Sitagliptin/Metformin (JANUMET) Re-examination Study (0431A-182): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Sitagliptin/Metformin (JANUMET) Re-examination Study (0431A-182) (NCT01065766), a registered phase not stated study. The primary outcome is Percentage of Participants With Any Adverse Experience.

2. Clinical Question

This is a safety-focused question from a re-examination study, rather than a question about a treatment effect against a concurrent control. The stated purpose was to collect safety and efficacy information and reconfirm the clinical usefulness of sitagliptin/metformin for re-examination under the applicable regulations. The record identifies 9 outcome measures, but it does not report the primary outcome result itself. Consequently, the question can be described from the registered endpoint, but the percentage answering it cannot be read from the posted primary outcome information.

3. Trial Design

The registry describes a completed re-examination study of sitagliptin/metformin in usual practice. It lists Korean participants with type 2 diabetes mellitus treated with sitagliptin/metformin and an enrollment of 4065. The study began in 2009-03, and primary completion was recorded in 2013-05. Merck Sharp & Dohme LLC is identified as the sponsor.

The record does not describe a randomized comparison. It states that allocation was not stated and cautions that the arms are not a like-for-like control comparison. The participant description identifies a treated group, but the record does not provide enough information to characterize any other group as a valid concurrent comparator. Accordingly, the posted information does not establish a controlled comparison of outcomes between treatment strategies.

The primary outcome is the percentage of participants with any adverse experience, assessed over up to 26 weeks in participants included in the safety evaluation. The registry defines an adverse event as an unfavorable and unintended change in body structure, function, or chemistry temporally associated with study-drug administration, regardless of whether it was considered related to the product. The safety summary reports a denominator of 4033 participants for the listed serious and other adverse-event counts.

The record lists 9 outcome measures and no analyses. It does not report the detailed protocol, recruitment procedures, how usual-practice treatment was selected, follow-up visit schedule, or reasons participants might not enter the safety evaluation. Those details are not reported in the registry record, so the study design should not be elaborated beyond the registered description. Its stated re-examination purpose and observational, non-comparative presentation are important context for reading the posted safety information.

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 were included in the safety evaluation

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: Baseline characteristics were only reported for the Safety Population (4033) who qualified for the study and not for the 4065 participants from whom CRFs were collected.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With Any Adverse Experience, measured over Up to 26 weeks.

The primary endpoint is the percentage of participants with any adverse experience among those included in the safety evaluation, over up to 26 weeks. An adverse event is defined broadly: it is an unfavorable and unintended change in body structure, function, or chemistry that is temporally associated with study-drug administration. The definition does not require the event to be judged caused by the treatment.

A percentage expresses how often an event was observed in a defined population, using the number of participants with an event in relation to the relevant safety population. That makes the endpoint useful for describing the frequency of reported adverse experiences during the stated observation period. It is a descriptive safety measure, not by itself a causal estimate of harm attributable to treatment. In a study without a suitable concurrent comparator, background events and other influences cannot be separated from events related to treatment through a treatment-group contrast.

The registry gives the endpoint definition and population but does not report the primary percentage or its uncertainty. The separate safety summary lists serious and other adverse-event counts, but those counts should not be substituted for the missing result for any adverse experience. The primary endpoint's result is not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a binary event measure at the participant level: a participant either had at least one qualifying adverse experience during the stated period or did not. The registry expresses the endpoint as a percentage. The analysis population is described as all participants included in the safety evaluation, and the timeframe is up to 26 weeks. The record does not report the observed primary percentage or an accompanying uncertainty interval.

What does a percentage estimate?

In general, a percentage is a proportion expressed on a percentage scale. Its numerator is the number of participants meeting the event definition, and its denominator is the number of participants assessed for that endpoint. The denominator matters because a percentage cannot be interpreted without knowing which participants were counted and how missing observations were handled. For the primary endpoint, the registry names the safety-evaluation population but does not provide the result or explain how participants with incomplete follow-up were treated.

In general, a confidence interval describes the range of values compatible with the observed data under a statistical model and procedure. It communicates precision as well as the point estimate. A narrow interval generally indicates greater precision than a wide one, while neither interval width nor a point estimate alone resolves whether the events were caused by treatment. No confidence interval for the primary outcome is reported in the registry record, so its precision cannot be judged from the posted primary result.

Why does the event definition matter?

The registered definition includes unfavorable and unintended changes temporally associated with study-drug administration whether or not considered related to the product. This is a broad collection rule. Temporal association establishes that an event occurred during a relevant period; it does not establish causation. In general, causal interpretation requires careful consideration of the study design, comparator, event ascertainment, and other possible explanations. The record does not provide a randomized control comparison, and it states that allocation was not stated.

The outcome is also different from an event count. A participant-level percentage typically counts participants who experienced an event, rather than counting every occurrence of that event. The registry does not provide enough detail to determine how repeated events or multiple types of events were handled for the primary endpoint. The reported serious and other adverse-event categories should therefore be read only as the listed categories and counts, not as a replacement definition for the primary outcome.

What can planning calculations tell readers?

In general, a sample-size calculation estimates how many participants would be needed under stated assumptions to detect a specified effect with a chosen error rate and power. It is a planning exercise, not a measure of the power actually achieved after a study has been completed. Any planning illustration based on an observed effect remains conditional on that effect and its assumptions. The stated calculation assumptions use a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a fraction of the observed effect. The registry does not report a like-for-like randomized comparison, and the primary outcome result is not reported, so such planning assumptions cannot supply a missing primary estimate or establish observed power.

In general, a two-sided significance level sets a threshold for assessing data against a null hypothesis in either direction. It does not describe the probability that a result is true, and it does not measure clinical importance. Equal allocation and a normal approximation are modeling assumptions for a comparison; they are not evidence that the study itself used that allocation or method. The registry does not report the protocol's statistical plan, the calculation's effect value, or a rationale for the planned sample size.

What methods are not documented?

The registry lists 9 outcome measures and no analyses. It does not report the statistical method used for the primary endpoint, adjustment variables, confidence intervals, hypothesis tests, interim analyses, handling of missing data, or a prespecified analysis plan. Those procedures should not be inferred from the endpoint format. In general, missingness can affect a proportion if participants without complete outcome information differ from those assessed; transparent reporting of denominators and missing-data handling helps readers evaluate that risk.

In general, over-dispersion is relevant when observed variation is greater than a model expects, which can make conventional uncertainty estimates too small. It is not possible to determine whether this concern applies to the primary analysis because the registry does not report the model or analysis results. The record supports a description of the registered endpoint and a limited reading of the posted safety counts, but not a reconstruction of unreported statistical procedures.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 9 outcome measures and no analyses. It does not identify a multiplicity strategy, such as a hierarchy of outcomes or an adjustment for testing several outcomes. It also does not report whether the primary endpoint was the only confirmatory question or how secondary outcomes were to be interpreted. In general, when several hypotheses are tested, the chance of at least one apparently unusual result can increase unless the analysis plan accounts for the set of tests. That general concern cannot be quantified for this study from the posted information.

The registry does not report a missing-data method or the number of participants with incomplete primary outcome follow-up. The primary endpoint population is described as participants included in the safety evaluation, but criteria for inclusion in that population and the treatment of missing event information are not given. The safety summary denominator is 4033, while enrollment is 4065; the reason for this difference is not reported in the registry record. It would be inappropriate to assume that the difference reflects a specific form of withdrawal, exclusion, or missingness.

The record does not report whether analyses were planned for all enrolled participants, the safety population, or another population beyond the primary endpoint's stated safety group. It also does not explain whether all 9 outcome measures were analyzed. In general, analysis populations and missing-data procedures matter because they determine which participants contribute to each estimate and can influence how representative the result is. Here, the absence of those details, together with the missing primary outcome result, limits assessment of both the estimated frequency and the reliability of comparisons across outcomes.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: angina unstable (0.0%), dyspnoea (0.0%), acute myocardial infarction (0.0%), atrial flutter (0.0%), coronary artery occlusion (0.0%).

The posted safety summary lists 17 participants affected in the serious adverse-event category, with 4033 at risk. It lists 0 participants affected in the other adverse-event category, also with 4033 at risk. These are descriptive counts for the categories as recorded; they are not a comparison with an untreated or alternative-treatment group. The registry does not report deaths in this summary, so a death count should not be inferred from the record.

The serious-event terms include ANGina UNSTABLE, DYSPNOEA, ACUTE MYOCARDIAL INFARCTION, ATRIAL FLUTTER, CORONARY ARTERY OCCLUSION, and ABDOMINAL PAIN. Each is listed with a reported percentage of 0.0%. Because percentages are rounded, a displayed 0.0% does not necessarily establish that the corresponding event count was zero. The registry does not provide term-specific counts in the posted information.

These serious-event details are not the primary endpoint result. The primary question concerns any adverse experience, and its percentage is not reported in the registry record. The serious-event counts therefore should not be used to infer the overall frequency of adverse experiences or whether events were caused by treatment.

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

The registry record documents a completed usual-practice re-examination study in Korean participants with type 2 diabetes treated with sitagliptin/metformin. It establishes the stated purpose, the primary safety endpoint, its broad adverse-event definition, the follow-up period of up to 26 weeks, and the recorded enrollment. It also contains limited serious and other adverse-event counts for the safety population.

Those details do not establish a comparative treatment effect. The registry does not describe a randomized control comparison, states that allocation was not stated, and cautions that the arms are not a like-for-like control comparison. The posted record also does not report the primary percentage for any adverse experience or its statistical uncertainty. As a result, readers cannot use the primary outcome information to judge the estimated frequency or its precision.

In general, a descriptive event frequency can help characterize what was recorded in a defined population and observation period. It cannot by itself show that treatment caused an event, or that the observed frequency would differ under another treatment or no treatment. Those conclusions depend on a suitable comparison and clear methods for selecting participants, collecting events, and analyzing missing information. Those details are not reported in the registry record.

The posted serious-event count and the reported 0.0% term percentages should also be read narrowly. They describe the registry entries, not a complete causal assessment or an assurance that events did not occur. The record does not supply enough information to resolve the missing primary estimate, explain the safety denominator, or assess how comprehensive event reporting was.

13. Why This Trial Matters Statistically

This study is statistically relevant because it illustrates the difference between a registered clinical question and a reported result. The registry defines a participant-level safety endpoint and identifies its population and observation window, but the primary percentage is not reported in the registry record. Without the estimate and its uncertainty, the central descriptive question cannot be answered quantitatively from the posted primary outcome information.

It also illustrates why study design constrains interpretation. The stated setting is usual practice, and the registry does not identify a randomized comparison or a like-for-like control group. A treated-group frequency can describe events recorded in that group, but it does not alone estimate what would have happened under a different treatment strategy. Design and analysis must support the comparison being claimed.

The difference between enrollment of 4065 and a safety denominator of 4033 is another reminder that denominators need explanation. The registry does not report why those figures differ or how participants outside the safety denominator were handled. Transparent population definitions and missing-data reporting are essential to understanding who contributes to an estimate.

Finally, the serious-event summary demonstrates why rounded percentages and event counts should be distinguished. A reported 0.0% is a rounded display and does not necessarily mean the event count was zero; the registry does not list term-specific counts. These points are broadly useful when reading registry results: estimates, denominators, uncertainty, event definitions, and design context all matter, and none can be replaced by a single headline number.

14. 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 most direct limitation for interpretation is that the registry does not report the primary outcome percentage, despite defining the endpoint and its timeframe. It also does not report an uncertainty interval or analysis result for that endpoint. The main safety question can therefore be identified, but its estimated frequency and precision cannot be evaluated from the posted primary outcome information.

The registry lists enrollment of 4065 and a safety denominator of 4033 for the posted adverse-event categories, but does not explain the difference. It does not report the criteria for entry into the safety evaluation, follow-up completeness, missing-data handling, or reasons that participants might not contribute to a particular outcome. These omissions make it difficult to assess the representativeness of the safety denominator.

The record describes sitagliptin/metformin use in usual practice and does not provide a randomized, like-for-like comparator. It therefore offers no basis for a controlled estimate of relative risk or a causal treatment contrast. Allocation is not stated. The registry also does not report detailed event-collection procedures, adjudication methods, or how event relatedness was assessed in practice.

Although 9 outcome measures are listed, the registry reports no analyses. The statistical plan, multiplicity approach, interim analyses, and methods for handling repeated or multiple events are not reported. The serious-event summary gives counts for categories and rounded percentages for listed terms, but not term-specific counts. These limitations concern what the registry record documents; they do not establish that a particular procedure was or was not conducted outside the record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Sitagliptin/Metformin (JANUMET) Re-examination Study (0431A-182) — NCT01065766.
• Registry record last updated 2015-03-06; status last verified 2015-02.
• Results first posted 2014-04-17.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

NCT01065766 is a completed re-examination study of sitagliptin/metformin (JANUMET) in usual practice among Korean participants with type 2 diabetes mellitus. Merck Sharp & Dohme LLC is listed as sponsor. Enrollment was 4065; the study began in 2009-03 and primary completion was recorded in 2013-05.

The primary endpoint is the percentage of participants in the safety evaluation with any adverse experience over up to 26 weeks. The primary outcome result is not reported in the registry record. The safety summary lists 17 participants affected in the serious-event category and 0 in the other adverse-event category, each among 4033 at risk. The record lists 9 outcome measures and no analyses, and it does not describe a like-for-like randomized comparison.