A Study of LY3561774 in Participants With Mixed Dyslipidemia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY3561774 in Participants With Mixed Dyslipidemia (NCT05256654), a randomized phase 2 study. The primary outcome is Percent Change From Baseline for Apolipoprotein B (ApoB) at Day 180.

2. Clinical Question

This is a question about the between-group pattern in a continuous laboratory measure at a specified follow-up time, not about a clinical event or a direct measure of how participants feel or function. A negative percent change represents a lower measured apoB level relative to baseline; the between-group comparison describes how the average modeled changes differed. The registry record gives a separate comparison for each dose against placebo.

The study is identified as Phase 2 and randomized, double-blind, placebo-controlled, and parallel-group. Its brief summary describes a multicenter study of efficacy and safety in participants with mixed dyslipidemia who were taking a stable statin dose. The record lists 205 participants enrolled. It does not report the ages, baseline clinical characteristics, or the number of participants in each analysis population beyond the outcome-specific counts.

3. Trial Design

The record identifies NCT05256654 as a Phase 2 randomized, double-blind, placebo-controlled, parallel-group study of LY3561774 in adults with mixed dyslipidemia. Eli Lilly and Company is listed as the sponsor. The record gives a study start date of 2022-07-20, a primary completion date of 2024-03-04, and a status of completed. The brief summary describes the trial as multicenter and Phase 2b; the formal phase listing is Phase 2.

Participants were assigned to placebo or one of three LY3561774 dose groups: 100 mg, 400 mg, or 800 mg. The listed dosing was subcutaneous on Day 0 and Day 90 (-5 to +10 days), with follow-up through Day 360. The registry record describes the study as double-blind but does not report the specific procedures used to maintain masking or the allocation ratio.

The primary endpoint was percent change from baseline in apoB at Day 180. Its analysis population was defined as randomized participants who received at least 1 dose and had an evaluable baseline apoB value and at least 1 post-baseline measurement. The outcome summaries list 57 participants for placebo, 30 for LY3561774 100 mg, 58 for LY3561774 400 mg, and 59 for LY3561774 800 mg. These are the counts associated with the posted endpoint summaries; the record does not provide a full accounting of participant flow or reasons for missing measurements in these results.

The registry record does not report the planned sample-size justification, allocation ratio, randomization procedure, or details of any interim analyses. It also does not report the trial's complete statistical analysis plan. Those omissions limit what can be inferred about the rationale and prespecification of the 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 receiving at least 1 dose of study drug with evaluable apoB values at baseline, and at least 1 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

6. Primary Endpoint

The registry lists the primary outcome as Percent Change From Baseline for Apolipoprotein B (ApoB) at Day 180, measured over Baseline, Day 180.

The primary endpoint is percent change from baseline in apolipoprotein B (apoB) at Day 180. The registry describes it as the change in apoB from baseline to Day 180 expressed as a percentage of baseline levels. ApoB is a continuous laboratory measure, so the result is expressed as a modeled mean change rather than a count of events. The reported arm summaries are least-squares means, with standard errors, from a mixed model for repeated measures adjusted for baseline.

Percent change places the follow-up change in relation to the baseline value, allowing the result to be described on a relative scale rather than in the original measurement units. A baseline-adjusted model is intended to account for baseline measurements when estimating follow-up patterns. These are general features of such analyses; the registry record does not describe additional model terms, covariance structure, or assumptions.

The Day 180 measurement provides a common follow-up point for comparing the randomized groups. The relevant statistical contrast is the difference in modeled average percent change between each dose and placebo. A negative contrast indicates a more negative modeled change in the dose group than in placebo, while the confidence interval indicates the range of values compatible with the reported estimate under the model. This endpoint is a surrogate laboratory measure, not a direct count of clinical outcomes.

The primary analysis population required at least 1 dose and at least 1 post-baseline apoB measurement, as well as an evaluable baseline value. The record does not state how participants without qualifying measurements were handled in the analysis, beyond that population definition.

7. Results Posted in the Registry

• LY3561774 100 mg: mean -14.10 versus -11.60 on control; difference -2.50 (95% CI -14.60 to 9.60), standardized effect d = -0.09; z-test p = 0.686.
• LY3561774 400 mg: mean -24.30 versus -11.60 on control; difference -12.70 (95% CI -22.09 to -3.31), standardized effect d = -0.50; z-test p = 0.008.
• LY3561774 800 mg: mean -19.00 versus -11.60 on control; difference -7.40 (95% CI -17.11 to 2.31), standardized effect d = -0.28; z-test p = 0.135.

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.

Percent Change From Baseline for Angiopoietin-like Protein 3 (ANGPTL3) at Day 180

• 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:
  • LY3561774 100 mg: mean -55.70 versus -3.20 on control; difference -52.50 (95% CI -67.00 to -38.00), standardized effect d = -1.31; z-test p = <0.001.
  • LY3561774 400 mg: mean -70.80 versus -3.20 on control; difference -67.60 (95% CI -80.32 to -54.88), standardized effect d = -1.96; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for LY3561774 100 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for LY3561774 400 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent Change From Baseline for Low Density Lipoprotein-Cholesterol (LDL-C) at Day 180

• 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:
  • LY3561774 100 mg: mean -9.90 versus -8.70 on control; difference -1.20 (95% CI -14.21 to 11.81), standardized effect d = -0.04; z-test p = 0.856.
  • LY3561774 400 mg: mean -24.00 versus -8.70 on control; difference -15.30 (95% CI -25.15 to -5.45), standardized effect d = -0.57; z-test p = 0.002.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between LY3561774 100 mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for LY3561774 400 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent Change From Baseline for High Density Lipoprotein-Cholesterol (HDL-C) at Day 180

• 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:
  • LY3561774 100 mg: mean -2.10 versus 4.30 on control; difference -6.40 (95% CI -14.82 to 2.02), standardized effect d = -0.33; z-test p = 0.136.
  • LY3561774 400 mg: mean -12.80 versus 4.30 on control; difference -17.10 (95% CI -23.70 to -10.50), standardized effect d = -0.95; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between LY3561774 100 mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for LY3561774 400 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary results cover a broader set of lipid measures than the primary apoB endpoint. The registry record lists 12 secondary outcome measures. Numerical results are available for ANGPTL3, LDL-C, and HDL-C at Day 180; results for the other secondary measures are not reported in the registry record. These secondary measures include non-HDL-C and triglycerides in the listed outcomes.

At a broad level, the available Day 180 results show more negative modeled changes in several LY3561774 groups than in placebo, with the size and pattern varying by measure and dose. The sponsor-reported secondary comparisons include results for ANGPTL3 and LDL-C at 100 mg and 400 mg, and for HDL-C at 100 mg and 400 mg. They do not include sponsor comparisons for every active dose and every posted secondary measure. The primary and secondary measures therefore provide related but not interchangeable views of the biomarker pattern.

Secondary endpoints can help describe whether changes in the primary measure occur alongside changes in other laboratory measures. They do not independently confirm the primary result, and they do not turn a biomarker pattern into evidence about unreported clinical outcomes. The results also vary across outcomes and dose groups, so a single summary of all secondary measures would conceal important differences.

Multiplicity matters because testing many outcomes and dose comparisons creates more opportunities for apparently notable results by chance. The registry record does not report whether a hierarchy, adjustment, or other multiplicity strategy was prespecified or used for secondary analyses. Consequently, unadjusted secondary results carry less weight than the designated primary analysis and should be interpreted as supportive or exploratory descriptions rather than isolated definitive findings. The record does not provide enough information to determine how the sponsor intended the secondary endpoints to support formal claims.

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

• Percent Change From Baseline for Angiopoietin-like Protein 3 (ANGPTL3) at Day 180
• Percent Change From Baseline for Low Density Lipoprotein-Cholesterol (LDL-C) at Day 180
• Percent Change From Baseline for High Density Lipoprotein-Cholesterol (HDL-C) at Day 180
• Percent Change From Baseline for Non-High-Density Lipoprotein-Cholesterol (Non-HDL-C) at Day 180
• Percent Change From Baseline for Triglycerides at Day 180
• Percent Change From Baseline for Angiopoietin-like Protein 3 (ANGPTL3)
• Percent Change From Baseline for Non-High-Density Lipoprotein-Cholesterol (Non-HDL-C)
• Percent Change From Baseline for High Density Lipoprotein-Cholesterol (HDL-C)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: percent change in apoB from baseline to Day 180. For a continuous outcome, the registry reports a modeled mean for each arm and a mean difference comparing each active dose with placebo. These summaries describe group averages, not the distribution of individual participant responses. The primary arm estimates are least-squares means and their reported dispersion is standard error.

What does the mixed model do?

The registry says the primary least-squares means use a mixed model for repeated measures (MMRM) adjusted for baseline. In general, a repeated-measures model analyzes measurements taken from participants over time while accounting for the fact that observations from the same participant are related. Baseline adjustment means that baseline apoB is included in the model rather than leaving the comparison wholly unadjusted for the starting measurement. The registry record does not report the model's full specification, such as its covariance structure, all included terms, or the method used to handle missing outcome measurements. Those details should not be inferred.

A least-squares mean is a model-based estimate of an arm's average outcome under the fitted model. It is not necessarily the same as a simple arithmetic average of observed values. The sponsor's reported net mean differences are likewise model-based comparisons. They are the primary source for interpreting the trial's planned outcome analysis; the simple recalculations from summary statistics are approximate and unadjusted.

What are standard errors and confidence intervals?

A standard error describes the statistical uncertainty in an estimate, reflecting how much the estimate would vary across repeated samples under the model and its assumptions. It is not the same as the spread of individual participant values. A confidence interval communicates uncertainty about an estimate by giving a range of values compatible with the data and analysis. The reported primary comparisons use 95% confidence intervals. A confidence interval that includes zero does not establish that the true difference is zero; it indicates that zero is among the values not ruled out by that interval under the analysis.

The sponsor's primary results are based on mixed-model analyses. The separate recalculations use the posted arm means and standard errors to approximate unadjusted contrasts and intervals. They do not reproduce the full repeated-measures model. In addition, the recalculated pooled standard deviations are approximate. Because the registry's arm estimates are adjusted model-based means, and because the original model details are not reported, these recalculations should be viewed as supplementary checks rather than substitutes for the sponsor's analysis. Where the estimates differ, the sponsor's own analysis takes precedence.

Why do unadjusted p-values require care?

A p-value describes how compatible the data are with a specified null hypothesis under the assumptions of the analysis; it is not the probability that the null hypothesis is true. The recalculated p-values are unadjusted comparisons. The registry record lists multiple doses and multiple outcomes, but does not report whether or how the trial's analysis controlled the increased chance of false-positive findings across comparisons. Without that information, a p-value from an individual contrast should not be treated as a complete account of the evidence.

The sponsor-reported primary p-values are 0.691 for 100 mg, 0.008 for 400 mg, and 0.140 for 800 mg. The sponsor also reports confidence intervals and mixed-model mean differences, which give more context than p-values alone. The record does not say whether these p-values were adjusted for multiple comparisons.

What do planning calculations represent?

The sample-size illustrations use the observed effect and stated assumptions to show the participants per arm that would be required under those assumptions to detect specified fractions of that observed effect at 80% or 90% power. They are planning illustrations, not evidence that the trial had a particular probability of detecting an effect. The original trial design assumptions and sample-size justification are not reported in the registry record. Smaller effects require more participants in these illustrations, because a smaller average separation between groups is harder to distinguish from random variation at a given significance level.

General statistical interpretation also depends on design and measurement quality. Randomization supports a fair comparison in expectation, and blinding can reduce some forms of bias, but neither feature removes uncertainty from finite sample sizes, missing measurements, model assumptions, or multiplicity. The registry record describes randomized double-blind allocation but does not provide enough detail to assess all of those issues.

11. Confidence Intervals and Precision

The sponsor-reported primary comparisons include 95% confidence intervals, which show the range of effect estimates compatible with the model and data under its assumptions. For LY3561774 100 mg versus placebo, the mean difference (net) is -2.8, with a 95% confidence interval from -15.5 to 11.9. Because that interval includes zero and spans values on either side, the direction and size of the contrast are not precisely determined by this estimate.

For 400 mg versus placebo, the reported mean difference (net) is -14.3, with a 95% confidence interval from -23.6 to -3.9. The interval lies below zero, while still allowing a range of possible magnitudes. For 800 mg versus placebo, the mean difference (net) is -8.3, with a 95% confidence interval from -18.3 to 2.9. This interval includes zero, so the data are compatible with both a more negative contrast and values near or on the other side of zero under the model.

Confidence intervals are not guarantees that the true value lies within the displayed range, nor do they account for every source of uncertainty. They describe sampling uncertainty conditional on the analysis and assumptions. The registry record does not report all model details or missing-data procedures, which limits assessment of how robust these intervals are to alternative choices.

The arm-level standard errors are also relevant but should not be confused with standard deviations of participant outcomes. The record reports standard errors of 3.65 for placebo, 4.98 for 100 mg, 3.1 for 400 mg, and 3.35 for 800 mg. These describe uncertainty around the arm-level least-squares means. The sponsor's confidence intervals for the between-group comparisons are the more direct measure of uncertainty for the primary question.

The intervals and point estimates distinguish the precision of the three comparisons, but do not settle clinical importance. The registry record does not report a threshold for a clinically important difference in apoB, so the estimates cannot be classified against such a threshold from this record.

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 sample-size illustrations are reported as participants per arm for 80% power and participants per arm for 90% power. They are not total event counts: this is a continuous outcome, and the listed figures are per-arm participant counts. The calculations are planning illustrations based on the observed effect, not the original design assumptions for this trial.

The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is the stated fraction of the observed effect. For example, the rows for planning for 75% or 50% of the observed effect show the implications of aiming to detect a smaller effect than the observed one. Smaller effects need more participants because the separation between group averages is less pronounced relative to random variation.

The 80% power column gives the modeled participant count per arm for a planning scenario in which the test would detect the specified effect 80% of the time if that effect and the assumptions were correct. The 90% power column gives the corresponding count for 90% power. Higher planned power generally requires a larger sample under the same assumptions. Each dose comparison has its own illustration because the observed effect and variability differ across comparisons.

These figures are not observed power. They do not describe the probability that the completed trial detected an effect, and they should not be read as evidence that a comparison was adequately powered. The registry record's original sample-size justification and design assumptions are not reported.

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 = -2.500; pooled standard deviation σ = 27.462.
2. n = 2 × (1.96 + 0.842)² × 27.462² / -2.500² = 1,894.1, rounded up to 1,895 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 <- -2.5                      # observed difference in means
sigma <- 27.4615812920309                     # 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(5256654)
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 = 1,895 (80% power), 2,536 (90% power)
 75% of observed effect: n per arm = 3,368 (80% power), 4,508 (90% power)
 50% of observed effect: n per arm = 7,577 (80% power), 10,143 (90% power)
power.t.test: 1895.1 
Simulated power at n = 1,895 per arm: 0.800 (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. Analyses Reported by the Sponsor

The sponsor reports the primary comparison using a mixed-model analysis adjusted for baseline and repeated measurements. Those reported results are the appropriate primary estimates to use when describing the trial's own analysis: mean differences (net) of -2.8, -14.3, and -8.3 for 100 mg, 400 mg, and 800 mg, respectively, against placebo.

The separate recalculated comparisons are simple, unadjusted approximations based on the posted arm-level means and standard errors. They do not reproduce the sponsor's mixed model or its adjustment structure. For 100 mg, the recalculated contrast is -2.5 with a 95% interval from -14.6 to 9.602 and an unadjusted p-value of 0.686, while the sponsor reports -2.8, an interval from -15.5 to 11.9, and p = 0.691. For 400 mg, the recalculation is -12.7, with an interval from -22.09 to -3.314 and p = 0.008; the sponsor reports -14.3, an interval from -23.6 to -3.9, and p = 0.008. For 800 mg, the recalculation is -7.4, with an interval from -17.11 to 2.31 and p = 0.135; the sponsor reports -8.3, an interval from -18.3 to 2.9, and p = 0.140.

The differences are consistent with comparing an approximate unadjusted calculation to a model-based result, not evidence that one estimate should be substituted for the other. The sponsor's own analysis takes precedence. The recalculations can help illustrate the scale and direction of the contrasts, but they are not a reconstruction of the trial's full analysis.

15. Multiplicity, Missing Data and Analysis Populations

The primary analysis population is described as randomized participants who received at least 1 dose of study drug, had evaluable apoB at baseline, and had at least 1 post-baseline measurement. That definition is narrower than all randomized participants and may exclude participants without qualifying measurements. The registry record does not report a complete participant flow for the primary endpoint, reasons for missing measurements, or the number excluded at each analysis step.

The primary outcome uses a mixed model for repeated measures, but the record does not describe its missing-data assumptions, imputation approach, or sensitivity analyses. General statistical context: repeated-measures models can use available observations under specified assumptions, but the validity of the resulting estimates depends in part on how missingness relates to observed and unobserved outcomes. Without the model details and missing-data analyses, the robustness of the primary estimates to missing data cannot be assessed from the registry record.

There are multiple active-dose comparisons with placebo and multiple secondary outcomes. The record does not report whether multiplicity was controlled for the primary dose comparisons, the secondary outcomes, or any subgroup analyses. When many hypotheses are tested, the chance of at least one apparently notable result can increase. A prespecified testing hierarchy or adjustment can address that issue, but no such procedure is described in the registry record. The reported p-values should therefore be understood as the values associated with the listed analyses, not as evidence that multiplicity was accounted for.

The record also does not report interim analyses, the full statistical analysis plan, or the original sample-size justification. It is therefore not possible to establish from this record which analyses were prespecified, how the target enrollment was chosen, or whether any planned adjustments were made during the study. These gaps limit interpretation of statistical certainty and analysis choices; they do not alter the numerical results reported by the sponsor.

16. 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: radius fracture (3.5%), cellulitis (3.3%), angina pectoris (1.8%), pneumonia (1.8%), hypocalcaemia (1.8%).

The safety summary reports serious adverse events in 5 of 57 participants in the placebo group, 1 of 30 in the LY3561774 100 mg group, 3 of 58 in the 400 mg group, and 2 of 59 in the 800 mg group. The registry also reports 16, 14, 14, and 9 participants, respectively, with other adverse events. These are counts among the listed participants at risk in each group; the record does not provide additional detail about event duration, severity beyond the serious classification, or attribution to study treatment.

No deaths are reported in any of the four groups. The record lists serious-event terms including radius fracture, cellulitis, angina pectoris, pneumonia, hypocalcaemia, and brain abscess, with percentages attached to those terms. The registry information presented does not identify those terms by treatment group in this list, so they should not be attributed to a particular arm.

These counts describe events observed in the trial and are not a comparative safety analysis. Differences in counts should be interpreted cautiously because the group sizes vary and the record does not report a formal statistical comparison of adverse-event rates. The safety information does not establish causation or characterize risks outside the participants and follow-up described in the record.

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

The primary result is a comparison of modeled average percent change in apoB at Day 180 between each LY3561774 dose group and placebo. The sponsor-reported estimate for 400 mg is -14.3, with a 95% confidence interval from -23.6 to -3.9 and p = 0.008. The intervals for 100 mg and 800 mg include zero. These are findings about the posted endpoint and analysis, not a complete account of the effects of treatment or the trial's clinical implications.

ApoB percent change is a laboratory outcome. The registry record does not report clinical event results that would show whether the observed biomarker differences correspond to differences in health outcomes. Nor does the record provide a threshold for a clinically important apoB change. Statistical evidence about a group-average biomarker contrast cannot, by itself, establish the magnitude of patient-level benefit or harm.

The trial's primary comparison is model-based, while the additional recalculations are approximate and unadjusted. The sponsor's reported analysis takes precedence. Important details about missing-data assumptions, multiplicity, and the full analysis plan are not reported in the registry record, so they cannot be resolved from the posted results alone.

The results also should not be read as a direct comparison among the active doses. Each dose is compared with placebo; the record does not report a prespecified statistical test of one active dose against another. The primary outcome results do not establish a dose-response relationship, and the secondary results are not a substitute for such an analysis.

In short, the posted data describe the trial's measured apoB changes, the sponsor's estimated dose-versus-placebo contrasts, and their statistical uncertainty. They do not determine how the findings apply beyond the studied participants, how they relate to clinical outcomes, or what an individual should do. The record identifies participants with mixed dyslipidemia on stable statin therapy, and the results should be understood within that study context.

18. Why This Trial Matters Statistically

This trial is statistically informative because it compares three dose groups with placebo using randomization and blinding, while focusing on a continuous biomarker endpoint measured at a common follow-up time. The design supports estimation of average between-group differences, and the registry reports model-based estimates with confidence intervals rather than only arm-level changes or p-values.

The results also illustrate why arm-level estimates and treatment contrasts answer different questions. The placebo and active-arm least-squares means describe modeled changes within each group, while the net mean differences describe the relative contrast against placebo. The distinction is important when placebo participants also show a change from baseline.

The trial highlights how precision and analysis methods shape interpretation. The sponsor's reported confidence intervals give a range of plausible contrasts under the mixed model, while simple recalculations from summary statistics yield approximate unadjusted comparisons. Keeping those analyses distinct prevents an approximate check from being mistaken for the trial's primary analysis.

Finally, the registry record makes clear that statistical significance is only one part of interpretation. Multiple doses and secondary outcomes raise questions about multiplicity, and incomplete reporting of missing-data methods, the full statistical plan, and the original design assumptions limits evaluation of robustness. The trial's measured biomarker results can be described precisely, but broader claims require information and outcomes not reported in the registry record.

19. 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 are specific to the information reported for this trial. First, the primary analysis population requires receipt of at least 1 dose and at least 1 post-baseline apoB measurement. The registry record does not report how many randomized participants failed to meet those criteria or why measurements were unavailable. The posted outcome counts therefore do not, by themselves, show the full path from enrollment to analysis.

Second, the sponsor's primary estimates come from an MMRM adjusted for baseline, but the registry record does not give enough detail to evaluate the complete model specification, its missing-data assumptions, or sensitivity analyses. The approximate recalculations are based on arm summaries and cannot fill that gap. They also differ from the sponsor's estimates, so the sponsor analysis remains the principal source for the trial's reported comparison.

Third, the record does not report the multiplicity strategy across three dose-versus-placebo comparisons and numerous outcomes. It also does not report the complete analysis plan, the original sample-size justification, or interim analyses. These omissions make it difficult to assess the prespecification and statistical context of individual p-values.

Fourth, although the record reports 12 secondary outcomes, numerical results are not available for all of them. The sponsor-reported secondary contrasts also cover only some dose and outcome combinations. Thus, the overall pattern cannot be comprehensively evaluated from the reported numerical secondary results.

Finally, the primary endpoint is a biomarker at Day 180, and the registry record does not report clinical event outcomes or a clinically important difference threshold for apoB. The results do not establish whether the observed biomarker contrasts translate into differences in clinical outcomes. The listed study population and regimen also define the context of the evidence; the record does not report information sufficient to assess generalizability beyond that context.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study of LY3561774 in Participants With Mixed Dyslipidemia — NCT05256654.
• Registry record last updated 2025-03-17; status last verified 2025-03.
• Results first posted 2025-03-17.
• 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.

23. Record Summary

NCT05256654 is a completed Phase 2 randomized, double-blind, placebo-controlled, parallel-group study of LY3561774 in adults with mixed dyslipidemia. The study enrolled 205 participants and compared subcutaneous LY3561774 at 100 mg, 400 mg, and 800 mg with placebo. The listed doses were administered on Day 0 and Day 90, with follow-up through Day 360.

The primary endpoint was percent change from baseline in apoB at Day 180, analyzed using baseline-adjusted least-squares means from a mixed model for repeated measures. The sponsor-reported 400 mg comparison with placebo was -14.3, with a 95% confidence interval from -23.6 to -3.9 and p = 0.008; the reported intervals for 100 mg and 800 mg included zero. Approximate recalculations differ from the sponsor's primary analysis, which takes precedence.

The record also reports secondary lipid outcomes and adverse-event counts. Multiplicity procedures, missing-data details, the original sample-size justification, and the complete statistical analysis plan are not reported in the registry record.