A Study of LY3502970 in Participants With Type 2 Diabetes: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY3502970 in Participants With Type 2 Diabetes (NCT04426474), a randomized phase 1 study. The primary outcome is Number of Participants With One or More Serious Adverse Event(s) (SAEs) Considered by the Investigator to be Related to Study Drug.

2. Clinical Question

This is a safety-focused Phase 1 question. It differs from a question about whether a treatment improves a clinical outcome: the primary endpoint counts participants with investigator-attributed, treatment-related serious adverse events during the stated follow-up. A count of zero in a group means that no participant in that group was recorded as having this particular endpoint; it does not establish that no other adverse events occurred or that risk is absent.

The study description says blood tests were planned to measure the amount of LY3502970 in the bloodstream, how long the body takes to eliminate it, and its effect on blood sugar. The listed secondary outcomes include maximum observed concentration, area under the concentration-versus-time curve from time 0 to 24 hours, change from baseline to Week 12 in fasting plasma glucose, and change from baseline to Week 12 in fasting insulin. The posted primary result addresses the serious adverse event question, not those secondary questions.

3. Trial Design

The registry classifies NCT04426474 as a randomized, double-masked, sequential Phase 1 study of LY3502970 in participants with type 2 diabetes. Eli Lilly and Company is listed as the sponsor. The study is marked completed, with a start date of 2020-10-08 and a primary completion date of 2021-07-12. The enrollment recorded in the registry is 68.

Participants were assigned to placebo or one of five LY3502970 dose schedules. The listed active schedules are 3/6/12/21 mg QD, 3/6/9 mg QD, 3/6/12/15 mg QD, 3/6/12/21/27 mg QD, and 3/6/9/21/36/45 mg QD. The intervention description says LY3502970 was administered orally, with doses of 3, 6, 9, 12, 15, 21, 27, 36 and 45 milligrams across the study. Placebo was also administered orally.

Sequential describes the registry's model classification; the registry record does not report further operational details about the sequence, dose progression, or assignment process. The brief description says participation could last up to 18 weeks and could include up to 14 visits, including three overnight stays in the study center. These are described as possible maximums, not the duration or visit count experienced by every participant.

The primary endpoint population is defined as all participants who received at least one dose of study drug. The registry does not report additional detail about exclusions, adherence requirements, or analysis-set construction. The primary endpoint is assessed from baseline through follow-up, up to Day 105. Although randomization and masking are recorded, the registry record does not report the allocation ratio or details of who was masked. This design is therefore best understood from the registry at the level of its recorded classifications and listed treatment groups, without inferring procedures that are not described.

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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All participants who received at least one dose of study drug.

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 participants who received at least one dose of study drug.

Only the first 6 of 7 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With One or More Serious Adverse Event(s) (SAEs) Considered by the Investigator to be Related to Study Drug, measured over Baseline through Follow-up (up to Day 105).

The primary endpoint is the number of participants with one or more serious adverse events that the investigator considered related to study drug. It is a participant-level count: a person is counted if at least one qualifying event occurred during the stated timeframe, rather than being counted once for every event. The timeframe is baseline through follow-up, up to Day 105, and the population is participants who received at least one dose of study drug.

The registry defines a serious adverse event as an untoward medical occurrence that, at any dose, results in death, is life-threatening, requires inpatient hospitalization or prolongation of existing hospitalization, results in persistent disability or incapacity, or is a congenital anomaly or birth defect. Other situations can qualify based on medical judgment. For this primary endpoint, the investigator must also consider the event related to study drug.

Such an endpoint is used to describe an important safety outcome during the study period. It gives a direct count of participants meeting the recorded seriousness and relatedness criteria. It does not capture every adverse event, and the posted count should not be read as a complete account of tolerability. The registry says that summaries of serious and other non-serious adverse events, regardless of causality, are reported in the Reported Adverse Events module. The primary endpoint result therefore addresses a narrower question than the full adverse-event record.

The posted results record one participant with this endpoint in the placebo group and zero in each LY3502970 group. Counts in a small early-phase study are descriptive and can be imprecise. They do not by themselves establish that an event was caused by a treatment or that a group has no risk of such events.

7. Results Posted in the Registry

• 3/6/12/21 mg LY3502970 QD: 0.0% (0/14) versus 5.9% (1/17) on control; risk difference -5.9 percentage points (95% CI -17.1 to 5.3); unadjusted two-proportion z-test p = 0.356.
• 3/6/12/15 mg LY3502970 QD: 0.0% (0/10) versus 5.9% (1/17) on control; risk difference -5.9 percentage points (95% CI -17.1 to 5.3); unadjusted two-proportion z-test p = 0.434.

8. Statistical Interpretation

9. Statistical Methods Explained

What kind of outcome is this?

The endpoint is a binary participant outcome represented as a count: each participant either met the definition of one or more related serious adverse events during follow-up or did not. The displayed group results are counts, not event rates per unit of time. In general, a count of participants with an event is often interpreted alongside the number at risk in that group, because the same count can have different implications in groups of different sizes. The posted group results include the group sizes, but the registry record does not report a separate time-to-event analysis for this endpoint.

The outcome is also a composite in the sense that several kinds of serious medical occurrence can satisfy the seriousness definition. The qualifying event must be judged related to study drug by the investigator to count toward the primary endpoint. That attribution is part of the recorded endpoint definition; it does not establish causation independently of that judgment.

How should a risk difference be read?

A risk difference compares the proportion of participants with the event in one group with the proportion in another group. In these posted comparisons, the reference group is placebo QD and the comparison groups are the 3/6/12/21 mg LY3502970 QD schedule and the 3/6/12/15 mg LY3502970 QD schedule. A negative estimate means the observed event proportion is lower in the listed active schedule group than in placebo. Here, each active group has zero recorded primary endpoint events, while placebo has one. The magnitude of a risk difference is an estimate from the observed data, not a guarantee of the difference that would appear in another study.

General statistical explanation: a confidence interval expresses a range of values compatible with the data under the method's assumptions. A wide interval signals limited precision. When an interval includes zero for a risk difference, the data are compatible with no difference as well as with differences in either direction within the interval. The registry's intervals for both posted comparisons cross zero. The record does not report the method used to calculate those intervals, so a more specific account of their construction is not available.

What does a p-value contribute?

A p-value describes how unusual data at least as incompatible with a stated null hypothesis would be if that null hypothesis and the test assumptions were true. It is not the probability that the null hypothesis is true, and it is not a measure of clinical importance. The posted unadjusted p-values are 0.356 for the 3/6/12/21 mg comparison and 0.434 for the 3/6/12/15 mg comparison. These results do not provide compelling evidence against a no-difference null under conventional testing, but sparse event data mean that a lack of statistical evidence should not be interpreted as evidence that the risks are identical.

The values are identified as unadjusted. The registry record does not report whether these comparisons were prespecified, whether other tests were performed, or whether a multiplicity adjustment was used for any analysis. It also does not report the statistical test used for these comparisons. Consequently, the p-values should be read as the posted unadjusted results rather than as a complete account of the trial's analysis strategy.

What do planning illustrations mean?

General statistical explanation: sample-size planning uses assumptions about the effect to detect, allocation, significance level, and statistical method to illustrate how much information a future study might need. The registry's planning assumptions describe a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. These are planning assumptions, not a statement of the original trial design. Any planning illustrations based on the observed effect are not observed power. The registry record does not report the trial's own sample-size justification or planned power target.

Sample-size calculations based on a sparse observed outcome can be especially sensitive to the observed effect estimate. A planning illustration should therefore be treated as conditional on its assumptions, not as a definitive requirement for another study. The registry record does not report a planned sample-size calculation, interim analysis plan, or detailed statistical analysis plan.

How do the pharmacology outcomes fit?

The listed secondary outcomes cover pharmacokinetics and pharmacodynamics. Maximum observed concentration and area under the concentration-versus-time curve from time 0 to 24 hours characterize drug exposure. Changes from baseline to Week 12 in fasting plasma glucose and fasting insulin describe selected pharmacodynamic measurements. The record lists four secondary outcomes, but does not include their result values in the registry record for this analysis. Their numerical findings, analysis methods, and handling of missing measurements are not reported in the registry record. They should not be inferred from the primary safety counts.

10. Confidence Intervals and Precision

The main precision issue is the small number of observed primary endpoint events. The placebo group has one participant with an investigator-related serious adverse event, while each LY3502970 schedule group has zero. When event counts are this sparse, the observed comparison can be strongly affected by only a small number of outcomes. A zero count is a description of the observed sample; it does not mean the underlying event probability is known to be zero.

The registry posts confidence intervals for the risk differences in the two comparisons. Each interval spans both negative and positive values, so the data are compatible with a lower event proportion in the active schedule group, no difference, or a higher event proportion within the interval's limits. The intervals therefore do not precisely identify the direction or magnitude of a group difference. The posted unadjusted p-values, 0.356 and 0.434, are consistent with this uncertainty. They are not evidence that the groups are equivalent.

Confidence intervals quantify statistical uncertainty under the assumptions of the method used to construct them. They do not account automatically for every source of uncertainty, including possible measurement or attribution issues, differences in follow-up, or limitations in generalizability. The registry record does not report the interval method, so the interval's specific assumptions cannot be evaluated from this record alone.

The group sizes shown in the posted results also indicate that the comparisons draw on relatively small groups. The enrollment figure for the full study should not be mistaken for the number contributing to each comparison: the primary endpoint results are listed by the individual placebo and dose-schedule groups. Precision is therefore best judged from the group-level data and the sparse event count, not from enrollment alone. The record does not report a separate precision target or a planned confidence-interval width.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary safety endpoint and four secondary outcomes: two pharmacokinetic measures and changes from baseline to Week 12 in fasting plasma glucose and fasting insulin. The posted inferential comparisons for the primary endpoint include two LY3502970 schedules versus placebo. Because several outcomes and comparisons may be considered, multiplicity can matter: repeated statistical testing can increase the chance of at least one apparently notable result by chance. The registry record does not report a multiplicity strategy, a hierarchy among secondary outcomes, or whether any adjustment was used. The posted primary comparison p-values are identified as unadjusted.

The registry defines the primary endpoint population as participants who received at least one dose of study drug. That identifies a treated population for this outcome, but the record does not report further details about analysis populations, such as whether randomized participants who received no dose were analyzed elsewhere, or whether any per-protocol population was used. The group counts in the posted outcome are therefore interpreted according to the stated treated-population definition.

The registry record does not report how missing outcome observations were handled, whether every participant completed follow-up, or whether any participants were excluded from the endpoint analysis. It also does not report whether missingness was considered in the analysis or whether sensitivity analyses were performed. For a safety outcome, the absence of a posted event count is not enough to determine whether all participants had complete observation through the full follow-up period.

The record does not report an interim analysis plan or a detailed statistical analysis plan. These gaps limit assessment of whether the reported comparisons and endpoint analyses followed prespecified procedures. They do not change the posted counts, but they constrain how fully the analysis can be evaluated. Results for the secondary outcomes are not reported in the registry record available for this account, so no conclusions about those measures can be drawn from the primary safety result.

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: hand fracture (5.9%), skin laceration (5.9%), lung neoplasm (5.9%).

The primary safety result counts participants with at least one serious adverse event that the investigator considered related to study drug. The placebo QD group has one such participant; each LY3502970 schedule group has zero. These figures refer only to the primary endpoint definition and the follow-up window from baseline through follow-up, up to Day 105. They are not a count of all serious events, all adverse events, or all events regardless of attribution.

The registry separately lists other adverse events regardless of causality. The numbers of participants with these other events vary across the groups, with group counts from seven to ten. The record also lists hand fracture, skin laceration, and lung neoplasm at 5.9% each among the top serious adverse event terms. These listed terms should be understood as reported terms, not as a causal comparison between treatment groups. The registry records zero deaths in each group.

In general, a zero event count means no event meeting the recorded definition was observed in that group during the recorded period. It does not establish that the event cannot occur. Attribution to study drug is an investigator judgment recorded by the trial, and the primary endpoint is narrower than an assessment of every potential safety concern. Sparse counts, group size, and the limited follow-up period all matter when interpreting these figures.

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

The posted data show that one participant in the placebo QD group met the primary endpoint definition and that no participants in the LY3502970 schedule groups did so during the stated follow-up. The endpoint requires a serious adverse event that the investigator considered related to study drug. This is a description of the recorded results, not proof that placebo caused the observed event or that LY3502970 carries no risk of such events.

The two posted unadjusted comparisons have p-values of 0.356 and 0.434. Their confidence intervals span zero, indicating that the data do not precisely determine whether the event proportion differs between the compared groups. The small number of events means the estimates are uncertain. The results do not establish equivalence, rule out a meaningful difference, or support a firm ranking of the schedules.

This result does not answer whether LY3502970 changes blood glucose, insulin, or drug exposure. Those are listed as secondary pharmacodynamic and pharmacokinetic outcomes, and their results are not reported in the registry record covered by these primary safety data. Nor does the result establish long-term safety: the primary endpoint follow-up ends at up to Day 105. The record also does not provide evidence for populations or settings beyond the participants and study conditions described.

It is important to keep the primary endpoint distinct from the broader adverse-event record. The registry lists other adverse events regardless of causality, and participants in every group are recorded with such events. Those broader results do not change the definition of the primary outcome. A full safety assessment would require consideration of the different event categories, their timing and severity, follow-up completeness, and the wider evidence base; those matters cannot be resolved from the primary endpoint counts alone.

14. Why This Trial Matters Statistically

This trial illustrates a central statistical challenge in early-phase safety research: clinically important events may be uncommon, while group sizes and follow-up are limited. The primary endpoint is direct and interpretable as a participant count, but one event in the placebo group and zero in each active schedule provide little information for estimating small differences precisely. The confidence intervals and unadjusted p-values convey this uncertainty rather than converting the observed pattern into a definitive group comparison.

The study also includes multiple active dose schedules. This creates an informative structure for describing safety and pharmacology across dose sequences, but the posted inferential comparisons cover only two schedules versus placebo. The registry record does not report a multiplicity strategy or the rationale for which comparisons were posted. That makes it important to distinguish the full set of listed groups from the narrower set of reported tests.

More broadly, the endpoint combines a clinical seriousness definition with investigator judgment about relatedness. The resulting count is useful for describing the trial's prespecified safety question, while its interpretation depends on the event definition and attribution process. A primary endpoint count cannot replace the broader adverse-event record or pharmacokinetic and pharmacodynamic measures.

Statistically, the study is a reminder that absence of observed events is not the same as evidence of absence, and that a nonsignificant test is not an equivalence result. The most informative reading considers event counts, group sizes, uncertainty intervals, endpoint scope, and duration together. These features define what the trial can describe and where its evidence remains limited.

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 primary endpoint has very few observed events: one in the placebo group and zero in the active schedule groups. This sparse outcome limits precision and makes estimates sensitive to individual observations. The resulting comparisons cannot establish that the schedules have equal risks, and zero observed events in a group do not show that the underlying risk is zero.

The endpoint is restricted to serious adverse events that the investigator considered related to study drug. It therefore does not represent all serious adverse events or all adverse events. The registry lists other adverse events regardless of causality, but the primary endpoint counts a narrower category. Attribution is based on investigator judgment, and the record does not report further details about the assessment process.

Follow-up for the primary endpoint is baseline through follow-up, up to Day 105. This limits what can be said about events beyond that period. The trial is a Phase 1 study with multiple sequential dose schedules, and group sizes are small. The registry record does not report the trial's own sample-size justification, a detailed statistical analysis plan, interim analyses, or a multiplicity strategy. It also does not report missing-data handling, completion of follow-up by group, or the specific methods used for the posted confidence intervals and tests.

Only two of the listed active schedules have posted inferential comparisons against placebo. The registry record does not report comparative inference for the remaining schedules. The secondary outcomes are listed, but their results are not reported in the registry record for this analysis. These limitations mean the primary safety counts should be read as a narrow, descriptive result rather than a complete assessment of dose-related safety, pharmacology, or clinical effects.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study of LY3502970 in Participants With Type 2 Diabetes — NCT04426474.
• Registry record last updated 2026-05-26; status last verified 2026-04.
• Results first posted 2026-05-26.
• 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.

19. Record Summary

NCT04426474 is a completed, randomized, double-masked, sequential Phase 1 study sponsored by Eli Lilly and Company. It enrolled participants with type 2 diabetes and evaluated oral LY3502970 dose schedules against oral placebo. The registry records enrollment of 68, a start date of 2020-10-08, and a primary completion date of 2021-07-12.

The primary endpoint was the number of treated participants with one or more serious adverse events considered related to study drug, from baseline through follow-up up to Day 105. The posted result is one participant in the placebo QD group and zero in each LY3502970 group. The two reported unadjusted comparisons have p-values of 0.356 and 0.434, with confidence intervals spanning zero. These sparse results are uncertain and do not establish equivalence or absence of risk.

The registry also lists pharmacokinetic and pharmacodynamic secondary outcomes, but their results are not reported in the registry record covered by these primary safety findings.