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 ClinicalTrials.gov record.
1. Trial at a Glance
POINT was a randomized, double-blind, parallel phase 3 trial evaluating clopidogrel versus placebo in participants with transient ischemic attack. The registry reports 4881.0 participants, two treatment arms, two registered primary endpoints, and formal statistical analyses for all 13 posted outcome measures.
| Feature | POINT |
|---|---|
| Trial name | Platelet-Oriented Inhibition in New TIA and Minor Ischemic Stroke (POINT) Trial |
| Phase | Phase 3 |
| Status | Terminated |
| Condition | Ischemic Attack, Transient |
| Design | Randomized, double-blind, parallel |
| Allocation | Randomized |
| Primary purpose | Treatment |
| Enrollment | 4881.0 |
| Interventions | Clopidogrel; placebo |
| Primary endpoints | Composite of Ischemic Stroke, Myocardial Infarction, or Death From Ischemic Vascular Causes; Major Hemorrhage |
| Primary endpoint type | Binary in the registry profile; formal posted analyses use time-to-event methods |
| Statistical method posted | Log-rank test |
| Effect measure posted | Hazard ratio |
| Hypothesis type | Superiority |
| Lead sponsor | University of California, San Francisco |
| ClinicalTrials.gov | NCT00991029 |
2. Clinical Question
The statistical question is whether participants assigned to clopidogrel differed from those assigned to placebo with respect to the registered primary efficacy endpoint and the registered primary safety endpoint during up to 90 days of follow-up.
Population
Participants in a phase 3 trial whose listed condition was ischemic attack, transient.
Intervention
Clopidogrel.
Comparator
Placebo.
Primary question
How does clopidogrel compare with placebo for the time to the registered primary efficacy and major-hemorrhage endpoints through 90 days?
3. Trial Design
Clopidogrel
- Intervention type: drug
- Compared directly with placebo
- Primary efficacy and safety endpoints analyzed through up to 90 days
Placebo
- Intervention type: drug
- Comparator for clopidogrel
- Primary efficacy and safety endpoints analyzed through up to 90 days
The ClinicalTrials.gov record identifies the study as randomized, double-blind, and parallel. These design features are important statistically because randomization creates the basis for a comparative treatment analysis, while double-blinding is intended to reduce the influence of knowledge of treatment assignment on trial conduct and assessment.
4. Trial Timeline
Trial start
The registry lists 2010-05-28 as the study start date.
Primary completion
The registry lists 2018-04-09 as the primary completion date.
Terminated
The ClinicalTrials.gov record identifies the study status as TERMINATED.
5. Primary Endpoints
| Endpoint | Registry definition | Time frame | Posted analysis |
|---|---|---|---|
| Composite of Ischemic Stroke, Myocardial Infarction, or Death From Ischemic Vascular Causes | Primary efficacy outcome: Number of Participants with Ischemic Stroke, Myocardial Infarction, or Death From Ischemic Vascular Causes | Up to 90 days | Log Rank; hazard ratio; superiority |
| Major Hemorrhage | Primary safety outcome: Number of Participants with major hemorrhage | Up to 90 days | Log Rank; hazard ratio; superiority |
An important statistical detail is visible in the ClinicalTrials.gov record: the registry profile describes the two primary endpoints as binary, while the formal statistical analyses posted for them classify the endpoints as time-to-event and use the log-rank test with a hazard ratio. That distinction matters because a binary analysis asks whether an event occurred by a specified time, whereas a time-to-event analysis also uses information about when the event occurred and can account for censoring.
6. Statistical Methodology
Log-rank test
The posted formal analyses for the primary endpoints and the other listed time-to-event outcomes use the log-rank test. The log-rank framework compares event-time distributions between treatment groups over the period of follow-up.
Conceptually, the test asks whether the observed pattern of event times differs between the randomized groups over follow-up. The registry reports the corresponding effect measure as a hazard ratio.
Hazard ratio
The reported effect measure for the formal analyses is the hazard ratio (HR). An HR below 1 indicates a lower estimated instantaneous event rate in the clopidogrel group relative to placebo under the time-to-event model; an HR above 1 indicates a higher estimated instantaneous event rate.
The HR is a relative time-to-event measure. It is not itself an absolute risk difference, a probability of benefit, or the percentage of participants who experienced the event.
Confidence intervals
Every primary analysis in the ClinicalTrials.gov record has a two-sided 95% confidence interval. The interval describes statistical uncertainty around the estimated hazard ratio under the analysis framework. It does not describe the range of effects that individual participants experience.
Superiority testing
The primary analyses are identified as superiority analyses. Thus, the inferential question is whether the treatment groups differ, rather than whether clopidogrel meets a prespecified non-inferiority margin.
Analysis population and censoring
The ClinicalTrials.gov record identifies the formal endpoints as time-to-event outcomes but do not provide a separate analysis-population definition, censoring rules, missing-data strategy, stratification factors, or Bayesian analysis. Those elements therefore are not specified on this page. For a time-to-event analysis, participants who do not experience the event during observed follow-up can contribute information up to their censoring time, but the exact censoring rules for POINT are not reported in the ClinicalTrials.gov record.
7. Primary Efficacy Result
Composite of Ischemic Stroke, Myocardial Infarction, or Death From Ischemic Vascular Causes
Hazard ratio for the primary efficacy endpoint
95% CI: 0.59–0.95 · P = 0.02
Clopidogrel vs placebo · Up to 90 days
| Endpoint | Groups compared | Method | Effect estimate | 95% CI | P-value |
|---|---|---|---|---|---|
| Composite of Ischemic Stroke, Myocardial Infarction, or Death From Ischemic Vascular Causes | Clopidogrel vs Placebo | Log Rank | HR 0.75 | 0.59–0.95 | 0.02 |
An HR of 0.75 means that the estimated instantaneous rate of experiencing the composite endpoint was approximately 75% as high with clopidogrel as with placebo under the reported time-to-event analysis. Equivalently, this corresponds to a 25% lower estimated hazard for the composite endpoint.
The HR does not mean that 25% of participants benefited, that the absolute probability of the composite endpoint was reduced by 25 percentage points, or that every participant experienced the same proportional reduction.
The 95% CI of 0.59–0.95 describes the precision of the estimated relative effect. Because the interval lies below 1, it is consistent with a lower estimated hazard in the clopidogrel group under this analysis. The interval does not tell us how much benefit any particular participant would experience.
The P-value of 0.02 addresses statistical evidence against the relevant null hypothesis under the reported testing framework. It does not measure the magnitude of the treatment effect. Effect magnitude and precision are better conveyed by the HR and its confidence interval.
The ClinicalTrials.gov record does not report the number of events in each treatment arm, median event-free time, Kaplan-Meier estimates, censoring counts, or proportional-hazards diagnostics. Those quantities therefore cannot be inferred from the HR and P-value alone.
8. Primary Safety Result
Major Hemorrhage
Hazard ratio for major hemorrhage
95% CI: 1.10–4.87 · P = 0.02
Clopidogrel vs placebo · Up to 90 days
| Endpoint | Groups compared | Method | Effect estimate | 95% CI | P-value |
|---|---|---|---|---|---|
| Major Hemorrhage | Clopidogrel vs Placebo | Log Rank | HR 2.32 | 1.10–4.87 | 0.02 |
An HR of 2.32 means that the estimated instantaneous rate of major hemorrhage was approximately 2.32 times as high with clopidogrel as with placebo under the reported time-to-event analysis. Expressed as a relative comparison, this is an approximately 132% higher estimated hazard.
The HR does not mean that 2.32 times as many participants necessarily experienced major hemorrhage, because a hazard ratio is not a risk ratio and does not directly provide absolute event probabilities.
The 95% CI of 1.10–4.87 indicates substantial uncertainty around the estimated relative hazard. Its lower and upper limits are both above 1, while the width of the interval shows that the point estimate should not be treated as an exact measure of the underlying effect.
The P-value of 0.02 describes evidence against the null hypothesis under the posted superiority analysis. It does not quantify the clinical importance of hemorrhage, nor does it tell us the absolute frequency of major hemorrhage.
Because the ClinicalTrials.gov record does not provide event counts for this endpoint, absolute risks and numbers needed to treat or harm cannot be calculated from the ClinicalTrials.gov record without introducing outside data.
9. Secondary Endpoint Results
The registry reports formal statistical analyses for six secondary outcomes in the ClinicalTrials.gov record. Each uses the log-rank test, compares clopidogrel with placebo, reports a hazard ratio, and identifies the hypothesis type as superiority.
| Secondary endpoint | Time frame | HR | 95% CI | P-value |
|---|---|---|---|---|
| Ischemic Stroke | Up to 90 days | 0.72 | 0.56–0.92 | 0.01 |
| Myocardial Infarction | Up to 90 days | 1.44 | 0.55–3.78 | 0.46 |
| Death From Ischemic Vascular Causes | Up to 90 days | 1.51 | 0.43–5.35 | 0.52 |
| Ischemic or Hemorrhagic Stroke | Up to 90 days | 0.74 | 0.58–0.94 | 0.01 |
| Composite of Ischemic Stroke, Myocardial Infarction, Death From Ischemic Vascular Causes, or Major Hemorrhage | Up to 90 days | 0.84 | 0.67–1.05 | 0.13 |
| Death From Any Cause | up to 90 days | 1.51 | 0.73–3.13 | 0.27 |
Reading the secondary results together
The secondary results are not all in the same direction. The hazard ratio for ischemic stroke is 0.72, while the hazard ratios for myocardial infarction and death from ischemic vascular causes are 1.44 and 1.51, respectively. The confidence intervals for those latter two endpoints are wide and include 1.
The combined ischemic-or-hemorrhagic stroke endpoint has an HR of 0.74, with a 95% CI of 0.58–0.94 and P = 0.01. The broader composite that also includes major hemorrhage has an HR of 0.84, with a 95% CI of 0.67–1.05 and P = 0.13.
These comparisons illustrate why individual component endpoints should not automatically be treated as interchangeable with a prespecified composite endpoint. A composite can behave differently from one component because its treatment effect reflects the combined occurrence of all components.
10. Other Pre-Specified Endpoint Results
The ClinicalTrials.gov record also report formal analyses for five other pre-specified outcomes. They use the same log-rank/hazard-ratio framework unless otherwise noted.
| Outcome | Time frame | HR | 95% CI | P-value |
|---|---|---|---|---|
| Hemorrhagic Stroke | up to 90 days | 1.68 | 0.4–7.03 | 0.47 |
| Symptomatic Intracerebral Hemorrhage | up to 90 days | 1.01 | 0.14–7.14 | 0.99 |
| Major Hemorrhage Other Than Intracranial Hemorrhage | up to 90 days | 2.45 | 1.01–5.9 | 0.04 |
| Minor Hemorrhage | up to 90 days | 3.12 | 1.67–5.83 | <0.001 |
| Death From Any Cause | up to 90 days | 1.51 | 0.73–3.13 | 0.27 |
| Other Symptomatic Intracranial Hemorrhage | up to 90 days | Not reported | Not reported | 0.16 |
The ClinicalTrials.gov record does not provide an effect estimate or confidence interval for Other Symptomatic Intracranial Hemorrhage; only the P-value of 0.16 is reported. It would therefore be inappropriate to reconstruct an HR or confidence interval from the P-value.
11. Safety Results
The ClinicalTrials.gov record provides serious adverse events by treatment arm as affected participants divided by participants at risk.
| Safety measure | Clopidogrel | Placebo |
|---|---|---|
| Serious adverse events | 382 / 2432 | 382 / 2449 |
The affected-participant counts are identical at 382 in the two arms, while the reported numbers at risk are 2432 for clopidogrel and 2449 for placebo. The ClinicalTrials.gov record does not provide a formal comparative statistical analysis for serious adverse events, so no relative-risk, hazard-ratio, or P-value should be inferred from these counts alone.
12. Statistical Methods Explained
Why was a log-rank test used?
The formal analyses classify the endpoints as time-to-event outcomes. The log-rank test is designed to compare the timing of events between two groups across follow-up rather than simply classifying each participant as an event or non-event at the end of observation.
What does an HR of 0.75 mean?
For the primary efficacy endpoint, an HR of 0.75 indicates an estimated instantaneous event rate approximately 75% as high in the clopidogrel group as in the placebo group under the reported model. It corresponds to a 25% lower estimated hazard, not a 25-percentage-point reduction in absolute risk.
What does an HR of 2.32 mean?
For major hemorrhage, an HR of 2.32 indicates an estimated instantaneous event rate approximately 2.32 times that in the placebo group. It does not tell us the absolute number or proportion of participants who experienced major hemorrhage.
Why does the confidence interval matter?
The point estimate is only one summary of the treatment comparison. For the primary efficacy endpoint, the 95% CI is 0.59–0.95; for major hemorrhage, it is 1.10–4.87. The width of each interval conveys information about statistical precision that the HR alone cannot provide.
Why doesn't the P-value measure effect size?
A P-value quantifies evidence against a specified null hypothesis within a statistical testing framework. It is affected by both the observed data and the amount of information available. The magnitude of an effect is better described by the HR, while its uncertainty is described by the confidence interval.
Why are composite endpoints statistically important?
The primary efficacy endpoint combines ischemic stroke, myocardial infarction, and death from ischemic vascular causes. A composite can increase the number of observed events, but its interpretation depends on all of its components. A treatment effect on the composite should not automatically be assumed to be identical for every component.
What does the registry not tell us?
The ClinicalTrials.gov record does not report Kaplan-Meier event probabilities, median event times, treatment-group event counts for the primary endpoints, proportional-hazards diagnostics, censoring rules, missing-data procedures, stratification factors, Bayesian methods, crossover, or a formal multiplicity-adjustment strategy. Those features should not be invented from the reported HRs and P-values.
13. Interpreting Hazard Ratios Carefully
The primary efficacy HR of 0.75 describes a relative time-to-event comparison. Without absolute event probabilities or event counts by treatment group, it cannot be converted into an absolute risk reduction from the ClinicalTrials.gov record.
The major-hemorrhage HR of 2.32 is above 1, whereas the primary efficacy HR of 0.75 is below 1. Statistically, this illustrates that efficacy and safety endpoints can show different treatment effects and should be examined separately.
The efficacy interval of 0.59–0.95 is narrower than the major-hemorrhage interval of 1.10–4.87 on the HR scale. This difference indicates that the major-hemorrhage estimate is less precise in the registry-reported analysis, even though both P-values are 0.02.
The primary efficacy and major-hemorrhage analyses both report P = 0.02, but their estimated effects are in opposite directions and have different confidence intervals. Equal P-values do not imply equal effect sizes, equal clinical importance, or equal precision.
14. Caution About the Proportional-Hazards Interpretation
A single hazard ratio is a compact summary of a time-to-event comparison. In many survival analyses, its interpretation is clearest when the relative hazards are reasonably stable over time. The registry-reported POINT data do not provide a proportional-hazards diagnostic, time-varying effect analysis, or the underlying event-time data.
Accordingly, the HRs on this page should be interpreted as the reported hazard-ratio estimates from the registry analyses, rather than as proof that the hazard ratio was constant throughout the full 90-day period.
15. Primary Endpoint Results at a Glance
| Primary endpoint | Direction of HR | HR | 95% CI | P-value | Statistical interpretation |
|---|---|---|---|---|---|
| Composite of Ischemic Stroke, Myocardial Infarction, or Death From Ischemic Vascular Causes | Below 1 | 0.75 | 0.59–0.95 | 0.02 | Lower estimated hazard with clopidogrel under the reported superiority analysis |
| Major Hemorrhage | Above 1 | 2.32 | 1.10–4.87 | 0.02 | Higher estimated hazard with clopidogrel under the reported superiority analysis |
16. What the Secondary Results Add
The secondary analyses provide a more granular view of the components and related outcomes. The ischemic stroke HR of 0.72 is below 1, while the myocardial infarction HR of 1.44 and death from ischemic vascular causes HR of 1.51 are above 1. Their confidence intervals are broad enough that the latter two estimates include 1.
The broader stroke endpoint has an HR of 0.74, while the four-component composite that adds major hemorrhage has an HR of 0.84. These differences illustrate a fundamental property of composite outcomes: adding an endpoint with a different treatment effect can change the overall estimate.
The hemorrhage outcomes provide another important statistical pattern. Major hemorrhage other than intracranial hemorrhage has an HR of 2.45 with a 95% CI of 1.01–5.9, while minor hemorrhage has an HR of 3.12 with a 95% CI of 1.67–5.83. The point estimates are not interchangeable with the primary major-hemorrhage HR because they represent different registered outcomes.
17. Limitations
- Limited absolute information: the statistical analyses posted on ClinicalTrials.gov provide HRs, confidence intervals, and P-values but do not provide event counts by treatment group for the primary endpoints.
- No Kaplan-Meier estimates: the ClinicalTrials.gov record does not include survival probabilities or cumulative event probabilities at specific times.
- No median event times: median time to event is not reported in the ClinicalTrials.gov record.
- Unreported censoring rules: the ClinicalTrials.gov record does not specify how censoring was handled for the posted analyses.
- Unreported proportional-hazards diagnostics: no assessment of the proportional-hazards assumption is included in the ClinicalTrials.gov record.
- Multiplicity information is incomplete: 13 statistical analyses are posted, but the ClinicalTrials.gov record does not identify an alpha-allocation or multiplicity-adjustment procedure.
- Secondary endpoints are not equivalent to primary endpoints: secondary and other pre-specified analyses should be interpreted according to their stated role rather than being treated as additional primary outcomes.
- Some estimates are imprecise: several secondary outcomes have wide confidence intervals, particularly myocardial infarction, death from ischemic vascular causes, hemorrhagic stroke, and symptomatic intracerebral hemorrhage.
- Incomplete safety comparisons: serious adverse event counts are provided by arm, but the ClinicalTrials.gov record does not provide a formal statistical comparison for that safety measure.
- No analysis-population details: the ClinicalTrials.gov record does not specify an ITT, per-protocol, or as-treated definition for each analysis.
- No missing-data strategy: imputation procedures are not reported in the ClinicalTrials.gov record.
- No Bayesian analysis: Bayesian methods are not identified in the statistical analyses posted on ClinicalTrials.gov.
18. Why This Trial Matters Statistically
POINT is a useful teaching case because its registry results illustrate how a randomized clinical trial can simultaneously report efficacy and safety endpoints using the same time-to-event framework while producing treatment effects in different directions.
| Concept | How it appears in POINT |
|---|---|
| Randomization | The trial is identified as randomized with two treatment arms. |
| Double-blinding | The study is classified as double-blind. |
| Parallel-group design | The design model is parallel. |
| Time-to-event analysis | The posted formal analyses classify the outcomes as time-to-event. |
| Log-rank test | The registry reports Log Rank for the formal statistical analyses. |
| Hazard ratio | The effect measure reported for the formal analyses is hazard ratio. |
| Confidence intervals | Both primary analyses report two-sided 95% confidence intervals. |
| Superiority testing | The primary analyses are identified as superiority analyses. |
| Composite endpoint | The primary efficacy endpoint combines ischemic stroke, myocardial infarction, and death from ischemic vascular causes. |
| Safety endpoint | Major hemorrhage is a registered primary endpoint. |
| Component outcomes | Secondary analyses separately examine ischemic stroke, myocardial infarction, and death from ischemic vascular causes. |
| Multiple analyses | The ClinicalTrials.gov record contains 13 posted statistical analyses. |
19. Clinical Interpretation vs Statistical Interpretation
Statistical interpretation
The primary efficacy analysis reports HR 0.75 (95% CI 0.59–0.95; P = 0.02), while the primary major-hemorrhage analysis reports HR 2.32 (95% CI 1.10–4.87; P = 0.02). These estimates describe different endpoints and move in opposite directions.
Clinical interpretation
The ClinicalTrials.gov record supports separate consideration of ischemic outcomes and hemorrhagic outcomes. They do not provide enough absolute event information to calculate an absolute benefit-risk balance from the registry results alone.
20. Reading the Two Primary Endpoints Together
The POINT registry results are particularly instructive because the two primary endpoints are not simply two measures of the same phenomenon. The first is a composite efficacy endpoint involving ischemic stroke, myocardial infarction, or death from ischemic vascular causes. The second is major hemorrhage, a safety outcome.
The efficacy HR of 0.75 and the safety HR of 2.32 therefore should not be mathematically combined into a single score or treated as if one cancels the other. A proper statistical interpretation preserves the endpoint definitions and evaluates each estimate on its own scale.
A P-value alone is insufficient. For POINT, the endpoint definition and the direction and precision of the hazard ratio materially change the interpretation of the reported evidence.
21. Related Tutorials
Learn more about the methods used in this trial:
22. Related Statistical Calculators
23. Sources
- ClinicalTrials.gov: POINT — NCT00991029. Official trial registry record and source for the trial data analyzed on this page.
- PubMed: PMID 41717934.
- PubMed: PMID 39222701.
- PubMed: PMID 38174567.
- PubMed: PMID 35538232.
- PubMed: PMID 35043692.
Continue through the Clinical Biostats statistical pathway
Use the related tutorials and calculators to explore the survival-analysis concepts illustrated by POINT, including hazard ratios, confidence intervals, log-rank testing, and time-to-event endpoints.
24. Record Summary
POINT is a randomized, double-blind, parallel phase 3 trial with 4881.0 enrolled participants and two treatment arms, clopidogrel and placebo. The ClinicalTrials.gov record reports formal time-to-event analyses using the log-rank test and hazard ratios for two primary endpoints and additional secondary and other pre-specified outcomes.
For the primary efficacy endpoint, the reported HR was 0.75 (95% CI 0.59–0.95; P = 0.02), corresponding to a 25% lower estimated hazard under the reported model. For major hemorrhage, the reported HR was 2.32 (95% CI 1.10–4.87; P = 0.02), corresponding to an approximately 132% higher estimated hazard. The secondary results show that treatment effects varied across individual ischemic and hemorrhagic outcomes, reinforcing the importance of preserving endpoint definitions rather than reducing the trial to a single statistic.