A Study of Tirzepatide (LY3298176) in Chinese Participants Without Type 2 Diabetes Who Have Obesity or Overweight (SURMOUNT-CN): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of Tirzepatide (LY3298176) in Chinese Participants Without Type 2 Diabetes Who Have Obesity or Overweight (SURMOUNT-CN) (NCT05024032), a randomized phase 3 study. The primary outcome is Mean Percent Change From Baseline in Body Weight.

2. Clinical Question

The trial’s primary endpoint is a continuous measure: percentage change in body weight from baseline. The analysis compares adjusted group means rather than asking only how many participants crossed a particular weight-loss threshold. The registry record describes the primary measure at baseline and Week 52 and specifies that the least-squares mean was estimated using a mixed model with repeated measures.

The result addresses the average difference between assigned groups under the trial’s conditions. It does not, by itself, describe every participant’s individual response or establish what would happen in people outside the stated population. The registry record lists obesity, overweight, and metabolism and nutrition disorder among the conditions. The official title specifies overweight with weight-related comorbidities. Other eligibility details are not reported in the registry record.

3. Trial Design

SURMOUNT-CN was a Phase 3, randomized, double-blind, parallel-group, placebo-controlled trial sponsored by Eli Lilly and Company. The registry record lists enrollment of 210 and status as completed. It records a start date of 2021-09-01 and a primary completion date of 2022-12-27.

Participants were assigned to tirzepatide or matching placebo. The active treatment groups had maintenance doses of 10 mg and 15 mg. For the 10 mg group, escalation began at 2.5 mg, followed by 5 mg and 7.5 mg before reaching 10 mg. For the 15 mg group, escalation proceeded from 2.5 mg through 5 mg, 7.5 mg, 10 mg and 12.5 mg before reaching 15 mg. Treatment was administered subcutaneously once weekly; placebo was also administered subcutaneously once weekly.

The registry record describes double masking but does not specify which individuals or roles were masked. The primary endpoint population was defined as participants who received at least one dose of study drug and had evaluable body weight data. The arm counts used for the primary endpoint are 70 for 10 mg tirzepatide, 68 for 15 mg tirzepatide, and 68 for placebo. These endpoint counts need not match the trial’s listed enrollment because the endpoint population has its own evaluability criteria.

The original protocol’s sample-size justification, allocation procedure details, exact visit schedule beyond the endpoint timeframes, and trial-specific assumptions for the design are not reported in the registry record. The posted planning illustrations based on observed effects are separate from the trial’s original design calculations.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

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

5. Baseline Characteristics

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

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

6. Primary Endpoint

The registry lists the primary outcome as Mean Percent Change From Baseline in Body Weight, measured over Baseline, Week 52.

The primary endpoint is mean percent change from baseline in body weight at Week 52. It expresses each participant’s change relative to their own baseline weight, then estimates a group mean. A negative mean indicates a decrease from baseline. The registry record reports least-squares means, which are model-based estimates adjusted for the variables specified in the analysis rather than simple averages alone.

Using a continuous outcome retains information about the size of changes across the group. It differs from a threshold endpoint, which classifies participants according to whether they reach a specified percentage reduction. The primary measure therefore addresses the average magnitude of change, while secondary threshold outcomes describe the proportion meeting particular cutoffs.

Weight is the outcome directly named in the trial’s stated main purpose. Measuring change from baseline also accounts for each participant’s starting value in defining the outcome. The primary analysis used baseline, sex, presence of comorbidities, treatment, time, and treatment-by-time terms in a mixed model with repeated measures. The registry record identifies baseline and Week 52 as the primary timeframe. It does not report the full protocol rationale for choosing this endpoint or the specific handling of all missing endpoint observations.

7. Results Posted in the Registry

• 10 mg Tirzepatide: mean -14.40 versus -2.40 on control; difference -12.00 (95% CI -14.74 to -9.26), standardized effect d = -1.46; z-test p = <0.001.
• 15 mg Tirzepatide: mean -19.90 versus -2.40 on control; difference -17.50 (95% CI -20.29 to -14.71), standardized effect d = -2.11; 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.

Mean Change From Baseline 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 errors.
• Result:
  • 10 mg Tirzepatide: mean -9.00 versus -1.80 on control; difference -7.20 (95% CI -8.85 to -5.55), standardized effect d = -1.46; z-test p = <0.001.
  • 15 mg Tirzepatide: mean -11.10 versus -1.80 on control; difference -9.30 (95% CI -10.98 to -7.62), standardized effect d = -1.86; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for 10 mg Tirzepatide 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 15 mg Tirzepatide than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Who Achieve ≥10% Body Weight Reduction

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • 10 mg Tirzepatide: 70.0% (49/70) versus 14.7% (10/68) on control; risk difference 55.3 percentage points (95% CI 41.7 to 68.9), risk ratio 4.76 (2.63–8.61); unadjusted two-proportion z-test p = <0.001.
  • 15 mg Tirzepatide: 83.8% (57/68) versus 14.7% (10/68) on control; risk difference 69.1 percentage points (95% CI 57.0 to 81.3), risk ratio 5.70 (3.19–10.20); 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 10 mg Tirzepatide 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 15 mg Tirzepatide than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Who Achieve ≥15% Body Weight Reduction

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • 10 mg Tirzepatide: 48.6% (34/70) versus 2.9% (2/68) on control; risk difference 45.6 percentage points (95% CI 33.3 to 58.0), risk ratio 16.51 (4.13–66.07); unadjusted two-proportion z-test p = <0.001.
  • 15 mg Tirzepatide: 72.1% (49/68) versus 2.9% (2/68) on control; risk difference 69.1 percentage points (95% CI 57.7 to 80.5), risk ratio 24.50 (6.20–96.74); 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 10 mg Tirzepatide 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 15 mg Tirzepatide than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary outcomes cover several related dimensions: body-weight change at Week 20, thresholds for body-weight reduction at Week 52, waist circumference, absolute body weight, body mass index, hemoglobin A1c, and fasting glucose. Across the available weight-related results, the general pattern complements the primary endpoint: the secondary measures address earlier change, categorical thresholds, or other ways of characterizing weight change, rather than replacing the primary Week 52 mean percent change.

The registry record lists 21 outcome measures and 33 analyses, with 19 secondary outcomes posted. That breadth gives readers more context about the outcomes assessed, but it also creates multiple opportunities to observe nominally notable results. The record does not report a multiplicity adjustment or a prespecified hierarchy for interpreting the secondary tests. Unadjusted secondary p-values therefore carry less confirmatory weight than a primary test protected by a clearly specified testing strategy; the record does not establish that such protection was applied.

Secondary outcomes can be supportive when they align with the primary result, but related measures are not independent replications. They may share participants, data collection, and underlying outcome characteristics. Their interpretation also depends on their own analysis populations and methods. The registry record does not provide all details needed to assess those features across every secondary analysis. The overall pattern is best treated as contextual evidence alongside the primary endpoint, rather than as a collection of separate definitive conclusions.

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

• Mean Change From Baseline in Body Weight
• Percentage of Participants Who Achieve ≥10% Body Weight Reduction
• Percentage of Participants Who Achieve ≥15% Body Weight Reduction
• Mean Change From Baseline in Waist Circumference
• Mean Change From Baseline in Absolute Body Weight
• Mean Change From Baseline in Body Mass Index (BMI)
• Mean Change From Baseline in Hemoglobin A1c (HbA1c)
• Mean Change From Baseline in Fasting Glucose (FSG)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, and the registry record reports least-squares means and standard errors. A least-squares mean is a model-based group estimate, adjusted according to the included model terms. The posted primary model included baseline, sex, presence of comorbidities, treatment, time, and treatment-by-time, with Type III sums of squares. A treatment-by-time term allows the treatment contrast to vary over the modeled time points. The record identifies a mixed model with repeated measures but does not report further implementation details such as covariance structure or degrees-of-freedom method.

What does a model-based mean difference represent?

The mean difference compares the estimated outcome in one treatment group with the estimated outcome in placebo. For the primary endpoint, the reported differences are -12.0 for 10 mg and -17.5 for 15 mg, in percentage-change units. A negative value means the estimated change is lower in the tirzepatide group on this scale. Because the analysis uses least-squares means from a model, these contrasts are not simply the subtraction of unadjusted arm means, even when recalculated summary-statistic estimates happen to be close.

In general, adjustment can account for modeled baseline or other covariate differences and make the estimand correspond to the specified model. It does not guarantee elimination of bias from missing data, unmeasured factors, or departures from model assumptions. The registry record states which terms were included but does not provide all diagnostics or assumptions needed to evaluate model fit.

Why use repeated-measures modeling?

In general, repeated-measures models use outcome observations collected over time and account for the fact that measurements from the same participant are related. They can estimate group patterns across visits while using available repeated observations under the model’s assumptions. Such models do not automatically solve every missing-data problem. Conclusions can depend on why observations are missing and on how well the model represents the data. The registry record does not report the full missing-data strategy, sensitivity analyses, or assumptions about missing observations.

How should standard errors and intervals be read?

A standard error describes the estimated sampling uncertainty of a statistic, rather than the variability among individual participants. The arm-level primary estimates have reported standard errors of 0.98 for 10 mg, 1.01 for 15 mg, and 1.0 for placebo. In general, a confidence interval gives a range of values compatible with the data and analysis at a stated confidence level. The sponsor’s reported 95% intervals are for the adjusted mean differences. Intervals from the recalculation use a simpler unadjusted approach and should not be treated as the model’s own intervals.

The recalculated continuous-outcome intervals use an estimated pooled standard deviation derived approximately from the posted standard errors and group counts. This is why the recalculation is described as approximate. It is useful as a statistical cross-check, but it does not reproduce the trial’s mixed model, its repeated observations, or its adjustment terms. General statistical interpretation should therefore distinguish a transparent summary-statistic calculation from the sponsor’s stated analysis.

What does a p-value establish?

In general, a p-value measures how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the test assumptions held. The reported primary comparisons each have p <0.001. That result is evidence against a zero difference under the analysis, but it is not the probability that the treatment has no effect and does not express effect size. A small p-value also does not establish that the model assumptions are correct or that all relevant comparisons have been accounted for.

The registry record identifies the primary analysis method and reports the model-based contrasts, confidence intervals, and p-values. It does not report whether the tests were adjusted for multiplicity, details of prespecified testing order, interim analyses, or a full statistical analysis plan. Those omissions limit assessment of how the inferential results were organized across the outcome family. The trial’s original sample-size justification and design assumptions are also not reported in the registry record. The posted sample-size illustrations use observed effects and are not evidence about the trial’s planned power.

11. Confidence Intervals and Precision

The sponsor’s primary estimates are accompanied by 95% confidence intervals. For 10 mg tirzepatide versus placebo, the reported mean difference is -12.0, with an interval from -14.8 to -9.3. For 15 mg versus placebo, it is -17.5, with an interval from -20.3 to -14.8. In general, a confidence interval reflects statistical uncertainty in an estimate under the analysis assumptions; it is not a range containing a known proportion of individual participant outcomes.

Both reported intervals lie below zero, consistent with the direction of the estimated contrasts and the reported p-values of <0.001. The interval for each dose communicates a range of values compatible with that comparison, not certainty that the true difference equals the point estimate. The interval also does not capture every source of uncertainty, such as possible bias from missing data or choices not represented in the model.

The re-calculated intervals are -14.74 to -9.256 for 10 mg and -20.29 to -14.71 for 15 mg. They are derived from summary statistics and are approximate, while the sponsor’s intervals come from the mixed-model analysis. Their general alignment offers a check on the scale and direction of the posted contrast, but the sponsor’s model-based results take precedence for interpreting the trial analysis.

Precision should be considered alongside the number of endpoint observations, model specification, and analysis population. The registry record reports endpoint group counts and standard errors, but does not report a full account of missingness or sensitivity analyses. Confidence intervals quantify sampling uncertainty as represented by the analysis; they do not resolve these other limitations.

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 translate an observed effect into hypothetical group sizes under stated assumptions. For the continuous comparisons discussed in the primary analysis, the figures are participants per arm, not total participants. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each illustration uses a stated fraction of the observed effect. These are planning calculations based on the observed result, not the trial’s original design assumptions, which are not reported in the registry record.

The 80% power column gives the estimated participants per arm for a hypothetical study to have an 80% chance of detecting the specified effect under the calculation assumptions, if that effect and the assumptions were correct. The 90% power column gives the corresponding planning figure for a 90% chance. In general, greater target power requires more participants for the same effect. The curve uses the same planning logic: it illustrates how the estimated group size changes with the effect being targeted.

Rows planning for 75% or 50% of the observed effect ask what group sizes would be needed if the target difference were smaller than the observed difference. Smaller effects are harder to distinguish from random variation, so they require more participants under otherwise unchanged assumptions. The numbers are not observed power, and they do not show the power the completed trial actually had. They also do not account for every design feature that might be relevant to a real study, including missing outcomes, multiplicity, or changes to the analysis model.

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 = -12.000; pooled standard deviation σ = 8.222.
2. n = 2 × (1.96 + 0.842)² × 8.222² / -12.000² = 7.4, rounded up to 8 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 <- -12                      # observed difference in means
sigma <- 8.22242807991726                     # 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(5024032)
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 = 8 (80% power), 10 (90% power)
 75% of observed effect: n per arm = 14 (80% power), 18 (90% power)
 50% of observed effect: n per arm = 30 (80% power), 40 (90% power)
power.t.test: 8.4 
Simulated power at n = 8 per arm: 0.776 (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’s reported primary comparisons use mixed-model analysis and give least-squares mean differences with 95% confidence intervals and p-values. The reported difference is -12.0 for 10 mg versus placebo and -17.5 for 15 mg versus placebo; both have p <0.001. Those are the trial’s own reported inferential analyses and are the appropriate starting point for describing the results.

The recalculated comparisons use posted arm-level summary statistics to make simple, unadjusted estimates. They yield -12.0 for 10 mg and -17.5 for 15 mg, with approximate confidence intervals from -14.74 to -9.256 and from -20.29 to -14.71, respectively. These calculations are checks, not replacements for the repeated-measures model. They do not reproduce the model’s covariate adjustment or use its full data structure.

The registry record does not flag a discrepancy between the posted sponsor analysis and the recalculated summary-statistic results. Even so, the two approaches answer the comparison through different methods. Numerical similarity supports a basic consistency check but does not establish that the simpler calculation has the same statistical properties as the sponsor’s analysis. When interpreting the trial, the sponsor’s adjusted analysis takes precedence.

15. Multiplicity, Missing Data and Analysis Populations

The registry record reports multiple outcomes and analyses, including 21 outcome measures and 33 analyses. It does not report whether the primary or secondary p-values were adjusted for multiplicity, whether comparisons followed a prespecified testing hierarchy, or whether any interim analyses were conducted. Without that information, nominal p-values should be interpreted as results for the individual reported tests, not as evidence that the overall chance of a false-positive conclusion across all outcomes has been controlled.

The primary analysis population is described as participants who received at least one dose of study drug and had evaluable body weight data. This identifies the population used for that endpoint, but the record does not describe all reasons that data may have been unavailable, how missing measurements were handled, or whether sensitivity analyses tested alternative assumptions. A mixed model with repeated measures is named, but its presence alone does not specify how missing values were treated or guarantee robustness to every missing-data mechanism.

The record also does not describe an intention-to-treat analysis population, protocol-deviation handling, or the treatment of intercurrent events. Those details are important for understanding precisely which treatment effect the estimates target. The original sample-size rationale, design power assumptions, interim-monitoring plan, and full statistical analysis plan are not reported in the registry record. As a result, the posted data support interpretation of the reported endpoint estimates, but do not allow a complete audit of prespecification, multiplicity control, or missing-data sensitivity.

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: abortion induced (3.0%), uterine polyp (2.9%), epididymitis (2.8%), large intestine polyp (1.4%), covid-19 (1.4%).

The registry record reports serious adverse events among 3 participants at risk in the 10 mg group, 8 in the 15 mg group, and 6 in the placebo group. The corresponding numbers at risk were 70, 71, and 69. It reports 0 deaths in each group. These are participant counts, not event rates calculated for a common follow-up duration.

Other adverse events affected 61 participants at risk in the 10 mg group, 56 in the 15 mg group, and 39 in the placebo group. The serious and other adverse-event summaries describe different categories and should not be combined. The registry also lists serious-event terms, including abortion induced and uterine polyp, but the listed terms alone do not establish causation or provide the full clinical context for each event.

These figures describe events recorded in the trial groups; they do not establish that an event was caused by study treatment. The record does not provide enough detail to assess event timing, duration, severity beyond the serious classification, relatedness judgments, or participant-level overlap. Differences in counts should therefore be read descriptively, with attention to the numbers at risk and the limited context available.

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

The primary results show that the estimated mean percent change in body weight at Week 52 differed between each tirzepatide group and placebo in the posted mixed-model analysis. The contrasts were -12.0 for 10 mg and -17.5 for 15 mg, with both 95% confidence intervals below zero and p-values of <0.001. These findings describe estimated average differences for the endpoint population defined in the registry record.

They do not tell readers what any particular participant’s result would be. An average can coexist with a range of individual outcomes, and the registry record does not provide the full distribution needed to describe that variation. The results also do not, on their own, establish how durable changes are beyond the stated Week 52 endpoint or what the consequences are for outcomes not measured in the primary analysis.

The study population was Chinese participants without type 2 diabetes who had obesity or overweight with weight-related comorbidities. The record does not establish that the same estimates apply to populations with different characteristics or settings. The statistical results are also conditional on the study’s design, observed endpoint data, and analysis assumptions. Details about missing-data sensitivity, multiplicity handling, and the full analysis plan are not reported in the registry record.

Statistical evidence of a difference is not the same as a judgment about clinical importance, overall benefit and risk, or what an individual should do. Those questions require broader evidence and context than this endpoint comparison provides. The results should be read as a trial-based estimate of group differences, with the stated uncertainty and limits, rather than as a guarantee of an individual outcome.

18. Why This Trial Matters Statistically

This trial offers a clear example of how a randomized, double-blind, placebo-controlled design can frame a comparison of adjusted average outcomes. The primary endpoint is continuous, and the reported least-squares mean differences retain the magnitude and direction of group change rather than reducing the result to whether participants crossed a threshold.

The paired reporting of point estimates, confidence intervals, and p-values illustrates why statistical interpretation should not rely on a significance label alone. The point estimate describes the observed contrast on the endpoint scale, the interval conveys uncertainty under the analysis, and the p-value addresses compatibility with a null hypothesis under test assumptions. Each contributes different information.

The registry record also makes the distinction between a sponsor’s model-based analysis and a summary-statistic recalculation visible. A simple re-calculation can be a useful check, but it does not reproduce the specified repeated-measures model. This is an important general lesson for reading trial summaries: close numerical agreement does not make analyses interchangeable.

Finally, the study highlights the value of transparency about populations, missing data, multiplicity, and planning assumptions. The record identifies the primary analysis population and model terms, yet leaves important design and analysis details unreported. Recognizing both what the results quantify and what the registry does not document is central to sound statistical interpretation.

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.

The registry record provides the primary endpoint estimates and analysis method, but does not report the complete protocol or statistical analysis plan. Original sample-size justification and design assumptions are not reported, nor are interim analyses or a multiplicity strategy. These omissions limit assessment of how fully the reported tests correspond to a prespecified plan.

The primary analysis population required at least one dose and evaluable body weight data. The record does not explain the extent or reasons for missing measurements, describe all missing-data procedures, or report sensitivity analyses. The named mixed model with repeated measures is not enough to assess the consequences of missingness without further details about model implementation and assumptions.

The recalculated continuous estimates rely on approximate standard deviations inferred from posted standard errors and group counts. They are unadjusted and do not replicate the sponsor’s repeated-measures model. They provide a check on the reported scale and direction, not an independent confirmatory analysis.

There are also limits to the safety summaries: counts are reported, but the available details do not establish causality or provide event-level timing and context. The reported serious-event counts have different numbers at risk across groups. Finally, the population is specifically described as Chinese participants without type 2 diabetes with obesity or overweight and weight-related comorbidities. The registry record does not provide evidence to determine how directly the estimates generalize beyond that population.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study of Tirzepatide (LY3298176) in Chinese Participants Without Type 2 Diabetes Who Have Obesity or Overweight (SURMOUNT-CN) — NCT05024032.
• Registry record last updated 2024-01-19; status last verified 2023-12.
• Results first posted 2024-01-19.
• 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

NCT05024032, SURMOUNT-CN, is a completed Phase 3 randomized, double-blind, parallel-group, placebo-controlled study sponsored by Eli Lilly and Company. It enrolled 210 Chinese participants without type 2 diabetes who had obesity or overweight with weight-related comorbidities. Participants received once-weekly subcutaneous tirzepatide at a 10 mg or 15 mg maintenance dose, or matching placebo.

The primary endpoint was mean percent change from baseline in body weight at Week 52, analyzed with a mixed model with repeated measures. The reported least-squares mean differences versus placebo were -12.0 for 10 mg and -17.5 for 15 mg; both had p <0.001. Important details about the original sample-size rationale, multiplicity, and missing-data sensitivity are not reported in the registry record.