Efficacy and Safety Study of Saxagliptin + Metformin Immediate Release (IR) Versus Metformin IR Alone in Type 2 Diabetes Mellitus: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety Study of Saxagliptin + Metformin Immediate Release (IR) Versus Metformin IR Alone in Type 2 Diabetes Mellitus (NCT00885378), a randomized phase 3 study. The primary outcome is Mean Hemoglobin A1C (A1c) and Change From Baseline to Week 12.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group Phase 3 trial sponsored by AstraZeneca. The registry lists an enrollment of 166 participants and a completed status. The recorded start was 2009-05, and primary completion was 2010-02. The registry classifies masking as quadruple, while the official title calls the trial double-blind. The record does not explain how those descriptions relate to one another or identify which groups of people were masked.

Participants were assigned to saxagliptin plus metformin immediate release or placebo plus metformin immediate release. The official title specifies saxagliptin 2.5 mg twice daily and describes participants as having inadequate glycemic control on metformin immediate release alone. The trial's stated purpose was to compare the reduction in A1C between the groups. The registry also lists fasting plasma glucose and the proportions meeting specified A1C thresholds at Week 12 among secondary outcomes.

The primary endpoint is described at baseline and Week 12. The analysis population for that endpoint included randomized participants with both a baseline and post-baseline value up to Week 12; it is not described as every randomized participant. Details of the randomization procedure, allocation concealment, metformin dosing, adherence, participant flow, and the reasons for any missing endpoint measurements are not reported in the registry record. The number enrolled should therefore not be treated as the number contributing to every analysis.

4. Participant Flow and Accounting

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

Before assignment: Of the 166 subjects who entered the lead-in period, 6 discontinued: 3 withdrawal of consent, 1 poor/noncompliance, 1 adverse event (AE; abdominal pain secondary to partial small bowel obstruction), and 1 elevated liver enzymes that did not meet study exclusion criteria but was discontinued by the investigator.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Randomized participants with both a baseline value and post-baseline value (up to Week 12).

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 Mean Hemoglobin A1C (A1c) and Change From Baseline to Week 12, measured over Baseline, Week 12.

The primary outcome was mean hemoglobin A1C and change from baseline to Week 12, measured as a percentage of glycosylated hemoglobins. The registry specifies that mean change was adjusted for baseline and that dispersion was reported as a standard error. Its analysis population consisted of randomized participants with both baseline and post-baseline values up to Week 12. The numerical group results, adjusted contrast, and uncertainty estimates are not reported in the registry record.

General explanation: A1C is a continuous measure of glycemia, so reporting a mean describes the average value in a group, while a mean change describes the average movement from a starting measurement. Comparing changes can help characterize how groups differed over the study period. Baseline adjustment is a statistical approach intended to account for participants' starting measurements when estimating change. It does not by itself show how large or clinically important a difference is; that interpretation depends on the estimated contrast, its precision, and relevant clinical context.

The registry also identifies response thresholds of A1C < 7.0% and A1C <= 6.5% at Week 12 as secondary outcomes. Those are categorical outcomes, unlike the continuous primary measure. Their results are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

General explanation: A randomized parallel-group design assigns participants to separate groups and follows those groups under their assigned regimens. Randomization is intended to reduce systematic differences between groups at entry, on average, although the registry record does not describe the specific sequence-generation or concealment methods. Parallel assignment means the comparison is between groups rather than a planned sequence in which each participant receives both regimens.

What does baseline adjustment mean?

The primary outcome is a mean change from baseline adjusted for baseline. In general, adjustment includes the starting measurement in a statistical model when estimating the outcome contrast. Baseline values can vary across participants, and accounting for them may improve the comparison's precision or address chance imbalance. The registry record does not report the exact model, covariates beyond baseline, assumptions, or estimation procedure, so the precise implementation cannot be assessed.

What does the standard error describe?

The registry names standard error as the dispersion measure. In general, a standard error describes the estimated sampling variability of a statistic, such as a group mean. It is not the same as the spread of individual participant measurements. The record does not include numerical standard errors for the primary results, so their size and the resulting precision cannot be evaluated. A confidence interval would usually communicate uncertainty around an estimate more directly, but whether one was calculated or reported for the primary comparison is not stated in this registry record.

Why distinguish a continuous outcome from a response threshold?

General explanation: A continuous outcome retains information about the measured values and can be summarized by a mean and a mean change. A threshold outcome classifies participants according to whether a value falls on one side of a cutoff. The registry lists both kinds of outcomes: mean A1C and change, as well as the proportion meeting the specified Week 12 A1C thresholds. Threshold summaries may be easier to interpret as response categories, but they discard information about how far values lie from the cutoff. No numerical results for either kind of outcome are reported in this record.

What does over-dispersion mean in general?

General explanation: Over-dispersion occurs when observed variability is greater than a statistical model assumes. It matters because a model that understates variability can produce uncertainty estimates that are too small. This concept is particularly relevant to some count or binary-data models; the registry record does not identify an over-dispersion assessment or report a model for the secondary threshold outcomes. It would therefore be inappropriate to infer whether over-dispersion was present or how it was handled.

What can the planning assumptions establish?

The record describes a sample-size planning illustration based on an observed effect, with two-sided significance level 0.05, equal allocation, and a normal approximation. It specifies that the effect to detect is a stated fraction of the observed effect. It also distinguishes planning quantities expressed as participants per arm from total event counts for time-to-event outcomes. These are planning conventions, not observed trial findings and not observed power. The registry record does not report the numerical planning outputs, the fractions used, or a protocol-based sample-size justification. The illustration should not be mistaken for the trial's original design calculation.

The record does not give the statistical test, model specification, variance assumptions, confidence level, handling of protocol deviations, or any interim-analysis plan. The presence of outcome and analysis counts does not supply those details. A careful reading should separate the endpoint definition and stated planning assumptions from methods that are not described and from numerical results that are absent.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 12 outcome measures and 4 analyses. It also identifies several secondary outcomes, including fasting plasma glucose and two A1C response thresholds at Week 12. Testing multiple outcomes or contrasts can raise a multiplicity question: when many statistical tests are conducted, the chance of at least one apparently unusual result can increase if no adjustment or prioritization is used. General explanation: approaches to multiplicity include prespecifying a primary comparison, adjusting significance thresholds, or treating secondary findings as exploratory. The multiplicity strategy for this trial is not reported in the registry record.

The primary analysis population required a baseline and post-baseline value up to Week 12. The registry does not report how many randomized participants lacked such measurements, the reasons for missingness, or the method used to address missing outcome data. It also does not report whether the main analysis used imputation, a likelihood-based approach, a complete-case analysis beyond the stated population definition, or sensitivity analyses. These details matter because conclusions can depend on assumptions about why measurements are missing and how unobserved outcomes are handled.

The record does not give results for all randomized participants or compare those results with the endpoint population. It also does not describe a per-protocol population, an intention-to-treat analysis, or other analysis populations. The stated primary population should therefore be read as the registry's endpoint definition, not as proof that a particular analysis strategy or missing-data method was used.

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: myocardial infarction (1.4%), pulmonary oedema (1.4%), back pain (1.2%).

The registry lists serious adverse events for two groups: placebo plus metformin immediate release had 1 affected participant among 86 at risk, and saxagliptin 2.5 mg plus metformin immediate release had 1 affected participant among 74 at risk. Other adverse events are listed as 0 in both groups. The record does not report deaths for either group. These figures are descriptive counts and denominators; they do not provide a formal comparison or establish that the groups had equivalent safety.

The serious-event terms listed in the record are MYOCARDIAL INFARCTION (1.4%), PULMONARY OEDEMA (1.4%), and BACK PAIN (1.2%). The record does not state a group attribution alongside these terms in the information available, so they should not be assigned to an arm. It also does not provide event timing, duration, severity details beyond the serious-event classification, exposure-adjusted rates, or a causal assessment. Small descriptive counts can be difficult to interpret, and a count alone does not show whether an event was caused by a study intervention.

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

The record establishes that a randomized, placebo-controlled, parallel-group Phase 3 trial was designed to compare saxagliptin 2.5 mg twice daily plus metformin immediate release with placebo plus metformin immediate release in participants with type 2 diabetes. It defines mean A1C change to Week 12 as the primary endpoint and describes baseline adjustment and the population used for that endpoint. Those design details clarify the question the trial addressed.

The record does not report the numerical primary efficacy comparison. It therefore does not show the observed between-group difference, how uncertain that estimate was, or whether the result met a statistical criterion. It also does not provide numerical results for the secondary outcomes listed. The trial's purpose or endpoint definition must not be treated as evidence of a particular result.

General explanation: Statistical significance and clinical importance are different considerations. Statistical uncertainty concerns how precisely an effect is estimated under the analysis assumptions; clinical importance concerns whether the magnitude would matter in context. Assessing either requires the actual estimates and appropriate contextual information. Neither can be determined from an endpoint description alone.

The serious adverse event counts provide limited descriptive safety information. They do not establish a causal relationship, rule out uncommon events, or show that the groups had the same risk. The registry's event-term percentages do not have an explicitly stated group attribution in this record. A fuller safety interpretation would require additional details, including the events' context and how participants were followed.

Accordingly, this registry record supports understanding the design and the intended statistical question, but not a conclusion about the comparative efficacy or overall safety of the regimens. Further result details and analysis methods are not reported in the registry record.

13. Why This Trial Matters Statistically

This trial illustrates why the endpoint definition and the result estimate need to be read together. The record names a continuous primary outcome, identifies baseline adjustment, specifies Week 12, and defines an analysis population requiring both baseline and post-baseline measurements. Those elements are important for understanding what a reported estimate would represent and to whom it would apply.

It also illustrates the distinction between a trial's intended question and its registry record's available evidence. A completed randomized trial with a stated primary outcome does not, by itself, communicate the size or precision of its findings. Without the primary contrast and uncertainty estimate, readers cannot assess the observed result from this record. The same applies to the listed secondary endpoints: their presence does not reveal their outcomes.

The listing of multiple outcomes and analyses raises a statistical reporting issue. Interpretation of several outcomes depends partly on how priorities and multiplicity were handled, yet the registry record does not report that strategy. Similarly, the defined primary analysis population makes missing-data handling relevant, but those methods and the number of participants with missing measurements are not reported.

Finally, the safety information underscores the difference between descriptive counts and comparative inference. Serious-event counts and listed event terms can orient readers to what was recorded, but they do not establish causation or a reliable difference between groups. Taken together, the record is useful for identifying the design and analysis questions a reader should ask, while leaving the central efficacy estimate and several key statistical details unavailable.

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.

A central limitation of this registry record is that it does not report the numerical primary outcome results. The group means, mean changes, adjusted between-group estimate, and uncertainty measures are absent. The secondary outcome results are also not reported in the record. Consequently, the statistical and clinical magnitude of the primary comparison cannot be evaluated from this information.

The outcome population is defined as randomized participants with both baseline and post-baseline measurements up to Week 12, but the record does not report the number included in that population or the handling of missing measurements. The analysis model and its assumptions are not described in sufficient detail to reproduce or assess the primary analysis. Multiplicity procedures and any interim-analysis plan are also not reported in the registry record.

The record gives enrollment as 166, while the serious-event groups have their own at-risk denominators. These figures describe different recorded aspects of the trial; the record does not explain participant flow or the reasons the denominators differ from enrollment. The serious-event term percentages are listed without clear group attribution in this record, limiting arm-specific interpretation. Deaths are not reported.

Other trial details that could aid interpretation—including eligibility criteria beyond the brief description, treatment adherence, follow-up and exposure details, and the handling of protocol deviations—are not reported in the registry record. The record's generic planning assumptions are not a substitute for the trial's original sample-size justification, which is not reported.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Efficacy and Safety Study of Saxagliptin + Metformin Immediate Release (IR) Versus Metformin IR Alone in Type 2 Diabetes Mellitus — NCT00885378.
• Registry record last updated 2015-06-01; status last verified 2015-05.
• Results first posted 2011-12-16.
• 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 randomized, parallel-group trial compared saxagliptin 2.5 mg twice daily plus metformin immediate release with placebo plus metformin immediate release in type 2 diabetes. Enrollment was 166. The primary outcome was mean A1C and change from baseline to Week 12, adjusted for baseline, among randomized participants with baseline and post-baseline values. Numerical efficacy results and key analysis details are not reported in the registry record.

The registry lists secondary glycemic outcomes and serious adverse event counts, but these do not establish a comparative efficacy or safety conclusion. The primary estimate, its precision, multiplicity approach, and missing-data methods are not reported.