Efficacy and Safety of Efpeglenatide Versus Placebo in Patients With Type 2 Diabetes Mellitus Inadequately Controlled With Metformin Alone or in Combination With Sulfonylurea: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety of Efpeglenatide Versus Placebo in Patients With Type 2 Diabetes Mellitus Inadequately Controlled With Metformin Alone or in Combination With Sulfonylurea (NCT03770728), a randomized phase 3 study. The primary outcome is Change From Baseline to Week 30 in HbA1c.

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, parallel-group, quadruple-masked study comparing once-weekly efpeglenatide with matched placebo. The official study title describes a multicenter, double-blind, placebo-controlled study lasting 30 weeks. Participants continued metformin alone or metformin with a sulfonylurea as background therapy. The registry lists efpeglenatide groups receiving 2 mg, 4 mg, or 6 mg, as well as a placebo group.

The registry records enrollment as 312. The primary endpoint was change from baseline to Week 30 in HbA1c. Its analysis description says that all Week 30 assessment values available were included and that the analysis used the intent-to-treat population. Participants were analyzed according to their randomized treatment group, irrespective of rescue therapy use and compliance with study procedures. The arm-level primary endpoint results include 48 participants in the placebo group, 48 in the 2 mg group, 49 in the 4 mg group, and 48 in the 6 mg group. These endpoint-specific counts should be read as the numbers contributing to the posted summaries, not as a complete account of participant flow.

The registry lists a start date of 2019-08-01 and a primary completion date of 2020-11-28. Study status is recorded as terminated. The reason for termination, whether recruitment or follow-up was affected, and any consequences for interpretation are not reported in the registry record. The original sample-size justification, planned analysis details, and any interim analyses are also not reported in the registry record. The registry includes posted arm-level outcome summaries, but no reported analyses are listed. This means the statistical comparisons accompanying the outcome summaries should be treated as descriptive, unadjusted calculations rather than as a substitute for a complete prespecified trial 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.

Before assignment: A total of 312 participants were randomized in 1:1:1:1 ratio to either placebo, efpeglenatide 2 milligrams (mg), efpeglenatide 4 mg, or efpeglenatide 6 mg treatment arms, stratified by screening glycated hemoglobin (HbA1c) values (less than \[\<\]8%, greater than or equal to \[\>=\]8%) and sulfonylurea (SU) use at screening (Yes/No).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Analysis was performed on Intent-to-treat (ITT) population, which included all participants randomized irrespective of rescue therapy use and compliance with the study protocol and procedures, and were analyzed according to the treatment group allocated by randomization. Here, "Overall number of participants analyzed"= participants evaluable for this outcome measure.

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: Analysis was performed on Intent-to-treat (ITT) population, which included all participants randomized irrespective of rescue therapy use and compliance with the study protocol and procedures, and were analyzed according to the treatment group allocated by randomization.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline to Week 30 in HbA1c, measured over Baseline to Week 30.

The primary endpoint is change in HbA1c from baseline to Week 30, expressed as a percentage of HbA1c. HbA1c is a continuous measure of glycemic control. Change from baseline describes how the measure differs at follow-up from its starting value, while comparing mean changes between randomized groups puts the observed changes in the context of the placebo group.

In general, a change below zero means the measured value at follow-up is lower than at baseline. For this endpoint, the posted group means are negative in all four groups. A between-group mean difference is expressed as the efpeglenatide group mean change minus the placebo mean change. A negative difference therefore indicates a more negative mean change in the efpeglenatide group than in the placebo group; it does not, by itself, establish the result of a prespecified inferential analysis.

HbA1c was selected as the primary measure because the stated primary objective was to compare efpeglenatide and placebo on HbA1c change. The registry says the analysis included all available Week 30 assessment values and used the intent-to-treat population, with participants analyzed by randomized group irrespective of rescue therapy use or compliance. The registry record does not report the original analysis model, adjustments, or a detailed missing-data method. The endpoint-specific results are means and standard deviations, so they describe both the average change and the spread of individual changes in each group.

7. Results Posted in the Registry

• Efpeglenatide 2 mg: mean -1.05 versus -0.27 on control; difference -0.78 (95% CI -1.14 to -0.42), standardized effect d = -0.87; z-test p = <0.001.
• Efpeglenatide 4 mg: mean -1.46 versus -0.27 on control; difference -1.19 (95% CI -1.55 to -0.83), standardized effect d = -1.31; z-test p = <0.001.
• Efpeglenatide 6 mg: mean -1.36 versus -0.27 on control; difference -1.09 (95% CI -1.49 to -0.69), standardized effect d = -1.08; z-test p = <0.001.

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.

Number of Participants With HbA1c <7.0%

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Efpeglenatide 2 mg: 34.6% (27/78) versus 13.9% (11/79) on control; risk difference 20.7 percentage points (95% CI 7.7 to 33.7), risk ratio 2.49 (1.33–4.66); unadjusted two-proportion z-test p = 0.002.
  • Efpeglenatide 4 mg: 42.9% (33/77) versus 13.9% (11/79) on control; risk difference 28.9 percentage points (95% CI 15.5 to 42.4), risk ratio 3.08 (1.68–5.64); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Efpeglenatide 2 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 proportion with the event is statistically higher for Efpeglenatide 4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Week 30 in Fasting Plasma Glucose (FPG)

• 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 deviations.
• Result:
  • Efpeglenatide 2 mg: mean -0.97 versus 0.12 on control; difference -1.09 (95% CI -2.08 to -0.10), standardized effect d = -0.45; z-test p = 0.031.
  • Efpeglenatide 4 mg: mean -1.75 versus 0.12 on control; difference -1.87 (95% CI -2.85 to -0.89), standardized effect d = -0.78; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Efpeglenatide 2 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 Efpeglenatide 4 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Week 30 in Body Weight

• 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 deviations.
• Result:
  • Efpeglenatide 2 mg: mean -2.49 versus -1.89 on control; difference -0.60 (95% CI -2.55 to 1.35), standardized effect d = -0.12; z-test p = 0.546.
  • Efpeglenatide 4 mg: mean -2.72 versus -1.89 on control; difference -0.83 (95% CI -3.27 to 1.61), standardized effect d = -0.14; z-test p = 0.505.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Efpeglenatide 2 mg 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 Efpeglenatide 4 mg and the control. The interval gives the range of effects that remain compatible with the data.

Across the posted secondary outcomes, the broad pattern is that the HbA1c threshold counts and fasting plasma glucose summaries tend to point in a direction consistent with the primary endpoint’s group-mean pattern. Body-weight changes are also reported, but their variability and the unadjusted comparison intervals make that outcome less conclusive in the posted summaries. These outcomes assess related but distinct aspects of glycemic control and body weight; they are not substitutes for the primary HbA1c change endpoint.

The registry lists additional hypoglycemia outcomes, including participants with at least one event and events per participant-year. However, results for those outcomes are not reported in the registry record. That absence means the listed outcomes cannot contribute a result-based comparison in this interpretation. Similarly, some posted secondary outcomes have arm-level summaries without a full set of comparisons, and the record lists no reported analyses for the secondary endpoints.

General statistical explanation: Secondary outcomes are often useful for context, but each additional outcome or group comparison creates another opportunity to observe a result that appears notable by chance. If many hypotheses are tested without an appropriate multiplicity strategy, unadjusted p-values can overstate the strength of the overall evidence. The registry record does not report whether secondary outcomes were formally tested, how their testing was ordered, or whether any adjustment was planned. Therefore, the unadjusted secondary comparisons carry less weight than a fully specified and reported primary analysis.

The secondary results can help describe whether the general direction of findings extends to related measures, but they do not establish that the primary result is robust under different endpoints or analyses. The registry’s incomplete reporting of secondary analyses, and the absence of posted hypoglycemia results, limit how much can be concluded from the broader outcome set. These results should be treated as supportive description rather than independent confirmation.

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

• Number of Participants With HbA1c <7.0%
• Change From Baseline to Week 30 in Fasting Plasma Glucose (FPG)
• Change From Baseline to Week 30 in Body Weight
• Number of Participants With At Least One Hypoglycemic Events (Documented Symptomatic Hypoglycemia <3.0 mmol/L [<54 mg/dL], Severe Hypoglycemia)
• Number of Hypoglycemic Events (Documented Symptomatic Hypoglycemia <3.0 mmol/L [<54 mg/dL] and Severe Hypoglycemia) Per Participant-Year

9. Statistical Interpretation

10. Statistical Methods Explained

General statistical explanation: The primary measure is continuous, so the registry reports a mean and standard deviation for each randomized group. The mean describes the group’s average change. The standard deviation describes the spread of participant-level changes around that mean. A mean difference compares the average change in one efpeglenatide group with the average change in placebo; it is not the same as a change within either group alone.

The posted primary summaries report mean changes of -0.27 for placebo, -1.05 for efpeglenatide 2 mg, -1.46 for 4 mg, and -1.36 for 6 mg. The corresponding standard deviations are 0.92, 0.88, 0.9, and 1.09. The unadjusted mean differences compare each efpeglenatide group with placebo. For example, the reported difference of -0.78 for 2 mg is on the HbA1c change scale. A negative difference means the efpeglenatide group’s mean change is more negative than the placebo group’s mean change.

General statistical explanation: A standard error describes the sampling uncertainty of an estimate. The registry calculations list standard errors for the group means and use the observed variability and endpoint-specific group sizes in the comparisons. A confidence interval combines an estimate with its standard error to give a range of values compatible with the calculation’s assumptions. The interval is not a range containing every participant’s result, and it is not a guarantee about the true effect. Its interpretation also depends on the statistical method used.

The primary comparisons are labeled unadjusted. Their p-values are reported as <0.001 for each efpeglenatide dose versus placebo. A p-value is a measure of how compatible the observed data are with a specified null model, assuming that model and the calculation are appropriate. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of a difference. Because the registry record does not report a planned statistical analysis or multiplicity procedure, these p-values should not be treated as adjusted evidence from the complete trial analysis.

The record identifies the primary analysis population as intent-to-treat. It describes this as including all randomized participants irrespective of rescue therapy use and compliance, analyzed in the group allocated by randomization. However, the endpoint description also says that all available Week 30 assessment values were included. The registry record does not explain how missing Week 30 values were handled or whether any imputation or sensitivity analyses were used. The primary endpoint counts therefore identify the participants contributing to the posted summaries, but do not fully describe missing outcomes or the original analysis population flow.

General statistical explanation: Binary outcomes, such as whether a participant reached a threshold, are summarized as counts and denominators. A risk difference compares the proportions between groups on the probability scale. In the posted HbA1c threshold results, the unadjusted differences are 0.207 for 2 mg versus placebo and 0.289 for 4 mg versus placebo. The 6 mg arm has a posted count but no comparison in the registry summaries. These recalculated comparisons are unadjusted; the registry does not provide a reported analysis for this outcome.

For continuous secondary outcomes, the posted comparisons are mean differences. The fasting plasma glucose summaries include placebo and all three dose groups, while the posted comparisons cover 2 mg and 4 mg versus placebo. The body-weight summaries also include all groups, but the posted comparisons cover 2 mg and 4 mg versus placebo. Missing comparisons should not be interpreted as evidence that a comparison was null or not conducted; the registry record does not report analyses for these endpoints.

General statistical explanation: Over-dispersion refers to variability in data that is greater than a statistical model expects. It can make standard errors too small if ignored, which can make uncertainty appear narrower than it is. The registry’s continuous summaries include standard deviations, but it does not report a model-based analysis that allows assessment of over-dispersion. This concept is relevant to model choice in general; it is not a claim that over-dispersion occurred in this trial.

The reported sample-size illustrations use the observed effects and assume a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They are planning illustrations rather than a reconstruction of the trial’s design. The trial’s original sample-size assumptions are not reported in the registry record. The posted comparisons are simple unadjusted re-calculations from summary statistics, rather than registry-reported inferential analyses. Since the discrepancy indicator is false, there is no stated conflict between these calculations and a sponsor analysis in the record; however, the registry lists no reported analyses to serve as a sponsor analysis for these comparisons.

General statistical explanation: Randomization helps make treatment groups comparable on average at the start of a study, but it does not remove uncertainty or reporting limitations. Masking can reduce some sources of bias in treatment delivery and outcome assessment, though the record does not describe how masking was maintained or evaluated. Statistical interpretation still depends on the endpoint definition, the analysis population, missing-data handling, and the planned approach to multiple comparisons. Several of those details are not reported in the registry record.

11. Confidence Intervals and Precision

The primary endpoint estimates are accompanied by confidence intervals for the unadjusted differences from placebo. For efpeglenatide 2 mg, the mean difference is -0.78, with a 95% confidence interval from -1.14 to -0.420. For 4 mg, the difference is -1.19, with an interval from -1.552 to -0.828. For 6 mg, the difference is -1.09, with an interval from -1.494 to -0.687. Each interval lies below zero, indicating that the estimated differences in these summary-statistic calculations are more negative than zero.

General statistical explanation: A confidence interval reflects the precision of an estimate under the method’s assumptions. A narrower interval indicates less sampling uncertainty than a wider interval on the same scale. The interval should not be interpreted as containing all plausible results under every analysis, nor as a range of individual participant responses. Here, the intervals are unadjusted and are based on the posted arm-level summaries. The registry record does not report whether the trial’s own analysis used the same method or any covariate adjustment.

The intervals’ endpoints are not interchangeable with the p-values or with a clinical judgment about importance. The p-values are also unadjusted, and the original approach to multiple comparisons is not reported in the registry record. Thus, the intervals describe precision for the stated pairwise calculations, not an overall family of comparisons adjusted for the three efpeglenatide doses. The estimate and interval should be considered together: the estimate gives the direction and magnitude on the HbA1c change scale, while the interval conveys uncertainty around that estimate.

The secondary continuous outcomes have confidence intervals for the recalculated comparisons, but their uncertainty differs across outcomes and groups. For body-weight change, the reported intervals for the 2 mg and 4 mg comparisons include zero; for fasting plasma glucose, the listed comparison intervals are below zero. These summaries are unadjusted and should be read alongside the differing standard deviations and endpoint-specific participant counts. No confidence interval can resolve missing information about the original analysis plan or missing outcomes.

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 show participants per arm for the continuous and binary outcomes in this study. They do not show total events: the total-events convention applies to time-to-event outcomes, and no time-to-event outcome is posted among these results. The values are planning illustrations computed from the observed effect, not the trial’s original design assumptions. The registry record does not report the trial’s original sample-size justification.

The planning calculations assume a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers an effect set at the stated fraction of the observed effect. For each assumed effect, the 80% power column gives the estimated participants needed per arm for the calculation to have an 80% chance of detecting that effect under the assumptions. The 90% power column gives the corresponding participants per arm for a 90% chance. These are not counts of participants enrolled or analyzed in the trial; they are planning quantities.

The curve should be interpreted as a display of how the calculated sample size changes as the effect being targeted changes. Smaller effects require more participants to detect, all else held constant. The illustrations use the observed effects as their starting point, so they are sensitive to the estimates from this study and should not be treated as a general sample-size recommendation. The trial’s actual design may have been based on assumptions that differ from these illustrations. These values are planning illustrations, not observed power.

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 = -0.780; pooled standard deviation σ = 0.900.
2. n = 2 × (1.96 + 0.842)² × 0.900² / -0.780² = 20.9, rounded up to 21 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 <- -0.78                      # observed difference in means
sigma <- 0.900222194794152                     # 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(3770728)
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 = 21 (80% power), 28 (90% power)
 75% of observed effect: n per arm = 38 (80% power), 50 (90% power)
 50% of observed effect: n per arm = 84 (80% power), 112 (90% power)
power.t.test: 21.9 
Simulated power at n = 21 per arm: 0.780 (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 primary question compares three efpeglenatide dose groups with placebo. The registry record provides unadjusted p-values for these comparisons but does not report whether the original statistical plan adjusted for multiple comparisons, used a hierarchical testing sequence, or applied another method to control the overall chance of false-positive findings. The posted unadjusted p-values therefore address the individual comparisons as calculated, not necessarily the set of dose comparisons as a whole.

The same concern applies to the several secondary outcomes. The registry lists outcomes related to HbA1c threshold attainment, fasting plasma glucose, body weight, and hypoglycemia. It does not report a secondary-outcome testing strategy or multiplicity procedure. Unadjusted results across multiple outcomes are exploratory in interpretation unless the planned testing framework is known. The registry record lists no reported analyses, so there is no posted trial analysis to clarify how the results were tested or interpreted by the investigators.

Missing-data handling is also not reported in the registry record. The primary analysis description says all available Week 30 assessment values were included, while also defining the intent-to-treat population as all randomized participants analyzed according to assigned group, irrespective of rescue therapy use and compliance. The record does not explain how participants without Week 30 values were treated, whether values were imputed, or whether sensitivity analyses assessed the impact of missingness. The posted participant counts differ by endpoint and group; those counts alone do not identify why data are absent.

The registry does not report the original statistical model, covariate adjustments, or any interim-analysis plan. It also does not state the reason the study was terminated. These omissions prevent an assessment of whether the posted summaries match the prespecified analysis and whether study termination affected the data available for analysis. They are gaps in the registry record, not evidence that a particular procedure was or was not used.

15. 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: transient ischaemic attack (2.6%), cerebral ischaemia (1.3%), acute myocardial infarction (1.3%), pneumonia (1.3%), intraductal proliferative breast lesion (1.3%).

The safety summaries list the number of participants at risk and the number affected by serious adverse events and other adverse events in each group. For serious adverse events, the counts are 3 of 79 for placebo, 4 of 78 for efpeglenatide 2 mg, 5 of 80 for 4 mg, and 2 of 75 for 6 mg. For other adverse events, the counts are 21 of 79, 30 of 78, 36 of 80, and 32 of 75, respectively. The record reports zero deaths in each group.

These are counts of participants affected, not event rates per unit of follow-up and not measures of treatment effect. The registry also lists serious-event terms, including transient ischaemic attack at 2.6%, and several terms at 1.3%. The serious-event counts and term percentages do not establish a causal relationship with study treatment. The registry record does not provide a comparative safety analysis or further detail about event timing, exposure, or adjudication.

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

The posted results support a narrow statistical description: at Week 30, the mean HbA1c change in each efpeglenatide group was more negative than the mean change in the placebo group, and the unadjusted confidence intervals for those differences lie below zero. The reported group means, variability, and endpoint-specific counts describe the observed data. They do not, on their own, answer every question about the trial’s prespecified analysis or the reliability of all outcomes.

These results do not establish a treatment recommendation, and they should not be translated into an individual prediction. A group mean does not describe every participant’s response. The comparisons are each against placebo; they do not show that one efpeglenatide dose is superior to another or establish a dose-response relationship. The 4 mg group has the most negative posted primary mean, but the record does not report a direct dose-to-dose analysis.

The results also do not establish how durable any observed changes might be beyond the Week 30 endpoint. The registry record reports a 30-week study and does not provide longer-term outcome results in the registry record for this analysis. The reason for termination and its implications are not reported in the registry record. Safety counts offer a descriptive accounting of participants affected by events, but cannot establish causation or settle comparative safety without a reported analysis and fuller context.

Interpretation is limited by the absence of a reported original statistical plan, missing-data method, and multiplicity approach. The endpoint description identifies an intent-to-treat population and available Week 30 assessments, but the registry does not explain how unavailable outcomes were handled. Secondary outcomes are incomplete, and the listed hypoglycemia outcomes have no reported results. Accordingly, the posted primary summaries are informative about the observed group pattern, while the full inferential and clinical meaning remains constrained by what the registry record does not report.

17. Why This Trial Matters Statistically

Statistically, the study illustrates why the distinction between posted summaries and a complete trial analysis matters. The primary endpoint summaries show differences in mean change between placebo and each efpeglenatide group, with unadjusted confidence intervals that do not cross zero. Those calculations provide a transparent account of the direction and precision of the posted results, but they cannot replace a prespecified analysis that explains the model, handling of missing values, and multiplicity control.

The endpoint-specific counts and standard deviations also show why a single headline result is not enough. The amount of information contributing to each outcome varies, and the uncertainty differs by measure. Related secondary outcomes can add context, but incomplete analyses and unreported hypoglycemia results limit their value as corroboration. Safety counts are another distinct evidence stream and should not be conflated with efficacy comparisons.

The study is recorded as terminated, yet the reason and its implications are not reported in the registry record. That status makes clear why transparent reporting of participant flow, analysis populations, and study conduct is important for evaluating precision and potential bias. The registry record also does not report the original sample-size justification, so retrospective planning illustrations should not be mistaken for the assumptions that governed the study’s design.

The central statistical lesson is to distinguish observed group summaries, unadjusted recalculations, and the trial’s own planned inferential conclusions. They can inform one another, but are not interchangeable. Clear reporting of the analysis plan and the disposition of missing outcomes is necessary to judge how strongly the observed pattern supports the intended comparison.

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 are specific to the available record. The study status is terminated, but the reason for termination and its effect on recruitment, follow-up, or analysis are not reported in the registry record. The study is described as lasting 30 weeks, so these outcome summaries do not provide information about results beyond that timeframe.

The primary endpoint summaries include 48 participants in placebo, 48 in efpeglenatide 2 mg, 49 in 4 mg, and 48 in 6 mg. The registry describes an intent-to-treat population but also says the primary analysis included available Week 30 assessment values. It does not explain missing outcomes, participant flow, or sensitivity analyses. Counts for secondary outcomes differ, and the record does not explain the reasons for those differences.

The registry lists no reported analyses. The original model, covariate adjustments, multiplicity procedure, interim analyses, and sample-size justification are not reported in the registry record. As a result, the unadjusted comparisons cannot be verified against a reported prespecified analysis. Secondary results are incomplete: several outcomes are listed, but the hypoglycemia outcomes do not have posted results, and not all arm-level secondary summaries have corresponding comparisons.

The arm description for efpeglenatide 4 mg is truncated, and the 6 mg description ends before the full maintenance details are stated. The record does not provide additional eligibility characteristics or detail about the background-therapy distribution. These limitations restrict the level of detail possible when describing treatment delivery and the population represented by the summaries.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Efficacy and Safety of Efpeglenatide Versus Placebo in Patients With Type 2 Diabetes Mellitus Inadequately Controlled With Metformin Alone or in Combination With Sulfonylurea — NCT03770728.
• Registry record last updated 2021-12-02; status last verified 2021-11.
• Results first posted 2021-12-02.
• 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

NCT03770728 is a Phase 3 randomized, parallel-group, quadruple-masked, placebo-controlled study of once-weekly efpeglenatide in participants with type 2 diabetes inadequately controlled on metformin alone or with a sulfonylurea. The study compared placebo with efpeglenatide 2 mg, 4 mg, and 6 mg, with background therapy continued. Enrollment is recorded as 312, and the study status is terminated.

The primary endpoint was change in HbA1c from baseline to Week 30. Posted arm-level means show more negative changes in each efpeglenatide group than in placebo. The accompanying unadjusted comparisons have confidence intervals below zero. The registry record lists no reported analyses, and does not report the original statistical plan, missing-data method, multiplicity procedure, sample-size justification, or reason for termination. Secondary summaries and safety counts offer additional description but do not resolve these limitations.