Long-Term Extension Trial of Tildrakizumab to Prove Its Safety in Subjects With Psoriatic Arthritis Who Have Previously Completed Study With Tildrakizumab.: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Long-Term Extension Trial of Tildrakizumab to Prove Its Safety in Subjects With Psoriatic Arthritis Who Have Previously Completed Study With Tildrakizumab. (NCT03552276), a non-randomized phase 2, phase 3 study. The primary outcome is Number of Participants With Adverse Events.

2. Clinical Question

The study concerns safety during long-term tildrakizumab treatment among people with psoriatic arthritis who had previously completed a study of tildrakizumab. Its primary outcome is the number of participants with adverse events through week 208. The registry lists treatment groups with different doses and schedules, including groups that switched from a higher dose to a lower dose.

This is therefore a descriptive safety question rather than a randomized test of comparative efficacy. The posted counts can describe how many participants were recorded with serious and other adverse events in each listed group. They do not establish that differences between groups were caused by dose or schedule. The registry does not report a primary analysis result, a comparison estimate, or an analysis population definition.

3. Trial Design

This completed study is registered as a phase 2 and phase 3 long-term extension study. It began on 2018-07-11 and had primary completion on 2023-09-18. Enrollment was 281. The stated purpose was to demonstrate the safety of tildrakizumab in participants with psoriatic arthritis who had previously completed a tildrakizumab study.

Allocation is listed as non-randomized, masking as none, and the study model as sequential. Treatment groups include tildrakizumab 200 mg q4 weeks, tildrakizumab 200 mg q12 weeks, and tildrakizumab 100 mg q12 weeks. Other listed groups switched from 200 mg q4 weeks to 100 mg q12 weeks, or from 200 mg q12 weeks to 100 mg q12 weeks. These are not randomized arms, and they do not form a like-for-like control comparison.

The registry lists adverse events through week 208 as the primary outcome. It also reports counts of participants affected by serious and other adverse events for each treatment group. The listed group sizes at risk vary, so the counts should be read in the context of those group sizes; they are not directly comparable as though every group had the same number of participants.

The registry record does not describe how participants entered each sequence, the rationale for individual dose changes, the detailed eligibility criteria, or the timing and conduct of safety assessments. A more detailed protocol description is not reported in the registry record. The record marks the study as completed, but completion status alone does not supply a formal efficacy or safety 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: This was a long-term extension (LTE) study in subjects with Psoriatic arthritis who had completed the treatment with tildra in the parent study,CLR\_16\_23(NCT02980692). In LTE, there was no randomization and subjects continued to receive the treatment assigned during the parent study into the LTE upto Wk 52 to maintain blind of the parent study. Post the DBL of CLR 16-23, the blind was no longer needed, all subjects who had entered the LTE study received open label dose of tildra 100 mg q12 wks.

Overall Study

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With Adverse Events, measured over upto week 208.

The primary endpoint is the number of participants with adverse events through week 208. It is a count of people who experienced an event, rather than a count of all event episodes. If one participant experienced more than one event, the participant-count outcome would not, by itself, describe the total number or recurrence of those episodes.

A participant count is useful for describing the breadth of recorded safety experience: it indicates how many people in a group were affected during the stated follow-up period. The registry also gives separate counts for participants with serious adverse events and participants with other adverse events. These categories provide a way to distinguish serious events from the other events reported, but the registry record does not give the detailed classification rules or event-level summaries in the outcome description.

The endpoint is a safety measure, not a measure of change in psoriatic arthritis symptoms or disease activity. It does not by itself show whether an event was caused by treatment. Causality assessment, severity grading, and the detailed definitions used for each event are not reported in the registry record. Nor does a count alone describe the timing of events or account for differences in follow-up across participants.

The stated timeframe is through week 208. This gives the intended horizon for the outcome, but the registry does not explain whether all participants contributed observations for the full period or how incomplete follow-up was handled. Those details are necessary to understand the extent and completeness of observation behind the counts.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a non-randomized, sequential study with no masking. These design features matter when interpreting safety counts. Random assignment can help balance measured and unmeasured participant characteristics across comparison groups; without randomization, groups may differ for reasons that are not described in the registry. In a sequential treatment study, participants’ dose histories and changes in treatment are also relevant. A comparison across such groups is descriptive unless a suitable analysis addresses differences in participant characteristics, treatment history, follow-up, and other potential sources of bias. The registry does not report such an analysis.

What do the participant counts represent?

The primary outcome counts participants with adverse events through week 208. The posted serious and other adverse-event summaries likewise give participant counts and group sizes at risk. A count indicates the number of people recorded in the category, not the number of event episodes. A participant may have more than one event, so event counts and counts of affected participants answer different questions. The registry does not provide event-level totals or a detailed account of how repeat events were handled.

Counts also need a denominator and a defined observation period to support interpretation. The registry gives group sizes at risk alongside the affected-participant counts, and the stated endpoint timeframe is through week 208. However, it does not report how much follow-up each participant contributed, whether all participants were observed to the same point, or how withdrawal and missing observations were handled. A raw count does not adjust for unequal follow-up or differences in who entered each group.

Why are these groups not a causal comparison?

For a randomized comparison, treatment assignment is designed to make groups comparable on average. Here, assignment is explicitly non-randomized, and some groups represent a change from 200 mg to 100 mg q12 weeks. The treatment histories and reasons for moving between regimens could be associated with participant characteristics or prior experience. Those details are not reported in the registry record. As a result, the difference between observed counts in two groups cannot be attributed to the treatment schedule based on these data alone.

Masking is listed as none. In general, masking can reduce the influence of expectations on reporting or assessment, depending on the outcome and the procedures used. For adverse events, what is recorded may depend on how events are identified, collected, classified, and judged. The registry does not provide enough information about these procedures to assess their possible influence.

What can a formal analysis add?

A comparative analysis could estimate a difference between groups and describe its uncertainty, for example with a confidence interval. In general, a confidence interval gives a range of values compatible with the data and the method’s assumptions; it helps show precision rather than proving that an effect is present or absent. A hypothesis test can assess compatibility with a specified null hypothesis, but its result does not replace evaluation of design, bias, or clinical context. The registry lists 0 analyses and reports no comparison estimate, confidence interval, or p-value for the primary outcome.

Different models may be appropriate for different outcomes. In general, a binary outcome analysis treats whether a participant experienced an event as the outcome. A time-to-event analysis can use event timing and account for varying observation periods under its assumptions. A count model may be relevant when the outcome is the number of recurrent events; over-dispersion matters when event-count variability exceeds what a simple model assumes, because it can affect uncertainty estimates. These are general statistical concepts, not methods reported for this study. The registry record does not report a model for the primary endpoint or event-level analyses.

How should planning illustrations be read?

Any sample-size illustrations associated with the posted results are planning exercises, not observed trial findings and not evidence of observed power. The stated assumptions use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The planning effect is framed as a stated fraction of the observed effect. For non-time-to-event outcomes, such illustrations are expressed as participants per arm; time-to-event illustrations are described in terms of total events. The registry record does not report the trial’s own sample-size justification, and the specific illustration values or effect fraction are not reported in the record.

These planning calculations cannot repair the design limitations. A sample-size illustration concerns the size of a future study under specified assumptions; it does not turn non-randomized groups into comparable controls, explain missing observations, or establish a causal effect. The registry does not report a protocol-based sample-size rationale, a statistical analysis plan, or interim-analysis procedures. Those aspects therefore cannot be inferred from the posted counts.

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("Tildrakizumab 200 mg q4 Weeks", "Tildrakizumab 200 mg q12 Weeks", "Tildrakizumab 100 mg q12 Weeks", "Tildrakizumab 200 mg q4 Weeks Switched to Tildraki", "Tildrakizumab 200 mg q12 Weeks Switched to Tildrak")
n      <- c(5, 22, 49, 54, 151)
events <- c(5, 14, 36, 44, 125)
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  Tildrakizumab 200 mg q4 Weeks  5  5  100.0  47.8  100.0  56.6  100.0  54.1  99.6
ARM  Tildrakizumab 200 mg q12 Weeks  22  14  63.6  40.7  82.8  43.0  80.3  42.7  80.3
ARM  Tildrakizumab 100 mg q12 Weeks  49  36  73.5  58.9  85.1  59.7  83.8  59.7  83.8
ARM  Tildrakizumab 200 mg q4 Weeks Switched to Tildraki  54  44  81.5  68.6  90.7  69.2  89.6  69.1  89.6
ARM  Tildrakizumab 200 mg q12 Weeks Switched to Tildrak  151  125  82.8  75.8  88.4  76.0  88.0  76.0  88.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 1 outcome measure and 0 analyses. It identifies adverse-event participants through week 208 as the primary outcome, but does not report a formal statistical analysis of that endpoint. No hypothesis tests, p-values, confidence intervals, or adjusted treatment comparisons are reported. As a result, there is no basis in the registry record for assessing statistical evidence across multiple tested outcomes or comparisons.

Multiplicity concerns arise when analyses involve multiple outcomes, time points, groups, or hypotheses. In general, examining many comparisons can increase the chance of a seemingly notable result arising by chance. Adjustment procedures or a prespecified hierarchy can address that issue in some settings, but the record does not report whether multiplicity was considered or what approach, if any, was planned. The absence of reported analyses means that no adjustment strategy can be evaluated from these results.

The registry does not define the primary analysis population. Its population field for the primary outcome is blank, and the record does not say whether all enrolled participants, participants receiving treatment, or another defined group contributed to the endpoint. The group sizes at risk are reported for the adverse-event summaries, but the rules used to establish those denominators are not described.

Missing-data handling is also not reported in the registry record. The record does not explain how participants who stopped treatment, withdrew, or had incomplete follow-up were handled, nor does it specify whether event information after treatment discontinuation was collected. Without these details, the completeness and comparability of observation through week 208 are uncertain. The registry also does not report imputation, sensitivity analyses, or other procedures for addressing missing outcome information.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: abdominal abscess (20.0%), craniocerebral injury (20.0%), subdural haematoma (20.0%), tibia fracture (20.0%), subarachnoid haemorrhage (20.0%).

The serious adverse-event counts are 3 of 5, 2 of 22, 7 of 49, 3 of 54, and 25 of 151 across the five listed treatment histories, in the order described in the registry. These are numbers of affected participants, not numbers of serious-event episodes. The other-adverse-event counts are 5 of 5, 14 of 22, 36 of 49, 44 of 54, and 125 of 151. The registry also reports deaths of 0, 1, 0, 0, and 1 in those groups, respectively.

These figures describe the recorded safety experience in each group. They are not a randomized comparison, and the group sizes differ. The registry does not report adjusted estimates or uncertainty intervals, so the counts alone do not establish whether differences are meaningful or attributable to a treatment regimen. Nor do they indicate whether an adverse event was considered related to tildrakizumab.

The registry lists several serious-event terms with percentages, including five terms at 20.0% and Retinal migraine at 4.5%. Their denominators and event-level context are not explained in the reported information, so these percentages should not be interpreted as comparable risks across treatment groups. Definitions, severity assessments, causes of death, and detailed event narratives are not reported in the registry record.

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

The posted results describe adverse-event experience in a completed, long-term extension study among participants with psoriatic arthritis who had previously completed a tildrakizumab study. They provide participant counts for serious and other adverse events across the listed treatment histories, and the registry states that the primary outcome timeframe extends through week 208. These figures are descriptive summaries of the recorded groups.

They do not establish that one dose or schedule is safer than another. The study was non-randomized, unmasked, and sequential, and some groups reflect a change in dose. Without random assignment and a reported analysis accounting for group differences, the observed counts cannot isolate the effect of treatment from other influences. The record contains no formal comparison estimate or measure of its precision.

The counts also do not show how many event episodes occurred, when events arose, how long participants were followed, or whether events were judged related to treatment. The registry does not report detailed event definitions, missing-data methods, the primary analysis population, or the treatment of participants with incomplete follow-up. These omissions limit interpretation of both the completeness and the meaning of the safety summaries.

The record therefore supports a narrow conclusion: it documents that adverse events, including serious events, were recorded among participants in each listed group during the extension study. It does not provide a basis for a causal claim, a comparative safety ranking, or a conclusion about efficacy. Further interpretation would require the protocol and fuller analysis information, which are not reported in the registry record.

14. Why This Trial Matters Statistically

Long-term extension studies can add descriptive information about safety experience beyond the earlier study that participants completed. This record is relevant to statistical interpretation because it presents safety counts over a stated timeframe of through week 208 and includes several treatment histories, including groups that switched regimens. It also makes clear that the design was non-randomized and sequential, features that shape what can be concluded from the results.

For biostatisticians and clinical researchers, the distinction between a count and a comparative estimate is important. The registry reports the number of participants with serious and other adverse events, but it does not report an estimated contrast between regimens or the uncertainty around one. A larger count in one group cannot be interpreted independently of group size, follow-up, participant mix, and treatment history. Those factors are not fully.

The record also illustrates why the analysis population, missing-data rules, and event definitions matter for safety reporting. Knowing who contributed to each group and how incomplete observation was handled is essential to understand what the counts represent. These details are not reported in the registry record, as are a formal analysis plan and multiplicity procedures.

Its statistical importance is therefore not that it resolves comparative safety questions, but that it presents real-world trial-record summaries whose design and reporting boundaries must be respected. It offers a descriptive account of recorded events in a long-term extension setting while leaving important questions about precision, comparability, and event attribution unanswered.

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.

The main limitation is the non-randomized, sequential design. The listed groups are not like-for-like control arms, and some represent a switch in dose and schedule. The registry does not explain why participants moved between regimens or describe characteristics that might differ across groups. Consequently, the group counts cannot support a causal comparison of treatment schedules.

The registry reports no formal analyses for the primary outcome. It provides no adjusted estimate, confidence interval, p-value, or other description of statistical uncertainty. It also does not report the analysis population, a statistical analysis plan, the sample-size justification, or interim-analysis procedures. The planning assumptions described for illustrative sample-size calculations do not constitute the trial’s own design rationale or an analysis of its results.

Safety interpretation is further limited by absent detail about event definitions, seriousness assessment, causality assessment, timing, repeat events, and causes of death. The record does not describe how adverse events were collected or adjudicated. Serious-event term percentages are listed, but their denominators and relationship to the group summaries are not explained in the registry record.

Finally, follow-up completeness and missing-data handling are not reported. Although the outcome timeframe is through week 208, the record does not state whether every participant had that duration of observation, how withdrawals were handled, or whether events after treatment discontinuation were captured. These uncertainties constrain interpretation of the counts as a complete account of long-term safety experience.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Long-Term Extension Trial of Tildrakizumab to Prove Its Safety in Subjects With Psoriatic Arthritis Who Have Previously Completed Study With Tildrakizumab. — NCT03552276.
• Registry record last updated 2024-11-21; status last verified 2024-10.
• Results first posted 2024-11-21.
• 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

NCT03552276 is a completed phase 2 and phase 3 long-term extension study sponsored by Sun Pharmaceutical Industries Limited. The registry lists enrollment of 281, non-randomized allocation, no masking, and a sequential study model. The study began on 2018-07-11 and had primary completion on 2023-09-18.

Participants with psoriatic arthritis had previously completed a tildrakizumab study. Listed regimens include tildrakizumab 200 mg q4 weeks, 200 mg q12 weeks, and 100 mg q12 weeks, as well as treatment histories that switched from 200 mg to 100 mg q12 weeks.

The primary outcome is the number of participants with adverse events through week 208. The registry reports group-level counts of participants with serious and other adverse events and deaths, but lists 0 analyses. It does not report a formal comparative analysis, analysis population, missing-data handling, or detailed statistical plan. The safety counts are descriptive and do not establish causal differences between treatment histories.