A Study of LY2439821 in Rheumatoid Arthritis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY2439821 in Rheumatoid Arthritis (NCT01236118), a non-randomized phase 1 study. The primary outcome is Number of Participants With Adverse Events (AEs) [Clinically Significant Events].

2. Clinical Question

3. Trial Design

This was a Phase 1, non-randomized, open-label, parallel-group study of LY2439821. The registry describes it as an extension study for Japanese participants with rheumatoid arthritis who had completed Study I1F-JE-RHAL (NCT01253265). Participants were also taking concomitant methotrexate. The stated purpose was to evaluate safety and tolerability during subcutaneous dosing over 48 weeks.

The registry lists 28 enrolled participants and three dose groups: 30 mg, 80 mg, and 160 mg. The first two group descriptions state that participants began with a weekly schedule for the first 3 doses and then received doses every 2 weeks until week 44. Those descriptions also mention a possible increase to 160 mg once the safety of LY2439821 180 mg was confirmed by a Data Review Meeting; the available wording is incomplete. The 160 mg group description states that dosing was every 2 weeks for the first 3 doses and then every 4 weeks until Week 44. These are descriptions of the regimens, not evidence that the groups were comparable.

Because the study was open-label and non-randomized, participants and investigators were not masked to treatment, and the registry does not identify a randomized assignment procedure. The dose groups may differ in ways that affect adverse-event counts. No protocol details explaining how participants entered each dose group are reported in the registry record. The study is marked completed. Its recorded primary completion date is 2013-01, and its start is listed as 2010-12.

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: Eligible participants must have completed Study I1F-JE-RHAL (NCT01253265) to meet the enrollment criteria of this study.

Overall Study

Reasons for not completing this period:

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

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With Adverse Events (AEs) [Clinically Significant Events], measured over Baseline through study completion (up to Week 56).

The primary outcome is the number of participants with adverse events, including serious adverse events, from baseline through study completion, up to Week 56. The population is all enrolled participants. The outcome description says it counts participants who experienced one or more adverse events and serious adverse events. It also refers to adverse events of all causalities and drug-related events; the record does not provide a separate breakdown of the primary count by attribution.

This is a participant-count outcome: it records whether participants experienced an event, rather than how many total event episodes occurred or how long participants remained event-free. A participant with multiple events can still contribute to a count of participants with at least one event. Counts are useful for describing how many people in a study experienced the safety outcomes being monitored. They do not, by themselves, establish why an event occurred or whether the event was caused by the study drug.

Safety and tolerability were the stated purpose of this extension study. An adverse-event outcome therefore addresses the type of question the record set out to monitor. The registry also directs readers to its reported adverse-events information for summaries of serious and other non-serious events, regardless of causality. No primary endpoint estimate beyond the posted group counts is 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 participant-level measure: a participant either had at least one qualifying event during the outcome window or did not. The reported group counts pair the number of participants with an event with the number at risk in that group. This is a straightforward way to describe event occurrence, but it does not preserve information about repeated episodes, event timing, duration, or severity beyond the serious-versus-other distinction reported.

What does a participant count capture?

A count of participants with at least one event answers how many people experienced an event, not how many events occurred in total. If a participant has more than one event, a participant-level count still includes that person once for the relevant outcome. This can be useful when the focus is the proportion of people affected, but it gives no detail on recurrence or event burden. The registry gives separate serious-event and other-event counts, but does not provide a complete event-level analysis in the primary outcome description.

Why does the study design matter?

Random allocation is one way to make comparison groups more similar, on average, in factors that could influence outcomes. This study was non-randomized, and the registry explicitly warns that its arms are not like-for-like control groups. Differences in participant characteristics, treatment history, exposure, or other factors could contribute to differences in observed counts. The record does not report enough detail to assess or adjust for such differences. As a result, comparing the group counts is descriptive and cannot isolate a causal dose effect.

The study was also open-label. In general, knowledge of treatment can influence reporting, clinical assessment, and decisions about recording an event. Whether or how those processes affected this study is not reported in the registry record. Open-label status does not invalidate the counts, but it is relevant context when interpreting recorded adverse events.

How should uncertainty be understood?

A confidence interval is a range of values compatible with the observed data under a specified statistical model. In general, intervals help show how imprecise an estimate may be, especially when the number of participants is limited. No confidence intervals for the primary outcome are reported in the registry record. Without them, the posted counts do not quantify the uncertainty around the underlying event frequencies. The small group denominators also mean that a change in the status of a participant could materially alter a group's descriptive count.

The registry record reports no inferential analysis for this outcome. It does not report a statistical model, adjustment variables, hypothesis tests, or a prespecified comparison between dose groups. Consequently, no claim of statistical significance can be made from the posted counts. The absence of a reported test should not be interpreted as evidence that groups are equivalent; equivalence requires an appropriate design and analysis.

What do planning illustrations mean?

Sample-size planning illustrations are not observations from the study and are not a measure of observed power. The stated planning assumptions describe a hypothetical calculation using an effect based on the observed effect, equal allocation, a two-sided significance level of 0.05, and a normal approximation. The target effect is described as a stated fraction of the observed effect. Such illustrations depend on their assumptions and do not replace a trial's design justification. The trial's own sample-size justification is not reported in the registry record. Because this study was non-randomized and its groups are not like-for-like controls, a hypothetical two-arm planning calculation should not be mistaken for a sound basis for causal comparisons in this study.

General statistical practice also considers over-dispersion when count data vary more than a chosen model expects. That issue is relevant to analyses of event counts or rates, but the primary outcome is a count of participants with at least one event rather than a recurrent-event rate. No model or over-dispersion assessment is reported in the registry record. The available results are best read as direct descriptive counts, without inferring an unreported model or calculation.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and no analysis results. It does not report a multiplicity plan, such as how multiple statistical tests or endpoints would be handled. Since no inferential tests are reported, there is no reported multiplicity adjustment to interpret. This does not establish that multiplicity was or was not considered in the full study protocol; that information is not reported in the registry record.

The primary outcome population is all enrolled participants. The registry does not describe an alternative analysis population, exclusions from the primary analysis, or a rule for assigning participants to dose groups for analysis. It also does not report how missing outcome information, incomplete follow-up, or withdrawals were handled. The record therefore does not establish whether every enrolled participant had complete observation through the stated outcome window.

Missingness can affect a safety summary if participants with incomplete observation differ from those with complete observation. In general, the amount and pattern of missing data, and the assumptions used to address it, matter for interpretation. Here, those details are not reported in the registry record. The reported denominators should be understood as the group counts posted for the outcome, not as proof that no data were missing.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

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: aortic dissection (16.7%), acute myocardial infarction (5.9%), cellulitis (5.9%), eczema infected (5.9%).

For serious adverse events, the posted counts are 1 of 6 participants in the 30 mg group, 0 of 5 in the 80 mg group, and 2 of 17 in the 160 mg group. The denominator is the number at risk reported for that group, while the numerator is the number of participants affected. These are participant counts over the primary outcome window, not event totals or exposure-adjusted rates.

The counts for other adverse events are 6 of 6, 5 of 5, and 16 of 17, respectively. These are described as other events and are distinct from the serious-event counts. The registry says summaries of serious and other non-serious events regardless of causality are located in its reported adverse-events information. The group counts alone do not identify whether an event was judged related to LY2439821.

The absence of a serious event in a group does not prove that no such event could occur, and observed events do not by themselves establish drug causation. The groups were not randomized comparators, and their sizes differ. Deaths are not reported in the registry record.

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

The result is a descriptive account of safety events recorded among participants in a non-randomized, open-label extension study. The primary outcome counts participants with one or more adverse events and serious adverse events from baseline through study completion, up to Week 56. The posted group counts show that serious events were recorded in the 30 mg and 160 mg groups, while none were recorded in the 80 mg group; other adverse events were recorded in all three groups.

These observations do not show that LY2439821 caused any particular event. The outcome description includes events of all causalities and drug-related events, and the posted group counts do not distinguish them. Nor do the counts show that one dose is safer than another. Non-randomized groups are not necessarily comparable, and the registry explicitly says they are not like-for-like controls. No adjusted comparative analysis or confidence interval is reported.

The results also do not establish absence of risk. A group with no recorded serious adverse events still has limited information about uncommon outcomes, particularly when its denominator is small. The registry's primary outcome is a count of affected participants, not a complete account of each event's timing, recurrence, duration, or clinical course. Term-specific descriptions and further adverse-event summaries may provide additional detail, but they do not convert this design into a controlled causal comparison.

Finally, these findings should not be read as evidence about treatment benefit. The stated purpose was evaluation of safety and tolerability. The registry record does not report an efficacy endpoint or comparative efficacy analysis. The study can describe what was recorded in the enrolled participants under the study regimens, but it cannot by itself answer whether treatment improves rheumatoid arthritis outcomes or how its effects compare with another treatment.

13. Why This Trial Matters Statistically

This study illustrates why the design and the outcome definition matter as much as the numerical counts. The primary outcome is a participant-level safety measure, and the registry provides counts within dose groups. Those counts are easy to understand, but the non-randomized, open-label design limits what can be inferred from differences between groups. A numerical contrast in observed counts is not automatically evidence of a dose effect.

The record also illustrates the distinction between describing an event and attributing it. Safety monitoring records events that occur during a study; deciding whether an event was caused by a treatment is a separate question. Here, the endpoint description includes events across causalities, while the group totals do not offer a separate causal attribution analysis. Readers should avoid treating every recorded event as drug-related.

Small group denominators make precision especially important. Counts communicate what was observed, but without reported confidence intervals or a prespecified inferential analysis they do not quantify uncertainty or support a formal comparison. A zero count is not proof of zero underlying risk, and a larger count in another arm is not proof of a higher risk when group allocation was not randomized.

The record further shows why planning calculations should be kept separate from observed evidence. A sample-size illustration based on an observed effect is hypothetical and does not establish that the study was designed to detect a reliable difference. The study's own sample-size justification is not reported in the registry record. Taken together, these points make this a useful example of interpreting descriptive safety data without overstating causal or comparative conclusions.

14. 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 for interpretation is the non-randomized design. The registry cautions that the dose groups are not like-for-like controls, so differences in their adverse-event counts cannot be attributed to dose without further design and analysis support. The open-label design is also relevant because event reporting and assessment may be influenced by awareness of treatment; the registry does not describe safeguards or procedures to address this.

The total enrollment was 28, divided among groups with denominators of 6, 5, and 17 for the reported adverse-event outcomes. These denominators provide limited information about uncommon events. No confidence intervals or formal analyses are reported, so the precision of the group estimates is not quantified. The registry does not report a sample-size justification for the study.

The outcome window extends from baseline through study completion, up to Week 56, while the study purpose describes evaluation over 48 weeks and the dose schedules refer to treatment through week 44. Participant-level exposure durations are not reported in the registry record. The record also does not report missing-data handling, withdrawals, event-level timing, or a separate analysis of events by causal attribution. Deaths are not reported in the registry record.

Finally, the primary outcome is a count of participants with events, not an analysis of event frequency over exposure time. The record does not report a controlled efficacy comparison. These limitations restrict interpretation to the descriptive safety information recorded for the enrolled participants.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Study of LY2439821 in Rheumatoid Arthritis — NCT01236118.
• Registry record last updated 2016-05-26; status last verified 2016-04.
• Results first posted 2016-05-26.
• 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.

18. Record Summary

NCT01236118 is a completed Phase 1, non-randomized, open-label, parallel-group extension study of LY2439821 in Japanese participants with rheumatoid arthritis who had completed Study I1F-JE-RHAL (NCT01253265). Participants were receiving concomitant methotrexate. Enrollment was 28, and the study's stated purpose was to evaluate safety and tolerability of subcutaneous dosing over 48 weeks.

The primary outcome counts participants with adverse events and serious adverse events from baseline through study completion, up to Week 56. The registry reports serious-event counts of 1 of 6, 0 of 5, and 2 of 17 across the 30 mg, 80 mg, and 160 mg groups, respectively. It reports other adverse-event counts of 6 of 6, 5 of 5, and 16 of 17. The record cautions that the arms are not like-for-like control groups; no inferential comparison is reported. The study start is listed as 2010-12 and primary completion as 2013-01.