This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Comprehensive Add on Study in Japan (NCT01204294), a randomized phase 3 study. The primary outcome is Incidence of Adverse Events (AEs).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT01204294 |
| Phase | Phase 3 |
| Condition | Diabetes Mellitus, Type 2 |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | None (open label) |
| Enrollment | 574 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Boehringer Ingelheim |
| Results posted | Yes |
2. Clinical Question
Population
The study enrolled patients with type 2 diabetes mellitus and insufficient glycaemic control despite diet, exercise, and treatment with one approved antidiabetic drug. The primary safety outcome used the treated set: patients who received at least one dose of randomized study medication during the 52-week treatment period. Further eligibility details are not reported in the registry record.
Intervention
The study examined linagliptin, 5 mg orally once daily, as add-on treatment over 52 weeks. Background treatments listed with linagliptin were a biguanide, a glinide, a glitazone, a sulfonylurea, and an alpha-glucosidase inhibitor.
Comparator
The listed comparison regimens were sulfonylurea plus metformin and alpha-glucosidase inhibitor plus metformin. The registry record does not report an allocation ratio or a single pooled comparator. The listed groups therefore represent several treatment strategies, rather than one simple two-arm contrast.
Primary question
The primary safety question concerned adverse events from first study-drug administration through 7 days after the last administration, up to 382 days. The record describes counts for patients with any adverse event, severe adverse events, adverse events leading to treatment discontinuation, and hypoglycaemic events. It does not report one primary numerical comparison or an inferential analysis of these categories.
In practical terms, the registry record asks about safety and efficacy of adding linagliptin in patients whose glycaemic control was insufficient on background treatment. The primary endpoint is safety-related, while glycosylated haemoglobin A1c (HbA1c) is listed as a secondary outcome. The posted results available for interpretation include group counts for serious and other adverse events, but no HbA1c results or statistical comparisons. Thus, the available information describes event counts in the randomized groups; it does not establish a comparative treatment effect or answer the full efficacy question.
3. Trial Design
The registry record describes a phase 3, randomized, open-label, parallel-group study titled “Comprehensive Add on Study in Japan.” It lists an enrollment of 574 and a planned treatment period of 52 weeks. The study started in 2010-09, reached primary completion in 2012-01, and is recorded as completed. Boehringer Ingelheim is listed as the sponsor.
Randomization assigns participants to treatment groups by chance, helping balance measured and unmeasured characteristics on average across groups. The parallel-group structure means participants were assigned to a group rather than crossing between the listed strategies. The study was unmasked: patients and study personnel were not blinded to the assigned treatment. Open-label conduct can be relevant to the reporting and assessment of adverse events, particularly when outcomes depend on recognition or clinical judgment. The registry record does not describe specific safeguards for outcome assessment.
The listed linagliptin add-on groups paired it with a biguanide, glinide, glitazone, sulfonylurea, or alpha-glucosidase inhibitor. The other listed groups paired metformin with a sulfonylurea or alpha-glucosidase inhibitor. These are multiple active treatment combinations; the registry record does not identify one common comparator for every linagliptin group. It also does not report the allocation ratio, details of randomization sequence generation, concealment procedures, or group-specific planned enrollment.
Eligibility is described broadly as type 2 diabetes with insufficient glycaemic control despite diet, exercise, and one approved antidiabetic drug. The record does not report further eligibility criteria, background-drug dose rules, adherence procedures, or details of permitted changes in treatment. The treated set for the primary safety outcome included patients receiving at least one dose of randomized study medication during the 52-week treatment period. The record does not describe other analysis populations or how participants who did not complete follow-up were handled.
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.
Only the first 6 of 7 groups are shown.
Overall Study
| Stage | Bigu+Lina | Glin+Lina | Glit+Lina | SU+Lina | A-GI+Lina | SU+Met |
|---|---|---|---|---|---|---|
| STARTED | 82 | 66 | 74 | 143 | 85 | 63 |
| COMPLETED | 79 | 58 | 69 | 132 | 83 | 58 |
| NOT COMPLETED | 3 | 8 | 5 | 11 | 2 | 5 |
Reasons for not completing this period:
| Reason | Bigu+Lina | Glin+Lina | Glit+Lina | SU+Lina | A-GI+Lina | SU+Met |
|---|---|---|---|---|---|---|
| Adverse Event | 2 | 6 | 0 | 7 | 1 | 4 |
| Protocol Violation | 1 | 0 | 2 | 1 | 0 | 0 |
| Withdrawal by Subject | 0 | 2 | 2 | 1 | 1 | 1 |
| Lack of Efficacy | 0 | 0 | 0 | 2 | 0 | 0 |
| Other (house moving) | 0 | 0 | 1 | 0 | 0 | 0 |
Analysis population for the primary outcome, as defined in the registry: The treated set (TS) comprised all patients who received at least one dose of randomised study medication in the 52-week treatment period
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.
Only the first 6 of 8 groups are shown.
| Characteristic | Unit | Bigu+Lina | Glin+Lina | Glit+Lina | SU+Lina | A-GI+Lina | SU+Met |
|---|---|---|---|---|---|---|---|
| Participants analysed | 82 | 66 | 74 | 143 | 85 | 63 | |
| Age, Customized | years | 58.4 (SD 9.9) | 62.6 (SD 8.8) | 60.4 (SD 9.4) | 61.8 (SD 10.8) | 62.0 (SD 10.4) | 61.2 (SD 10.6) |
| Sex: Female, Male: Female | Participants | 33 | 18 | 16 | 38 | 30 | 19 |
| Sex: Female, Male: Male | Participants | 49 | 48 | 58 | 105 | 55 | 44 |
6. Primary Endpoint
The registry lists the primary outcome as Incidence of Adverse Events (AEs), measured over The first drug administration through 7 days after the last drug administration, up to 382 days.
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | not applicable |
| Unit | Patients |
| Endpoint classification | Binary Endpoint |
The primary endpoint is titled incidence of adverse events and is expressed as a number of patients. The record describes several safety categories: patients with any adverse event, severe adverse events, adverse events leading to study-drug discontinuation, and hypoglycaemic events. The observation window began with first drug administration and continued through 7 days after the last administration, up to 382 days. The defined population was the treated set, comprising patients who received at least one dose of randomized study medication in the 52-week treatment period.
Counting patients with events is useful in safety reporting because it describes how many people experienced an event within each group. It is different from counting every event: a patient with more than one event may still contribute as one patient to a patient-count endpoint. The posted group figures distinguish serious adverse events from other adverse events, but do not provide a full breakdown for every category named in the endpoint description. No analysis or effect estimate for the primary endpoint is reported in the registry record.
General: safety endpoints are used to characterize unwanted medical events during treatment and follow-up. Such counts do not, by themselves, show that treatment caused an event. Interpretation also depends on how events were defined, collected, classified, and assessed, and on the completeness of follow-up. Those details are not reported in the registry record. HbA1c is listed as a secondary outcome, but numerical results for that outcome are not reported in the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The posted safety data give group-specific counts of patients with serious adverse events and other adverse events, alongside the numbers at risk for those categories. For example, the Bigu+Lina group had 8 patients with serious adverse events among 82 at risk and 55 patients with other adverse events among 82 at risk. The Glin+Lina group had 5 among 66 for serious adverse events and 41 among 66 for other adverse events. The Glit+Lina group had 2 among 74 and 37 among 74, respectively. These are descriptive counts, not adjusted comparisons.
For SU+Lina, the counts were 7 among 143 for serious adverse events and 83 among 143 for other adverse events. For A-GI+Lina, they were 7 among 85 and 54 among 85. For SU+Met, they were 5 among 63 and 31 among 63. For A-GI+Met, they were 3 among 61 and 33 among 61. The registry record does not report confidence intervals, p-values, adjusted estimates, or an analysis that compares these groups. No ranking of the groups or conclusion about differences is justified from these counts alone.
Each count is tied to its own group denominator and to the definitions used in the registry record. The data do not state whether every participant had the same duration of observation, nor do they provide person-time. The record lists the observation window as first drug administration through 7 days after the last administration, up to 382 days; that is not a substitute for participant-level follow-up information. As a result, the counts should not be interpreted as event rates per unit of time.
The listed serious-event terms include benign prostatic hyperplasia at 2.4%, and pneumonia, cataract, positional vertigo, viral gastroenteritis, and prostate cancer at 1.6% each. These percentages are reported terms, but the record does not provide the underlying term counts or denominators in the details available for interpretation. They therefore should not be compared across groups or treated as a complete account of serious events.
Randomization supports comparisons when the groups, outcomes, analysis population, and statistical analysis are specified and evaluated together. Here, the registry record presents multiple treatment combinations, several safety categories, and descriptive counts, without a reported comparative analysis. Differences in counts can reflect group size, event occurrence, follow-up, or chance; the available record does not quantify the uncertainty around any contrast. The data describe events among treated participants, but do not establish whether any combination caused more or fewer events than another.
The endpoint also includes severe events, discontinuations due to adverse events, and hypoglycaemic events, but the available group figures do not provide the counts for all those categories separately. Absence of those specific counts should not be interpreted as zero events. Death counts are marked as null for the groups; deaths are not reported in the registry record. The secondary HbA1c outcome is named without numerical results. Consequently, this information supports a limited descriptive reading of safety counts, not a conclusion about efficacy or an overall benefit-risk balance.
9. Statistical Methods Explained
What the posted counts represent. The primary endpoint is described as a count of patients, and the group results distinguish patients with serious adverse events from patients with other adverse events. A patient count is a binary outcome at the person level: each person is classified according to whether the specified event category occurred during the defined observation period. This differs from an event count, which may count multiple events in one person. The registry record does not provide a detailed data dictionary clarifying every category or whether categories overlap.
Denominators and population. Each group has a number at risk paired with the number of patients affected. The primary safety population is the treated set, defined as patients receiving at least one dose of randomized study medication during the 52-week treatment period. This means the endpoint population is not necessarily identical to every randomized participant. The record does not report group-level exclusions from the treated set, the number randomized to each group, or how participants with incomplete follow-up were handled. Those details matter when assessing whether the denominators capture all relevant participants and whether event ascertainment was comparable.
Descriptive summaries versus comparisons. A count describes the observed data in one group. To estimate a comparative effect, an analysis would need to define which groups are being contrasted and how the outcome is summarized across them. A risk difference, risk ratio, odds ratio, or model-based contrast would require a specified comparison and analysis. No such estimates are reported in the registry record. No confidence intervals or p-values for these safety comparisons are reported either. Without an inferential analysis, the numerical counts alone do not establish whether apparent group differences are larger than might plausibly arise through sampling variation.
General: a confidence interval expresses the precision of an estimated quantity under the assumptions of its analysis. A wider interval indicates greater uncertainty, while a narrower interval indicates greater precision. A p-value, when used, assesses the compatibility of data with a specified null model; it is not a measure of clinical importance or the probability that a treatment works. Neither type of result can be inferred from the counts without performing an analysis, and no recalculated comparison is presented for these data.
Multiple treatment groups. The randomized study includes several linagliptin add-on combinations and two metformin combinations. Comparisons could be framed in different ways, such as one specific linagliptin combination against one specific metformin combination, but the registry record does not specify a single primary pairwise contrast for the posted safety counts. Combining groups would also require a stated rationale and analysis plan. No pooled comparison is reported, so the group counts should remain associated with their own treatment labels.
Multiplicity. General: when many outcomes or group comparisons are tested, the chance of obtaining at least one apparently notable result by chance can increase. Statistical plans may address this through prespecified testing sequences, adjusted significance thresholds, or other procedures. The registry record does not report a multiplicity strategy, a hierarchy of comparisons, or a testing sequence. Since no inferential tests are posted, there is no basis to describe any result as multiplicity-adjusted or confirmatory.
Over-dispersion and count models. General: over-dispersion occurs when observed variation in counts exceeds what a chosen probability model expects. It matters in analyses of event counts because standard errors can be too small if a model assumes less variability than the data contain. The primary endpoint is described as patients with an event, not as a repeated-event total; the posted data do not provide the participant-level information needed to assess over-dispersion or fit a count model. The registry record does not report such an analysis.
Planning illustrations. The registry record describes a planning illustration based on an observed effect, using a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It says that the effect to detect is a stated fraction of the observed effect. Such planning calculations are not observed power and do not describe the trial's actual design justification. The record does not report a sample-size justification, the trial's own power calculation, or a prespecified effect size used in planning. The available safety endpoint also has several categories and is not reduced to one comparison, so the descriptive group counts should not be treated as a single effect estimate for a planning calculation.
Analysis populations and missingness. General: an analysis population specifies which randomized participants contribute to a particular estimate. A treated-set safety analysis can differ from an intention-to-treat efficacy analysis, which usually retains participants according to randomized assignment. Missing outcome data can affect estimates if the chance of missingness is related to treatment or outcome. The registry record defines the treated set for safety but does not report an intention-to-treat population, missing-data methods, imputation, or sensitivity analyses. The posted counts therefore cannot show how missing follow-up may have affected the results.
10. Multiplicity, Missing Data and Analysis Populations
The primary endpoint description includes several adverse-event categories, while the study also lists HbA1c as a secondary outcome. Multiple treatment combinations create potential choices about which groups and outcomes to compare. General: when many comparisons are made, a prespecified multiplicity approach can help control the chance of false-positive findings. The registry record does not report a multiplicity adjustment, testing hierarchy, or plan identifying which comparisons were confirmatory. Since comparative tests are not reported, no claim about statistical significance or adjustment is supported.
The safety population is defined as the treated set, including patients who received at least one dose of randomized study medication during the 52-week treatment period. The record does not report whether an intention-to-treat analysis was conducted for efficacy, how participants with missing outcomes were handled, or whether any sensitivity analyses assessed missingness. It also does not report group-specific follow-up completeness or reasons for withdrawal. These omissions limit assessment of whether the observed counts represent comparable follow-up across groups.
General: missing data can affect interpretation when participants with unavailable outcomes differ systematically from those with observed outcomes. The direction and size of any resulting bias depend on why data are missing and on the analysis assumptions. With no reported missing-data methods or completeness details, the extent of any impact cannot be assessed. The registry record does not report an interim-analysis plan or stopping rules; their presence or absence should not be inferred.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Bigu+Lina | 8 | 82 | 9.8% |
| Glin+Lina | 5 | 66 | 7.6% |
| Glit+Lina | 2 | 74 | 2.7% |
| SU+Lina | 7 | 143 | 4.9% |
| A-GI+Lina | 7 | 85 | 8.2% |
| SU+Met | 5 | 63 | 7.9% |
| A-GI+Met | 3 | 61 | 4.9% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Bigu+Lina | 55 of 82 |
| Glin+Lina | 41 of 66 |
| Glit+Lina | 37 of 74 |
| SU+Lina | 83 of 143 |
| A-GI+Lina | 54 of 85 |
| SU+Met | 31 of 63 |
Most frequent serious adverse event terms
| Event term | Organ system | Bigu+Lina | Glin+Lina | Glit+Lina | SU+Lina | A-GI+Lina | SU+Met |
|---|---|---|---|---|---|---|---|
| Prostate cancer | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 0 of 85 | 1 of 63 |
| Cerebral infarction | Nervous system disorders | 1 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 0 of 85 | 1 of 63 |
| Benign prostatic hyperplasia | Reproductive system and breast disorders | 0 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 2 of 85 | 0 of 63 |
| Infectious peritonitis | Infections and infestations | 1 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 0 of 85 | 0 of 63 |
| Pneumonia | Infections and infestations | 0 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 1 of 85 | 0 of 63 |
| Pyelonephritis acute | Infections and infestations | 1 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 0 of 85 | 0 of 63 |
| Gastroenteritis viral | Infections and infestations | 0 of 82 | 0 of 66 | 0 of 74 | 0 of 143 | 0 of 85 | 1 of 63 |
| Haemangioma of liver | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 0 of 82 | 1 of 66 | 0 of 74 | 0 of 143 | 0 of 85 | 0 of 63 |
| Lip and/or oral cavity cancer recurrent | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 0 of 82 | 0 of 66 | 0 of 74 | 1 of 143 | 0 of 85 | 0 of 63 |
| Metastases to lymph nodes | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 0 of 82 | 0 of 66 | 0 of 74 | 1 of 143 | 0 of 85 | 0 of 63 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Bigu+Lina | Glin+Lina | Glit+Lina | SU+Lina | A-GI+Lina | SU+Met |
|---|---|---|---|---|---|---|---|
| Nasopharyngitis | Infections and infestations | 30 of 82 | 30 of 66 | 25 of 74 | 45 of 143 | 35 of 85 | 13 of 63 |
| Hypoglycaemia | Metabolism and nutrition disorders | 0 of 82 | 0 of 66 | 2 of 74 | 20 of 143 | 1 of 85 | 10 of 63 |
| Pharyngitis | Infections and infestations | 5 of 82 | 5 of 66 | 3 of 74 | 5 of 143 | 2 of 85 | 2 of 63 |
| Fall | Injury, poisoning and procedural complications | 4 of 82 | 3 of 66 | 1 of 74 | 10 of 143 | 3 of 85 | 1 of 63 |
| Constipation | Gastrointestinal disorders | 3 of 82 | 3 of 66 | 2 of 74 | 4 of 143 | 5 of 85 | 4 of 63 |
| Bronchitis | Infections and infestations | 9 of 82 | 1 of 66 | 1 of 74 | 5 of 143 | 3 of 85 | 1 of 63 |
| Contusion | Injury, poisoning and procedural complications | 4 of 82 | 2 of 66 | 1 of 74 | 10 of 143 | 2 of 85 | 1 of 63 |
| Upper respiratory tract inflammation | Respiratory, thoracic and mediastinal disorders | 4 of 82 | 2 of 66 | 6 of 74 | 4 of 143 | 3 of 85 | 0 of 63 |
| Gastroenteritis | Infections and infestations | 2 of 82 | 1 of 66 | 2 of 74 | 4 of 143 | 4 of 85 | 4 of 63 |
| Back pain | Musculoskeletal and connective tissue disorders | 4 of 82 | 1 of 66 | 1 of 74 | 4 of 143 | 5 of 85 | 1 of 63 |
Serious events with the highest arm-level rate: benign prostatic hyperplasia (2.4%), pneumonia (1.6%), cataract (1.6%), vertigo positional (1.6%), gastroenteritis viral (1.6%).
The serious adverse-event figures are patient counts accompanied by the number at risk in each group. Bigu+Lina recorded 8 patients with serious adverse events among 82 at risk; Glin+Lina recorded 5 among 66; Glit+Lina recorded 2 among 74; SU+Lina recorded 7 among 143; A-GI+Lina recorded 7 among 85; SU+Met recorded 5 among 63; and A-GI+Met recorded 3 among 61. These are the posted counts, not adjusted comparisons or estimates of causal effects.
The corresponding counts for other adverse events were 55 among 82 for Bigu+Lina, 41 among 66 for Glin+Lina, 37 among 74 for Glit+Lina, 83 among 143 for SU+Lina, 54 among 85 for A-GI+Lina, 31 among 63 for SU+Met, and 33 among 61 for A-GI+Met. The record does not say that the “other” category is mutually exclusive from serious events, so these numbers should not be added together or treated as a total of unique patients.
The listed serious-event terms have reported percentages, but the detailed underlying counts and denominators are not reported in the registry record. Death figures are marked as null, so deaths are not reported in the registry record; null does not mean that no deaths occurred. The counts also do not establish whether events were caused by study treatment.
12. What the Result Does, and Does Not, Mean
The posted results offer a descriptive account of adverse-event counts among treated participants in the listed randomized groups. They show that serious and other adverse events were recorded, with counts that vary across groups. The record also lists several serious-event terms and their percentages. This is useful context for understanding what the registry reports, but it does not by itself answer whether one strategy has a different safety profile from another.
A treatment effect requires a defined contrast and an estimate that accounts for the relevant outcome data and uncertainty. The registry record does not report comparative estimates, confidence intervals, p-values, or an analysis of the primary endpoint. It also does not provide all category-specific results described in the endpoint definition. The counts should therefore not be read as evidence that one treatment is safer or less safe, nor as evidence that a treatment caused an individual event.
The study's stated objective includes safety and efficacy, but the primary outcome is adverse events and HbA1c is listed as a secondary outcome. Numerical HbA1c results are not reported in the registry record. On the information available, no conclusion about glycaemic efficacy can be drawn. Likewise, the available safety results are not enough to establish an overall benefit-risk balance.
General: statistical uncertainty matters because observed group counts are subject to sampling variation. A confidence interval or an appropriate model-based comparison can help show how precisely a difference is estimated, provided the comparison and assumptions are suitable. Such precision information is not reported for these results. Moreover, open-label conduct and the lack of reported detail about event assessment, follow-up completeness, and missing data are relevant when judging how comparable the event counts may be.
The most defensible interpretation is consequently narrow: the registry records specified numbers of patients with serious and other adverse events in the treated groups, alongside a defined safety observation window. It does not provide the analyses needed to attribute differences to treatment, quantify uncertainty in comparisons, or evaluate the listed secondary efficacy outcome. Absence of a reported analysis is not evidence that groups were equivalent, and an unreported category should not be interpreted as having no events.
13. Why This Trial Matters Statistically
This trial is statistically informative as an example of the difference between a randomized design and a reported comparative analysis. Randomization creates a framework for comparing assigned treatment strategies, but the design alone does not supply an effect estimate. The registry record lists several combinations and posts group-level safety counts, yet it does not report a single comparison, uncertainty interval, or statistical test for the primary endpoint.
The endpoint also illustrates why an outcome definition matters. The primary safety description encompasses several categories: any adverse event, severe adverse events, events leading to treatment discontinuation, and hypoglycaemic events. The posted group figures distinguish serious from other adverse events, but do not provide separate results for every named category. A reader therefore needs to distinguish the broad endpoint description from the specific results actually reported.
The treated-set definition is another important statistical detail. It identifies who contributes to the primary safety summary, but the record does not give a complete account of randomized participants, missing outcomes, follow-up completeness, or other analysis populations. Those details influence how representative and comparable the observed counts are.
Finally, multiple groups and outcomes invite multiple possible comparisons. Without a reported comparison plan or multiplicity procedure, it is not appropriate to select apparent differences after seeing the counts and present them as confirmatory. These features make the record a useful lesson in cautious interpretation: descriptive safety data can inform what was recorded, while causal and inferential conclusions require transparent outcome definitions, analysis populations, planned contrasts, and uncertainty estimates.
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.
Several trial-specific reporting gaps restrict interpretation. Although the design is randomized and parallel, the registry record does not report the allocation ratio, randomization sequence method, allocation concealment, or planned group sizes. It does not give detailed eligibility criteria or explain how the background antidiabetic treatment was managed. These omissions make it difficult to assess the operational details of the design.
The study was open-label, and the record does not describe how adverse events were elicited, adjudicated, or assessed. Because adverse-event reporting can involve clinical judgment and participant reporting, lack of masking is relevant context. The record also does not report group-specific follow-up completeness, withdrawals, exposure time, or the handling of missing safety data. Counts should not be interpreted as person-time rates, and the potential effect of missing data cannot be assessed.
The primary endpoint description includes several categories, but the posted group results do not provide every category separately. The record does not report comparative estimates, confidence intervals, p-values, adjusted analyses, or a multiplicity plan. Death figures are null, and deaths are not reported in the registry record. The serious-event term percentages are listed without the detailed underlying counts and denominators needed for further comparison. HbA1c is named as a secondary outcome, but numerical results are not reported in the registry record.
These limitations are about what the registry record reports; they do not establish what analyses or procedures may have occurred outside the record. They mean that the posted data support only a restricted descriptive interpretation and do not allow a full assessment of treatment effects, precision, missingness, or overall safety and efficacy.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Comprehensive Add on Study in Japan — NCT01204294.
- Registry record last updated 2014-03-28; status last verified 2014-02.
- Results first posted 2013-01-23.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
The registry record describes a completed, phase 3 randomized, open-label, parallel-group study of linagliptin add-on therapy in patients with type 2 diabetes and insufficient glycaemic control on background treatment. Enrollment was 574. The listed treatment period was 52 weeks, with study start in 2010-09 and primary completion in 2012-01. Boehringer Ingelheim is listed as sponsor.
The primary safety outcome concerned adverse events in the treated set, from first drug administration through 7 days after the last administration, up to 382 days. The posted group data give counts of patients with serious and other adverse events. HbA1c is listed as a secondary outcome, but numerical results are not reported in the registry record. Comparative statistical analyses, uncertainty estimates, multiplicity methods, and missing-data methods are also not reported in the registry record. Accordingly, the available results describe event counts without establishing comparative treatment effects.