Real World Effectiveness of Combining an Employer-based Weight Management Program With Medication for Chronic Weight Management in Employees With Obesity: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Real World Effectiveness of Combining an Employer-based Weight Management Program With Medication for Chronic Weight Management in Employees With Obesity (NCT03799198), a randomized phase 4 study. The primary outcome is Change in Body Weight.

2. Clinical Question

This is a comparison of two treatment strategies, not a comparison of medication against no weight-management support. Both groups were assigned to the employer-based program; the medication component distinguishes the strategies. Random allocation gives the comparison a trial basis, while the pragmatic setting reflects delivery through an integrated medical weight-management program for employees.

The registry also identifies outcomes concerning weight-loss thresholds, attendance at shared medical appointments, prescription coverage, and work-related measures. Those outcomes can help describe different facets of the intervention, but the central question is the between-group comparison in change in body weight. The record does not report detailed eligibility criteria, participant characteristics, or the names of the medications used, so those details cannot be used to refine the population or intervention description.

3. Trial Design

This was a Phase 4, randomized, open-label, parallel-group trial. The registry records enrollment of 200 and describes equal chances of assignment to the two strategies. The two groups were the Cleveland Clinic Integrated Medical Weight Management Program plus medication for chronic weight management, and the same program without medication. Masking was none, so participants and study personnel were not masked according to the registry.

The study was pragmatic in its stated purpose: it compared the program with medication against the program without medication in an employer-based setting. The intervention description says the combined-strategy group would receive one of five approved drugs after discussion with the study doctor. The medication names and the criteria used to select among them are not reported in the registry record. The program-alone group received the weight-management program without medication for weight loss.

The registry lists the study as completed. Its recorded start was 2019-01-07, and primary completion was 2020-05-22. The brief summary describes an individual participant duration of approximately one year, while the primary endpoint is measured from month 0 to month 12.

Randomization and the parallel design support a direct comparison of assigned strategies. However, the open-label design can matter for outcomes influenced by awareness of assignment, including attendance or self-reported work measures. Body weight is a more directly measured outcome, but the registry record does not describe the weighing procedures, adherence assessment, crossover, or treatment discontinuation. The detailed randomization procedure and the trial's original design assumptions are not reported in the registry record.

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: Participants were randomized in a 1:1 manner to receive either Cleveland Clinic's Integrated Medical Weight Management Program (WMP) with medication for chronic weight management (WMP + Rx) or Cleveland Clinic's Integrated Medical WMP alone (WMP).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The FAS comprised of all randomized participants.

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: Full analysis set (FAS) comprised of all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Change in Body Weight, measured over Month 0, month 12.

The primary endpoint is percentage change in body weight from baseline, designated month 0, to month 12. It expresses the change relative to starting body weight, allowing weight change to be described on a common percentage scale rather than as an absolute amount. Negative values indicate a reduction from baseline; a more negative group estimate therefore represents a larger average percentage reduction.

The registry presents this outcome as a least-squares mean with standard error and identifies the primary analysis population as the Full Analysis Set, comprising all randomized participants. The posted group estimates are -7.69% for the program-plus-medication group and -4.19% for the program-alone group. The reported assessment period is month 0 to month 12.

A continuous endpoint uses the observed range of change rather than reducing each participant's outcome to a yes-or-no threshold. This can retain information about the magnitude of change, while the percentage scale accounts for differences in starting body weight. Weight change is directly relevant to the trial's stated comparison of chronic weight-management strategies. It does not, by itself, describe other health outcomes, work effects, medication use, or the durability of changes beyond the stated assessment period. The registry record does not report additional details about measurement procedures or how observations missing at month 12 were handled.

7. Results Posted in the Registry

• Weight Management Program (WMP): mean -4.19 versus -7.69 on control; difference 3.50 (95% CI 1.49 to 5.51), standardized effect d = 0.48; 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.

Participants Achieving 5% or More Reduction in Body Weight

• 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:
  • Weight Management Program (WMP): 45.0% (45/100) versus 62.0% (62/100) on control; risk difference -17.0 percentage points (95% CI -30.6 to -3.4), risk ratio 0.73 (0.56–0.95); unadjusted two-proportion z-test p = 0.016.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically lower for Weight Management Program (WMP) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Participants Achieving 10% or More Reduction in Body Weight

• 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:
  • Weight Management Program (WMP): 22.0% (22/100) versus 35.0% (35/100) on control; risk difference -13.0 percentage points (95% CI -25.4 to -0.6), risk ratio 0.63 (0.40–0.99); unadjusted two-proportion z-test p = 0.042.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically lower for Weight Management Program (WMP) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Number of Shared Medical Appointments (SMAs) Attended

• 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:
  • Weight Management Program (WMP): mean 7.40 versus 9.70 on control; difference -2.30 (95% CI -3.26 to -1.34), standardized effect d = -0.66; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Weight Management Program (WMP) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted numerical secondary outcomes cover weight-loss thresholds and attendance at shared medical appointments. Their overall pattern is broadly consistent with the primary result: the combined-strategy group had larger reported proportions reaching the weight-loss thresholds and a higher mean number of appointments attended. These outcomes provide related but distinct descriptions of the trial. They do not replace the primary continuous measure, and attendance is a process measure rather than a weight outcome.

The registry lists additional secondary outcome topics, including prescription coverage and work-related measures, but numerical results for those topics are not included in the outcome summaries. The record lists 15 secondary outcomes as posted, while the complete outcome list includes a broader range of measures. For outcomes without numerical results, the result is not reported in the registry record.

Secondary findings generally carry less weight than the designated primary result when many outcomes are examined. Each separate test creates another opportunity for an apparently notable result to arise by chance, particularly when several outcomes or thresholds are considered. A multiplicity adjustment or a prespecified hierarchy can help control how such results are interpreted, but a multiplicity plan is not reported in the registry record. The posted secondary comparisons do not have sponsor-reported analyses in the record, so their displayed unadjusted comparisons should be regarded as descriptive rather than as a set of confirmatory claims.

The secondary outcomes can help assess whether the observed primary pattern is accompanied by related changes in threshold attainment or program engagement. They cannot establish the mechanism for the primary result, distinguish medication effects from program effects, or show that increased attendance caused greater weight change. Because the measures differ in type and may be affected by different sources of bias, consistency across them is informative but not conclusive.

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

• Participants Achieving 5% or More Reduction in Body Weight
• Participants Achieving 10% or More Reduction in Body Weight
• Number of Shared Medical Appointments (SMAs) Attended
• Participants Attending 9 or More SMAs
• Proportion of Days Covered by Prescription Claims for Medication for Chronic Weight Management
• Participants Covered by Prescription Claims for Medication for Chronic Weight Management for at Least 80% of Days
• Change in 'At-Work Productivity Loss Index' as Measured by Work Limitations Questionnaire Self-administered Short-Form (WLQ-8)
• Change in 'Time Management' as Measured by WLQ-8

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: percentage change in body weight. The registry reports least-squares means, a standard error for each group estimate, and an ANCOVA treatment difference. These quantities describe different aspects of the result. A group estimate describes the modeled average change; its standard error represents uncertainty in that estimate. The treatment difference compares the two group estimates, and its confidence interval describes a range of values compatible with the analysis under its assumptions.

What does ANCOVA contribute?

In general, analysis of covariance (ANCOVA) compares outcomes between groups while adjusting for covariates included in the model. Adjustment can improve precision when the covariates are informative, and can account for baseline or other specified characteristics. The registry identifies ANCOVA as the sponsor's primary method but does not report the covariates, model details, or diagnostics. It is therefore not possible to assess from the registry record exactly what adjustment was performed or how model assumptions were checked.

The sponsor reports a treatment difference of -3.50, a 95% confidence interval from -5.51 to -1.50, and p < 0.001. The sign depends on the subtraction order used for the contrast. In the posted group means, the combined-strategy group has the more negative mean change. A simple recalculation using the posted group means gives a difference of 3.5 when the program-alone group is subtracted from the combined group in reverse order from the sponsor's stated treatment difference. Reversing a contrast changes the sign, not the underlying comparison. The sponsor's own analysis takes precedence over this unadjusted recalculation.

What does the standard error describe?

In general, a standard error describes the sampling uncertainty of an estimated quantity. It is not the spread of individual participant outcomes; a standard deviation describes that kind of spread. The primary group values are presented as least-squares means with standard errors, not as means with standard deviations. The registry does not post confidence limits for the two separate group estimates. The sponsor does post a confidence interval for the between-group treatment difference, which is the more direct quantity for assessing the comparative effect.

A confidence interval is interpreted in relation to the estimate and the method used to construct it. A narrower interval indicates greater precision under the analysis assumptions, while a wider interval indicates more uncertainty about the comparative magnitude. A confidence interval does not ensure that every value inside it is equally plausible, nor does it address design limitations such as unmeasured differences or missing outcome data.

Why distinguish adjusted and unadjusted comparisons?

The posted recalculation is an unadjusted comparison of summary values. It does not reproduce the ANCOVA model, because the registry record does not give the model inputs needed to do so. Recalculated results are useful for checking the direction and approximate scale of the reported contrast, but they should not be substituted for the sponsor's analysis. Here, the sponsor's and recalculated contrasts have opposite signs because they are expressed in opposite directions. The primary reported p-value is p < 0.001; the recalculated p-value is also p < 0.001.

For secondary continuous outcomes, the posted summaries can also be compared by group. For binary outcomes, the recorded percentages describe the share meeting a threshold, and a risk difference describes the contrast in those proportions. General statistical interpretation of either measure depends on the definition of the outcome, the population analyzed, and the handling of missing observations. The registry record does not report adjusted analyses for the secondary results listed in the posted summaries.

Why can over-dispersion matter?

In general, over-dispersion occurs when variability in data is greater than a statistical model expects. It can make standard errors too small if the analysis does not account for the extra variability. The primary outcome is continuous, and the registry identifies ANCOVA, but it does not report an over-dispersion assessment or model diagnostics. This general issue is not evidence that over-dispersion occurred in this trial. It is relevant as a reminder that model assumptions and their checks affect uncertainty estimates.

For appointment counts, general count-data methods may be considered when observations are nonnegative counts and variability is not well described by a normal model. The registry's posted secondary summary gives a mean and standard deviation for the number of shared medical appointments attended; the method used for any sponsor analysis of that outcome is not reported in the registry record. The same caution applies to binary secondary outcomes: a simple proportion comparison is not the same as an adjusted model, and the record does not identify a sponsor-reported analysis for those outcomes.

Finally, statistical significance and practical importance are distinct questions. A p-value describes how incompatible the observed data are with a specified null hypothesis under an analysis model; it does not state the probability that the null hypothesis is true or quantify the importance of a result. The estimated contrast and its confidence interval provide the scale and precision needed for interpretation, while the trial design and limitations determine how broadly the findings can be applied.

11. Confidence Intervals and Precision

The sponsor's primary analysis reports a treatment difference of -3.50 with a 95% confidence interval from -5.51 to -1.50. This interval lies on one side of zero and is consistent with the reported p < 0.001 for the comparison under the sponsor's analysis. The interval indicates that the estimated contrast is not a single exact value: there is uncertainty about its magnitude. Its negative sign reflects the sponsor's contrast convention; the combined-strategy group had a more negative mean percentage change than the program-alone group.

The unadjusted recalculation expresses the contrast in reverse, as 3.5, with a recalculated interval from 1.49 to 5.51. The reversed signs do not represent conflicting directions. They arise from reversing which group is subtracted from which. The sponsor's adjusted result is the primary reported analysis and takes precedence over this recalculation. The small difference between the endpoint digits of the two intervals is not a basis for treating the analyses as identical: one is the sponsor's ANCOVA result, while the other is recalculated from posted summaries.

Precision concerns the uncertainty around the estimated group contrast, not the certainty that the same result would occur in every setting or for every participant. The group-specific standard errors, 0.72 and 0.73, describe uncertainty in the posted least-squares mean estimates. The registry does not report confidence intervals for those separate means. Nor does the confidence interval address whether missing outcomes, treatment adherence, or the open-label design could affect interpretation; those are distinct considerations. The stated interval is conditional on the analysis and its assumptions, and the registry record does not provide enough model detail to evaluate all of them.

12. Planning a Similar Trial: Sample Size

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

The planning estimates illustrate how many participants per arm would be needed under specified hypothetical conditions to detect a stated fraction of an observed effect. For these outcomes, the figures are participants per arm, not total events. The 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. The trial's own original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the number of participants per arm associated with an 80% chance of detecting the chosen effect under those planning assumptions, if that effect is truly present. The 90% power column gives the corresponding number for a higher chance of detection. These are prospective planning quantities, not guarantees: actual power depends on the true effect, variability, analysis, and other assumptions. Smaller effects require more participants than larger effects, which is why planning for 75% or 50% of the observed effect produces larger sample-size estimates than planning for 100%.

For the primary outcome, the planning illustration uses the observed effect from the posted comparison as its reference. The same approach is used for the posted secondary comparisons. These calculations do not establish the study's original target enrollment, and they do not indicate the probability that the study's results are true. This is not observed power. The estimates are planning illustrations based on observed effects and the stated assumptions, rather than a retrospective measure of what the completed trial achieved.

When interpreting a planning curve, the central idea is how the required number changes as the target effect becomes smaller or the desired detection probability becomes higher. The figures depend on the assumptions and should not be treated as universal requirements for future studies. Any new design would need assumptions appropriate to its population, outcome variability, allocation, follow-up, and analysis plan.

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 = 3.500; pooled standard deviation σ = 7.250.
2. n = 2 × (1.96 + 0.842)² × 7.250² / 3.500² = 67.4, rounded up to 68 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 <- 3.5                      # observed difference in means
sigma <- 7.25017241174305                     # 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(3799198)
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 = 68 (80% power), 91 (90% power)
 75% of observed effect: n per arm = 120 (80% power), 161 (90% power)
 50% of observed effect: n per arm = 270 (80% power), 361 (90% power)
power.t.test: 68.3 
Simulated power at n = 68 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's primary analysis is an ANCOVA and reports a treatment difference of -3.50, a 95% confidence interval from -5.51 to -1.50, and p < 0.001. The registry labels the analysis as a superiority analysis. Its reported contrast uses the opposite sign from the simple recalculation based on the two posted group means: the sponsor's result is negative, while subtracting the combined group's mean change from the program-alone group's mean change gives a positive 3.5. Both express the same ordering of group estimates.

The recalculation is unadjusted and uses posted summaries; it cannot reproduce the sponsor's ANCOVA without the model details. The sponsor's own analysis takes precedence. Its confidence interval differs slightly at the final endpoint digit from the unadjusted recalculation, which is expected to be possible when an adjusted model and a summary-based calculation are not the same analysis. The record does not report which covariates were used or provide enough detail to fully reconcile the estimates.

Both analyses report p < 0.001. Agreement in direction and broad scale is a useful consistency check, but the recalculation should not be presented as an independent confirmation or a substitute primary analysis. Interpretation should center on the sponsor's reported adjusted treatment difference and its confidence interval, with the simple calculation serving only as a descriptive comparison of the posted group summaries.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several outcomes, time points, or contrasts are tested. The more tests conducted, the greater the chance that at least one result may appear statistically notable even when there is no corresponding effect. The registry identifies change in body weight as the primary outcome and lists multiple secondary outcomes, including threshold-based weight outcomes, attendance, prescription coverage, and work-related measures. A multiplicity adjustment, testing hierarchy, or other plan for interpreting the family of secondary analyses is not reported in the registry record.

Accordingly, the primary result has a clearer confirmatory status than the unadjusted secondary comparisons. The secondary findings can describe patterns and generate questions, but their p-values should not be read as if each were the only test performed. The record does not specify which secondary analyses were planned as confirmatory, whether all listed outcomes were analyzed, or whether any additional exploratory outcomes were examined.

The primary population is described as the Full Analysis Set, comprising all randomized participants. This indicates the stated analysis population, but the registry does not provide a participant flow account or explain how missing month-12 measurements were handled. It does not report whether imputation, a repeated-measures method, complete-case analysis, or another approach was used. The amount and pattern of missing outcome data are also not reported in the registry record.

Missingness can affect interpretation if the availability of an outcome is related to treatment assignment or to the outcome itself. Statistical methods cannot remove that concern without assumptions, and the registry record does not give the information needed to assess those assumptions. The detailed analysis population for each secondary outcome, protocol deviations, adherence, and sensitivity analyses are not reported in the registry record. These omissions do not invalidate the posted primary result, but they limit independent assessment of how robust it is to alternative missing-data assumptions and analysis choices.

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 0% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: atrial fibrillation (1.0%), atrial tachycardia (1.0%), congestive cardiomyopathy (1.0%), appendicitis (1.0%), gastroenteritis salmonella (1.0%).

The registry lists serious adverse events for both groups: 8 affected participants in the program-plus-medication group and 11 in the program-alone group, with 100 at risk in each group. The record also lists one death in the program-alone group and none in the combined group. These are descriptive safety counts; they do not by themselves establish that the intervention caused or prevented an event. The registry does not provide a causal assessment or enough detail to compare the clinical context of the events.

Serious adverse event terms listed include atrial fibrillation, atrial tachycardia, congestive cardiomyopathy, appendicitis, gastroenteritis salmonella, and procedural vomiting, each shown with a percentage of 1.0%. Those term-level figures should be read as event reporting in the registry, not as a complete account of event timing, severity beyond the serious classification, relatedness, or outcomes. The record does not explain whether any participant experienced more than one event, so event terms should not be added to infer a count of affected individuals.

The registry shows zero at risk and zero affected for other adverse events in both groups. Because the at-risk denominator is recorded as zero for that category, those entries should not be interpreted as evidence that no other adverse events occurred among participants. The safety information is limited to the counts and terms listed; broader safety details are not reported in the registry record.

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

The primary result is a comparison of assignment to two strategies over the stated month 0 to month 12 period. The posted group estimates show a larger average percentage reduction in body weight for the program-plus-medication group than for the program-alone group. The sponsor's ANCOVA estimate and confidence interval indicate that the observed between-group contrast was estimated with uncertainty, but the interval does not include zero under the reported analysis.

This does not establish that every participant experienced a reduction or that individual responses were uniform. A group mean can coexist with a range of individual outcomes. It also does not identify which medication contributed to the group result, because the combined group could receive one of five medications and medication-specific findings are not reported. Since both groups received the weight-management program, the comparison is not medication versus no treatment and cannot separate the contribution of the program from the contribution of medication in the combined strategy.

The trial was open label, and the registry does not report detailed adherence, missing-data methods, or the covariates in the primary model. These details matter when assessing the strength and generalizability of the estimate. The result is tied to the Cleveland Clinic Integrated Medical Weight Management Program and the employee population described in the record; participant characteristics and detailed eligibility criteria are not reported in the registry record. The record also does not establish whether the effect persisted beyond month 12.

A statistically notable result is not itself a judgment about clinical importance, value, or suitability for an individual. The posted data address a group comparison on body-weight change and related measured outcomes. They do not establish effects on long-term health, work performance, or outcomes that were not numerically reported. The safety figures are descriptive and do not support a causal safety conclusion. Taken together, the results are evidence about the particular randomized strategies and follow-up reported, not a universal estimate for all settings or medication choices.

18. Why This Trial Matters Statistically

This trial is statistically informative because it compares two recognizable care strategies in a randomized, parallel-group design: a weight-management program paired with medication and the program alone. The design makes the treatment contrast explicit and gives the primary estimate a defined interpretation. The open-label nature and pragmatic setting also make it useful to consider how trial design and routine delivery can affect what an estimate represents.

The primary outcome is continuous percentage change in body weight, while the secondary outcomes include binary thresholds and program attendance. That range of outcome types illustrates why results should be interpreted according to the measure and analysis used. A continuous average, a proportion meeting a threshold, and an attendance mean answer related but nonidentical questions. The secondary results add context but also raise multiplicity concerns because the registry lists multiple outcomes.

The difference between the sponsor's adjusted analysis and a simple recalculation is another useful statistical distinction. Posted summary values permit a transparent unadjusted comparison, but they do not reproduce ANCOVA. The contrast's sign also depends on the subtraction order, so a negative estimate in the sponsor's analysis can represent the same ordering as a positive recalculated contrast. Keeping the model, contrast direction, and uncertainty separate prevents an apparent sign discrepancy from being mistaken for a disagreement about which group had the more negative mean change.

Finally, the registry record illustrates the boundary between a clear headline estimate and the information needed for full appraisal. The primary population is identified and the sponsor's confidence interval is posted, but covariates, missing-data procedures, multiplicity handling, and original design assumptions are not reported. Such omissions are important because they shape confidence in precision, robustness, and generalizability without changing the numerical results that are recorded.

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 trial-specific details needed for a fuller appraisal are not reported in the registry record. These include detailed eligibility criteria and baseline characteristics, the names and selection criteria for the medications, the randomization procedure, and the original sample-size justification. The registry describes an approximately one-year intervention and a month 12 primary assessment, but it does not provide detail about treatment adherence, discontinuation, crossover, or medication exposure over follow-up.

The registry identifies ANCOVA for the primary analysis but does not report its covariates, model specification, or diagnostic checks. It also does not describe handling of missing month-12 outcomes or provide a participant flow account. These gaps limit assessment of the adjusted estimate's reproducibility and sensitivity to missing data. The primary analysis population is stated as all randomized participants, but the record does not explain whether every randomized participant contributed an observed month-12 outcome.

The open-label design could influence outcomes involving participant behavior or self-report, such as attendance or work-related measures. The primary outcome is body-weight change, but the record does not provide measurement procedures. The secondary findings are unadjusted in the posted comparisons, and a multiplicity strategy is not reported. Numerical results for some listed secondary outcome topics are not reported in the registry record.

Safety information is limited to serious-event counts, selected terms, and the recorded death count. Event relatedness, timing, and a fuller description of non-serious adverse events are not reported in the registry record. Finally, the employee setting and use of a particular integrated program constrain direct generalization to other populations or delivery models. The record does not report follow-up beyond month 12, so persistence of the observed weight-change pattern cannot be assessed from these results.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Real World Effectiveness of Combining an Employer-based Weight Management Program With Medication for Chronic Weight Management in Employees With Obesity — NCT03799198.
• Registry record last updated 2022-11-14; status last verified 2022-11.
• Results first posted 2021-06-18.
• 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

This completed Phase 4 randomized, open-label, parallel-group trial enrolled 200 employees with obesity. It compared the Cleveland Clinic Integrated Medical Weight Management Program plus medication for chronic weight management with the program alone. The registry records a study start of 2019-01-07 and primary completion of 2020-05-22.

The primary outcome was percentage change in body weight from month 0 to month 12 in the Full Analysis Set. Posted least-squares mean changes were -7.69% for the program-plus-medication group and -4.19% for the program-alone group. The sponsor reported an ANCOVA treatment difference of -3.50, with a 95% confidence interval from -5.51 to -1.50 and p < 0.001. A simple recalculation gives the reversed contrast direction; the sponsor's analysis takes precedence.

The record also lists secondary outcomes and serious adverse event counts. Details concerning missing-data handling, multiplicity, medication-specific results, and the original design assumptions are not reported in the registry record.