BI 655066/ABBV-066/Risankizumab Compared to Placebo in Patients With Active Psoriatic Arthritis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for BI 655066/ABBV-066/Risankizumab Compared to Placebo in Patients With Active Psoriatic Arthritis (NCT02719171), a randomized phase 2 study. The primary outcome is Percentage of Participants Achieving American College of Rheumatology 20% (ACR20) Response at Week 16.

2. Clinical Question

The trial record describes a short-term comparison of multiple dosing schedules with placebo, rather than a comparison of a single schedule with usual care. The main response measure combines joint counts with patient, investigator, functional, and inflammatory assessments. The registry record identifies clinical efficacy and safety assessment and dose selection for further clinical trials as the trial’s overall purpose.

3. Trial Design

This was a randomized, double-blind, parallel-group, placebo-controlled phase 2 study of risankizumab in active psoriatic arthritis. The registry record lists enrollment of 185 participants. The study began in 2016-04, had primary completion in 2017-05, and is marked completed. The sponsor is AbbVie.

Five treatment groups are described. Participants assigned to placebo received injections every 4 weeks for 16 weeks. Risankizumab groups received 150 mg every 4 weeks for 16 weeks, 150 mg at Weeks 0, 4, and 16, 150 mg at Weeks 0 and 12, or 75 mg at Week 0. These schedules differ in dose timing and, for one group, dose amount. The information in the registry record does not explain the rationale for each schedule or the original sample-size justification.

The primary endpoint was assessed at Week 16 in the FAS. The primary outcome is presented as the percentage of participants who achieved ACR20 response, with a 90% confidence interval for each group. The reported group sizes for that outcome are 42 for placebo, 42 for each of the first two 150 mg schedules, 39 for the 150 mg Weeks 0 and 12 group, and 20 for the 75 mg Week 0 group. Additional combined-group summaries are also posted, but the registry record does not explain their role in the original trial plan.

Secondary outcomes listed in the record include ACR50 and ACR70 response, tender and swollen joint counts, HAQ-DI, SF-36 physical and mental component scores, and dactylitis count. The posted results also include a PASI90 outcome for subsets of the groups. The registry record does not report further details of the randomization procedure, allocation concealment, or a full statistical analysis plan.

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: This study included a 6-week screening period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: FAS

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 (FAS): 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 Achieving American College of Rheumatology 20% (ACR20) Response at Week 16, measured over Week 16.

The primary endpoint is the percentage of participants who achieved an ACR20 response at Week 16. A response required at least 20% improvement from baseline in tender joint count and swollen joint count, plus at least 20% improvement in at least three of five additional measures: patient assessment of pain, patient global assessment of disease activity, investigator global assessment of disease activity, HAQ-DI, and C-reactive protein.

This is a composite response measure: it counts participants who satisfy multiple criteria spanning joint findings, assessments of disease activity and function, and an acute phase reactant. A threshold-based endpoint can make the result easier to interpret as the proportion reaching a specified response standard, but it does not convey the full range of change in each component. Participants just below the threshold and those with little change are both classified as not achieving the endpoint.

ACR20 was used as the primary response measure in this trial; the registry record does not report why this endpoint was selected over other possible measures. General statistical context: expressing a binary endpoint as a percentage describes how often the defined event occurred in each group. It does not, by itself, show the magnitude of change among participants who did not cross the response threshold. Nonresponder imputation was used for missing primary endpoint data, so missing participants were classified as nonresponders for this outcome.

7. Results Posted in the Registry

• Risankizumab 150 mg Every 4 Weeks: 57.1% (24/42) versus 35.7% (15/42) on control; risk difference 21.4 percentage points (95% CI 0.6 to 42.3), risk ratio 1.60 (0.99–2.59); unadjusted two-proportion z-test p = 0.049.
• Risankizumab 150 mg Weeks 0, 4, and 16: 61.9% (26/42) versus 35.7% (15/42) on control; risk difference 26.2 percentage points (95% CI 5.6 to 46.8), risk ratio 1.73 (1.08–2.77); unadjusted two-proportion z-test p = 0.016.
• Risankizumab 150 mg Weeks 0 and 12: 59.0% (23/39) versus 35.7% (15/42) on control; risk difference 23.3 percentage points (95% CI 2.1 to 44.4), risk ratio 1.65 (1.02–2.68); unadjusted two-proportion z-test p = 0.036.
• Risankizumab 75 mg Week 0: 65.0% (13/20) versus 35.7% (15/42) on control; risk difference 29.3 percentage points (95% CI 3.9 to 54.7), risk ratio 1.82 (1.08–3.05); unadjusted two-proportion z-test p = 0.030.

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 Achieving American College of Rheumatology 50% (ACR50) Response at Week 16

• 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:
  • Risankizumab 150 mg Every 4 Weeks: 23.8% (10/42) versus 11.9% (5/42) on control; risk difference 11.9 percentage points (95% CI -4.3 to 28.1), risk ratio 2.00 (0.75–5.35); unadjusted two-proportion z-test p = 0.154.
  • Risankizumab 150 mg Weeks 0, 4, and 16: 23.8% (10/42) versus 11.9% (5/42) on control; risk difference 11.9 percentage points (95% CI -4.3 to 28.1), risk ratio 2.00 (0.75–5.35); unadjusted two-proportion z-test p = 0.154.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Risankizumab 150 mg Every 4 Weeks 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 Risankizumab 150 mg Weeks 0, 4, and 16 and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants Achieving American College of Rheumatology 70% (ACR70) Response at Week 16

• 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:
  • Risankizumab 150 mg Every 4 Weeks: 14.3% (6/42) versus 0.0% (0/42) on control; risk difference 14.3 percentage points (95% CI 3.7 to 24.9); unadjusted two-proportion z-test p = 0.011.
  • Risankizumab 150 mg Weeks 0, 4, and 16: 7.1% (3/42) versus 0.0% (0/42) on control; risk difference 7.1 percentage points (95% CI -0.6 to 14.9); unadjusted two-proportion z-test p = 0.078.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Risankizumab 150 mg Every 4 Weeks than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Risankizumab 150 mg Weeks 0, 4, and 16 and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants Achieving 90% Improvement in Psoriasis Area and Severity Index (PASI) Score (PASI90) at Week 16

• 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:
  • Risankizumab 150 mg Every 4 Weeks: 58.3% (7/12) versus 9.5% (2/21) on control; risk difference 48.8 percentage points (95% CI 18.2 to 79.4), risk ratio 6.13 (1.51–24.90); unadjusted two-proportion z-test p = 0.002.
  • Risankizumab 150 mg Weeks 0, 4, and 16: 66.7% (12/18) versus 9.5% (2/21) on control; risk difference 57.1 percentage points (95% CI 32.0 to 82.3), risk ratio 7.00 (1.80–27.22); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Risankizumab 150 mg Every 4 Weeks than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Risankizumab 150 mg Weeks 0, 4, and 16 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary results include ACR50, ACR70, and PASI90 response percentages. Across these measures, the group estimates generally show more participants meeting response thresholds in risankizumab groups than in placebo, while the amount of precision varies with the group sizes. ACR50 and ACR70 are progressively stricter response thresholds than ACR20; PASI90 concerns improvement in psoriasis severity rather than the same joint-response composite. These measures can add context to the primary outcome, but they capture different aspects of disease response.

The secondary outcome list also includes tender and swollen joint counts, HAQ-DI, SF-36 physical and mental component scores, and dactylitis count. Although these outcomes are listed in the registry record, their numerical results are not reported in the registry record information summarized for this analysis. The number of outcome measures is listed as 12, with 11 secondary outcomes posted, and the record lists 23 analyses overall.

Unadjusted secondary comparisons carry less weight as confirmatory evidence when many outcomes or comparisons are examined. General statistical context: repeated testing increases the chance that at least one apparently noteworthy result arises by chance, unless the analysis plan controls that risk. The registry record does not report a multiplicity adjustment or a hierarchy that would establish which secondary findings were confirmatory. Secondary results should therefore be read as supportive or exploratory descriptions alongside the primary endpoint, not as independent proof of a broad pattern. Their differing populations and group sizes, including the smaller subsets for PASI90, also limit direct comparisons across endpoints.

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

• Percentage of Participants Achieving American College of Rheumatology 50% (ACR50) Response at Week 16
• Percentage of Participants Achieving American College of Rheumatology 70% (ACR70) Response at Week 16
• Tender Joint Count (TJC68): Change From Baseline to Week 16
• Swollen Joint Count (SJC): Change From Baseline to Week 16
• Health Assessment Questionnaire Disability Index (HAQ-DI) Score: Change From Baseline to Week 16
• Short Form-36 Health Status Survey (SF-36) Physical Component: Change From Baseline to Week 16
• SF-36 Mental Component: Change From Baseline to Week 16
• Dactylitis Count: Change From Baseline to Week 16 in Participants With Dactylitis at Baseline

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary: each participant is classified as having achieved or not achieved ACR20 response at Week 16. The group percentages describe the observed response proportions under the registry’s stated analysis, while the confidence intervals express uncertainty about the underlying response proportions. The posted primary result uses a 90% confidence interval. General statistical context: a confidence interval is a range generated by a method that, under its assumptions and repeated use, has a specified coverage rate. It is not a guarantee that the true value lies inside a particular calculated interval.

What is a risk difference?

The recalculated comparisons use risk difference, the difference between the response proportions in the risankizumab and placebo groups. The estimates are on the probability scale, so they represent an absolute contrast rather than a relative measure. For example, the risk-difference estimate for 150 mg every 4 weeks is 0.214. Its 90% confidence interval runs from 0.006 to 0.423. The interval indicates that the estimated contrast is imprecise, even though its lower endpoint is just above zero. The registry record also contains relative risk and odds-ratio calculations for some comparisons, but the central interpretation uses risk differences.

What do the p-values say?

The recalculated p-values are unadjusted. In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be under the assumptions of the test. It is not the probability that the null hypothesis is true, nor a measure of the size or clinical importance of an effect. Because several comparisons are reported, interpreting each unadjusted p-value as if it were the only test can overstate the strength of evidence. The registry record does not report a multiplicity adjustment for these comparisons.

How was missing primary outcome data handled?

The primary endpoint description states that nonresponder imputation was used for missing data. Under this approach, participants with missing response information are classified as not meeting the response endpoint. General statistical context: this makes the handling of missing values explicit, but the resulting estimate depends on that assumption. The registry record does not report the amount or pattern of missing primary endpoint data or provide sensitivity analyses using other assumptions.

What is the analysis population?

The primary outcome population is identified as FAS in the registry record. The record does not report a fuller definition of that population in the information summarized for the endpoint, so the acronym should not be expanded into assumptions about exactly who was included. General statistical context: analysis-population definitions matter because exclusions or deviations from randomized assignment can change the population to which an estimate applies.

How should combined groups be understood?

Two ACR20 summaries combine participants from specified risankizumab schedules. The record lists these grouped estimates and recalculated comparisons but does not report whether the pooling was specified before the results were observed or explain the rationale. They therefore should not be treated as evidence from a separately randomized arm. Grouping can increase the number of observations contributing to a summary, but it can also obscure differences between schedules if their outcomes differ.

The registry record includes a sponsor-reported Cochran-Mantel-Haenszel analysis, as well as the unadjusted risk-difference recalculations. These are not interchangeable statistical summaries. The sponsor analysis is described using the registry’s label, Mean Difference (Final Values), whereas the recalculations compare binary response proportions. Their numerical estimates should not be combined as though they were produced by the same method or expressed on the same scale.

General statistical context: over-dispersion is relevant when observed variability exceeds what a chosen probability model expects; accounting for it can affect standard errors and uncertainty estimates. The endpoint is binary and the registry record does not report an over-dispersion model for this analysis. The registry record also does not report the original statistical plan, a prespecified testing hierarchy, or interim analyses. Those details cannot be inferred from the posted outcome summaries.

11. Confidence Intervals and Precision

The primary endpoint group percentages have 90% confidence intervals. For placebo, the interval is 23.5 to 49.5 around the reported 35.7% response. For the 150 mg every-4-weeks schedule, it is 43.3 to 70.2 around 57.1%; for the 150 mg Weeks 0, 4, and 16 schedule, 48.0 to 74.4 around 61.9%; and for the 150 mg Weeks 0 and 12 schedule, 44.6 to 72.3 around 59.0%. The interval for 75 mg at Week 0 is 44.2 to 82.3 around 65.0% and is especially broad in the context of its group size of 20.

The risk-difference intervals also show substantial uncertainty. For the individual schedules, the lower and upper limits are 0.006 and 0.423, 0.056 and 0.468, 0.021 and 0.444, and 0.038 and 0.547, respectively. These intervals all have lower limits above zero, but that observation does not account for multiplicity or establish that one schedule is better than another. The intervals are for comparisons with placebo, not direct comparisons between risankizumab schedules.

General statistical context: an interval’s width reflects both the data and the method used to calculate it. Small samples and event proportions can yield limited precision. A confidence interval is not a prediction interval for individual participants, and overlap or non-overlap between separate group intervals is not a substitute for a direct statistical comparison. In this trial, the posted estimates are compatible with a range of possible response percentages and risk differences, particularly for the smaller group. The registry record does not report a prespecified precision target for the primary endpoint.

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 estimates are planning illustrations based on the observed effect, not the original trial’s design calculations. They report participants per arm for these binary outcomes, not total events. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; each scenario targets a stated fraction of the observed effect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

For example, using the 150 mg every-4-weeks comparison with placebo, planning for 100% of the observed effect gives 84 participants per arm for 80% power and 112 participants per arm for 90% power. Planning for 75% of the observed effect gives 149 participants per arm for 80% power and 199 participants per arm for 90% power. Planning for 50% of the observed effect gives 330 participants per arm for 80% power and 441 participants per arm for 90% power.

In plain terms, the 80% power column is the estimated group size per arm for a study designed to have an 80% chance of detecting the specified effect under the stated assumptions, if that effect is real. The 90% column describes the corresponding target for a 90% chance. Smaller effects need more participants to detect because they are harder to distinguish from random variation. These are planning estimates, not observed power; they do not tell whether the completed trial had a particular probability of success after its results were known. The scenarios also should not be read as evidence that the observed effect will recur in a new 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 = 0.357; treatment proportion p₁ = 0.571; average p̄ = 0.464.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.7053 = 1.3824.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6888 = 0.5797.
4. n = (1.3824 + 0.5797)² / (0.2143)² = 83.8, rounded up to 84 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 <- 0.357142857142857                          # control proportion
p1 <- 0.571428571428571                          # 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(2719171)
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 = 84 (80% power), 112 (90% power)
 75% of observed effect: n per arm = 149 (80% power), 199 (90% power)
 50% of observed effect: n per arm = 330 (80% power), 441 (90% power)
power.prop.test: 83.8 
Simulated power at n = 84 per arm: 0.811 (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 registry record includes a sponsor-reported Cochran-Mantel-Haenszel analysis comparing placebo with the combined group labeled as risankizumab 150 mg every 4 weeks and 150 mg at Weeks 0, 4, and 16. It reports a Mean Difference (Final Values) of 24.0, with a 90% confidence interval from 9.3 to 38.7 and p = 0.007.

This is distinct from the unadjusted recalculation of the binary ACR20 response proportions. That recalculation compares the 84 participants in the combined risankizumab group with the 42 participants in placebo and gives a risk difference of 0.238, a 90% confidence interval from 0.059 to 0.417, and p = 0.012. The registry labels the sponsor analysis as a mean difference in final values, so it should not be interpreted as the same estimand or scale as the risk difference without additional detail. The registry record does not report enough methodological information to reconcile the two summaries further.

The trial data do not indicate a flagged discrepancy between the posted result and the simple unadjusted recalculation. The sponsor-reported method and the recalculation answer related but not necessarily identical statistical questions. The record does not report the full sponsor analysis specification, adjustment variables, or the role of this combined-group analysis in the prespecified plan.

15. Multiplicity, Missing Data and Analysis Populations

The registry record presents several primary endpoint comparisons against placebo, along with combined-group comparisons and multiple secondary outcomes. The recalculated p-values are unadjusted. The record does not report a multiplicity adjustment, a hierarchy of hypotheses, or a plan defining which comparisons were intended to support confirmatory conclusions. Without such information, the individual p-values should be treated as nominal summaries rather than as evidence adjusted for the full set of analyses.

The primary endpoint specifies nonresponder imputation for missing data. This means missing primary endpoint information was handled by classifying participants as nonresponders. The amount and pattern of missingness are not reported in the registry record, and sensitivity analyses under alternative missing-data assumptions are not reported in the registry record. The record also does not provide a fuller description of the FAS population or details sufficient to assess how participants with protocol deviations were handled.

More broadly, the original statistical analysis plan, sample-size justification, interim analyses, and detailed rules for selecting the reported analyses are not reported in the registry record. Their absence from the posted record does not establish that no such plans or procedures existed; it means they cannot be evaluated from these results alone. The posted outcome data therefore support descriptive reading of the Week 16 estimates, while the confirmatory status of individual contrasts remains unclear. The record also does not report how the combined risankizumab groups were defined for analysis or whether those groupings were specified before outcome data were available.

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: acute myocardial infarction (5.0%), cardiac failure congestive (5.0%), coronary artery occlusion (5.0%), abdominal pain upper (5.0%), gastroenteritis (5.0%).

The registry record reports serious adverse events for each treatment group during the stated study period, with the listed at-risk counts matching the primary endpoint group sizes. Serious adverse events were reported for 2 of 42 participants receiving placebo, 3 of 42 receiving risankizumab 150 mg every 4 weeks, 0 of 42 receiving 150 mg at Weeks 0, 4, and 16, 2 of 39 receiving 150 mg at Weeks 0 and 12, and 3 of 20 receiving 75 mg at Week 0. Deaths are reported as 0 in every group.

Other adverse events affecting participants are reported for 25 of 42 in placebo, 16 of 42 in the every-4-weeks group, 13 of 42 in the Weeks 0, 4, and 16 group, 19 of 39 in the Weeks 0 and 12 group, and 13 of 20 in the 75 mg Week 0 group. These counts are descriptive and do not by themselves establish that event rates differ between groups. The registry record lists several serious-event terms at 5.0%, but does not provide enough context in the summarized information to interpret those term percentages as comparative risks. These short-term counts should not be treated as a complete assessment of safety beyond the reported trial period.

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

The results describe the proportion of participants meeting a defined response threshold at Week 16 in a phase 2, dose-ranging study. In the posted data, the ACR20 percentages are higher in each risankizumab schedule than in placebo. The unadjusted comparisons also estimate positive risk differences, with confidence intervals that convey uncertainty around those contrasts. These data are a snapshot at one endpoint and one time point, not a complete account of changes in every disease measure.

The results do not establish which risankizumab schedule is preferable. The individual schedules were not directly compared in the reported recalculations, and differences between their response percentages should not be interpreted as a tested ranking. The combined-group analyses also do not represent separately randomized schedules. The record does not report a multiplicity plan, so the unadjusted p-values do not account for the collection of comparisons.

The findings do not establish longer-term outcomes, results in populations not described by the trial, or effects on endpoints whose numerical results are not posted in the registry record. ACR20 is a threshold-based composite; it does not show the full distribution of improvement or worsening in each component. Missing primary data were handled as nonresponse, and the record does not report the extent of missingness or alternative analyses.

General statistical context: statistical evidence and clinical importance are different questions. A p-value or confidence interval does not determine whether an observed contrast is important to patients, and the registry record does not report a clinical importance threshold for this endpoint. The results are best read as evidence about the observed Week 16 response patterns and their precision, within the groups and analysis definitions recorded for this trial.

18. Why This Trial Matters Statistically

This trial illustrates why a dose-ranging study with several schedules requires careful attention to what each comparison represents. The placebo-controlled design provides a reference for the Week 16 ACR20 response percentages, while the different schedules create multiple contrasts and an opportunity to examine a range of dosing patterns. The posted estimates make both the event proportion and its uncertainty visible rather than relying only on a single significance test.

It also illustrates the distinction between an endpoint percentage and a treatment contrast. The group response percentages describe each arm; the risk differences express the unadjusted absolute contrast with placebo. Confidence intervals show that these estimates remain uncertain, particularly where group sizes are smaller. Combined-group analyses add another layer: they may summarize more participants, but they should not be mistaken for additional randomized arms or for direct comparisons among schedules.

The record is also useful for showing the limits of registry results. Although multiple secondary outcomes and analyses are listed, the analysis plan and multiplicity approach are not reported. That makes it important to distinguish the primary endpoint from a broader set of secondary findings and to avoid treating each nominal p-value as equally confirmatory. Reporting the missing-data method for the primary endpoint is informative, but the absence of missingness details limits assessment of its impact.

These features make the trial a practical example of reading response rates, risk differences, confidence intervals, and planning illustrations together, while keeping descriptive findings separate from claims about long-term or comparative effects not addressed by the posted results.

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.

The primary endpoint is measured at Week 16, and the registry record does not report longer-term ACR20 results in the information summarized for this analysis. The trial is described as phase 2 and proof-of-concept, with 185 participants enrolled across multiple schedules. Group sizes for the primary endpoint range from 20 to 42 in the individual arms, which limits precision, especially for the 75 mg Week 0 group. The 90% confidence interval for that group is broad.

The registry record does not report the original sample-size justification, detailed randomization procedures, allocation concealment, or the complete statistical analysis plan. It does not report an approach to multiplicity, so the unadjusted comparisons cannot be interpreted as adjusted confirmatory tests. It also does not report the extent or pattern of missing primary outcome data, or sensitivity analyses beyond the stated nonresponder imputation.

The posted results include combined-group summaries whose analytic rationale and prespecification are not reported in the registry record. The sponsor-reported analysis uses a different label and method description from the binary risk-difference recalculations, and further detail is not reported in the registry record to clarify their relationship. Numerical results for several listed secondary outcomes are not reported in the registry record information. Finally, the registry record’s descriptions do not establish how representative the enrolled participants were of broader clinical populations, so generalizability cannot be assessed from these results alone.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: BI 655066/ABBV-066/Risankizumab Compared to Placebo in Patients With Active Psoriatic Arthritis — NCT02719171.
• Registry record last updated 2019-05-30; status last verified 2019-05.
• Results first posted 2019-05-30.
• 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, parallel-group, phase 2, placebo-controlled proof-of-concept study of risankizumab in adults with active psoriatic arthritis. Enrollment was 185. Treatment schedules included three 150 mg regimens and a single 75 mg dose schedule, with placebo as comparator. The primary outcome was ACR20 response at Week 16 in the FAS, with nonresponder imputation for missing data.

ACR20 response percentages were higher in each risankizumab group than in placebo in the posted results. The unadjusted risk-difference recalculations give positive estimates for each individual schedule, with 90% confidence intervals reflecting uncertainty. Several secondary outcomes and safety counts are also posted, but multiplicity procedures, original sample-size rationale, and further details of the statistical plan are not reported in the registry record.