Individualizing Dual Antiplatelet Therapy After Percutaneous Coronary Intervention - The IDEAL-PCI Registry: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Individualizing Dual Antiplatelet Therapy After Percutaneous Coronary Intervention - The IDEAL-PCI Registry (NCT01515345), a non-randomized phase 3 study. The primary outcome is Definite Stent Thrombosis.

2. Clinical Question

Statistically, the central question is whether the observed endpoint experience differs between the treatment strategies, and how precisely any difference can be estimated. The available record identifies the groups and endpoint but does not report primary endpoint counts, effect estimates, confidence intervals, or a significance test. Consequently, the registry information supports describing the question and design, but not quantifying the primary outcome comparison.

3. Trial Design

IDEAL-PCI is recorded as a phase 3, parallel, nonrandomized, unmasked study. Its status is completed. The registry lists enrollment as 1008 and gives a start date of 2011-07 and primary completion date of 2013-01. The sponsor is Kaiser Franz Josef Hospital. These registry descriptors characterize the study, but do not establish how participants were assigned to the arms.

The two arm descriptions are standard therapy and individualized therapy. Standard therapy is described as standard dual antiplatelet therapy after PCI for stable CVD and ACS populations. Individualized therapy is described as dual antiplatelet therapy modified according to clopidogrel on-treatment platelet reactivity measured by the Multiplate Analyzer. The intervention listings include prasugrel or ticagrelor and clopidogrel. The registry record does not provide further detail about treatment selection, dosing, adherence, or how a platelet reactivity result led to a specific medication change.

Nonrandomized allocation is important to interpretation. Without random assignment, the characteristics that led clinicians or participants to receive a particular strategy may also relate to outcomes. Differences between the groups could therefore reflect treatment strategy, differences in underlying risk, or other factors. The record does not report an adjustment method that would address such differences. It specifically identifies the arms as not being a like-for-like control comparison.

The primary endpoint is definite stent thrombosis at 30 days. Probable stent thrombosis is listed as a secondary outcome. The record also lists three outcome measures and no analysis records. The protocol’s sample-size justification, allocation procedures, masking procedures beyond the unmasked designation, and statistical analysis plan 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.

Overall Study

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 Definite Stent Thrombosis, measured over 30 days.

The primary endpoint is definite stent thrombosis, reported as a count of participants, with a timeframe of 30 days. The registry defines definite stent thrombosis as angiographic or pathological confirmation of stent thrombosis. The posted definition therefore emphasizes confirmation through specified diagnostic evidence rather than relying only on a suspicion or symptom description.

In general, a clearly defined endpoint helps researchers determine which events are counted consistently. A confirmed event can be more specific than a broader clinical category, although the record does not provide details about event adjudication, diagnostic procedures, or the criteria used to classify individual cases. Those details are not reported in the registry record.

The endpoint is clinically focused on a complication related to coronary stent implantation, while its binary form records whether a participant had the event during the stated timeframe. For a binary endpoint, a group comparison may be described using event counts and an effect measure such as a risk difference or relative measure. Such measures require the relevant outcome data and a defined analysis. The registry information does not report primary endpoint counts by arm or an estimated treatment contrast, so no numerical conclusion about this endpoint can be drawn.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

For a binary endpoint such as definite stent thrombosis, the basic data are whether each participant experienced the event during the specified timeframe. A group’s event count is meaningful alongside the number of participants included in that endpoint analysis. A comparison can then be expressed as an absolute difference or a relative measure. The choice of measure affects how the result is interpreted: an absolute difference describes separation in event probability, while a relative measure describes one probability in relation to another. The registry record does not report primary endpoint counts, denominators, or a treatment-effect estimate, so none of these comparisons can be reconstructed.

General statistical explanation: an estimate is a summary of the observed data, while a confidence interval conveys uncertainty around that estimate under the assumptions of the chosen method. The interval does not guarantee that the true effect lies within its bounds. Its usefulness depends on sound outcome measurement, appropriate analysis, and an adequate treatment of the study design. No primary endpoint confidence interval is reported in the registry record.

A p-value is a measure of how compatible observed data are with a specified null hypothesis under a statistical model. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of an effect. A p-value requires a defined analysis and assumptions. The record lists no analysis records, and a primary endpoint p-value is not reported in the registry record.

Nonrandomized treatment allocation creates a risk of confounding. In general, confounding occurs when a factor related to treatment choice is also related to the outcome. For example, clinicians may choose a treatment strategy based on clinical information; if that information also predicts the endpoint, a simple unadjusted comparison can combine treatment differences with baseline risk differences. Statistical adjustment can sometimes reduce measured confounding when suitable variables and methods are available, but it cannot ensure control of unmeasured confounding. The registry record does not report an adjusted analysis or its covariates.

The registry identifies the study as unmasked. Lack of masking can matter when knowledge of treatment influences care, outcome assessment, or reporting. The primary endpoint definition involves angiographic or pathological confirmation, but the record does not describe who assessed events or whether event classification was blinded. It would be speculative to infer how masking or adjudication was handled beyond the registry’s unmasked designation.

The record gives planning assumptions for sample-size illustrations: a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. It states that the effect to detect is expressed as a fraction of the observed effect. These are assumptions for planning illustrations, not a description of the trial’s own design rationale. The sample-size justification for the registry study is not reported in the registry record. A planning calculation based on an observed effect is not observed power and does not establish that the study was adequately powered for its endpoint.

General explanation: power is the probability that a specified design and analysis will detect an effect of a stated size under its assumptions. It depends on the assumed effect, outcome frequency, variability, allocation, significance level, and analysis. A retrospective power calculation based on an observed estimate is not a replacement for a confidence interval: it does not clarify the precision of the observed effect. The listed planning assumptions alone do not give an endpoint-specific power result or justify a conclusion about the primary analysis.

Equal allocation is an assumption in the sample-size illustrations, not a description of the observed arm sizes. The study itself is nonrandomized, and the registry record does not say that participants were allocated equally. The record also does not report interim analyses, stopping rules, a prespecified covariate strategy, or a detailed statistical analysis plan. These details should not be inferred from the phase designation or from the listed planning assumptions.

Over-dispersion is a general concern when observed variation exceeds what a statistical model assumes. It is relevant to models for outcomes where counts or repeated observations have more variability than the model allows, and can lead to uncertainty estimates that are too small if ignored. The primary endpoint is recorded as a binary participant outcome, and the registry does not report a model or indicate that over-dispersion was assessed. It is therefore not possible to say whether that issue arose in this study.

Missing outcome data can affect an estimate if participants without observed outcomes differ systematically from those with complete follow-up. Analysis populations, exclusions, and methods for handling missing data are not described in the registry record. Without those details, readers cannot assess whether the primary endpoint analysis included all enrolled participants, only those with observed outcome status, or another population. The enrollment count should not be treated as the endpoint analysis denominator.

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("Standard Therapy", "Individualized Therapy")
n      <- c(664, 343)
events <- c(1, 0)
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  Standard Therapy  664  1  0.2  0.0  0.8  0.0  0.8  0.0  0.8
ARM  Individualized Therapy  343  0  0.0  0.0  1.1  0.0  1.1  0.0  1.1

11. Multiplicity, Missing Data and Analysis Populations

The registry lists three outcome measures, with definite stent thrombosis identified as the primary outcome and probable stent thrombosis listed as a secondary outcome. The remaining outcome measure details are not reported in the registry record. The record lists no analysis records and does not describe a statistical plan for controlling multiplicity.

In general, multiplicity arises when several outcomes, comparisons, or analyses are tested. Considering many tests can increase the chance of at least one apparently unusual result, so a plan may specify which outcome is primary and whether adjustments or hierarchical testing will be used. The primary designation helps distinguish the main question from secondary outcomes, but does not show how multiplicity was handled. No adjustment method or testing sequence is reported in the registry record.

Details about missing observations, follow-up completeness, exclusions, and analysis populations are also not reported in the registry record. These matters affect which participants contribute to an outcome estimate and how representative that estimate may be. The group-specific at-risk counts in the serious adverse-event listing should not be assumed to be the denominators for the primary outcome analysis.

The record does not report interim analyses, missing-data assumptions, imputation methods, or sensitivity analyses. Without this information, the robustness of any outcome analysis to missingness or analytic choices cannot be evaluated. No assumptions about these procedures should be inferred from the completed status of the study.

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 0% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: cardiovascular death (2.6%), bleeding (timi minor) (1.7%), bleeding (timi major) (1.2%), probable stentthrombosis (0.3%), definite stentthrombosis (0.2%).

The serious adverse-event listing reports 26 affected among 664 at risk in the Standard Therapy group and 18 affected among 343 at risk in the Individualized Therapy group. These are the figures recorded for the two groups; the registry does not provide a formal adjusted comparison, confidence intervals, or a significance test for them. No rate difference should be inferred without an appropriate analysis.

The registry also lists serious-event terms with percentages: Cardiovascular death, 2.6%; Bleeding (TIMI minor), 1.7%; Bleeding (TIMI major), 1.2%; probable Stentthrombosis, 0.3%; and Definite stentthrombosis, 0.2%. The record does not give group-specific figures or denominators for these terms, nor does it explain how they relate to the group-level affected counts. They should not be treated as direct comparisons between treatment arms.

In general, safety data require attention to definitions, observation periods, denominators, and whether the listing counts participants, events, or both. The record labels these as serious adverse events but does not provide further detail about event collection or attribution. The listed figures are descriptive and do not establish that a treatment caused or prevented an event. The nonrandomized design is an additional limitation for comparing safety across arms.

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

The record describes a clinical question about individualized dual antiplatelet therapy after coronary stent implantation. In the individualized arm, treatment was modified according to clopidogrel on-treatment platelet reactivity measured by a Multiplate Analyzer. The registry’s stated purpose was to evaluate efficacy and safety, and the primary endpoint was definite stent thrombosis at 30 days.

What the record does not establish is whether the primary endpoint differed between the strategies. Primary endpoint counts by arm and a numerical estimate of the comparison are not reported in the registry record. The serious adverse-event figures are descriptive and are not a substitute for the primary outcome analysis. They also do not support a causal conclusion about safety.

The nonrandomized design means that treatment groups may differ for reasons related to treatment selection. Even if an outcome contrast were available, it would need to be interpreted in light of possible confounding, endpoint measurement, and any analytic adjustments. The registry does not report an adjusted analysis, its assumptions, or analysis populations. Thus, neither causation nor the robustness of a treatment comparison can be assessed from the reported information.

General statistical interpretation distinguishes the presence of an observed pattern from the precision and causal meaning of that pattern. A confidence interval can describe estimation uncertainty, while design and analysis assumptions shape whether the estimate is interpretable. The primary endpoint’s effect estimate and interval are not reported in the registry record, so its precision cannot be evaluated.

The findings described in the record should therefore be read as information about the study’s purpose, structure, endpoint definition, and limited safety listings. They do not establish that individualized therapy is superior, equivalent, or inferior to standard therapy. The record also does not support treatment recommendations. These conclusions would require results and methodological details that are not reported in the registry record.

14. Why This Trial Matters Statistically

This study raises a statistically important question about how treatment strategies can be compared when therapy is individualized using a measured biological response. The registry describes modification of dual antiplatelet therapy according to clopidogrel on-treatment platelet reactivity measured by the Multiplate Analyzer. That strategy makes the definition of treatment, the measurement process, and the relationship between test results and treatment changes central to interpretation.

The nonrandomized design is especially important. Treatment choice may be related to clinical characteristics that also predict outcomes. A comparison between arms can therefore mix the effect of the strategy with differences in participant risk. This is a general challenge in observational comparisons, and it cannot be resolved merely by naming an outcome or reporting a group count. Adjustment methods and the information used for adjustment would need to be described and evaluated.

The endpoint is also defined in a way that emphasizes confirmation: definite stent thrombosis requires angiographic or pathological confirmation within the stated 30-day timeframe. Such operational definitions are important because consistent classification underlies meaningful outcome comparisons. The registry does not report how endpoint assessments were performed, so the measurement process cannot be fully evaluated.

Finally, the record illustrates why outcome results and design information must be considered together. The stated enrollment and safety listings do not provide the missing primary endpoint contrast or its precision. Without that result and its analysis details, the central efficacy question remains unquantified in the registry record. Statistical interpretation requires not only a well-defined question but also the outcome data, an appropriate analysis, and transparent uncertainty estimates.

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 main limitation for interpreting the primary outcome is that the registry record does not report definite stent thrombosis counts by arm, an effect estimate, a confidence interval, or a test result. The endpoint definition and timeframe are present, but the comparative result cannot be assessed.

Allocation was nonrandomized, and the record explicitly notes that the arms are not a like-for-like control comparison. Baseline characteristics, reasons for treatment selection, and methods for addressing confounding are not reported in the registry record. Any between-arm difference would therefore require caution even if the numerical result were available.

The registry describes the study as unmasked, but does not report who assessed outcomes, whether events were independently adjudicated, or how the diagnostic confirmation requirement was applied. Treatment details beyond the arm descriptions and intervention listings—including specific regimens, adherence, and decision rules—are not reported in the registry record.

Analysis populations, missing-data handling, outcome-specific denominators, and follow-up completeness are not reported. The serious adverse-event listing gives group-level affected counts and at-risk counts, but does not provide an adjusted comparison or explain the relation of the listed serious-event percentages to those group figures. These safety details cannot replace a primary endpoint analysis.

The registry lists no analysis records and does not report a detailed statistical plan, multiplicity procedures, interim analyses, or the study’s sample-size justification. The planning assumptions described for sample-size illustrations should not be mistaken for evidence about the trial’s original design or the precision of its results. Together, these gaps constrain both causal interpretation and assessment of statistical uncertainty.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Individualizing Dual Antiplatelet Therapy After Percutaneous Coronary Intervention - The IDEAL-PCI Registry — NCT01515345.
• Registry record last updated 2017-04-25; status last verified 2017-03.
• Results first posted 2013-05-01.
• 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

The IDEAL-PCI Registry is recorded as a completed, phase 3, parallel, nonrandomized, unmasked study sponsored by Kaiser Franz Josef Hospital. The registry gives enrollment as 1008, with a start date of 2011-07 and primary completion date of 2013-01.

The study concerns individualizing dual antiplatelet therapy after coronary stent implantation. The individualized strategy modified therapy according to clopidogrel on-treatment platelet reactivity measured by a Multiplate Analyzer; the comparator was standard dual antiplatelet therapy after PCI. Definite stent thrombosis at 30 days was the primary endpoint, defined by angiographic or pathological confirmation. Probable stent thrombosis was listed as a secondary outcome.

Primary endpoint results and a comparative statistical analysis are not reported in the registry record. The record includes serious adverse-event counts by arm and a list of serious-event terms, but does not report a formal adjusted safety comparison. Nonrandomized allocation and missing analysis details limit causal and precision assessments.