Pioglitazone Special Drug Use Surveillance "Metabolic Syndrome in Patients With Type 2 Diabetes Mellitus": Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Pioglitazone Special Drug Use Surveillance "Metabolic Syndrome in Patients With Type 2 Diabetes Mellitus" (NCT02002975), a registered phase not stated study. The primary outcome is Percentage of Participants Who Met at Least One New Cerebral and Cardiovascular Events.

2. Clinical Question

3. Trial Design

This completed study is described as a special drug use surveillance of pioglitazone in patients with type 2 diabetes mellitus and metabolic syndrome. Its stated purpose was to assess new cerebral and cardiovascular events and changes in metabolic syndrome parameters during long-term treatment. The sponsor is Takeda. The registry lists enrollment of 18223 participants, a study start date of 2007-10-16, and primary completion on 2013-06-30.

The intervention description specifies pioglitazone at 15 to 30 mg, taken orally once daily before or after breakfast for 3 years. The primary outcome timeframe is from baseline up to 3 years. The study record describes a single pioglitazone group and does not identify a control group. Allocation is not stated, and the record indicates that the study is not a randomized comparison. Consequently, the design described is surveillance during treatment rather than a randomized estimate of differences between treatments.

The primary outcome population is the Full Analysis Set. The registry defines this as participants with efficacy data available at baseline and post-baseline (3 Month). It does not report the size of this analysis population. Secondary outcomes include changes from baseline in HbA1c (NGSP) according to the number of metabolic syndrome-related risk factors at final assessment, and the association between baseline characteristics, including such risk factors, and new cerebral and cardiovascular events. The record lists 13 outcome measures and 0 analyses. The detailed results for the primary outcome 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 with a historical diagnosis of type 2 diabetes mellitus were enrolled to receive pioglitazone 15 milligram (mg) - 30 mg tablet, orally, once daily for up to 3 years.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set included all participants who had efficacy data at baseline and post-baseline (3 Month) available.

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 included all participants who had efficacy data at baseline and post-baseline (3Month) available.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Who Met at Least One New Cerebral and Cardiovascular Events, measured over From Baseline, Up to 3 Years.

The primary endpoint is the percentage of participants who met at least one new cerebral or cardiovascular event from baseline up to 3 years. The registry also describes the outcome as the frequency of participants with at least one new event during the study. It groups the events under macroangiopathy and specifies sudden death, cerebral infarction, cerebral hemorrhage, subarachnoid hemorrhage, acute myocardial infarction, angina pectoris requiring intervention or hospitalization for treatment, cardiac failure requiring hospitalization for treatment, atrial fibrillation, and aortic dissection.

In general, a binary endpoint records whether each participant did or did not meet a defined event criterion during a specified period. Reporting the percentage affected can describe how often that criterion occurred in the outcome population. The event definition and timeframe matter: this endpoint combines different event types, and the record's definition requires intervention or hospitalization for some of them. The resulting percentage would therefore refer to the composite definition, not to each event type separately.

The registry record gives the endpoint definition but does not report the primary percentage, its numerator and denominator, or an uncertainty interval. It is therefore not possible to describe the observed frequency or its precision from the primary outcome information in the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary outcome as a percentage of participants with a binary event status. The explanatory points below describe general statistical concepts; they do not establish which methods were used in this study unless the registry record states them.

What does a binary percentage represent?

In general, a binary outcome classifies each participant according to whether a defined event occurred during the relevant observation period. The percentage is a way to express the number meeting the event definition relative to the number assessed. For this study, the event criterion is meeting at least one new cerebral or cardiovascular event from baseline up to 3 years. The registry says that reported data were the frequency of participants meeting at least one such event. It does not report the primary event count or percentage, nor the denominator used for that calculation.

The composite event definition includes multiple conditions. A participant meeting any one or more of the listed criteria qualifies for the endpoint. This approach can summarize a range of clinically distinct events in one outcome, but the combined percentage does not reveal the frequency of each component. Component-specific primary outcome results are not reported in the registry record.

How should uncertainty be understood?

In general, a confidence interval describes a range of values compatible with the observed data under a specified statistical method. Its width conveys statistical precision: a narrower interval indicates more precision, while a wider interval indicates less. A percentage without a confidence interval gives no direct interval-based account of uncertainty. The registry record does not report a confidence interval for the primary outcome, so its statistical precision cannot be evaluated from the primary results.

A p-value, when reported, addresses how compatible data are with a specified null hypothesis under the assumptions of the test. It does not measure the size or clinical importance of an effect. No primary-outcome p-value or hypothesis test is reported in the registry record. The record lists 0 analyses, so there is no posted primary-outcome analysis result to interpret.

What does the study design allow?

In general, a surveillance study can describe events recorded among people receiving a treatment in the setting and population under observation. A randomized comparison can support a different type of inference because treatment allocation is used to create comparison groups. Here, the registry does not state an allocation method, identifies the study as not randomized, and does not describe a control group. The observed safety counts therefore should not be read as a treatment-versus-control effect estimate. The record does not provide a comparative estimate for the primary outcome.

The registry describes a treatment schedule of 15 to 30 mg orally once daily before or after breakfast for 3 years, and a primary outcome window from baseline up to 3 years. The scheduled treatment duration and outcome window describe the intended period; they do not, by themselves, establish that every participant contributed the same length of follow-up. Individual follow-up duration and event ascertainment procedures are not reported in the registry record.

What do the planning assumptions mean?

In general, a sample-size planning calculation depends on assumptions about the effect to detect, significance level, allocation, and statistical method. The record describes a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and the effect specified as a fraction of the observed effect. It also states that the planning values are illustrations, not the study's own design. The study is not described as a randomized two-arm comparison, and the primary observed effect is not reported in the registry record. The planning assumptions therefore should not be read as evidence of the trial's design or as observed power. The numerical planning results are not part of the registry entries.

In general, over-dispersion refers to variability greater than expected under a statistical model. It can matter when the model assumes a particular variance structure, because underestimated variability can make uncertainty appear too small. The registry information does not identify a model for the primary binary outcome or report an over-dispersion assessment. No model-specific conclusion can be drawn.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Pioglitazone")
n      <- c(17651)
events <- c(178)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Pioglitazone  17651  178  1.0  0.9  1.2  0.9  1.2  0.9  1.2

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 13 outcome measures, including the primary event measure and secondary measures concerning HbA1c and baseline characteristics associated with new cerebral and cardiovascular events. When several outcomes or analyses are considered, multiplicity can arise: the chance of obtaining at least one apparently notable result may increase across multiple tests. General approaches can adjust testing or define a priority order, but the statistical plan for handling multiplicity is not reported in the registry record. The record lists 0 analyses, and no inferential results are available to assess.

The registry defines the primary outcome population as the Full Analysis Set, including participants with efficacy data at baseline and post-baseline (3 Month). The number in this set is not reported. The enrollment count is 18223, but the record does not establish that all enrolled participants were included in the primary analysis. The specific handling of missing outcome data, withdrawals, or participants without complete follow-up is not reported in the registry record.

In general, missing data can affect an estimate if the participants with observed information differ systematically from those without it. The impact depends on the amount and pattern of missingness and on the methods used to address it. The registry does not report missing-data assumptions, imputation methods, or sensitivity analyses for the primary outcome. It is therefore not possible to evaluate how missing information may have affected the posted primary result, which itself is not reported.

The definition of the Full Analysis Set indicates a baseline and post-baseline efficacy-data requirement, but does not describe all analysis-population rules. Other analysis populations and their sizes are not reported in the registry record.

12. 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 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cardiac failure (0.1%), acute myocardial infarction (0.1%), cerebral infarction (0.1%), sudden death (0.0%), angina pectoris (0.0%).

The pioglitazone group lists 17651 participants at risk for serious adverse events and 82 affected, and 17651 at risk for other adverse events and 467 affected. These are distinct safety categories in the registry record. They should be read as reported counts for the listed group, not as the primary cerebral and cardiovascular endpoint result. The record does not give deaths in this safety summary; death information is not reported in the registry record.

The listed serious adverse event terms include cardiac failure, acute myocardial infarction, and cerebral infarction, each reported as 0.1%. Sudden death, angina pectoris, and atrial fibrillation are each reported as 0.0%. The percentages are shown at the precision used in the registry, so a displayed 0.0% should not be interpreted as proof that no event occurred. The record does not supply detailed counts for each of these terms in the registry record.

In general, an adverse event listing describes events recorded during a study; it does not establish that treatment caused them. The absence of a randomized control comparison also limits comparative interpretation. Serious adverse event counts should be considered separately from the primary endpoint, which has its own definition and whose result is not reported in the registry record.

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

The registry record describes a surveillance study of pioglitazone in patients with type 2 diabetes mellitus, states its aim of tracking new cerebral and cardiovascular events and metabolic syndrome parameters, and defines a composite primary endpoint over a period from baseline up to 3 years. It also reports safety counts for the pioglitazone group and identifies selected serious adverse event terms. These details describe what the study was intended to observe and what safety figures were posted.

The primary endpoint result itself is not reported in the registry record. No primary percentage, event count, confidence interval, or test result is available in the stated details. Therefore, the record does not establish the frequency or precision of the primary endpoint in the analyzed population. Enrollment of 18223 does not resolve this, because the size of the Full Analysis Set is not stated.

The surveillance design also does not support a causal comparison with an untreated or alternative-treatment group. No comparator is described, allocation is not stated, and the record identifies the study as not randomized. The reported safety figures therefore do not show what would have occurred under another treatment or without treatment. Nor do they establish that treatment caused any event listed.

In general, an event frequency can be informative as a description of outcomes observed in a defined population over a stated period. Its interpretation depends on a clear denominator, consistent event identification, complete follow-up information, and suitable handling of missing data. The registry record does not report all of those details for the primary outcome. The defensible conclusion is limited to the study's stated objective, design features, endpoint definition, and posted safety counts; no conclusion about the primary event frequency or treatment effect can be drawn from the primary results recorded.

14. Why This Trial Matters Statistically

This study illustrates a statistical distinction between surveillance and comparative treatment evaluation. Surveillance can record events among people receiving a treatment, while a randomized comparison is designed to estimate differences between groups under a defined allocation process. The registry describes a single pioglitazone group, does not state allocation, and identifies the study as not randomized. That design context is essential when interpreting event counts: counts observed during treatment are not, by themselves, estimates of treatment-attributable risk or comparative benefit.

The primary outcome also illustrates how a composite endpoint works. The registry groups a range of cerebral and cardiovascular events under a criterion of at least one new event. A composite can summarize whether any listed event occurred, but it does not make the components interchangeable. Component-specific results and the primary composite result are not reported in the registry record, so neither their relative contribution nor the overall event frequency can be assessed.

The record reports enrollment of 18223, yet does not report the size of the Full Analysis Set or the primary endpoint estimate. This demonstrates why enrollment alone does not describe the information available for a particular analysis. A clear analysis denominator and uncertainty estimate are important for judging the precision of a reported percentage.

Finally, the registry lists 13 outcome measures and 0 analyses. In general, multiple outcomes can raise questions about which results were primary and how testing was handled. The statistical plan for multiplicity is not reported. Together, these features make the record useful for examining endpoint definitions and reporting limits, while restricting what can be inferred about the primary outcome.

15. 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 is that the primary endpoint result is not reported in the registry record. The record defines the percentage of participants with at least one new cerebral or cardiovascular event, but does not give the event count, percentage, confidence interval, or analysis denominator. Although enrollment is reported as 18223, the number in the Full Analysis Set is not stated.

The design offers no stated comparator and is identified as not randomized. Allocation is not stated. As a result, the record does not provide a like-for-like treatment comparison or a basis for attributing observed events to pioglitazone. The single described treatment group and safety counts must be interpreted as surveillance information rather than comparative effects.

The primary endpoint is a composite of multiple event types, some defined by a requirement for intervention or hospitalization. The record does not report component-specific primary outcome results or details of event adjudication and ascertainment. Follow-up is described as baseline up to 3 years, with pioglitazone scheduled for 3 years; individual follow-up and completeness are not reported in the registry record.

The record defines the Full Analysis Set through availability of baseline and post-baseline (3 Month) efficacy data, but does not report missing-data methods, sensitivity analyses, or the sizes of other analysis populations. It lists 13 outcome measures and 0 analyses; multiplicity procedures are not reported. These omissions limit assessment of precision, robustness, and the effect of incomplete data. The listed safety summary also does not report deaths, and percentages for selected serious event terms are rounded as displayed.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Pioglitazone Special Drug Use Surveillance "Metabolic Syndrome in Patients With Type 2 Diabetes Mellitus" — NCT02002975.
• Registry record last updated 2019-01-24; status last verified 2018-08.
• Results first posted 2019-01-24.
• 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.

19. Record Summary

NCT02002975 is a completed Takeda special drug use surveillance study of pioglitazone in patients with type 2 diabetes mellitus. Enrollment was 18223. The registry lists a start date of 2007-10-16 and primary completion on 2013-06-30.

The described regimen was pioglitazone 15 to 30 mg orally once daily before or after breakfast for 3 years. The primary endpoint was the percentage of participants meeting at least one new cerebral or cardiovascular event from baseline up to 3 years. The record defines a Full Analysis Set based on baseline and post-baseline (3 Month) efficacy data, but does not report its size or the primary endpoint result.

The record lists 13 outcome measures and 0 analyses. It reports serious adverse events for 82 of 17651 at risk and other adverse events for 467 of 17651 at risk in the pioglitazone group. No comparator is described, allocation is not stated, and the study is identified as not randomized.