Study of LY3016859 in Participants With Diabetic Nephropathy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of LY3016859 in Participants With Diabetic Nephropathy (NCT01774981), a randomized phase 1, phase 2 study. The primary outcome is Part B:Change From Baseline in Proteinuria.

2. Clinical Question

The study was organized in two parts. Part A escalated doses to investigate safety and tolerability; Part B evaluated proteinuria. The primary endpoint reported for Part B was change from baseline in proteinuria, measured in grams per 12 hour (g/12 hour). Proteinuria is described as the ratio of protein to creatinine.

The registry record reports mean changes for placebo and each of the three Part B dose groups. It also reports one-sided t-test comparisons of each dose group with placebo. These summaries address differences in the observed group means, but the record does not provide confidence intervals or an adjusted comparison estimate for those tests. The group results are based on the stated primary analysis population, which requires baseline and post-baseline measurements as well as receipt of at least one dose.

This question is narrower than whether LY3016859 changes kidney disease overall. The posted primary endpoint concerns proteinuria change over the specified follow-up, not every aspect of diabetic nephropathy or patient health. The registry record does not report a broader clinical outcome as the primary endpoint.

3. Trial Design

This completed study enrolled 60 participants and is listed as Phase 1 and Phase 2. Its design is recorded as randomized, triple-masked, and parallel. The registry record does not identify which groups of people were masked, or provide further details about the randomization process.

The two-part structure served different stated purposes. Part A was a dose-escalation component focused on safety and tolerability. Participants received placebo or 10 mg, 100 mg, or 750 mg LY3016859 by 60 minute intravenous infusion at Week 1 and Week 4. Part B focused on proteinuria. It compared placebo with 50 mg, 250 mg, or 750 mg LY3016859, given by 60 minute intravenous infusion at Weeks 1, 4, 7, 10, and 13.

The primary outcome was the Part B change from baseline in proteinuria, with the timeframe listed as baseline and 16 weeks. The primary analysis population was not simply all enrolled participants: it included randomized participants who received at least one Part B dose and had both a baseline and at least one post-baseline measurement. The record lists Part B outcomes for change from baseline in proteinuria and albuminuria over time as secondary outcomes.

Enrollment describes the overall study, while the primary endpoint summaries are reported separately for Part B. For that endpoint, the listed group sizes are 6.0 for placebo, 9.0 for 50 mg, 9.0 for 250 mg, and 11.0 for 750 mg. These are the analysis group sizes for the posted endpoint, not the overall enrollment. The registry record does not report the planned allocation ratio, the reason for the enrollment target, or additional details about how participants moved between the two parts.

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.

Only the first 6 of 8 groups are shown.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All randomized participants who received at least one dose of study drug in Part B with a baseline measurement and at least one post-baseline measurement.

5. Baseline Characteristics

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

Population: All randomized participants who received at least one dose of study drug.

Only the first 6 of 9 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Part B:Change From Baseline in Proteinuria, measured over Baseline, 16 Weeks.

The primary endpoint is mean change from baseline in proteinuria at 16 weeks, expressed in grams per 12 hour (g/12 hour). The registry record defines proteinuria as the ratio of protein to creatinine. A change score describes how a measurement at follow-up differs from that participant’s baseline measurement; the reported group value is the mean change among participants in the analysis population.

Proteinuria is the direct focus of Part B, whose stated purpose was to evaluate this measure. Tracking change from baseline gives a within-participant reference point for describing follow-up results across randomized groups. Comparing group summaries can then describe whether the observed mean change differs between a dose group and placebo. Such a comparison remains a summary of this endpoint and timeframe; it does not, by itself, describe every consequence of diabetic nephropathy.

The endpoint is continuous, and the registry reports the mean and standard deviation for each group. The record does not provide the individual participant measurements, the exact calculation procedure for the change score, or confidence intervals for the group means. It also does not report a precise endpoint-specific clinical interpretation threshold. Therefore, the numerical changes describe the posted measurements but do not establish how important a given change would be in clinical practice.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a continuous measure, reported as a mean with a standard deviation. A mean gives the average observed change in a group. A standard deviation describes how dispersed participant values are around that mean; it is not a confidence interval and does not directly describe the precision of the mean or of a between-group comparison. The posted standard deviations are 2.04 for placebo, 1.6 for 50 mg, 1.21 for 250 mg, and 2.23 for 750 mg.

What does a t-test compare?

A t-test evaluates whether the observed difference between two group means is compatible with a specified null model, taking account of the variability and sample sizes used in the test. The registry lists three one-sided t-tests, each comparing a LY3016859 dose group with placebo. The reported p-values are 0.045 for 50 mg, 0.081 for 250 mg, and 0.222 for 750 mg. A one-sided test evaluates evidence in a specified direction; the registry record does not state the direction in the analysis description. The p-value is not the probability that the null hypothesis is true, nor is it a measure of the size or clinical importance of a difference.

Why do confidence intervals matter?

General statistical explanation: a confidence interval gives a range of values compatible with the data and the assumptions of the estimation procedure. It helps readers judge precision and the range of effects that remain plausible, rather than relying on a threshold-based interpretation of a p-value. The registry record does not report confidence intervals for the three comparisons or a numerical comparison estimate. The displayed group standard deviations cannot substitute for those missing comparison intervals.

What does randomization contribute?

General statistical explanation: random assignment is intended to make treatment groups comparable, on average, with respect to measured and unmeasured characteristics at the point of assignment. It does not guarantee balance in every realized trial, particularly when group sizes are limited. The registry lists the study as randomized but does not report the allocation procedure or baseline values in the registry record. Thus, the design label alone does not show how closely the groups matched on participant characteristics.

Why can over-dispersion matter?

General statistical explanation: when participant outcomes vary widely, the standard error of a group estimate or contrast can increase, making a comparison less precise. The standard deviation reflects observed within-group variability, while a standard error also depends on the amount of data and the analysis model. The registry summaries show variability in every group, but do not provide the comparison standard errors or confidence intervals. No distributional diagnostics or alternative variance methods are reported in the registry record, so the suitability of additional modeling approaches cannot be assessed from these summaries alone.

How should the analysis population be understood?

The stated primary population includes randomized participants who received at least one Part B dose and had both a baseline measure and at least one post-baseline measure. This definition excludes participants who do not meet those criteria from the primary analysis. It is therefore important not to equate the endpoint group sizes with total enrollment. The group sizes for the endpoint are 6.0 for placebo, 9.0 for 50 mg, 9.0 for 250 mg, and 11.0 for 750 mg. The registry record does not report how many participants were excluded for each reason or how missing measurements were handled.

The planning assumptions described in the registry record concern a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect expressed as a fraction of the observed effect. Those are planning assumptions, not evidence that the study had a particular probability of detecting an effect. No resulting sample-size illustration counts are reported in the registry record. A planning illustration is not observed power and should not be confused with the actual analysis.

The reported comparisons are one-sided, whereas the stated planning assumption specifies a two-sided level. These descriptions concern different tasks: a planning calculation and an analysis test. The registry record does not report the prespecified rationale for the one-sided tests, whether the comparisons were planned in advance, or whether the analysis model included other covariates. Statistical methods beyond the listed t-tests are not reported in the registry record.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Placebo (Part B)", "50 mg LY3016859 (Part B)", "250 mg LY3016859 (Part B)", "750 mg LY3016859 (Part B)")
n   <- c(6, 9, 9, 11)
m   <- c(1.5, -0.4, 0.1, 0.7)
sp  <- c(2.04, 1.6, 1.21, 2.23)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Placebo (Part B)  6  1.500  2.040  -0.641  3.641
CARM  50 mg LY3016859 (Part B)  9  -0.400  1.600  -1.630  0.830
CARM  250 mg LY3016859 (Part B)  9  0.100  1.210  -0.830  1.030
CARM  750 mg LY3016859 (Part B)  11  0.700  2.230  -0.798  2.198

11. Analyses Reported by the Sponsor

The registry reports the sponsor’s three pairwise analyses as one-sided t-tests. Their p-values are 0.045 for the comparison of 50 mg with placebo, 0.081 for 250 mg with placebo, and 0.222 for 750 mg with placebo. The record does not report a separate recalculated comparison estimate, confidence interval, or recalculated p-value. The sponsor’s tests therefore cannot be checked against an independent numerical re-analysis from the posted summary statistics.

The arm-level means, standard deviations, and group sizes are available, but a comparison’s numerical estimate and uncertainty are not reported in the registry record. The posted p-values also do not state the magnitude of each dose-versus-placebo contrast. No discrepancy is flagged between a sponsor result and a recalculation in the registry record; however, without reported recalculated values, there is no numerical recalculation to compare with the sponsor’s analyses.

The reported tests should be read as the registry’s stated analyses, not as a complete account of the statistical evidence. In particular, a p-value does not replace an effect estimate and confidence interval, and the one-sided test direction is not described in detail. Further analysis-plan information, including the rationale for the testing direction, is not reported in the registry record.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists three primary-outcome comparisons: each of the 50 mg, 250 mg, and 750 mg groups is compared with placebo. It also lists two secondary outcomes, change from baseline in proteinuria over time and change from baseline in albuminuria over time. Across the record, four outcome measures and three analyses are reported. The registry does not state whether the three primary comparisons or the secondary outcomes were adjusted for multiple testing.

Multiplicity matters because conducting multiple tests can increase the chance of observing at least one apparently unusual result when all null hypotheses hold. Adjustment methods, a prespecified testing sequence, or a hierarchy among outcomes can address this concern in different ways. Which approach is appropriate depends on the study plan and the intended interpretation. The registry record does not report such a plan, so the three p-values should be read as the individual reported tests rather than as evidence of a stated family-wise testing procedure.

The analysis population requires at least one dose and both a baseline and at least one post-baseline measurement. This makes the endpoint analysis population narrower than all randomized participants. The record does not report the number of missing endpoint observations, reasons for missingness, imputation procedures, sensitivity analyses, or whether outcomes were analyzed under other population definitions. Those details are important because missing measurements and exclusions can affect the interpretation of a change-from-baseline result.

The registry’s planning assumptions include a two-sided significance level of 0.05, but those assumptions do not establish the multiplicity strategy for the reported one-sided comparisons. The record also does not report interim analyses or a prespecified statistical analysis plan. Without this information, it is not possible to determine from the registry record how missing data and multiple outcomes were handled beyond the stated primary analysis population and listed tests.

13. 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: sudden death (16.7%), phytobezoar (8.3%), transient ischemic attack (8.3%), anginal pain (7.7%), atrial fibrillation aggravated (7.7%).

Serious adverse events are reported separately by part and group. In Part A, the serious-event counts were 0 of 3 at risk for placebo, 0 of 4 for 10 mg, 0 of 4 for 100 mg, and 0 of 4 for 750 mg. In Part B, the counts were 1 of 6 for placebo, 3 of 14 for 50 mg, 6 of 13 for 250 mg, and 2 of 12 for 750 mg. The Part B at-risk counts differ from the primary endpoint analysis group sizes, so the safety denominators should not be substituted for the endpoint denominators.

The registry reports one death in Part B placebo and zero deaths in the other listed groups. It also lists serious-event terms with percentages, including Sudden death at 16.7%, Phytobezoar at 8.3%, Transient ischemic attack at 8.3%, Anginal pain at 7.7%, Atrial fibrillation aggravated at 7.7%, and Acalculous cholecystitis at 7.7%. The record excerpt does not describe the denominator or grouping used for each listed term, so those percentages should not be used to infer group-specific risks.

These counts are descriptive. Differences in group size, the two-part design, and limited counts affect how much can be inferred from comparisons. The registry record does not provide further detail about event timing or causality in the registry record.

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

The primary endpoint describes mean change in proteinuria from baseline to 16 weeks among the specified Part B analysis population. The group means range from -0.4 g/12 hour in the 50 mg group to 1.5 g/12 hour in the placebo group; the 250 mg and 750 mg group means are 0.1 and 0.7 g/12 hour. The reported standard deviations indicate participant-to-participant variation within each group. These summaries describe what was observed in the analyzed groups, not a guaranteed response for any individual participant.

The sponsor’s one-sided tests compare each dose group with placebo, but the registry does not provide confidence intervals or numerical between-group estimates for those tests. Consequently, the p-values do not communicate the precision or plausible range of a dose-versus-placebo difference. The registry record does not report a dose-response test, a multiplicity adjustment, or the direction specified for the one-sided tests.

These results do not establish whether a change in proteinuria is clinically important, how it relates to other outcomes, or what happens beyond the stated follow-up. The primary endpoint is a measurement of proteinuria, defined in the record as the ratio of protein to creatinine; it is not a complete measure of diabetic nephropathy. The secondary outcomes include proteinuria and albuminuria change over time, but their numerical results are not reported in the registry record.

The findings also should not be read as a comparison of all participants enrolled in the study. Part A investigated safety and tolerability, whereas the primary endpoint concerns Part B. The stated primary population required receipt of at least one Part B dose plus baseline and post-baseline measurements. Details about missing data and analyses of other populations are not reported in the registry record. Overall, the posted results offer group-level descriptions and individual one-sided tests, but leave important questions about precision, multiplicity, and broader clinical meaning unresolved.

15. Why This Trial Matters Statistically

This trial is statistically instructive because it combines a dose-escalation component with a later component focused on a continuous biomarker outcome. The two parts have different stated purposes and dosing schedules. Reading the results requires keeping those parts distinct: the safety and tolerability focus of Part A is not the same analysis as the Part B proteinuria endpoint.

The Part B results illustrate why means need to be considered alongside variability and group size. The arm summaries include standard deviations, and the endpoint groups range from 6.0 to 11.0 participants. The reported one-sided p-values do not supply effect estimates or confidence intervals. This makes it important to distinguish a test result from the size and precision of a treatment-group contrast.

The design also raises common questions about analysis populations and multiple comparisons. The primary population depends on dose receipt and availability of both baseline and post-baseline measurements. Three dose-versus-placebo tests are reported, while the registry does not describe a multiplicity procedure. These features affect how readers should interpret the nominal test results and how much they can infer from them.

Finally, the registry record demonstrates the value of transparent reporting of analysis details. The reported endpoint definition and test type are useful, but information about confidence intervals, missing-data handling, the direction of the one-sided tests, and adjustment for multiple testing is not reported in the registry record. Those details would help readers assess precision and the robustness of conclusions without treating a p-value as a complete summary of evidence.

16. 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 endpoint groups are limited in size, ranging from 6.0 participants in placebo to 11.0 in the 750 mg group. With group means and standard deviations alone, the precision of each mean and of the between-group contrasts cannot be fully assessed. Confidence intervals and comparison estimates are not reported in the registry record.

The analysis population includes only randomized participants who received at least one Part B dose and had baseline and post-baseline measurements. The registry does not give the number or characteristics of participants excluded from this population, the amount of missing outcome data, or how missingness was handled. It is therefore not possible to assess how those choices may have affected the posted endpoint summaries.

The reported analyses are one-sided t-tests, but the registry record does not report the rationale or prespecified direction for the tests. It also does not state whether multiplicity was addressed across the three comparisons or the listed secondary outcomes. The absence of these details limits interpretation of the reported p-values.

The endpoint concerns proteinuria change at the stated follow-up, and no clinical interpretation threshold is reported. Numerical results for the listed secondary outcomes are not available in the registry record. The registry record also does not report an analysis of dose-response, details of the randomization procedure, interim analyses, or the statistical analysis plan. These omissions limit assessment of the analysis choices and the broader meaning of the findings.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Study of LY3016859 in Participants With Diabetic Nephropathy — NCT01774981.
• Registry record last updated 2019-09-19; status last verified 2019-09.
• Results first posted 2017-08-15.
• 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.

20. Record Summary

The registry record describes NCT01774981, a completed randomized, triple-masked, parallel study of LY3016859 in participants with diabetic nephropathy. It lists Phase 1 and Phase 2 and an overall enrollment of 60. Part A was a dose-escalation component for safety and tolerability; Part B evaluated proteinuria.

The primary Part B endpoint was mean change from baseline in proteinuria at 16 weeks, measured in grams per 12 hour (g/12 hour). The posted means were 1.5 for placebo, -0.4 for 50 mg, 0.1 for 250 mg, and 0.7 for 750 mg. One-sided t-test p-values were reported for each dose-versus-placebo comparison, without comparison confidence intervals in the registry record.

The record lists secondary outcomes for proteinuria and albuminuria change over time. Further details about multiplicity, missing-data procedures, and the statistical analysis plan are not reported in the registry record.