Phase 2 Study of Ambrisentan for Liver Function Test Rescue in Pulmonary Arterial Hypertension: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Phase 2 Study of Ambrisentan for Liver Function Test Rescue in Pulmonary Arterial Hypertension (NCT00423592), a non-randomized phase 2 study. The primary outcome is The Incidence of Confirmed Serum Alanine Aminotransferase (ALT) or Aspartate Aminotransferase (AST) Concentrations > 3 x the Upper Limit of Normal (ULN) Considered to be Related to Ambrisentan and Resulted in Discontinuation of Study Drug..

2. Clinical Question

3. Trial Design

This was a Phase 2, open-label, multicenter, single-group study of ambrisentan. The registry record classifies allocation as non-randomized and masking as none. With no randomized comparator, the design describes experience during ambrisentan treatment rather than a controlled estimate of treatment differences. The registry lists 36 participants as enrolled.

Eligible participants were described as having pulmonary arterial hypertension, including idiopathic or familial pulmonary arterial hypertension, and as having previously discontinued endothelin receptor antagonist therapy because of elevated serum ALT or AST. The prior therapies identified in the study summary were bosentan or sitaxsentan. The study's stated focus was aminotransferase elevations and overall safety and tolerability during ambrisentan therapy.

The primary endpoint was assessed during 12 weeks of therapy, with the timeframe listed as Week 12. Its population was the safety analysis set: participants who received at least one dose of study drug. The record says that participants who received at least one dose were followed, to the extent possible, to the end of the study and included in safety analyses. This description does not establish how many participants completed follow-up or had endpoint data available.

The record lists a start of 2005-05, primary completion of 2006-01, and study status of completed. It also lists 16 outcome measures and 13 analyses. Those counts alone do not identify which analyses were prespecified, how they were conducted, or whether results were adjusted for multiple comparisons. Details of randomization procedures, a control group, and masking are not applicable to the recorded single-group design; other protocol and analysis details 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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The Safety analysis set was defined as all subjects who received at least 1 dose of study drug. All subjects who received at least 1 dose of ambrisentan were followed (to the extent possible) to the end of the study and included in the analyses of safety.

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 The Incidence of Confirmed Serum Alanine Aminotransferase (ALT) or Aspartate Aminotransferase (AST) Concentrations > 3 x the Upper Limit of Normal (ULN) Considered to be Related to Ambrisentan and Resulted in Discontinuation of Study Drug., measured over Week 12.

The primary endpoint counts participants who experienced a confirmed serum ALT or AST concentration greater than 3 x the upper limit of normal during 12 weeks of ambrisentan therapy, when the elevation was considered related to ambrisentan and led to discontinuation of study drug. It is therefore a binary participant-level event summarized as a number of participants: each participant either met the full endpoint definition or did not. An enzyme elevation alone, without the stated relationship and discontinuation criteria, would not necessarily meet this endpoint definition.

This endpoint was relevant to the study's stated safety question because participants had previously stopped endothelin receptor antagonist therapy due to elevated liver enzymes. Counting events that satisfy the laboratory threshold, attribution, and discontinuation conditions provides a focused description of this particular safety outcome in the treated group. It does not capture every possible liver laboratory change or every reason for treatment discontinuation.

The defined analysis population was the safety analysis set, consisting of participants who received at least one dose. The endpoint timeframe was Week 12. The number meeting the endpoint is not reported in the registry record. Without that result, the endpoint's observed frequency and its precision cannot be described from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The study is recorded as single-group and non-randomized, with no masking. These design features determine what statistical comparisons are possible. There is no randomized control group in the record against which to estimate a treatment contrast. The main endpoint is instead framed as a count of participants experiencing a specified event while receiving ambrisentan. A count can describe what happened in the study group, but without a comparison group it does not separate treatment-associated events from events that might also occur in the absence of treatment.

What does a binary endpoint represent?

General statistical explanation: a binary endpoint classifies each participant into one of two categories, such as meeting or not meeting an event definition. The primary endpoint is expressed as the number of participants meeting all of its criteria. Those criteria combine a confirmed laboratory threshold, attribution to ambrisentan, and discontinuation of study drug. This definition is narrower than a count of all ALT or AST elevations, because the other conditions must also be met. The registry record does not report the number meeting the definition.

What does the analysis population mean?

The primary endpoint description defines the safety analysis set as participants who received at least one dose of study drug. This is a treated population, rather than simply everyone enrolled. The record also says participants who received at least one dose were followed to the extent possible and included in safety analyses. It does not report the number with complete Week 12 outcome data, the number who discontinued for other reasons, or how incomplete observations were handled. These details matter because the denominator and ascertainment of events affect how a participant count should be interpreted.

What can a one-group result establish?

General statistical explanation: a one-group event count can describe observed events in the participants followed, but it cannot by itself establish how the event rate compares with another treatment or what would have happened to the same participants under a different condition. Differences in participant characteristics, follow-up, and event ascertainment can affect comparisons across separate studies. Because this design has no randomized comparator, an unadjusted between-group treatment effect is not available from the record.

How should uncertainty be considered?

General statistical explanation: statistical estimates are subject to sampling variation. A confidence interval communicates uncertainty around an estimate, while a hypothesis test evaluates data against a specified statistical model and null hypothesis. Neither a confidence interval nor a primary endpoint hypothesis test result is reported in the registry record. The endpoint count itself is also not reported, so the magnitude and precision of the primary safety finding cannot be assessed. No test, model, or confidence-interval method for this endpoint is reported in the registry record.

What is the role of the other outcomes?

The registry lists 16 outcome measures and 13 analyses. The listed secondary outcomes cover additional liver-enzyme thresholds and changes in 6-minute walk distance, Borg Dyspnea Index, WHO Functional Class, and SF-36 scales. These are distinct measures and do not all represent the same kind of outcome. For example, the liver-enzyme outcomes concern event occurrence and treatment modification, while the other listed measures concern change from baseline after 12 weeks. Their names and timeframes do not establish which results were available or how they were analyzed. Results for these outcomes are not reported in the registry record.

What is known about planning assumptions?

The record describes planning illustrations based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect, and distinguishes total events for time-to-event illustrations from participants per arm for other illustrations. These are described as planning illustrations, not the trial's own design. The study itself is recorded as a single-group, non-randomized trial, so the two-arm allocation assumption in those illustrations should not be mistaken for the actual trial design. The illustrations are not observed power and do not establish the trial's sample-size justification. The protocol's sample-size rationale is not reported in the registry record.

More generally, model choice and analytic decisions affect estimates and uncertainty. General statistical explanation: over-dispersion occurs when variability in count data exceeds what a chosen model expects; ignoring it can make uncertainty appear smaller than it is. The registry record does not report whether count models, over-dispersion assessments, or other particular statistical methods were used. Such methods should not be attributed to this study without a reported analysis plan or results description.

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("Ambrisentan")
n      <- c(36)
events <- c(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  Ambrisentan  36  0  0.0  0.0  9.7  -0.0  9.6  0.1  9.5

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 16 outcome measures and 13 analyses, including the primary safety outcome and a range of secondary safety, exercise, symptom, functional-class, and quality-of-life outcomes. When many outcomes are examined, the chance of at least one apparently notable result can increase if each is assessed separately. General statistical explanation: multiplicity procedures can control or describe this issue, but the choice depends on the analysis plan and the intended interpretation of the outcomes.

The registry record does not report whether any multiplicity adjustment was planned or used, which outcomes were considered confirmatory, or how the 13 analyses correspond to the 16 measures. It is therefore not possible to characterize the statistical plan for multiple outcomes from the listed counts alone.

Missing-data handling is also not reported in the registry record. The primary endpoint description defines the safety analysis set as participants who received at least one dose and states that participants were followed to the extent possible. It does not give the number with endpoint data at Week 12, describe missing laboratory measurements, or explain how missing outcomes were treated. These details are needed to understand whether the available observations fully represent the intended safety population.

The analysis population is specified for the primary outcome, but other analysis populations or rules for inclusion in individual secondary analyses are not reported in the registry record. The extent to which follow-up was complete and whether missingness differed across outcomes are also not reported. These gaps limit assessment of potential bias and reproducibility.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pulmonary hypertension (13.9%), anaemia (5.6%), atrial fibrillation (5.6%), dehydration (5.6%), microcytic anaemia (2.8%).

The posted serious adverse-event information lists the ambrisentan group with 36 participants at risk and 17 affected. The record also lists serious-event terms with percentages: pulmonary hypertension, 13.9%; anaemia, 5.6%; atrial fibrillation, 5.6%; dehydration, 5.6%; microcytic anaemia, 2.8%; and acute coronary syndrome, 2.8%. These are serious adverse-event figures, not the result for the primary liver-enzyme endpoint.

Term-level percentages should be read as the recorded percentages for those terms, not added together to obtain a total. A participant may have more than one event, and the registry record does not explain whether terms overlap at the participant level. The listed terms are not a complete account of every safety outcome described in the study. The registry record does not report the primary endpoint event count, and the serious-event figures do not answer whether participants met its combined laboratory, attribution, and discontinuation criteria.

General statistical explanation: adverse-event counts and percentages describe observed events in a defined group and period; they do not alone establish that treatment caused an event or allow comparison with an unobserved control group. This study was non-randomized and single-group, so its safety information should be interpreted as descriptive experience among the participants represented in the record.

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

The registry record identifies a focused question about liver-enzyme safety in participants who had previously discontinued endothelin receptor antagonist therapy because of increased ALT or AST. It specifies a primary endpoint combining a confirmed laboratory elevation greater than 3 x the upper limit of normal, attribution to ambrisentan, and discontinuation of study drug. This definition is useful for understanding exactly what the study intended to count.

The primary endpoint result is not reported in the registry record. As a result, the record does not establish how many participants met that definition, how common the endpoint was in the study group, or how precisely its frequency could be estimated. The listed serious adverse-event information supplies broader safety context but cannot substitute for the missing primary endpoint count.

The design also limits what can be inferred. The study was open-label, non-randomized, and single-group, with no randomized comparator. A descriptive outcome in this group would not by itself show how outcomes would differ under another treatment or no treatment. Nor would a one-group observation establish that ambrisentan caused every event considered related to it; the record does not provide a controlled comparison to assess that attribution.

The registry lists secondary measures spanning liver-enzyme events, exercise capacity, dyspnea, functional class, and SF-36 scales, but their results are not reported in the registry record. Their presence does not demonstrate a change in any of these domains. Likewise, enrollment of 36 participants and the study's completion status do not supply the missing outcome estimates or their uncertainty.

The most defensible interpretation is that the registry record documents the study's question, design, endpoint definition, and some serious adverse-event figures, while leaving the primary endpoint result and several analysis details unreported. It supports a description of what was planned and what safety terms were posted, not a comparative treatment conclusion.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of how a safety question can be defined around a specific, clinically consequential event. The primary endpoint is not simply an elevated laboratory value: it requires confirmation, a stated relationship to ambrisentan, and discontinuation of study drug. Such a composite definition focuses the count on a particular outcome while also making clear that other enzyme elevations may fall outside the endpoint.

The trial also illustrates the interpretive limits of a single-group safety study. Counts from a treated group can document observed events, but they cannot provide a randomized treatment comparison. The study's open-label design and lack of masking are additional features readers should recognize when considering assessment and attribution of events. The registry record specifies these design characteristics, but does not report the primary result needed to quantify the main safety question.

The record's listing of 16 outcome measures and 13 analyses highlights why analysis plans matter when a study addresses multiple outcomes. Without information on prespecification, multiplicity, missing data, and the analyses used, readers cannot fully evaluate how results across those measures were selected or interpreted. These are not details that can be inferred from the outcome names alone.

Finally, the record distinguishes study design from planning illustrations. The stated illustrations use a two-arm allocation assumption, while the trial itself is recorded as non-randomized and single-group. Keeping those purposes separate prevents a planning scenario from being mistaken for the actual design or for observed statistical power. The record is therefore a useful case for separating endpoint definition, design, planning assumptions, and reported results.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The most direct limitation is that the primary endpoint count is not reported in the registry record. Without the count, the main safety outcome cannot be quantified or assessed for precision. The record also does not report a confidence interval or other uncertainty estimate for that endpoint.

The study was non-randomized, open-label, and single-group, with no randomized comparator. Any outcome described for participants receiving ambrisentan would therefore lack a concurrent randomized contrast. The design cannot, by itself, distinguish observed treatment-period events from the counterfactual outcomes that might have occurred under another treatment or condition.

The record lists 36 participants enrolled and 36 at risk in the ambrisentan serious adverse-event group, but does not report endpoint-specific completeness of follow-up or missing-data methods. Although the safety analysis set is defined as participants receiving at least one dose, the record does not state how many had complete primary endpoint ascertainment at Week 12 or how any missing laboratory results were handled.

The listed serious-event terms provide only part of the safety picture, and the registry record does not explain overlap among terms at the participant level. The registry names secondary outcomes, but does not report their results or the methods used to analyze them. It also does not report whether multiplicity was addressed, the protocol's sample-size justification, interim analyses, or a detailed statistical analysis plan. These omissions limit evaluation of the results and the reproducibility of the analyses.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Phase 2 Study of Ambrisentan for Liver Function Test Rescue in Pulmonary Arterial Hypertension — NCT00423592.
• Registry record last updated 2013-06-17; status last verified 2013-06.
• Results first posted 2012-06-20.
• 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 registry record describes a completed Phase 2, open-label, multicenter, non-randomized, single-group study of ambrisentan. It lists 36 participants enrolled and focuses on participants with pulmonary arterial hypertension who had previously discontinued endothelin receptor antagonist therapy because of increased ALT or AST.

The primary endpoint was the number of participants in the safety analysis set with confirmed ALT or AST concentrations greater than 3 x the upper limit of normal, considered related to ambrisentan and resulting in discontinuation of study drug during 12 weeks of therapy. The primary endpoint result is not reported in the registry record.

The posted serious adverse-event information lists 17 affected among 36 at risk in the ambrisentan group, along with several event terms and percentages. The registry lists 16 outcome measures and 13 analyses, but does not report the primary result, results for the listed secondary measures, or key details of the statistical analysis plan.