A Study of Ixekizumab (LY2439821) in bDMARD-Naive Participants With Radiographic Axial Spondyloarthritis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of Ixekizumab (LY2439821) in bDMARD-Naive Participants With Radiographic Axial Spondyloarthritis (NCT02696785), a randomized phase 3 study. The primary outcome is Percentage of Participants Achieving an Assessment of Spondyloarthritis International Society 40 (ASAS40) Response.

2. Clinical Question

In statistical terms, this is a comparison of the frequency of a defined response across randomized groups at a specified time point. The primary outcome is binary for each participant: a participant either met the response definition or did not. Group percentages therefore describe the observed proportion meeting that definition, rather than the average change in a continuous score. The registry identifies the primary analysis population as all randomized participants, but further details about how missing week 16 measurements were handled are not reported in the registry record.

The study included two ixekizumab schedules and two comparison groups, so the clinical question is not limited to a single active-versus-placebo contrast. The posted results include separate comparisons of placebo with adalimumab, ixekizumab every four weeks, and ixekizumab every two weeks. These comparisons concern the stated response measure and time point; they do not by themselves establish effects on every symptom, function measure, imaging outcome, or longer-term outcome recorded in the trial.

3. Trial Design

This was a phase 3, randomized, double-blind, parallel-group study with placebo and active control. The official title describes a multicenter study, with a 16-week study period followed by long-term evaluation. The registry record lists 341 participants enrolled and the study status as completed. Detailed randomization procedures, allocation ratios, concealment procedures, and the planned sample-size justification are not reported in the registry record.

The four blinded-period groups were placebo, adalimumab 40 mg, ixekizumab 80 mg every four weeks, and ixekizumab 80 mg every two weeks. For both ixekizumab groups, treatment began with an 80 mg or 160 mg subcutaneous dose at baseline. The registry describes subsequent dosing to week 14. Placebo was given every two weeks to week 14, as was adalimumab. The primary endpoint was assessed at week 16, as specified in the outcome record. The reason for the timing between the dosing schedule and endpoint assessment is not reported in the registry record.

The registry also describes an extended treatment period to week 52. Participants initially assigned to placebo could receive ixekizumab every two weeks or every four weeks during that period; participants initially assigned to adalimumab could switch to ixekizumab beginning at week 20. The two ixekizumab groups continued their assigned schedule. These later treatment periods are distinct from the blinded-period comparison used for the primary endpoint, so the week 16 result should not be read as a comparison of long-term treatment strategies.

The registry lists spondyloarthritis as the condition and describes the target population as bDMARD-naive participants with radiographic axial spondyloarthritis. It does not report detailed eligibility criteria, baseline characteristics, the allocation ratio, or whether randomization was stratified. It also does not report a full protocol-level account of the planned statistical methods. The study design supports interpreting the posted primary results as randomized-group comparisons, while the exact analytic adjustments and handling of deviations from assigned treatment are not specified in the registry record.

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: Participants who completed study were eligible to enroll into a long-term study (Study I1F-MC-RHBY \[RHBY\]) for up to 2 additional years. Participants that do not enroll into study RHBY will complete the Post-Treatment Follow-Up Period.

Blinded Treatment Period

Reasons for not completing this period:

Washout Period

Reasons for not completing this period:

Extended Treatment Period

Reasons for not completing this period:

Follow-up Period

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All Randomized participants.

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: 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 an Assessment of Spondyloarthritis International Society 40 (ASAS40) Response, measured over Week 16.

The primary endpoint is the percentage of participants achieving an Assessment of Spondyloarthritis International Society 40 (ASAS40) response at week 16. The registry defines response as improvement from baseline of at least 40% and an absolute improvement of at least 2 units in at least three of four domains, with no worsening in the remaining domains. The domains are patient global assessment, spinal pain, the Bath Ankylosing Spondylitis Functional Index, and inflammation based on the mean of the fifth and sixth BASDAI questions about stiffness intensity and duration.

This is a composite binary endpoint: each participant is classified according to whether all parts of the response definition are met. The outcome is reported as a percentage of participants, so the group value represents the observed frequency of meeting the complete definition, not the size of an average change in one domain. The primary population is identified as all randomized participants.

General statistical context: A composite response can summarize change across several aspects of a condition rather than relying on one symptom or function measure. Requiring improvement in multiple domains and no worsening in the remaining domain makes the response definition more restrictive than improvement on a single component alone. At the same time, a binary threshold does not show how close nonresponders came to meeting the definition, or how much participants improved within each domain. The registry record supplies the endpoint definition but does not report the rationale for selecting this threshold or the planned approach to missing endpoint measurements.

7. Results Posted in the Registry

• Adalimumab: 35.6% (32/90) versus 18.4% (16/87) on control; risk difference 17.2 percentage points (95% CI 4.4 to 30.0), risk ratio 1.93 (1.15–3.26); unadjusted two-proportion z-test p = 0.010.
• IXE80Q4W: 48.1% (39/81) versus 18.4% (16/87) on control; risk difference 29.8 percentage points (95% CI 16.2 to 43.3), risk ratio 2.62 (1.59–4.30); unadjusted two-proportion z-test p = <0.001.
• IXE80Q2W: 51.8% (43/83) versus 18.4% (16/87) on control; risk difference 33.4 percentage points (95% CI 19.9 to 46.9), risk ratio 2.82 (1.73–4.59); unadjusted two-proportion z-test p = <0.001.

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 an ASAS20 Response

• 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:
  • Adalimumab 40mg: 58.9% (53/90) versus 40.2% (35/87) on control; risk difference 18.7 percentage points (95% CI 4.2 to 33.1), risk ratio 1.46 (1.07–1.99); unadjusted two-proportion z-test p = 0.013.
  • IXE80Q4W: 64.2% (52/81) versus 40.2% (35/87) on control; risk difference 24.0 percentage points (95% CI 9.3 to 38.6), risk ratio 1.60 (1.18–2.16); unadjusted two-proportion z-test p = 0.002.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Adalimumab 40mg 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 IXE80Q4W than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in Ankylosing Spondylitis Disease Activity Score (ASDAS)

• 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:
  • Adalimumab 40mg: mean -1.30 versus -0.46 on control; difference -0.84 (95% CI -1.11 to -0.57), standardized effect d = -0.92; z-test p = <0.001.
  • IXE80Q4W: mean -1.43 versus -0.46 on control; difference -0.97 (95% CI -1.25 to -0.69), standardized effect d = -1.05; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Adalimumab 40mg 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 mean is statistically lower for IXE80Q4W than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Achieving Bath Ankylosing Spondylitis Disease Activity Index 50 (BASDAI50) Response

• 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:
  • Adalimumab 40mg: 32.2% (29/90) versus 17.2% (15/87) on control; risk difference 15.0 percentage points (95% CI 2.5 to 27.5), risk ratio 1.87 (1.08–3.24); unadjusted two-proportion z-test p = 0.021.
  • IXE80Q4W: 42.0% (34/81) versus 17.2% (15/87) on control; risk difference 24.7 percentage points (95% CI 11.4 to 38.1), risk ratio 2.43 (1.44–4.12); 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 Adalimumab 40mg 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 IXE80Q4W than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary outcomes cover response measures, disease activity, function, imaging, and health status. Across the detailed secondary results, the overall direction is broadly consistent with the primary comparison: response percentages are higher in active-treatment groups than in placebo, and the reported ASDAS changes are more negative in the active groups than in placebo. These outcomes provide additional views of disease activity and response, but they do not replace the primary ASAS40 question.

Some secondary measures overlap conceptually with the primary endpoint. ASAS20 and BASDAI50 are response classifications, while ASDAS is a disease-activity score. Similar directional findings across related measures can support a coherent description of the observed pattern, but they are not independent replications: they involve the same trial population, treatment assignments, and assessment period. The registry also lists outcomes concerning function, spinal MRI, and health status; numerical results for the other listed outcomes are not reported in the registry record summarized in the posted results.

The registry lists 25 posted secondary outcomes, 26 outcome measures overall, and 72 analyses. Examining many endpoints and comparisons creates more opportunities for nominally notable findings to occur by chance. Unless multiplicity is controlled, an unadjusted p-value for a secondary analysis should not be read as if it were the sole confirmatory test. Whether the sponsor applied a multiplicity procedure, and which secondary outcomes were designated confirmatory, are not reported in the registry record. The secondary findings are therefore best treated as supporting context, with less inferential weight than the designated primary endpoint.

It is also important not to infer unreported comparisons. The posted secondary results include sponsor analyses for selected comparisons, but not every treatment pair or every outcome. The record does not establish that the two ixekizumab schedules differ from one another on secondary outcomes. The broader pattern can be described without claiming that every listed secondary measure showed the same result or that the secondary analyses independently establish efficacy.

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

• Percentage of Participants Achieving an ASAS20 Response
• Change From Baseline in Ankylosing Spondylitis Disease Activity Score (ASDAS)
• Percentage of Participants Achieving Bath Ankylosing Spondylitis Disease Activity Index 50 (BASDAI50) Response
• Change From Baseline in Bath Ankylosing Spondylitis Functional Index (BASFI)
• Percentage of Participants Achieving ASDAS Inactive Disease
• Change From Baseline in Magnetic Resonance Imaging (MRI) of the Spine (Ankylosing Spondylitis Spinal Magnetic Resonance Imaging [ASSpiMRI] - Berlin Score)
• Change From Baseline in 36-Item Short Form Health Survey (SF-36) Physical Component Summary (PCS) and Mental Component Summary (MCS) Scores
• Change From Baseline in ASAS Health Index (ASAS HI)

9. Statistical Interpretation

10. Statistical Methods Explained

General statistical context: The primary outcome is binary at the participant level: ASAS40 response was either achieved or not achieved. A percentage expresses the proportion of participants in a group who met the response definition. The groups had different numbers of participants, so the percentages are more useful for comparing response frequency than the raw counts alone. The posted group sizes and percentages are presented alongside the inferential results.

What do the risk differences express?

The recalculated contrasts use an unadjusted risk difference: the response proportion in an active group minus the response proportion in the placebo group. A risk difference is an absolute comparison on the probability scale. It answers how far apart the two observed response proportions are, rather than expressing how many times larger one group’s response odds are. The recalculations use the posted summary counts and do not incorporate any model-based adjustment. Their confidence intervals represent uncertainty around those simple contrasts under the recalculation method.

The recalculated primary comparisons are not identical to the sponsor’s reported analysis. The registry separately reports logistic-regression odds ratios and flags a discrepancy. Consequently, the sponsor’s own analysis takes precedence when describing the trial’s primary inferential result. The unadjusted recalculations remain useful as a transparent summary-scale comparison, but they should not be presented as the trial’s official adjusted result. The registry does not report the specific covariates, if any, included in the sponsor’s logistic regression.

How should the odds ratios be read?

The sponsor’s primary analyses use logistic regression and report odds ratios. An odds ratio compares the odds of meeting the response definition between groups. It is not the same as a risk difference, and it is not interchangeable with a ratio of the group percentages. When an outcome occurs with appreciable frequency, an odds ratio can appear farther from the null than a probability ratio. The reported odds ratios therefore need to be read on the odds scale, alongside the underlying response percentages, rather than translated into a percentage-point effect.

The registry labels these analyses as superiority comparisons. The reported p-values quantify how compatible the analyzed data are with the null hypothesis used for each comparison under the statistical model. They do not quantify the probability that the null hypothesis is true, the probability that the result will replicate, or the clinical importance of the observed difference. The registry record does not describe the full statistical model, its assumptions, or whether the sponsor adjusted for multiple comparisons.

What information does a confidence interval add?

General statistical context: A confidence interval gives a range of estimates compatible with the data and the method used, at the stated confidence level. A narrower interval indicates greater precision on that scale; a wider interval indicates more uncertainty. Intervals should be interpreted together with the effect measure: an interval for an odds ratio is not directly comparable in size with one for a risk difference. The sponsor reports 95% confidence intervals for its primary odds ratios. The simple recalculations also have intervals, but those are unadjusted and differ from the sponsor analysis.

A p-value and an interval answer related but different questions. The p-value summarizes evidence against a null value under a specified test, while the interval communicates a range of plausible effect estimates under the method. Neither replaces examination of the observed response percentages, the analysis population, the endpoint definition, or the limitations of the registry-level reporting.

What is not specified?

The primary outcome population is listed as all randomized participants. The registry record does not report the detailed missing-data method, treatment of participants who discontinued or deviated from assigned treatment, the precise regression specification, or the handling of multiplicity. It also does not provide the original sample-size justification or a complete statistical analysis plan. Those details matter because they can affect which observations enter an analysis, how uncertainty is estimated, and how conclusions are framed across multiple endpoints. They should not be inferred from the outcome values or from the fact that the study was randomized and double-blind.

The registry lists 26 outcome measures and 72 analyses. That breadth makes it important to distinguish the prespecified primary question from secondary and other analyses. Whether the listed tests were all planned in advance, whether any were selected after examining the data, and whether their p-values were adjusted are not reported in the registry record. The posted results can be described as recorded, but a complete appraisal of the analysis strategy requires details not contained in the registry entry.

11. Confidence Intervals and Precision

The sponsor’s primary odds-ratio estimates are accompanied by 95% confidence intervals. For adalimumab versus placebo, the reported odds ratio is 2.73 and the interval runs from 1.35 to 5.52. For ixekizumab every four weeks versus placebo, the estimate is 4.45 and the interval runs from 2.20 to 9.03. For ixekizumab every two weeks versus placebo, the estimate is 5.09 and the interval runs from 2.52 to 10.28. The intervals show that the estimates are not exact; a range of effect sizes remains compatible with each analysis.

All three sponsor intervals are above the odds-ratio null value of 1, consistent with the registry’s superiority labels and reported p-values. This does not mean that the true effect is known precisely, nor does it establish a difference between the two ixekizumab schedules. Their intervals are for separate comparisons with placebo, not a direct comparison with each other. The registry record does not report a confidence interval for an active-versus-active contrast.

The unadjusted risk-difference intervals are on a different scale and are not a substitute for the sponsor intervals. The recalculated differences are 0.172 for adalimumab, 0.298 for ixekizumab every four weeks, and 0.334 for ixekizumab every two weeks, with corresponding intervals of 0.044 to 0.300, 0.162 to 0.433, and 0.199 to 0.469. These are simple unadjusted recalculations. Since the record flags a discrepancy, the sponsor’s analysis takes precedence for the trial’s reported inference.

General statistical context: Precision depends on the amount of information and the variability of the estimate. A confidence interval describes uncertainty under the method used; it does not account for every possible source of bias, such as incomplete outcome data or unreported analytic choices. Here, the number of participants in each primary group is between 81 and 90, and the estimates are based on a binary response. The registry record does not provide a precision target or a rationale for the original trial size. The observed intervals should therefore be read as the uncertainty attached to the reported analyses, not as proof that all relevant uncertainty has been captured.

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 give the number of participants per arm, not a total across both arms and not the number of events. They are planning illustrations based on the observed effect, rather than the trial’s original design calculations. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. For each row, 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 estimated participants per arm for a future two-arm comparison to have 80% power under those assumptions and at the specified effect size. The 90% power column gives the corresponding participants per arm for 90% power. Power is a design property under assumed conditions; it is not a measure of how likely the observed result is true, and these illustrations are not observed power.

The rows scale the assumed target effect to 100%, 75%, or 50% of the observed effect. A smaller target effect requires more participants per arm to achieve the same stated power, because it is harder to distinguish a smaller difference from sampling variation. For example, the primary comparison of placebo with ixekizumab every two weeks gives planning figures of 31 participants per arm for 80% power and 41 for 90% power when planning for 100% of the observed effect. Planning for 50% of the observed effect gives 109 participants per arm for 80% power and 146 for 90% power. These are conditional illustrations, not claims about what the trial originally planned or what a future study must enroll.

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 = 0.184; treatment proportion p₁ = 0.356; average p̄ = 0.270.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6277 = 1.2302.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6158 = 0.5183.
4. n = (1.2302 + 0.5183)² / (0.1716)² = 103.8, rounded up to 104 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 <- 0.183908045977011                          # control proportion
p1 <- 0.355555555555556                          # 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(2696785)
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 = 104 (80% power), 139 (90% power)
 75% of observed effect: n per arm = 176 (80% power), 235 (90% power)
 50% of observed effect: n per arm = 373 (80% power), 499 (90% power)
power.prop.test: 103.8 
Simulated power at n = 104 per arm: 0.807 (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 primary results use logistic regression and report odds ratios with 95% confidence intervals and p-values. For placebo compared with adalimumab, the reported odds ratio is 2.73, with a 95% confidence interval from 1.35 to 5.52 and p = 0.005. For placebo compared with ixekizumab every four weeks, the odds ratio is 4.45, with a 95% confidence interval from 2.20 to 9.03 and p < 0.001. For placebo compared with ixekizumab every two weeks, it is 5.09, with a 95% confidence interval from 2.52 to 10.28 and p < 0.001.

The accompanying recalculations use unadjusted risk differences from the posted group summaries. They are not expected to be numerically identical to a logistic-regression odds ratio because they use a different effect measure and a different method. In addition, the record flags a discrepancy between the sponsor analyses and recalculations. The sponsor’s own analysis takes precedence for describing the trial’s inferential findings; the recalculated values are a supplementary unadjusted check.

The registry record does not state which covariates were included in the logistic regression or provide enough detail to reproduce the sponsor model. It also does not explain the source of the discrepancy. Therefore, the numerical distinction should be noted without attributing it to a particular adjustment, missing-data approach, or analytic decision. The posted sponsor estimates and their confidence intervals are the appropriate figures to quote as the trial’s reported analyses.

15. Multiplicity, Missing Data and Analysis Populations

The primary endpoint is identified as ASAS40 response at week 16, and its population is identified as all randomized participants. The registry record lists numerous additional outcomes and analyses, creating a multiplicity issue: when many endpoints or comparisons are tested, the chance of at least one apparently notable result can increase if each test is interpreted without adjustment. This general concern is particularly relevant to secondary outcomes, which should not automatically be treated as confirmatory evidence.

The registry does not report whether multiplicity was controlled, which testing hierarchy may have been used, or whether any secondary analyses were designated as confirmatory. It also does not report a complete statistical analysis plan or clarify whether the reported p-values are adjusted for multiple testing. The p-values should therefore be interpreted as posted for their individual analyses, without assuming family-wise error control or another correction.

Missing-data handling is also not reported in the registry record. The primary population is described as all randomized participants, but that alone does not specify how participants without an observed week 16 assessment were classified or modeled. The record does not state whether missing outcomes were imputed, treated as nonresponse, excluded from a particular analysis, or addressed through another method. Nor does it report the sensitivity analyses, if any, used to assess the effect of missing data.

The registry gives endpoint-specific group sizes, but does not explain any differences between the number randomized and the number contributing to each analysis. It also does not state the sponsor’s analysis estimand, the handling of treatment discontinuation, or how deviations from assigned treatment were treated. These omissions do not negate the posted results, but they limit independent reconstruction of the analysis and assessment of how robust the findings are to alternative assumptions. The registry record also does not report the trial’s original sample-size justification, interim-analysis plan, or a stopping rule, so none should be inferred.

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: adnexal torsion (5.9%), radius fracture (1.3%), road traffic accident (1.3%), blood creatine phosphokinase increased (1.3%), arthritis (1.3%).

The registry lists serious adverse event counts separately by treatment period and group. During blinded treatment, serious adverse events affected 0 of 86 participants in the placebo group, 3 of 90 in the adalimumab group, 1 of 83 in the ixekizumab every-two-weeks group, and 1 of 81 in the ixekizumab every-four-weeks group. No deaths are listed for these blinded-treatment groups.

These are counts of participants affected in the specified groups, not estimates of comparative safety or evidence that an event was caused by a treatment. The registry also lists serious-event counts during washout, extended-treatment, and follow-up periods. Those periods have different group labels and participant counts, and they should not be combined informally with the blinded-period groups to make a single comparison. No deaths are listed in the period-specific groups shown in the record.

The record includes other adverse-event counts as well as selected serious-event terms, but the summary does not provide a full account of event severity, exposure time, relatedness assessments, or comparative statistical analyses. Serious adverse event counts are therefore descriptive registry data. They do not establish that risks are equal or different between groups, and they do not capture the full balance of benefits and harms.

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

The primary result describes the proportion of randomized participants who met a specified multidomain ASAS40 response definition at week 16. The sponsor’s reported analyses show higher odds of that response in each active-treatment group than in the placebo group, with the stated confidence intervals and p-values. This is evidence about the recorded endpoint and the analyzed comparisons, not a complete account of every outcome important to participants.

The result does not mean that every participant in an active group responded, or that participants who did not meet ASAS40 had no improvement. A binary threshold groups participants into response and nonresponse categories; it does not show the amount of change for each person or how each of the four domains changed. The posted group percentages also do not predict an individual participant’s outcome.

The primary findings do not establish a difference between the two ixekizumab schedules. The sponsor analyses reported are each against placebo, and an active-versus-active comparison is not reported in the registry record. The results also do not establish long-term comparative effects: the primary endpoint is at week 16, while the registry describes later treatment changes through week 52. Those later periods involve different treatment assignments and are not the same comparison as the blinded-period primary analysis.

Nor do these results alone settle questions about safety, durability, function, imaging, or health status. The registry lists secondary outcomes and adverse-event counts, but the available descriptions and analyses do not constitute a complete assessment of all such questions. The registry does not report detailed missing-data methods, multiplicity procedures, or all model specifications, which leaves uncertainty about aspects of the analysis strategy.

General statistical context: Statistical evidence is one component of interpreting a clinical trial. Effect estimates describe the observed contrast, confidence intervals express uncertainty under the analysis method, and study design and analysis details affect how widely the result can be applied. The posted findings should be understood within this specific population, endpoint, time point, and set of reported comparisons. They are not a treatment recommendation and do not by themselves establish a universal conclusion for other populations or settings.

18. Why This Trial Matters Statistically

This trial presents several statistical features that matter when interpreting clinical evidence. It is randomized and double-blind, with both placebo and active control, and it evaluates two ixekizumab schedules. That structure supports comparisons of each assigned group during the blinded period, while also making it important to distinguish the planned placebo contrasts from any comparison between the active schedules. The registry’s sponsor analyses report the former; a direct active-versus-active result is not reported.

The primary endpoint is a multidomain response threshold rather than a single continuous measurement. This makes the outcome easy to express as the percentage meeting a defined response, but it also means that the result depends on crossing a threshold across several domains. The distinction between response frequency and average change is statistically important: they answer different questions and should not be conflated.

The record also illustrates why effect measures need clear labeling. Sponsor analyses use odds ratios from logistic regression, while the accompanying recalculations use unadjusted risk differences. These measures do not express effects on the same scale. Because a discrepancy is flagged, the sponsor’s own analysis takes precedence; the recalculations should remain clearly identified as unadjusted summaries rather than alternatives to the reported model.

Finally, the trial reports multiple outcomes and analyses. A primary result can be distinguished from secondary findings, but the registry record does not describe multiplicity control, full missing-data procedures, or the original sample-size rationale. Those details affect how strongly the broader set of findings can be interpreted. Reading the estimates together with their uncertainty, outcome definitions, and reporting limits is more informative than focusing on a single p-value.

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 registry-level information leaves important trial-specific details unavailable. Although the study is described as randomized, double-blind, and parallel-group, the randomization ratio, sequence generation, allocation concealment, and blinding procedures are not reported in the registry record. Detailed eligibility criteria and baseline characteristics are also not given in the information recorded for these results, limiting assessment of how closely the analyzed participants resemble other populations.

The primary endpoint occurs at week 16, while the described dosing schedules extend through week 14 during the blinded period and treatment changes occur during longer follow-up. The registry does not explain the timing choices in detail. The primary result therefore should not be extended to the later treatment period, where participants could receive different regimens.

The sponsor’s logistic-regression specification and covariates are not reported, and the record flags a discrepancy with simple unadjusted recalculations. The source of that discrepancy is not explained. The sponsor analysis takes precedence, but the absence of model details limits independent reproduction. Similarly, missing-data handling, sensitivity analyses, treatment discontinuation handling, multiplicity control, and the original sample-size justification are not reported in the registry record.

There are many listed outcomes and analyses, while the record gives detailed numerical results for only some of them. This limits interpretation of the overall pattern and makes unadjusted secondary p-values less definitive. The safety summary is also descriptive and separated by treatment period; it does not provide the fuller exposure, relatedness, or comparative analysis information needed to characterize all safety questions. These limitations reflect gaps in the registry-level reporting and should not be mistaken for proof that the trial did or did not address them in other documents.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study of Ixekizumab (LY2439821) in bDMARD-Naive Participants With Radiographic Axial Spondyloarthritis — NCT02696785.
• Registry record last updated 2019-11-19; status last verified 2018-11.
• Results first posted 2019-11-19.
• 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 phase 3, randomized, double-blind, parallel-group study in bDMARD-naive participants with radiographic axial spondyloarthritis. It lists 341 participants enrolled and a primary endpoint of ASAS40 response at week 16 in all randomized participants. The blinded-period comparisons involved placebo, adalimumab, and two ixekizumab schedules.

The sponsor reports logistic-regression odds ratios favoring each active group over placebo for the primary endpoint. Unadjusted recalculations are also available, but the record flags a discrepancy, so the sponsor’s analysis takes precedence. Secondary outcomes and period-specific adverse-event counts provide additional context, while multiplicity procedures, detailed missing-data handling, and several other statistical-plan details are not reported in the registry record.