A Study in Participants With Diabetic Kidney Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study in Participants With Diabetic Kidney Disease (NCT01113801), a randomized phase 2 study. The primary outcome is Change in Log Transformed (In) Serum Creatinine From Baseline to 12 Month Endpoint.

2. Clinical Question

The record identifies safety and renal efficacy as study aims. The primary outcome was the change in log-transformed serum creatinine, while secondary outcomes included urine protein-to-creatinine ratio, serum creatinine slope, estimated glomerular filtration rate slope, and a pharmacokinetic measure. The results therefore address several related but distinct aspects of kidney disease and drug exposure. They should not be treated as interchangeable measures: a change in a laboratory value, a trajectory over time, and a pharmacokinetic quantity each answer a different question.

3. Trial Design

This was a randomized, placebo-controlled, parallel-group Phase 2 study in participants with diabetic kidney disease due to type 1 or type 2 diabetes. The official title describes a multicenter study and calls it double-masked; the registry’s design classification records triple masking. These descriptions are both part of the record, and the registry does not explain the difference. The study is listed as terminated. The reason for termination is not reported in the registry record.

Participants were assigned to placebo or one of three LY2382770 dose groups: 2 mg, 10 mg, or 50 mg. The registry reports 417 enrolled participants, but enrollment is not the same as the number contributing data to each outcome. The primary analysis included randomized participants who received at least one dose and had evaluable baseline and post-baseline serum creatinine measurements. The primary outcome summaries report 85 participants in the placebo group, 90 in the 2 mg group, 91 in the 10 mg group, and 82 in the 50 mg group. Other endpoints have their own analysis counts.

The primary endpoint was assessed from baseline to the 12-month endpoint. The posted model description specifies an analysis of covariance with treatment, visit, and the treatment-by-visit interaction as fixed effects, subject as a random effect, and baseline log-transformed serum creatinine and baseline log-transformed first-morning urine protein-to-creatinine ratio as covariates. This describes the analysis reported for the primary outcome; other details of the statistical plan, including the original sample-size justification and any planned interim analyses, are not reported in the registry record.

Random assignment and masking are design features intended to reduce systematic differences in treatment comparisons, but they do not remove uncertainty from finite sample sizes or incomplete endpoint data. The posted result should be read in light of the endpoint-specific analysis populations and the study’s terminated status, rather than assuming every enrolled participant contributed to every 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.

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 1 dose of drug and had evaluable baseline and post baseline serum creatinine values.

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 1 dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Change in Log Transformed (In) Serum Creatinine From Baseline to 12 Month Endpoint, measured over Baseline, 12 months.

The primary endpoint is the change in log-transformed serum creatinine from baseline to the 12-month endpoint, measured in ln(mg/dL). Serum creatinine is a laboratory measure used in evaluating kidney function. A change over time gives a way to compare the average laboratory-value trajectory in the randomized groups during the study period. The logarithmic transformation means the analysis concerns values on a transformed scale, not a direct difference in the original mg/dL scale.

The registry describes the reported arm values as least-squares means, with standard errors as their measure of dispersion. Least-squares means are model-based group averages adjusted according to the specified analysis. The primary model included treatment, visit, and their interaction, while accounting for subject as a random effect and adjusting for baseline log-transformed serum creatinine and baseline log-transformed first-morning urine protein-to-creatinine ratio.

This endpoint is useful for a statistical comparison because it provides a defined laboratory outcome and time point across randomized groups. It is not a direct measure of symptoms, quality of life, or an individual participant’s future kidney health. Nor does a group-average change alone establish whether a difference is clinically meaningful. Interpretation depends on the size and uncertainty of the between-group estimates, the analysis population, and the broader pattern of outcomes. The registry does not report a threshold defining a clinically important change in this endpoint.

7. Results Posted in the Registry

• 2 mg LY2382770: mean 0.18 versus 0.13 on control; difference 0.05 (95% CI -0.00 to 0.10), standardized effect d = 0.28; z-test p = 0.063.
• 10 mg LY2382770: mean 0.17 versus 0.13 on control; difference 0.04 (95% CI -0.01 to 0.09), standardized effect d = 0.22; z-test p = 0.137.
• 50 mg LY2382770: mean 0.17 versus 0.13 on control; difference 0.04 (95% CI -0.01 to 0.09), standardized effect d = 0.22; z-test p = 0.147.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change in Log Transformed (ln) Urine Protein/Creatinine Ratio From Baseline to 12 Month Endpoint

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • 2 mg LY2382770: mean 0.05 versus 0.06 on control; difference -0.01 (95% CI -0.22 to 0.20), standardized effect d = -0.01; z-test p = 0.924.
  • 10 mg LY2382770: mean 0.05 versus 0.06 on control; difference -0.01 (95% CI -0.22 to 0.20), standardized effect d = -0.01; z-test p = 0.924.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 2 mg LY2382770 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 10 mg LY2382770 and the control. The interval gives the range of effects that remain compatible with the data.

Log Transformed (ln) Serum Creatinine Slope of Change From Baseline Through 12 Months

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • 2 mg LY2382770: mean 0.01 versus 0.02 on control; difference -0.00 (95% CI -0.01 to 0.01), standardized effect d = -0.07; z-test p = 0.607.
  • 10 mg LY2382770: mean 0.02 versus 0.02 on control; difference 0.00 (95% CI -0.01 to 0.01), standardized effect d = 0.04; z-test p = 0.769.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 2 mg LY2382770 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 10 mg LY2382770 and the control. The interval gives the range of effects that remain compatible with the data.

Estimated Glomerular Filtration Rate (eGFR) Slope of Change From Baseline Through 12 Months

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • 2 mg LY2382770: mean -0.37 versus -0.37 on control; difference 0.01 (95% CI -0.23 to 0.25), standardized effect d = 0.01; z-test p = 0.959.
  • 10 mg LY2382770: mean -0.56 versus -0.37 on control; difference -0.18 (95% CI -0.42 to 0.05), standardized effect d = -0.21; z-test p = 0.131.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 2 mg LY2382770 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 10 mg LY2382770 and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes extend the primary question across different measures: urine protein-to-creatinine ratio, serum creatinine slope, estimated glomerular filtration rate slope, and a pharmacokinetic measure. Taken together, these outcomes offer context about kidney-related laboratory trajectories and drug exposure, but they do not all measure the same construct or answer the same statistical question. A pattern across these measures can be informative only when the measurement scales, analysis populations, and uncertainty are considered separately.

The posted summaries do not provide a clear, uniformly consistent set of precise comparisons that resolves the primary endpoint’s uncertainty. Some recalculated contrasts are close to zero, while other arm summaries differ more visibly; the recalculated intervals remain broad relative to the estimates. These are descriptive observations from the posted summaries, not grounds for selecting a favorable outcome or dose. The secondary results do not erase the uncertainty in the primary comparison, nor should they be treated as independent confirmation of it.

The registry lists five outcome measures, while the summary record describes four secondary outcomes. The pharmacokinetic outcome is named, but numerical arm results are not included in the record analyzed for these results. Formal sponsor analyses for the secondary outcomes are not reported in the registry record. The available recalculated comparisons are unadjusted and are present for selected dose groups rather than uniformly across all groups and outcomes.

Multiplicity matters because examining multiple outcomes and contrasts creates more opportunities for apparently notable results to arise by chance. The registry does not report a multiplicity adjustment or a testing hierarchy that would establish which secondary comparisons were confirmatory. Consequently, secondary findings carry less weight than a prespecified, fully reported primary analysis. They are best viewed as exploratory context that may help frame further questions, not as decisive evidence on their own.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Change in Log Transformed (ln) Urine Protein/Creatinine Ratio From Baseline to 12 Month Endpoint
• Population Pharmacokinetics (PK) - Model-Estimated Area Under the Concentration -Time Curve (AUC ) Over a Dosing Interval
• Log Transformed (ln) Serum Creatinine Slope of Change From Baseline Through 12 Months
• Estimated Glomerular Filtration Rate (eGFR) Slope of Change From Baseline Through 12 Months

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint analysis is described as an analysis of covariance, or ANCOVA. In general, ANCOVA compares group outcomes while adjusting for selected baseline measures. The registry specifies treatment, visit, and treatment-by-visit interaction as fixed effects; subject as a random effect; and baseline log-transformed serum creatinine and baseline log-transformed first-morning urine protein-to-creatinine ratio as covariates. Including baseline measures can account statistically for some differences in starting values, while the treatment-by-visit term allows the modeled treatment contrast to vary by visit.

What do least-squares means represent?

In general, a least-squares mean is a model-based estimate of a group average after accounting for terms included in the model. It is not necessarily the simple arithmetic average of the observed values. The registry reports these means for each primary-outcome arm and gives standard errors as the dispersion measure. A standard error describes uncertainty in an estimated mean; it is not the spread of individual participant outcomes. Because the posted arm summaries are model-based, they should be interpreted together with the model description and the analysis population.

What does the log transformation change?

In general, taking the natural logarithm changes the scale on which values are analyzed. Differences on a log scale do not directly equal differences in the original measurement scale. The primary outcome is expressed in ln(mg/dL), so a reported change or contrast is a comparison on that transformed scale. Converting a log-scale contrast back to the original scale would require a specified transformation and interpretation; no such recalculation is made. The registry’s description also says that the baseline serum creatinine and urine protein-to-creatinine ratio covariates were log transformed.

How should the recalculated comparisons be read?

The posted least-squares means are accompanied by simple, unadjusted recalculations of mean differences between each selected dose group and placebo. These use the posted summary statistics and do not reproduce the full ANCOVA model. Their confidence intervals and p-values therefore serve as approximate, unadjusted comparisons rather than as the sponsor’s model-based inferential results. The registry record does not report formal sponsor comparison analyses for the primary outcome. The distinction matters: an unadjusted calculation cannot account for model terms or analysis details that are not represented by the summary statistics.

A confidence interval describes a range of values compatible with the data and the method used to construct the interval. In general, wider intervals indicate less precision, while narrower intervals indicate more precision. An interval that includes zero does not establish that the true difference is zero; it indicates that a zero difference remains among the values compatible with that interval. Conversely, an interval excluding zero would not alone establish clinical importance. The primary recalculated intervals all span zero, and their breadth indicates that the comparisons do not pin down a narrow effect estimate.

A p-value measures how unusual data at least as incompatible with a specified null hypothesis would be under the assumptions of the statistical test. It is not the probability that the null hypothesis is true, nor does it describe the size or importance of the contrast. The recalculated p-values are unadjusted. Since the record includes comparisons across dose groups and several outcomes, they should not be treated as multiplicity-adjusted evidence.

Why do the analysis populations differ?

The primary analysis population required randomization, at least one dose, and evaluable baseline and post-baseline serum creatinine data. This differs conceptually from the total enrollment: participants without the required measurements do not contribute to that endpoint’s analyzed result. The registry also reports different participant counts for secondary outcomes. A result from one endpoint’s analysis population should not automatically be generalized to another endpoint’s population. The record does not provide a complete account of missing measurements, reasons for missingness, or methods used to address missing data.

The secondary outcome summaries are also least-squares means with standard errors. Some secondary outcomes have recalculated comparisons for selected dose groups, but the registry’s formal reported-analysis lists for these outcomes are empty. The recalculated contrasts should therefore be treated as descriptive, unadjusted statistical summaries. They do not establish a prespecified testing hierarchy, control the chance of false-positive findings across outcomes, or show that one outcome was intended to confirm another.

Finally, the registry does not report the study’s original sample-size rationale, the complete prespecified statistical analysis plan, or interim-analysis details. The planning illustrations associated with the results are not the trial’s original design calculations. Without those protocol details, readers cannot verify whether all analytic choices and outcome comparisons were prespecified or how departures, if any, were handled.

11. Confidence Intervals and Precision

The primary comparison estimates are modest in magnitude on the log-transformed scale, but the uncertainty is substantial relative to the estimated differences. For the 2 mg, 10 mg, and 50 mg comparisons with placebo, the recalculated confidence intervals each span zero. Thus, the posted summary statistics are compatible with no difference as well as with differences in either direction within the interval limits. This does not demonstrate equivalence, because an equivalence question requires a defined margin and an analysis designed to assess it; such a margin is not reported in the registry record.

The intervals are recalculated from posted summary statistics and are unadjusted. They are not the model-based confidence intervals from the specified ANCOVA. They should be read as approximate descriptions of the precision available from the posted arm summaries, rather than as a replacement for the sponsor’s formal analysis. The registry does not report the sponsor’s primary comparison confidence intervals or formal p-values.

Precision also depends on which participants contribute to an endpoint. The primary outcome analysis counts differ by arm, and the secondary endpoint counts differ from those for the primary outcome. The standard errors reported for the arm means reflect uncertainty in those estimates, not the full range of participant-level values. A narrow standard error for an arm mean would not mean that individual outcomes were similar, and an endpoint’s precision cannot be judged from enrollment alone.

In general, a confidence interval is more informative than a point estimate alone because it makes uncertainty visible. Here, the intervals do not identify a narrow range of plausible between-group differences that would settle the clinical interpretation. The record does not state a clinically important difference threshold for serum creatinine, so the estimates cannot be classified against such a threshold. Statistical uncertainty and clinical importance are related but distinct questions.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are illustrations of the number of participants per arm under stated assumptions; they are not a report of the trial’s original sample-size design. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms being compared, and a normal approximation. Each planning scenario uses a stated fraction of the observed effect as the effect to detect. For these continuous outcomes, the displayed quantities are participants per arm, not total participants across the two arms. The record’s note about total events applies to time-to-event outcomes, which are not the outcomes represented by these planning figures.

The 80% power column gives the illustrative participants per arm for a design with an 80% probability of detecting the specified effect under the calculation assumptions, if that effect is present and the assumptions hold. The 90% power column gives the corresponding per-arm number for a design with a 90% probability under those same assumptions. Power is a property of a planned design under specified conditions; it is not a measure of how likely the posted result is to be correct.

Each row uses the observed effect or a smaller fraction of it. Smaller effects are harder to distinguish from random variation, so the planning illustration requires more participants per arm as the target effect becomes smaller. This relationship is important when considering whether an observed estimate is precise enough to answer a question about a smaller clinically relevant effect. In particular, planning around a point estimate from a trial can be unstable when that estimate is uncertain.

These figures are planning illustrations, not observed power. The original trial’s sample-size justification and design assumptions are not reported in the registry record. The planning calculations therefore should not be used to infer what the investigators expected when they designed the study or to characterize the probability that the trial’s result represents a true effect.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 0.050; pooled standard deviation σ = 0.178.
2. n = 2 × (1.96 + 0.842)² × 0.178² / 0.050² = 198.5, rounded up to 199 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- 0.05                      # observed difference in means
sigma <- 0.177802091706                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(1113801)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 199 (80% power), 266 (90% power)
 75% of observed effect: n per arm = 353 (80% power), 473 (90% power)
 50% of observed effect: n per arm = 795 (80% power), 1,063 (90% power)
power.t.test: 199.5 
Simulated power at n = 199 per arm: 0.797 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Multiplicity, Missing Data and Analysis Populations

The registry record does not report whether the statistical plan adjusted for multiple comparisons. The posted results involve three LY2382770 dose groups, a placebo comparison, and several outcomes. When many hypotheses are examined, the chance of at least one seemingly notable finding can increase. In general, multiplicity procedures or a prespecified testing hierarchy can control how such comparisons are interpreted. No such procedure or hierarchy is described in the registry record, so the unadjusted recalculated p-values should not be treated as if they account for all comparisons.

The record describes the primary ANCOVA model, but the complete statistical analysis plan is not reported. Details such as prespecified contrast definitions, handling of protocol deviations, assumptions checks, and rules for analysis decisions are therefore unavailable. The registry also does not report interim analyses or the trial’s original sample-size justification. The absence of these details means readers cannot assess whether the reported comparisons correspond to a fully specified confirmatory testing strategy.

Missing-data information is limited. The primary population includes randomized participants who received at least one dose and had evaluable baseline and post-baseline serum creatinine measurements. This definition makes clear that not all enrolled participants necessarily contributed to the primary endpoint, but the record does not give reasons for missing measurements, describe their timing, or report sensitivity analyses for missingness. It also does not report whether missing data were handled through imputation or another approach. No assumptions about those methods should be inferred from the endpoint counts alone.

The primary population is not simply all randomized participants: it has post-randomization requirements for dosing and evaluable measurements. This matters because the resulting estimate describes the participants meeting those analysis criteria. The record does not report enough information to assess how their outcomes may differ from those excluded from that endpoint analysis. Secondary outcomes have their own analysis counts, so their populations can differ as well.

These reporting gaps do not establish that the analyses were inappropriate. They limit what can be independently assessed from the registry record, particularly for confirmatory interpretation, missing-data robustness, and the relationship between planned and posted analyses.

15. 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: renal failure acute (7.6%), cardiac failure congestive (5.7%), cardiac failure (4.9%), renal failure chronic (4.9%), atrial fibrillation (3.9%).

The registry reports serious adverse events by group as counts of participants at risk and participants affected. The placebo group lists 39 affected among 103 at risk; the 2 mg group lists 44 among 105; the 10 mg group lists 37 among 103; and the 50 mg group lists 41 among 105. These counts describe the registry’s group-level reporting and should not be interpreted as causal comparisons by themselves. They do not show the timing, duration, recurrence, or clinical circumstances of events.

For other adverse events, the record lists 57 affected among 103 at risk in the placebo group, 67 among 105 in the 2 mg group, 62 among 103 in the 10 mg group, and 62 among 105 in the 50 mg group. The record also lists serious adverse event terms with percentages: renal failure acute, 7.6%; cardiac failure congestive, 5.7%; cardiac failure, 4.9%; renal failure chronic, 4.9%; atrial fibrillation, 3.9%; and acute myocardial infarction, 3.8%. The registry information presented does not establish that these term percentages are arm-specific.

Deaths are not reported in the registry record. Adverse-event counts need context, including event definitions, exposure time, severity details, and formal comparative analyses. The figures alone do not establish that an event was caused by treatment or that one group had greater risk.

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

The posted results show that the estimated average change in log-transformed serum creatinine at the 12-month endpoint was higher in each LY2382770 dose group than in placebo. The recalculated differences are small on that transformed scale, and their confidence intervals span zero. The estimates therefore remain uncertain: the summary statistics do not distinguish clearly between no difference and a range of possible differences. The unadjusted p-values do not resolve that uncertainty, and they do not account for multiple dose and outcome comparisons.

This does not mean the groups were proven equivalent. Establishing equivalence would require a prespecified margin and an analysis designed for that purpose, neither of which is reported in the registry record. Nor does the result establish that the drug has a clinically meaningful effect. The record does not report a clinical-importance threshold for the primary endpoint, and the statistical scale is log transformed.

The study’s results also do not describe each participant’s experience. Group means can conceal variation among participants, and the endpoint analysis population excludes people without the required dosing and evaluable measurements. The registry does not report enough detail about missing data to determine how excluded or unavailable measurements might affect the estimates.

The secondary outcome summaries add context but do not create a definitive conclusion. They cover different kidney-related measures and drug exposure, and their formal sponsor analyses and multiplicity handling are not reported. Their unadjusted recalculations should therefore be considered exploratory rather than as independent confirmation of the primary finding.

Finally, the study is listed as terminated, with no reason reported in the registry record. That status is relevant context but does not explain the observed endpoint estimates. Overall, the registry supports a cautious reading of uncertain group-level comparisons, not a medical recommendation or a definitive conclusion about treatment benefit or harm.

17. Why This Trial Matters Statistically

This trial illustrates why a point estimate, a p-value, and a confidence interval answer different questions. The estimated primary differences are positive, but the recalculated intervals span zero and the unadjusted p-values vary across dose comparisons. A single threshold-based reading of those p-values would discard information about the direction and precision of the estimates. The intervals make clear that the posted summary statistics do not pin down a narrow range of plausible contrasts.

The trial also highlights the distinction between a registry’s model description and an independent recalculation from arm summaries. The primary outcome was analyzed using ANCOVA with specified baseline covariates and repeated-visit terms, while the comparisons discussed alongside the arm values are simple unadjusted recalculations. Treating those as interchangeable would overstate what can be learned from the available summary data. Clear separation between model-based results and approximate re-analysis is essential for transparent interpretation.

Different endpoint populations further show why enrollment is not a universal denominator. Participants contributing to the primary outcome and secondary outcomes differ, and each result should be understood in relation to its own analysis population. The registry does not fully describe missingness, which limits assessment of the robustness and generalizability of those estimates.

Finally, multiple doses and multiple outcomes make multiplicity relevant. Without a reported testing hierarchy or adjustment, secondary signals deserve less weight than a complete, prespecified analysis. These statistical considerations matter even when a study is randomized and masked: strong design features improve comparisons, but they do not eliminate uncertainty, incomplete reporting, or the need to distinguish exploratory from confirmatory evidence.

18. 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.

Several limitations specific to this record constrain interpretation. The study is listed as terminated, but the reason is not reported in the registry record. Without that context, it is not possible to determine whether termination affected follow-up, outcome availability, or the timing and completeness of results. The record should not be used to infer a reason for termination.

The primary outcome analysis is limited to randomized participants who received at least one dose and had evaluable baseline and post-baseline serum creatinine. The registry reports the arm counts for this analysis, but does not provide a full participant flow or explain why other participants did not contribute. It also does not describe missing-data assumptions or sensitivity analyses. The resulting estimates may therefore be difficult to assess for robustness to missing measurements.

The registry reports a detailed primary model description but not the full statistical analysis plan. The original sample-size justification, interim-analysis details, multiplicity strategy, and clinically important difference threshold are not reported. As a result, it is not possible to verify from this record whether the posted outcome comparisons followed a prespecified confirmatory plan or whether the study was designed around a particular effect size.

The comparison estimates and p-values discussed are unadjusted recalculations from posted summary statistics, not the sponsor’s formal model-based primary comparisons. Their confidence intervals are approximate and should not be conflated with ANCOVA results. Formal sponsor analyses for the secondary outcomes are not reported, and the pharmacokinetic outcome is listed without numerical results in the available outcome summaries.

Finally, registry masking classifications are not fully aligned: the official title calls the study double-masked, while the design field records triple masking. The record does not explain the discrepancy. These limitations affect assessment of precision, analysis choices, and reporting completeness; they do not by themselves establish that the trial conduct or analyses were flawed.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Study in Participants With Diabetic Kidney Disease — NCT01113801.
• Registry record last updated 2019-09-17; status last verified 2019-09.
• Results first posted 2017-12-13.
• 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.

22. Record Summary

NCT01113801 is a randomized, parallel-group, placebo-controlled Phase 2 study of LY2382770 in participants with diabetic kidney disease due to type 1 or type 2 diabetes. It enrolled 417 participants and is listed as terminated. The official title describes a multicenter, double-masked study, while the registry design classification records triple masking.

The primary outcome was change in log-transformed serum creatinine from baseline to the 12-month endpoint. The registry describes an ANCOVA model and reports least-squares mean changes by arm. Unadjusted recalculations from the posted summaries estimate positive differences versus placebo for all three doses; their confidence intervals span zero. The registry does not report formal sponsor comparison analyses for the primary outcome.

Secondary outcomes cover urine protein-to-creatinine ratio, serum creatinine slope, estimated glomerular filtration rate slope, and pharmacokinetics. Formal sponsor analyses, multiplicity handling, the original sample-size justification, the reason for termination, and several missing-data details are not reported in the registry record.