. The registry record flags a discrepancy, making transparent separation of the sponsor’s results from recalculations important. The sponsor’s own analysis takes precedence for the reported comparisons.

The record also illustrates why statistical interpretation needs more than p-values. Confidence intervals convey the range of effects compatible with the analysis, secondary outcomes raise multiplicity considerations, and sample-size illustrations depend on specified planning assumptions. At the same time, unreported analysis details—especially missing-data handling and the multiplicity strategy—limit how fully the results can be evaluated. The study therefore offers interpretable estimates while also showing the value of complete statistical reporting.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

Several limitations specific to this trial follow from the available registry information. The primary outcome is a composite ACR20 response, so the overall percentage does not identify which of the joint, global, pain, function, or laboratory components drove individual responses. Component-level primary results are not reported in the information available for this analysis.

The primary endpoint is reported at Week 12, and the arm-level analysis denominators differ from the registry’s overall enrollment. The record identifies the Full Analysis Set but does not provide a complete participant-flow account or explain the handling of missing Week 12 responses. Without those details, the potential influence of missing outcomes or analysis exclusions cannot be assessed.

The registry record does not report the full statistical analysis plan, the original sample-size justification, the planned allocation ratio, the multiplicity strategy, or whether interim analyses occurred. It also does not specify the Cochran-Mantel-Haenszel strata or provide the details needed to reproduce that analysis. These reporting gaps make it difficult to determine whether all reported comparisons followed the original plan and how secondary p-values should be weighted.

The discrepancy flag is another reason to distinguish the sponsor’s reported results from simple recalculations. The recalculated comparisons are unadjusted checks based on posted summaries, whereas the sponsor reports Cochran-Mantel-Haenszel results; the sponsor’s analysis takes precedence. Finally, safety information is limited to reported event counts and selected terms. Detailed timing, severity, exposure-adjusted comparisons, and causal assessments are not reported in the record information used. These limitations define the scope of interpretation; they do not show that an unreported procedure or result was absent from the trial itself.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study to Evaluate the Efficacy, Safety, and Tolerability of NDI-034858 in Participants With Active Psoriatic Arthritis — NCT05153148.
• Registry record last updated 2024-05-31; status last verified 2024-05.
• Results first posted 2024-05-31.
• 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, placebo-controlled, parallel-group Phase 2b study of NDI-034858 in participants with active psoriatic arthritis. Participants received placebo or low, medium, or high dose NDI-034858 capsules orally once daily for 12 weeks. The primary endpoint was the percentage achieving at least an ACR20 response at Week 12.

The sponsor reported Cochran-Mantel-Haenszel risk-difference comparisons of each dose with placebo. The medium- and high-dose estimates were positive with 95% confidence intervals above zero; the low-dose interval included zero. Because the registry record flags a discrepancy with unadjusted recalculations, the sponsor’s analysis takes precedence. Secondary outcomes and adverse-event counts provide additional context, while missing-data methods, multiplicity handling, and several other analysis details are not reported in the registry record.