Safety and Efficacy Study of Subjects That Are Taking Saxagliptin Added Onto Metformin XR Compared to Subjects Taking Metformin XR Alone: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy Study of Subjects That Are Taking Saxagliptin Added Onto Metformin XR Compared to Subjects Taking Metformin XR Alone (NCT00683657), a randomized phase 3 study. The primary outcome is Change From Baseline in 24-Hour Mean Weighted Glucose (MWG) at Week 4.

2. Clinical Question

The protocol summary describes a comparison of 24-hour glucose control. The primary measure is intended to represent glucose across a full day rather than a single fasting or post-meal reading. Secondary outcomes listed in the record include postprandial glucose measures, mean daily glucose, and fasting plasma glucose. Their names indicate other aspects of glucose control, but their numerical results are not reported in the registry record.

3. Trial Design

This is a randomized, double-blind, placebo-controlled, parallel-group Phase 3 trial. The official title describes a multicenter study, and the record lists 93 enrolled participants. The trial status is completed. Its start is recorded as 2008-07, and primary completion is recorded as 2009-02.

The treatment comparison was saxagliptin 5 mg plus metformin XR versus placebo plus metformin XR. The intended population was people with type 2 diabetes whose glycemic control was inadequate with diet and exercise while taking a stable dose of metformin XR of at least 1500 mg/day. The registry describes the primary-outcome population more specifically as randomized participants who took at least 1 dose of double-blind treatment and had both baseline and Week 4 measurements.

Randomization is used to allocate participants to study groups, helping make the groups comparable on average with respect to measured and unmeasured characteristics. Double masking means that treatment assignment was concealed from more than one relevant study party, although the registry record does not specify exactly who was masked or how masking was maintained. A placebo comparison helps distinguish changes associated with the add-on treatment from changes that may occur while continuing metformin XR and participating in the trial.

The official title describes a 4-week trial, and the primary outcome timeframe is listed as baseline and Week 4. However, the primary-outcome description also refers to an adjusted change “at Week 24.” This is inconsistent with the other timing information in the record. The record does not clarify which wording is intended, so the discrepancy should not be silently resolved.

The record does not report further details of the randomization procedure, allocation concealment, visit schedule beyond the outcome descriptions, or the exact analysis methods. Those details should not be inferred from the broad design labels.

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: 218 subjects were enrolled and 128 entered the 4-week dietary and exercise, and metformin extended release (XR) lead-in period. Thirty-five subjects did not enter treatment period (21 no longer met study criteria, 7 withdrew consent, 7 for poor protocol compliance).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Randomized participants who took at least 1 dose of double-blind treatment. To be included in an analysis of change from baseline to Week 4 the subject must have had a baseline and a Week 4 measurement.

5. Baseline Characteristics

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

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in 24-Hour Mean Weighted Glucose (MWG) at Week 4, measured over Baseline, Week 4.

The primary endpoint is change from baseline in 24-hour mean weighted glucose at Week 4, measured in mg/dL. The registry describes the measure as an average across the full 24-hour period, calculated from the area under the curve of glucose measurements. It also states that the mean change was adjusted for baseline value.

Glucose measurements were scheduled around meals and at other times across the day and night. The recorded schedule includes measurements before meals, after meals, at midnight, at 3 AM, and at the end of the 24-hour domiciliary visit. This repeated sampling is intended to capture day-long glucose patterns rather than relying on one isolated measurement. The full measurement schedule is described in the registry record, but the actual endpoint values are not reported there.

In general, a change-from-baseline endpoint expresses how much the measured outcome changed from each participant’s starting value. An adjusted mean summarizes the average change while accounting for baseline value in the analysis. These methods can make a comparison more informative when participants begin at different levels, but they do not replace reporting the estimated treatment-group contrast and its uncertainty.

The registry also lists four secondary glucose outcomes: postprandial measures, mean daily glucose, and fasting plasma glucose. The listed outcome names alone do not establish the size, direction, or statistical precision of any treatment difference. The record does not report the primary endpoint estimates, a confidence interval, or a test result.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does randomization contribute?

Randomization assigns participants to treatment groups by a chance-based process. In general, this reduces the risk that treatment assignment is systematically linked to participant characteristics, although it does not guarantee that groups will be identical in a particular trial. The registry identifies this study as randomized but does not report the sequence-generation method or the procedure used to conceal allocation before assignment. Those details are therefore not reported in the registry record.

Why use a placebo and double masking?

A placebo comparator helps separate differences associated with the assigned add-on treatment from changes that may occur with ongoing background treatment, trial participation, or expectations. Here, both groups are described as receiving metformin XR, with saxagliptin or placebo added. In general, masking can reduce the influence of treatment expectations on care, participant reports, and outcome assessment. The record labels the trial double-blind but does not specify who was masked or provide operational details about maintaining the blind.

What does an adjusted mean change represent?

A change-from-baseline analysis compares a participant’s follow-up measurement with that participant’s starting measurement. The registry describes the primary result as an adjusted mean change and says it was adjusted for baseline value. In general, adjustment accounts statistically for baseline measurements when estimating group outcomes. It can improve precision and account for starting-value differences, depending on the analysis model and data. The registry record does not report the model specification, covariates beyond baseline value, or the estimates resulting from that model.

How should a confidence interval be read?

In general, a confidence interval expresses uncertainty around an estimated treatment contrast under a specified statistical model. A narrow interval indicates more precise estimation than a wide interval, while the interval’s position relative to a value of no difference helps readers understand which contrasts remain compatible with the data. It does not assign a probability to the true effect after the data have been observed. The registry record does not report a confidence interval for the primary outcome, so the precision of the estimate cannot be assessed.

What is the role of a significance test?

A significance test evaluates how compatible the observed data are with a specified null hypothesis under a statistical model. A p-value is not the probability that the null hypothesis is true, and it does not describe the clinical importance of a result. It should be considered alongside the effect estimate, its uncertainty, design limitations, and the analysis plan. No primary-outcome p-value or inferential test result is reported in the registry record.

Why can repeated glucose measurements matter?

The endpoint draws on measurements made throughout a 24-hour period. In general, repeated observations can represent variation across time more fully than a single measurement, but the resulting summary depends on how observations are collected and combined. The registry describes the area-under-the-curve approach and the measurement schedule. It does not report the underlying measurements, the handling of incomplete profiles, or further details of the calculation beyond the stated description.

What does over-dispersion mean in general?

Over-dispersion occurs when observed variability is greater than a statistical model assumes. When that happens, standard errors can be too small if the model does not account for the extra variability, making intervals too narrow and tests too optimistic. This concept is especially relevant to some count outcomes; it is not a claim about this trial’s continuous glucose endpoint. The registry record does not report an over-dispersion assessment or a model that would allow one to evaluate it.

How should planning calculations be distinguished from trial results?

The record describes planning illustrations based on the observed effect, using a two-sided significance level of 0.05, equal allocation, and a normal approximation. Such illustrations are planning calculations, not observed trial outcomes and not observed power. They depend on assumptions about the effect to detect. The record does not provide numerical sample-size illustrations in the information reported, and it does not report the trial’s own sample-size justification. A planning calculation cannot supply the missing endpoint estimate or its uncertainty.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists five outcome measures and five analyses, including the primary mean weighted glucose endpoint and secondary glucose outcomes. Considering several outcomes can create a multiplicity issue: in general, the more statistical comparisons made, the greater the chance that at least one result appears noteworthy by chance if each is assessed separately. Possible approaches include prespecifying a primary outcome, adjusting tests, or interpreting secondary analyses as exploratory. The registry record does not report a multiplicity-control plan, a testing hierarchy, or whether secondary analyses were adjusted.

The primary population is described as randomized participants who took at least 1 dose of double-blind treatment and had both a baseline and a Week 4 measurement. Requiring measurements at both time points means that participants without either measurement would not be included in that change analysis, according to the stated population description. The record does not report how many participants were excluded for missing measurements or how missing data were handled.

In general, missing outcome data can affect an estimate if the likelihood of missingness is related to participants’ outcomes or treatment assignment. Analysis choices such as complete-case analysis, imputation, or model-based methods make different assumptions. The registry record does not specify which approach was used, whether sensitivity analyses were conducted, or whether the primary analysis followed an intention-to-treat principle.

The record also does not report interim analyses, stopping rules, or a detailed statistical analysis plan. These items should not be inferred from the randomized, double-blind design or from the listed outcome measures. Without the missing-data and multiplicity details, readers cannot fully evaluate how the reported analyses would have addressed incomplete follow-up or multiple comparisons; in this case, the numerical endpoint results themselves are also not reported.

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 non-serious adverse event terms

The registry lists 47 participants at risk for serious adverse events in the placebo-plus-metformin group and 46 in the saxagliptin-plus-metformin group. It reports 0 serious adverse events in each group. These are the serious-event counts recorded for the stated groups; they do not establish that no adverse event of any kind occurred.

For other adverse events, the record lists 5 affected participants among 47 at risk in the placebo-plus-metformin group and 1 affected participant among 46 at risk in the saxagliptin-plus-metformin group. These are counts, not a complete description of event types, severity, timing, or relationship to treatment. The registry record does not list the specific terms for these other events in the information reported.

Deaths are recorded as null for both groups. That is not the same as a reported count of zero; whether deaths occurred is not reported in the registry record. The safety figures should be read separately from the primary glucose outcome, whose numerical results are also not reported. A small set of event counts cannot establish comparative safety beyond the events and participants captured in the record.

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

The record describes a clinical comparison of saxagliptin added to metformin XR against placebo added to metformin XR in people with type 2 diabetes and inadequate glycemic control on their existing regimen. It identifies a 24-hour mean weighted glucose change as the primary endpoint and specifies the general measurement approach. These details explain the intended question, but they are not findings about the treatment contrast.

The primary outcome estimates, between-group contrast, confidence interval, and p-value are not reported in the registry record. As a result, the posted information does not show how much either group changed, whether the groups differed, or how precisely any difference was estimated. The outcome definition alone cannot establish a beneficial, harmful, or null effect.

In general, an outcome may be statistically distinguishable from no difference yet still have limited practical importance, or an estimate may be uncertain even when its point estimate appears substantial. Interpreting a trial therefore requires both the estimated contrast and its uncertainty, as well as attention to the population, follow-up, outcome measurement, and analysis choices. Those primary numerical results are unavailable in the registry record.

The safety record reports zero serious adverse events in each group and counts of other adverse events in both groups. These entries should not be treated as a complete safety assessment or as a substitute for detailed event descriptions and follow-up. Death counts are not reported in the registry record.

The record also contains inconsistent timing language: the trial is described as 4 weeks and the primary timeframe as Week 4, but the endpoint description refers to Week 24. This leaves the assessment timing unclear in that description. The record does not explain the inconsistency.

Thus, the record supports a description of the design, population, outcome definition, and limited adverse-event counts. It does not support a numerical conclusion about the primary treatment effect or its precision, and it should not be read as evidence that a treatment works or does not work.

13. Why This Trial Matters Statistically

This trial is statistically informative as an example of the distinction between a clearly specified clinical question and a reported treatment-effect estimate. The registry identifies a randomized, double-blind, placebo-controlled comparison and describes a continuous glucose outcome measured across a full day. Those features define how the study sought to make a comparison, but interpretation still depends on reporting the estimates and their uncertainty.

The endpoint also illustrates why outcome construction matters. A full-day summary uses measurements taken at several times rather than relying only on a fasting value or a reading after one meal. In general, such a summary can capture a broader glucose profile, while its interpretation depends on measurement timing and the method used to combine observations. The registry describes those elements but does not report the resulting group values.

Change from baseline and baseline adjustment are common statistical approaches. In general, they can account for starting values, but a reader needs the model details and results to judge the estimate. Reporting the group contrast with an interval would allow assessment of both magnitude and precision. Without these statistics, neither a design label nor a list of outcomes can answer the clinical comparison.

The record also highlights the importance of consistent outcome timing. A 4-week title and Week 4 timeframe sit alongside a Week 24 reference in the endpoint description. Resolving this wording matters for understanding when the primary measurement was intended, but the registry does not clarify it.

Finally, the listed adverse-event counts demonstrate why safety summaries need careful reading: serious events, other events, and deaths are distinct entries, and unreported information should not be interpreted as zero. Taken together, these features make the record useful for evaluating what was planned and what remains unclear, while the missing efficacy estimates limit statistical interpretation of the central comparison.

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 main limitation for interpretation is that the registry record does not report the primary endpoint results. It gives no adjusted mean changes by group, no between-group estimate, and no confidence interval or p-value. The magnitude, direction, and precision of the primary comparison therefore cannot be assessed.

The timing description is internally inconsistent. The study is titled as a 4-week trial and the primary timeframe is baseline to Week 4, while the primary endpoint description refers to Week 24. The registry record does not explain which timing is correct.

Important analysis details are also not reported in the registry record. These include the statistical model, the approach to missing data, the handling of multiple outcomes, the randomization procedure, and whether interim analyses or sensitivity analyses were conducted. The primary analysis population is described, but the record does not report how many participants contributed to the endpoint or how many lacked required measurements.

The safety summary has limited detail. It provides group counts for serious and other adverse events, but does not provide event terms in the information reported. Death entries are null rather than stated counts. The counts therefore do not establish the full pattern of safety events.

Although the record gives an enrollment total and lists treatment arms, the adverse-event denominators are reported separately as groups at risk. The record does not provide enough additional outcome information to connect those safety summaries to efficacy results. These limitations restrict what can be concluded from the registry record, rather than establishing that unreported analyses or events did not occur.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Safety and Efficacy Study of Subjects That Are Taking Saxagliptin Added Onto Metformin XR Compared to Subjects Taking Metformin XR Alone — NCT00683657.
• Registry record last updated 2015-06-01; status last verified 2015-05.
• Results first posted 2010-03-10.
• 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

This completed Phase 3 trial randomized 93 participants in a double-blind, placebo-controlled, parallel-group comparison of saxagliptin 5 mg plus metformin XR with placebo plus metformin XR. The intended population had type 2 diabetes and inadequate glycemic control with diet and exercise while taking a stable metformin XR dose of at least 1500 mg/day.

The primary outcome was change from baseline in 24-hour mean weighted glucose, described as an adjusted mean in mg/dL. The title and timeframe indicate a 4-week assessment, although the endpoint description also refers to Week 24. Primary outcome estimates and uncertainty are not reported in the registry record. The record lists 0 serious adverse events in each group, other adverse events affecting 5 of 47 and 1 of 46 participants, respectively, and death counts as null.