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 Edoxaban Treatment Versus Vitamin K Antagonist in Patients With Atrial Fibrillation Undergoing Percutaneous Coronary Intervention (NCT02866175), a randomized phase 3 study. The primary outcome is Number of Participants With Adjudicated Major or Clinically Relevant Non-major Bleeding As First Event Defined by International Society on Thrombosis and Haemostasis Following Edoxaban-based Regimen Compared With Vitamin K Antagonist (VKA)-Based Regimen.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT02866175 |
| Phase | Phase 3 |
| Condition | Atrial Fibrillation |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | None (open label) |
| Enrollment | 1506 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Daiichi Sankyo Europe, GmbH, a Daiichi Sankyo Company |
| Results posted | Yes |
2. Clinical Question
Population
People with atrial fibrillation following successful percutaneous coronary intervention with stent placement. The primary endpoint was assessed in the Intent-to-Treat Analysis Set.
Intervention
An edoxaban-based antithrombotic regimen: edoxaban 60 mg once daily or 30 mg once daily, with clopidogrel 75 mg once daily. Prasugrel or ticagrelor could be used instead of clopidogrel when a documented clinical need was present.
Comparator
A vitamin K antagonist-based regimen with clopidogrel 75 mg once daily, or prasugrel or ticagrelor when a documented clinical need was present, together with aspirin. The registry description of the aspirin duration ends after “up to” and is therefore incomplete.
Primary question
How did the regimens compare for the occurrence of a participant’s first adjudicated major or clinically relevant non-major bleeding event, as defined by the International Society on Thrombosis and Haemostasis, from Day 1 to 12 months postdose?
The study addresses a comparison of antithrombotic strategies in a population with both atrial fibrillation and recent coronary stenting. Its stated focus is safety, with efficacy also to be explored. Bleeding is identified in the registry description as a central safety outcome for antithrombotic strategies and invasive procedures.
The intervention and comparator are regimen-level comparisons, not comparisons of edoxaban with a vitamin K antagonist in isolation. The regimens include antiplatelet therapy, and the comparator description also includes aspirin. The record allows some antiplatelet options to vary according to documented clinical need, so the comparison concerns the strategies as described rather than a single fixed combination for every participant.
The registry record does not report comparative primary-endpoint counts, an effect estimate, a confidence interval, or a p-value. The clinical question is therefore identifiable from the registered endpoint and treatment descriptions, but the posted record does not establish how the groups compared on that endpoint.
3. Trial Design
This is a Phase 3 randomized, parallel-group trial with no masking listed in the registry record. The total enrollment is 1506. The study is marked completed. Its recorded start date is 2017-02-24, and its primary completion date is 2019-06-06.
Participants were assigned to an edoxaban-based regimen or a vitamin K antagonist-based regimen after successful PCI with stent placement. The edoxaban regimen includes edoxaban 60 mg once daily or 30 mg once daily, with clopidogrel 75 mg once daily; prasugrel or ticagrelor could be used in the presence of a documented clinical need. The comparator includes a VKA with clopidogrel, or one of those alternative antiplatelet drugs when clinically needed, and aspirin. The registry description of the aspirin duration is cut off after “up to,” so its full planned duration is not reported in the registry record.
Random allocation supports a planned comparison between the assigned strategies, while the absence of masking means the record does not describe a masked treatment assignment. The endpoint description does specify adjudication of bleeding events. The process and details of adjudication beyond that description are not reported in the registry record.
The primary outcome timeframe is Day 1 to 12 months postdose. The registry lists seven outcome measures, including bleeding outcomes defined using ISTH, TIMI, and BARC classifications, efficacy endpoints, and treatment-emergent adverse events. The primary endpoint is the first major or clinically relevant non-major bleeding event, assessed in the Intent-to-Treat Analysis Set.
The registry record does not report the sample-size justification, planned statistical model, prespecified hypothesis-testing framework, interim analyses, or protocol deviations. The planning assumptions used in separate sample-size illustrations are not a description of the trial’s own design or its actual analysis plan.
4. Participant Flow and Accounting
The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.
Overall Study
| Stage | Edoxaban Regimen | Vitamin K Antagonist Regimen |
|---|---|---|
| STARTED | 751 | 755 |
| COMPLETED | 616 | 580 |
| NOT COMPLETED | 135 | 175 |
Reasons for not completing this period:
| Reason | Edoxaban Regimen | Vitamin K Antagonist Regimen |
|---|---|---|
| Adverse Event | 56 | 54 |
| Withdrawal by Subject | 31 | 52 |
| Death | 30 | 23 |
| Other | 7 | 14 |
| Progressive disease | 1 | 1 |
| Lost to Follow-up | 2 | 0 |
| Lack of Efficacy | 0 | 1 |
| Physician Decision | 3 | 15 |
| Did not receive treatment | 5 | 15 |
Analysis population for the primary outcome, as defined in the registry: First major or clinically relevant non-major bleeding was assessed in the Intent-to-Treat Analysis Set.
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.
| Characteristic | Unit | Edoxaban Regimen | Vitamin K Antagonist Regimen | Total |
|---|---|---|---|---|
| Participants analysed | 751 | 755 | 1506 | |
| Age, Categorical: <=18 years | Participants | 0 | 0 | 0 |
| Age, Categorical: Between 18 and 65 years | Participants | 226 | 202 | 428 |
| Age, Categorical: >=65 years | Participants | 525 | 553 | 1078 |
| Age, Continuous | years | 69.4 (SD 9.74) | 70.1 (SD 9.51) | 69.7 (SD 9.63) |
| Sex: Female, Male: Female | Participants | 194 | 192 | 386 |
| Sex: Female, Male: Male | Participants | 557 | 563 | 1120 |
| Race and Ethnicity Not Collected | Participants | — | — | 0 |
| Region of Enrollment: Romania | participants | 17 | 22 | 39 |
| Region of Enrollment: Hungary | participants | 49 | 54 | 103 |
| Region of Enrollment: Ukraine | participants | 169 | 175 | 344 |
| Region of Enrollment: United Kingdom | participants | 6 | 9 | 15 |
| Region of Enrollment: Portugal | participants | 12 | 12 | 24 |
| Region of Enrollment: Switzerland | participants | 2 | 5 | 7 |
| Region of Enrollment: Spain | participants | 58 | 57 | 115 |
| Region of Enrollment: Austria | participants | 18 | 8 | 26 |
| Region of Enrollment: Netherlands | participants | 3 | 7 | 10 |
| Region of Enrollment: South Korea | participants | 50 | 41 | 91 |
6. Primary Endpoint
The registry lists the primary outcome as Number of Participants With Adjudicated Major or Clinically Relevant Non-major Bleeding As First Event Defined by International Society on Thrombosis and Haemostasis Following Edoxaban-based Regimen Compared With Vitamin K Antagonist (VKA)-Based Regimen, measured over Day 1 to 12 months postdose.
| Element | Registry entry |
|---|---|
| Result type | Count Of Participants |
| Measure of spread | not applicable |
| Unit | Participants |
| Endpoint classification | Binary Endpoint |
The primary endpoint counts participants whose first adjudicated event was major or clinically relevant non-major bleeding, using the International Society on Thrombosis and Haemostasis definition. The timeframe is Day 1 to 12 months postdose, and the stated population is the Intent-to-Treat Analysis Set. The registry description also names other bleeding categories, including minor, life-threatening, provoked, spontaneous, and any bleeding, but the primary outcome is specifically the first major or clinically relevant non-major bleeding event.
Using the first event defines a participant-level endpoint and avoids treating repeated events in one person as though they came from separate participants. In general, an endpoint focused on clinically important bleeding can be informative when assessing antithrombotic strategies, because bleeding is a central safety concern identified in this trial’s registry description. The clinical importance of individual events may differ, which is one reason a prespecified definition and adjudication are relevant to consistent outcome classification.
The registry record supplies the endpoint definition and timeframe but does not report arm-specific event counts or a comparative estimate for this primary endpoint. It also does not report the detailed adjudication procedures or any separate analysis of time to first event. The registered endpoint therefore describes what was to be measured, while the comparative result cannot be determined from the posted primary-outcome information.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record identifies a randomized comparison and clearly describes the primary endpoint, its timeframe, and the analysis population. However, it does not report numerical results for the primary outcome by treatment group. No comparative effect estimate, confidence interval, or p-value for first major or clinically relevant non-major bleeding is reported in the registry record. Consequently, the posted primary-outcome information does not support a conclusion about the direction, size, or precision of the difference between regimens.
Other outcome measures are listed, including bleeding classifications, efficacy endpoints, and treatment-emergent adverse events. The registry record contains no listed analysis records. The descriptions of the outcomes alone do not establish the groups’ comparative outcomes. In particular, a list of endpoints should not be read as evidence that one regimen had more or fewer events than the other.
The available adverse-event figures are counts of participants, not comparative effect estimates. The registry lists serious adverse events for 176 of 746 participants in the Edoxaban Regimen group and 175 of 740 in the Vitamin K Antagonist Regimen group. It lists other adverse events for 457 of 746 and 447 of 740 participants, respectively, and deaths of 46 and 37, respectively. These are descriptive figures. The record does not report uncertainty intervals or a statistical comparison for these counts, and the listed deaths are not identified as treatment-related. They should not be interpreted as proof of a causal treatment effect.
General statistical interpretation depends on both the estimated contrast and its uncertainty. A confidence interval communicates a range of values compatible with the data under the analysis assumptions; it helps distinguish a precise estimate from one that remains uncertain. Because the primary comparative estimate and its interval are not reported in the registry record, the precision of the treatment comparison cannot be assessed from the posted primary outcome information.
The trial’s randomized design is relevant to interpreting a properly reported between-group analysis, but randomization by itself does not supply the missing outcome estimate, clarify missing follow-up, or resolve unreported analysis choices. The record also does not report the prespecified statistical plan, so it is not possible to establish which model, covariate adjustment, or testing procedure would govern a result. Any interpretation should therefore remain limited to the registered design, endpoint definitions, and descriptive adverse-event figures that are posted.
Sample-size illustrations based on an observed effect, if considered alongside the results, are planning calculations rather than observed power. The registry record’s planning assumptions describe a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the target effect expressed as a fraction of the observed effect. These assumptions do not establish the trial’s own sample-size rationale, and without the primary comparative result the illustrations cannot be used to judge the trial’s actual ability to detect that result.
9. Statistical Methods Explained
Randomization is a design method intended to make treatment groups comparable, on average, with respect to both measured and unmeasured characteristics. It supports causal interpretation when assignment, follow-up, outcome ascertainment, and analysis are handled appropriately. The registry record states that allocation was randomized, but it does not report the allocation procedure, concealment details, stratification factors, or the prespecified analysis plan. Those details cannot be inferred from the word “randomized.”
What does the primary endpoint count?
The endpoint counts participants with a first major or clinically relevant non-major bleeding event. A participant-level count is different from a count of all bleeding episodes: when someone has more than one event, the first-event definition focuses the primary outcome on whether and when an initial qualifying event occurred. The record specifies adjudication and an ISTH definition, which are intended to standardize how events are classified. The registry description does not provide the adjudication charter or the actual event counts.
In general, binary outcomes describe whether each participant did or did not experience an event within the defined period. Comparing such outcomes can be reported using event counts and an effect measure, such as a difference in event proportions or a relative measure. These measures answer different questions: an absolute contrast describes the difference in event frequency, while a relative contrast describes the event frequency in one group relative to the other. No effect estimate for the primary endpoint is reported in the registry record, so neither type of comparison can be interpreted.
Why do uncertainty intervals matter?
In general, a confidence interval communicates uncertainty around an estimate. Its width depends on factors such as the amount of information in the data and the variability of the outcome. A narrow interval indicates greater precision under the model and assumptions used; a wide interval indicates less precision. An interval also helps readers assess which values remain compatible with the observed data, rather than relying only on whether a significance threshold was crossed. The registry record does not report a primary-outcome confidence interval or other comparative uncertainty measure.
A p-value, in general, describes how incompatible the observed data are with a specified null hypothesis under the statistical model. It does not measure the size or clinical importance of an effect, and it does not give the probability that the null hypothesis is true. A p-value also cannot substitute for an effect estimate and its uncertainty. No primary-endpoint p-value is reported in the registry record.
What does “first event” imply for analysis?
Time-to-event methods can use both whether an event occurred and the time until it occurred, while accounting for participants whose event status is not observed through the full follow-up period. These methods require decisions about censoring, event timing, and assumptions about the pattern of risk over time. The primary endpoint is described as a first event within a stated timeframe, but the registry record does not report a time-to-event analysis, censoring rules, a model, or a hazard ratio. It would be inappropriate to assume that a particular time-to-event method was used merely because the outcome is defined as a first event.
In general, binary analyses may instead classify participants by whether an event occurred during follow-up. That approach and a time-to-event approach can use follow-up information differently, especially if participants have different observation times. The analysis method for the primary endpoint is not reported in the registry record. Accordingly, the endpoint definition alone does not identify the estimator or statistical test used.
How should planning illustrations be read?
The record describes a planning illustration based on the observed effect, using a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. It describes the effect to detect as a stated fraction of the observed effect. Such calculations are hypothetical planning exercises: they ask how many participants might be needed under specified assumptions to detect a chosen effect with a target power. They are not the number of participants actually analyzed, do not establish the study’s original sample-size justification, and are not observed power.
Power is a design-stage probability calculated under assumptions about the effect, variability, significance level, and analysis. Once results are observed, a retrospective “observed power” calculation based on the estimated effect does not provide an independent measure of evidential strength. The observed estimate and its uncertainty are more informative. The registry record does not report the trial’s own sample-size justification. Also, the primary comparative result needed to anchor an observed-effect illustration is not reported in the registry record.
Why do endpoint definitions and populations matter?
Bleeding classifications are not interchangeable. The registry lists outcomes using ISTH, TIMI, and BARC definitions, each of which classifies events according to its own criteria. A count under one definition should not be assumed to represent the same event set as a count under another. The record lists these secondary bleeding outcomes but does not report their comparative results.
The primary endpoint population is the Intent-to-Treat Analysis Set. In general, an intention-to-treat approach analyzes participants according to their assigned group, retaining the benefit of randomization even when treatment adherence changes. The registry record does not provide further details about exclusions, missing outcome data, treatment discontinuation, or how these situations were handled. Without those details and the outcome results, the robustness of any primary comparison cannot be evaluated.
10. Multiplicity, Missing Data and Analysis Populations
The registry lists seven outcome measures, covering several bleeding classifications, efficacy outcomes, and treatment-emergent adverse events. Examining multiple outcomes creates a multiplicity issue: in general, the more hypotheses tested, the greater the chance that at least one result appears statistically notable by chance if each is assessed separately. Prespecified outcome hierarchies or multiplicity adjustments can address this concern, but the methods depend on the analysis plan. The registry record does not report a hierarchy, adjustment procedure, or other multiplicity strategy.
The primary outcome is named, which distinguishes it from the listed secondary outcomes, but the record does not report the planned testing sequence or how secondary findings were to be interpreted. It also reports no analysis records. The presence of several registered outcomes should therefore not be treated as evidence that each was formally tested or that any observed finding would have controlled error across the family of outcomes.
Missing-data handling is also not reported in the registry record. The primary endpoint description identifies the Intent-to-Treat Analysis Set, but it does not state how missing outcome status, loss to follow-up, withdrawal, or incomplete observation was handled. In general, missingness can affect the estimate if participants with unobserved outcomes differ systematically from those with observed outcomes. Sensitivity analyses can examine how conclusions depend on assumptions about missing data, but no such analyses are reported in the registry record.
The record does not describe a detailed statistical analysis population beyond the stated Intent-to-Treat Analysis Set for the primary endpoint, nor does it report a per-protocol analysis or other population definitions. The number of enrolled participants alone does not establish how many were included in each endpoint analysis. These omissions limit evaluation of the analysis denominator, missing-data assumptions, and the reliability of any unposted comparative results.
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 |
|---|---|---|---|
| Edoxaban Regimen | 176 | 746 | 23.6% |
| Vitamin K Antagonist Regimen | 175 | 740 | 23.6% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Edoxaban Regimen | 46 of 746 |
| Vitamin K Antagonist Regimen | 37 of 740 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 1% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Edoxaban Regimen | 457 of 746 |
| Vitamin K Antagonist Regimen | 447 of 740 |
Most frequent serious adverse event terms
| Event term | Organ system | Edoxaban Regimen | Vitamin K Antagonist Regimen |
|---|---|---|---|
| Cardiac failure | Cardiac disorders | 29 of 746 | 35 of 740 |
| Atrial fibrillation | Cardiac disorders | 20 of 746 | 14 of 740 |
| Pneumonia | Infections and infestations | 14 of 746 | 13 of 740 |
| Chronic obstructive pulmonary disease | Respiratory, thoracic and mediastinal disorders | 5 of 746 | 9 of 740 |
| Cardiac failure congestive | Cardiac disorders | 6 of 746 | 5 of 740 |
| Acute kidney injury | Renal and urinary disorders | 3 of 746 | 7 of 740 |
| Non-cardiac chest pain | General disorders | 6 of 746 | 3 of 740 |
| Anaemia | Blood and lymphatic system disorders | 4 of 746 | 3 of 740 |
| Hypertensive crisis | Vascular disorders | 4 of 746 | 3 of 740 |
| Cholecystitis acute | Hepatobiliary disorders | 3 of 746 | 4 of 740 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Edoxaban Regimen | Vitamin K Antagonist Regimen |
|---|---|---|---|
| Cardiac failure | Cardiac disorders | 40 of 746 | 47 of 740 |
| Atrial fibrillation | Cardiac disorders | 39 of 746 | 41 of 740 |
| Non-cardiac chest pain | General disorders | 30 of 746 | 24 of 740 |
| Oedema peripheral | General disorders | 31 of 746 | 22 of 740 |
| Dizziness | Nervous system disorders | 30 of 746 | 22 of 740 |
| Dyspnoea | Respiratory, thoracic and mediastinal disorders | 22 of 746 | 26 of 740 |
| Nasopharyngitis | Infections and infestations | 25 of 746 | 22 of 740 |
| Hypertension | Vascular disorders | 23 of 746 | 23 of 740 |
| Pneumonia | Infections and infestations | 20 of 746 | 22 of 740 |
| Diarrhoea | Gastrointestinal disorders | 23 of 746 | 19 of 740 |
Serious events with the highest arm-level rate: cardiac failure (4.7%), atrial fibrillation (2.7%), pneumonia (1.9%), chronic obstructive pulmonary disease (1.2%), acute kidney injury (0.9%).
The registry lists serious adverse events for 176 of 746 participants in the Edoxaban Regimen group and 175 of 740 in the Vitamin K Antagonist Regimen group. It lists other adverse events for 457 of 746 and 447 of 740 participants, respectively. Deaths are listed for 46 participants in the Edoxaban Regimen group and 37 in the Vitamin K Antagonist Regimen group. These are descriptive participant counts in the registry record, not adjusted comparisons or estimates of causal effect.
The record also lists serious adverse-event terms and percentages: Cardiac failure, 4.7%; Atrial fibrillation, 2.7%; Pneumonia, 1.9%; Chronic obstructive pulmonary disease, 1.2%; Acute kidney injury, 0.9%; and Cardiac failure congestive, 0.8%. The posted information does not specify, alongside these terms, a treatment-group breakdown or an adjusted comparison. These terms should therefore be read as the listed serious-event categories, not as evidence that the regimens differ for any one condition.
General safety interpretation should distinguish event counts from event rates, account for how long participants were observed, and consider whether events were judged treatment-related. The registry record does not report comparative uncertainty estimates for these adverse-event counts or identify the listed deaths as treatment-related. A difference in descriptive counts alone does not establish that treatment caused an event or that one regimen is safer.
12. What the Result Does, and Does Not, Mean
The posted information establishes that this completed Phase 3 study randomized people with atrial fibrillation after PCI with stent placement to compare an edoxaban-based regimen with a vitamin K antagonist-based regimen. It also defines the primary outcome as first adjudicated major or clinically relevant non-major bleeding during Day 1 to 12 months postdose, in the Intent-to-Treat Analysis Set. The study’s stated purpose was to evaluate safety and explore efficacy.
What the registry record does not establish is the comparative primary-outcome result. It does not report the event counts by group, an effect estimate, a confidence interval, or a p-value for the primary endpoint. It also does not report comparative analyses for the listed secondary outcomes. Therefore the posted results do not show the size or precision of a between-regimen difference in the primary outcome, and they do not establish whether a difference is compatible with no effect or with a range of possible effects.
The adverse-event counts are useful descriptive information but do not answer the primary question by themselves. They do not provide an adjusted comparison, uncertainty interval, or attribution of deaths to treatment. Nor can the listed serious adverse-event terms be interpreted as comparative effects without group-specific results and their analysis context.
In general, a randomized trial’s findings must be interpreted with its outcome definitions, analysis population, follow-up, missing-data approach, and statistical plan in view. Several of these details are not reported in the registry record. The registered design and endpoint are not substitutes for the results, and the sample-size assumptions for a planning illustration are not evidence of the trial’s observed precision or power.
The appropriate conclusion from the posted record is limited: it documents the intended randomized comparison and the registered outcomes, along with descriptive adverse-event counts. It does not provide enough comparative primary-outcome information to characterize the magnitude, direction, or precision of the treatment contrast. No medical conclusion about the regimens follows from these incomplete comparative results.
13. Why This Trial Matters Statistically
This trial poses a statistically relevant question because the treatment strategies combine anticoagulant and antiplatelet therapy in people with atrial fibrillation following coronary stenting. The comparison is therefore between complete antithrombotic regimens, with some antiplatelet options allowed when a documented clinical need is present, rather than between isolated drugs under otherwise identical treatment conditions.
The primary outcome is a clinically focused, adjudicated bleeding endpoint. Defining the event using an established classification and specifying a first-event measure helps make the outcome interpretable and consistent. The registry also lists outcomes under other bleeding classification systems, which reflects a broader assessment of bleeding but introduces the need to distinguish endpoint definitions and account for multiple comparisons when interpreting analyses.
Randomization and the stated Intent-to-Treat Analysis Set are important design features for a treatment comparison. However, sound interpretation also depends on reporting the actual outcome counts, effect estimates, uncertainty, missing-data handling, and planned analysis methods. Those comparative primary results and several analysis details are not reported in the registry record. This is a reminder that a well-defined research question and design do not by themselves communicate the evidential strength of a result.
The record also illustrates why descriptive safety counts need context. Counts of participants with serious adverse events and deaths are important to report, but causal interpretation requires attention to treatment assignment, follow-up, endpoint definitions, and uncertainty. Without comparative analysis details, raw counts cannot establish a treatment effect.
Statistically, the main lesson is to separate what the registry documents—the design, endpoint definitions, and event summaries—from what it does not report: the comparative primary estimate and its precision. Keeping those distinctions clear prevents a registered objective or descriptive count from being mistaken for a demonstrated treatment difference.
14. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
The most consequential limitation for interpreting the registry record is the absence of comparative primary-endpoint results. The endpoint definition and observation timeframe are reported, but arm-specific event counts and an effect estimate with uncertainty are not reported in the registry record. The primary comparison therefore cannot be quantitatively interpreted.
The description of the vitamin K antagonist regimen is incomplete: the aspirin duration ends after “up to.” The full regimen duration is not reported in the registry record. This limits the ability to describe the planned comparator completely from the posted description. The record also permits alternative antiplatelet drugs when a documented clinical need exists, so the treatment strategies are not described as identical fixed combinations for every participant.
The record does not report the detailed statistical analysis plan, sample-size justification, interim analyses, allocation concealment, or detailed adjudication procedures. It also does not report how missing outcomes or follow-up were handled, or provide comparative analyses for the listed secondary outcomes. These omissions prevent assessment of the analysis choices, multiplicity control, and robustness of any unposted findings.
The serious adverse-event and death counts are descriptive. The posted record does not give comparative uncertainty estimates for those figures or identify the deaths as treatment-related. The serious-event terms and percentages are listed without a treatment-group breakdown in the information, so they cannot be used to compare regimens for those specific terms.
Finally, the registry’s planning assumptions describe an illustration based on an observed effect, not the trial’s original design rationale. The primary comparative effect needed to interpret such an illustration is not reported in the registry record. The illustrations therefore cannot repair the missing outcome comparison or establish observed power.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Edoxaban Treatment Versus Vitamin K Antagonist in Patients With Atrial Fibrillation Undergoing Percutaneous Coronary Intervention — NCT02866175.
- Registry record last updated 2020-05-06; status last verified 2020-04.
- Results first posted 2020-05-06.
- 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 describes a completed, randomized, parallel-group Phase 3 study with no masking listed, enrolling 1506 participants. It compares an edoxaban-based antithrombotic regimen with a vitamin K antagonist-based regimen in people with atrial fibrillation following successful PCI with stent placement.
The primary outcome is the first adjudicated major or clinically relevant non-major bleeding event by ISTH definition, assessed from Day 1 to 12 months postdose in the Intent-to-Treat Analysis Set. Seven outcome measures are listed, including additional bleeding classifications, efficacy outcomes, and treatment-emergent adverse events.
Descriptive adverse-event counts are reported for both groups, including serious adverse events, other adverse events, and deaths. However, comparative primary-outcome counts, estimates, confidence intervals, and p-values are not reported in the registry record. Detailed statistical methods, missing-data handling, multiplicity procedures, and the complete aspirin duration are also not reported in the registry record.