A Maintenance Study of Mirikizumab in Participants With Moderately to Severely Active Ulcerative Colitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Maintenance Study of Mirikizumab in Participants With Moderately to Severely Active Ulcerative Colitis (NCT03524092), a non-randomized phase 3 study. The primary outcome is Percentage of Participants in Clinical Remission at Week 40 (Mirikizumab Induction Responders).

2. Clinical Question

The central question is whether participants with moderately to severely active ulcerative colitis who responded to mirikizumab during the preceding induction study maintain clinical remission through Week 40 while receiving mirikizumab, compared with the maintenance groups described in the registry. The endpoint is clinical remission at Week 40, defined using rectal bleeding, stool frequency and endoscopic findings. This is a maintenance question: it concerns participants after an induction period, rather than an unselected population beginning therapy.

The study also records outcomes for participants who responded to placebo during induction, participants who did not respond during induction, delayed responders after extended induction, and participants who entered a loss-of-response rescue period. These groups followed different treatment pathways. Their outcomes should not be assumed to answer the same maintenance question or to be directly comparable without the relevant analysis details.

The registry record identifies the primary endpoint as the percentage of mirikizumab induction responders in clinical remission at Week 40. It describes a modified intention-to-treat population based on randomization, receipt of at least one dose of mirikizumab, and a baseline Modified Mayo Score. The record does not report the numerical primary endpoint estimate, its confidence interval, or a complete description of the particular analysis population used for the primary result. Consequently, it establishes what was intended to be measured, but not the size or precision of the result.

3. Trial Design

This is a phase 3, multicenter, double-blind, parallel-arm maintenance study in ulcerative colitis. The registry lists enrollment as 1328 and status as completed. The recorded study start is 2018-10-19, and primary completion is recorded as 2021-11-03. The official title describes the study as placebo-controlled, while the allocation entry is non-randomized. The registry record also cautions that the arms are not a like-for-like control comparison. These details make it important not to infer a randomized treatment contrast from the title or arm descriptions alone.

The maintenance pathways depend on response status in the preceding 12-week induction study, LUCENT-1. Participants who responded to blinded mirikizumab could continue mirikizumab 200 mg subcutaneously every 4 weeks, or enter a placebo-withdrawal pathway in which mirikizumab was stopped. Participants who responded to blinded placebo continued placebo. The record describes parallel pathways for a ME2 cohort.

Other participants followed different pathways. Induction nonresponders received additional open-label mirikizumab intravenously during extended induction. Those who responded after extended induction could enter open-label subcutaneous maintenance. Participants who lost response during maintenance could receive open-label intravenous rescue treatment. These pathways are relevant context, but they are not interchangeable with the primary maintenance population.

The endpoint timeframe is Week 40. The registry record does not report the detailed visit schedule beyond the schedules stated for treatment pathways, or the full protocol for handling treatment changes and discontinuation in the primary analysis. It also does not report a complete statistical analysis plan. The study title and design entries therefore describe important features, but do not resolve all questions about the exact comparison or analysis.

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: China Maximized Extended Enrollment (ME2):This is an extension phase of the main study,with an additional 151 participants enrolled in China.Safety was monitored and data was reported under Adverse Events (AE) section. Per global SAP and China ME2 SAP addendum,ME2 participants were included in a combined China population;China analyses pre-specified as descriptive, i.e.,exploratory, non-inferential (no multiplicity control/p-values); hence outcomes not reported separately by ME2 treatment arms.

Only the first 6 of 12 groups are shown.

Blinded Maintenance Period (Wk 0-40)

Reasons for not completing this period:

Loss of Response Rescue Period

Reasons for not completing this period:

Open Label Extended Induction (Wk 0-12)

Reasons for not completing this period:

Open Label Maintenance Period (Wk 12-40)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Modified intention-to-treat (mITT): All randomized participants receiving at least one dose of mirikizumab with baseline Modified Mayo Score; analyzed by randomized arm. Per Global SAP v4 and China ME2 Addendum, ME2 participants were included in a combined China population. China analyses were pre-specified as descriptive, i.e., exploratory, non-inferential (no multiplicity control/p-values). These are not part of confirmatory primary/secondary analyses; hence ME2 arms not reported separately

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.

Only the first 6 of 9 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants in Clinical Remission at Week 40 (Mirikizumab Induction Responders), measured over Week 40.

The primary endpoint is the percentage of mirikizumab induction responders in clinical remission at Week 40. Remission is defined using a 9-point modified Mayo score: rectal bleeding must score 0; stool frequency must score 0 or 1, with at least a one-point decrease from baseline; and endoscopy must score 0 or 1, excluding friability.

The components capture different aspects of ulcerative colitis. Stool frequency and rectal bleeding are based on participant diaries. Endoscopy is based on central reading of colonoscopy or sigmoidoscopy. Each component is scored from 0 to 3, with higher scores representing more abnormal findings. Combining symptoms with endoscopic assessment makes the endpoint broader than a symptom-only measure, while still relying on specified scoring rules.

A percentage is used because the outcome is whether each participant meets the remission definition at the specified time. The group percentage describes how common that defined state was among the participants included in the analysis. It does not describe how much each individual improved, nor does it by itself establish a causal treatment effect. Interpretation also depends on the analysis population, missing-outcome handling and the comparability of the groups.

The registry record identifies a 95% confidence interval as the dispersion measure, but does not report the primary estimate or its interval. The endpoint definition is therefore available, while the observed frequency and its precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a binary endpoint summarized as a percentage: each participant either meets the specified clinical-remission definition at Week 40 or does not. The registry describes the remission rule using rectal bleeding, stool frequency and endoscopy subscores. Because the outcome is binary, the group summary is a proportion expressed as a percentage rather than a mean change on a continuous scale.

What does a confidence interval convey?

A confidence interval describes uncertainty around an estimate under the statistical procedure used to calculate it. For a percentage, the interval helps indicate how precisely the observed group proportion is estimated. A narrow interval generally indicates greater precision than a wide interval, while neither interval width nor the point estimate alone answers whether a treatment caused an outcome. Interpretation depends on the analysis population, design and comparison being made.

The endpoint entry specifies a 95% confidence interval, but no interval limits or primary percentage are reported in the registry record. Precision therefore cannot be judged from the record. There is also no numerical contrast or interval for a between-group difference in the primary endpoint.

Why does the analysis population matter?

The endpoint title refers to mirikizumab induction responders. The population description defines a modified intention-to-treat population as randomized participants who received at least one dose of mirikizumab and had a correctly measured baseline Modified Mayo Score, with participants analyzed according to their randomized arm regardless of treatment actually received. These definitions address different aspects of who is included and how group assignment is treated. The record does not make fully clear how the responder description and the modified intention-to-treat definition combine for the primary endpoint.

Analyzing participants according to randomized arm can preserve the original group assignment in a randomized trial, even when received treatment differs. But the allocation entry is non-randomized, and the registry cautions against treating the arms as a like-for-like comparison. The meaning and protection offered by an arm-based analysis therefore cannot be assumed from the population wording alone.

How should planning calculations be read?

Any planning illustration based on the observed effect is a hypothetical sample-size calculation, not an observed measure of power. The stated calculation assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect considered is a stated fraction of the observed effect. Such illustrations describe the number of participants per arm that would be needed under those assumptions to detect a target effect. They do not show the probability that this completed study detected an effect, and they do not replace the trial's own design justification. The registry record does not report the trial's sample-size justification.

The suitability of a normal approximation depends on the outcome and data structure. For a percentage outcome, the approximation may be less dependable when event counts are sparse or proportions are near the boundaries. More generally, model assumptions should be checked against the actual data. The record does not report enough numerical endpoint information to evaluate those conditions for the primary analysis.

What do the other outcomes add?

The secondary outcomes cover additional remission and response definitions, patient-reported quality of life and bowel urgency, and fecal calprotectin. They represent different measurements and scales. Binary outcomes summarize whether a threshold was met; change-from-baseline outcomes describe movement on a measured scale. Results across these measures can complement the primary outcome, but their interpretation requires estimates, uncertainty intervals and analysis details. The registry record lists the outcomes without the numerical findings needed for that assessment.

The study also has different treatment pathways for induction responders, nonresponders, delayed responders and participants who lost response. Combining such groups without a clearly stated estimand and analysis plan could obscure the question each pathway addresses. The record's treatment descriptions identify the pathways, but do not report a complete statistical account of how each contributed to primary or secondary analyses.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Maintenance Period: Miri IR - PBO SC", "Maintenance Period: Miri IR - 200 mg Miri SC")
n      <- c(179, 365)
events <- c(45, 182)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Maintenance Period: Miri IR - PBO SC  179  45  25.1  19.0  32.2  19.4  32.0  19.4  32.0
ARM  Maintenance Period: Miri IR - 200 mg Miri SC  365  182  49.9  44.6  55.1  44.8  55.0  44.8  55.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and multiple secondary outcomes. When many outcomes or comparisons are assessed, the chance of obtaining at least one apparently notable result can increase unless the analysis plan accounts for multiplicity. The registry record does not report whether a multiplicity adjustment was planned, which outcomes or contrasts were included in any testing hierarchy, or how confirmatory claims were to be controlled. Without those details and numerical results, the secondary outcome list should be read as a set of registered measures, not as a set of independently confirmed conclusions.

The missing-data approach for the primary endpoint is not reported in the registry record. The record does not specify how participants without a Week 40 assessment, those who discontinued, or those who received rescue treatment were handled in the endpoint calculation. These choices can affect a binary remission percentage, especially when the probability of having an observed assessment differs between groups. The trial's detailed sensitivity analyses are also not reported in the registry record.

The population description identifies a modified intention-to-treat population: randomized participants receiving at least one dose of mirikizumab and with a correctly measured baseline Modified Mayo Score, analyzed by randomized arm. The primary endpoint title separately specifies mirikizumab induction responders. The record does not fully describe how the responder restriction relates to the stated population definition. It also says ME2 participants were included in a combined China population under a global analysis plan and a China addendum, but the description of China analyses is incomplete in the registry record.

These population and missing-data details matter because an estimate is only interpretable for the participants and outcome handling that generated it. No full statistical analysis plan, multiplicity procedure or missing-data rule is reported in the registry record.

12. 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: colitis ulcerative (8.3%), ankle fracture (8.3%), colorectal adenoma (8.3%), inguinal hernia (4.8%), clostridium difficile infection (4.8%).

The serious adverse event entries are presented by study group, with the number at risk and the number affected. In the maintenance group continuing 200 mg mirikizumab, 13 of 389 participants were recorded with a serious adverse event; in the mirikizumab-induction-responder placebo group, the figures are 16 of 192. The placebo-induction-responder placebo group records 8 of 135. The ME2 maintenance groups are listed separately, as are rescue, extended-induction and open-label maintenance groups.

These counts should be read in the context of the distinct pathways. Some groups received blinded maintenance treatment, some received rescue treatment after loss of response, and others received additional or open-label treatment after induction. The registry record does not provide a common exposure duration or a like-for-like safety comparison across all these groups. The numbers at risk are not evidence that the groups had equivalent follow-up or underlying characteristics.

The record also lists other adverse events and deaths by group. One death is recorded in the mirikizumab-induction-responder placebo group, and zero in each other listed group. The entries do not, by themselves, establish whether an event was caused by a study treatment. Serious adverse event counts describe events meeting a seriousness category, not severity ratings for every adverse event or a comparative causal effect. The listed serious-event terms and percentages are registry entries; their interpretation depends on the underlying denominators and reporting definitions.

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

The registry record establishes that the study assessed clinical remission at Week 40 in a maintenance setting following induction response. It supplies the endpoint definition, describes treatment pathways and identifies an intended modified intention-to-treat population. Those details explain what was to be measured and in whom, but they do not reveal the primary numerical result.

The record does not report the Week 40 remission percentage, its 95% confidence interval, or a numerical comparison between the maintenance groups. It is therefore not possible to quantify the observed remission frequency, judge its precision, or describe the size of a difference from this record. The endpoint's clinical definition cannot stand in for the missing estimate.

The study's entry for allocation is non-randomized, despite randomized language in the official title and some arm descriptions. The registry specifically warns that the arms are not a like-for-like control comparison. Accordingly, the group labels alone do not justify interpreting a difference as caused by treatment. That concern remains even if a numerical contrast is reported elsewhere, unless the design and analysis details clarify the basis for the comparison.

The enrolled population and pathways also constrain the question. The primary endpoint concerns mirikizumab induction responders, not all participants with ulcerative colitis or all those who began induction. Nonresponders, delayed responders and participants entering rescue treatment followed different routes. Their results, if considered, would address different clinical and statistical questions.

For a fuller interpretation, the registry would need to report the endpoint estimates and uncertainty, the precise analyzed groups, missing-data handling, multiplicity procedures and the planned comparison. The available record supports a description of the design and outcome definitions, but not a conclusion about the magnitude or reliability of the primary result.

14. Why This Trial Matters Statistically

This study illustrates why an endpoint definition and a numerical finding are distinct parts of clinical-trial evidence. A precise remission rule can make the intended outcome understandable and reproducible, but without the group estimate and uncertainty interval, readers cannot assess the observed frequency or its precision. The registry record contains the Week 40 definition, yet not the numerical primary result.

It also illustrates the importance of aligning the design description with the proposed comparison. A placebo-controlled title and arm descriptions referring to randomization appear alongside a non-randomized allocation entry and a warning against treating arms as like-for-like controls. That conflict is not a minor labeling issue: allocation affects how much confidence can be placed in a between-group contrast and what causal interpretation may be appropriate.

The responder-enriched maintenance question is another important statistical feature. A study of people who responded during an earlier induction period addresses maintenance among selected responders. It should not be read as estimating outcomes for everyone who might start treatment. Distinct pathways for nonresponders, delayed responders and participants receiving rescue reinforce the need to keep analysis populations separate.

Finally, a registered list of secondary measures does not establish how multiple outcomes were handled, and an endpoint definition does not explain how missing Week 40 observations were treated. Those analysis choices affect interpretation. The record makes clear which questions were intended to be examined, but the missing results and methods leave important limits on what can be concluded statistically.

15. 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.

A central limitation is the absence of numerical results for the primary endpoint in the registry record. The remission percentage and its 95% confidence interval are not reported, so the primary estimate's magnitude and precision cannot be evaluated. Numerical findings for the listed secondary outcomes are also not included in the record excerpt.

The allocation information is internally difficult to reconcile. The official title describes a randomized, placebo-controlled study and arm descriptions refer to randomization, while the allocation entry says non-randomized. The record also cautions that arms are not a like-for-like control comparison. Without clarification, the strength and interpretation of between-group contrasts remain uncertain.

The primary endpoint title focuses on mirikizumab induction responders, while the population description gives a modified intention-to-treat definition involving randomization, dosing and a baseline score. The record does not fully explain how these criteria were combined for the primary analysis. Details on missing outcomes, discontinuation, rescue treatment and sensitivity analyses are not reported in the registry record.

Multiplicity handling and the trial's sample-size justification are not reported in the registry record. The record also does not supply sufficient analysis detail to assess whether the primary comparison followed a prespecified statistical plan. Its descriptions of extended induction, rescue and open-label maintenance clarify that participants could follow different treatment pathways, but do not establish how all such pathways were incorporated into the reported efficacy analyses.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Maintenance Study of Mirikizumab in Participants With Moderately to Severely Active Ulcerative Colitis — NCT03524092.
• Registry record last updated 2026-05-13; status last verified 2026-05.
• Results first posted 2022-11-25.
• 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.

19. Record Summary

The record describes NCT03524092, a completed phase 3 maintenance study of mirikizumab in participants with moderately to severely active ulcerative colitis. Enrollment is listed as 1328. The study start is recorded as 2018-10-19 and primary completion as 2021-11-03. Its primary outcome is the percentage of mirikizumab induction responders in clinical remission at Week 40, defined using rectal bleeding, stool frequency and endoscopy subscores.

Study pathways include continued mirikizumab, placebo maintenance, extended induction for nonresponders, open-label maintenance for delayed responders, and rescue treatment after loss of response. The allocation entry is non-randomized, and the record cautions that arms are not a like-for-like control comparison despite randomized language in the title and arm descriptions.

The numerical primary endpoint estimate and confidence interval, missing-data procedures, multiplicity methods and complete analysis plan are not reported in the registry record. The record therefore supports description of the study question and design, but not an assessment of the primary result's magnitude or precision.