Safety And Efficacy Of Oral PF-4136309 In Patients With Chronic Hepatitis C Infection And Abnormal Liver Enzymes: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety And Efficacy Of Oral PF-4136309 In Patients With Chronic Hepatitis C Infection And Abnormal Liver Enzymes (NCT01226797), a randomized phase 2 study. The primary outcome is Percentage of Participants With a Response in Serum Alanine Aminotransferase (ALT) Level at Week 4.

2. Clinical Question

The clinical question is about a short-term laboratory response, not a direct measure of symptoms, complications, or long-term liver outcomes. ALT is an aminotransferase measured in blood; the trial’s response definition treats a reduction from baseline as the endpoint event. The registry says ALT was measured at a central laboratory and defines baseline using measurements from screening visits and pre-dose Day 1.

The posted primary results show a response in 25% of the PF-04136309 group and 36.36% of the placebo group. The unadjusted risk-difference estimate is -0.114, with a confidence interval extending from -0.489 to 0.262. These data describe the participants analyzed and the registry’s stated outcome definition; they do not establish whether the treatment changes health outcomes beyond this laboratory measure. The registry record does not report why the study was terminated or give a treatment rationale beyond evaluating efficacy and safety.

3. Trial Design

This was a randomized, double-blind, placebo-controlled phase 2 study of oral PF-04136309 in people with chronic hepatitis C infection and raised aminotransferases. The registry records quadruple masking, meaning the record identifies the study as masked at four levels, but it does not report which specific roles those levels covered. The official title specifies PF-04136309 500 mg twice daily. The intervention and comparator were PF-04136309 and placebo.

The registry records enrollment of 24 and lists the study status as terminated. The recorded start date is 2011-01-17, and the primary completion date is 2012-02-09. The reason for termination, whether recruitment or follow-up ended as planned, and the original enrollment target are not reported in the registry record. Nor is the original statistical design justification reported.

The primary endpoint was the percentage of participants with a response in serum ALT at Week 4. The registry defines a response as a reduction of at least 30% from baseline. The primary analysis population is described as the Full Analysis Set: randomized participants with a baseline value and at least one post-baseline value. Missing data were imputed using last observation carried forward (LOCF).

For the primary outcome, the posted results give an analysis group size of 12 for PF-04136309 and 11 for placebo. The safety results list 12 participants at risk in each group. These are the group counts attached to different reported analyses; the registry record does not explain the difference between the efficacy analysis counts and the safety counts. A protocol, detailed schedule of visits, and explanation of the termination are not reported in the registry record. The design labels therefore describe the recorded framework, while the available numerical results remain limited to the posted outcomes and analyses.

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: Full Analysis Set (FAS): all randomized participants who had a baseline value and at least 1 post-baseline value. Missing data was imputed using last observation carried forward (LOCF).

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 Percentage of Participants With a Response in Serum Alanine Aminotransferase (ALT) Level at Week 4, measured over Week 4.

The primary endpoint is the percentage of participants with a response in serum alanine aminotransferase (ALT) at Week 4. A responder was defined as a participant whose ALT fell by at least 30% from baseline. Baseline was defined as the mean of measurements from screening visits 1 and 2 and pre-dose Day 1; ALT was determined at a central laboratory.

This endpoint turns a continuous laboratory measurement into a binary outcome: each participant either meets the response definition or does not. The resulting percentage is the share of the analyzed group classified as a responder. Such a threshold can make a result easier to interpret as the frequency of a prespecified change, but it does not retain all information about the size of each participant’s ALT change. Two participants with different reductions may both count as responders if each passes the threshold, while a reduction just short of the cutoff is classified as no response.

As a general statistical point, a threshold-based response endpoint can be useful when a meaningful level of change has been defined in advance. However, the registry record does not explain how the 30% threshold was selected or report evidence that it corresponds to a patient-important benefit. ALT is a laboratory marker, so the result should be read as evidence about the defined Week 4 laboratory response, rather than as a direct measure of symptoms or longer-term clinical outcomes.

7. Results Posted in the Registry

• PF-04136309: 25.0% (3/12) versus 36.4% (4/11) on control; risk difference -11.4 percentage points (95% CI -48.9 to 26.2), risk ratio 0.69 (0.20–2.41); unadjusted two-proportion z-test p = 0.554.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Percentage of Participants With a Response in Serum Aspartate Aminotransferase (AST) Level From Baseline at Week 4

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • PF-04136309: 8.3% (1/12) versus 36.4% (4/11) on control; risk difference -28.0 percentage points (95% CI -60.5 to 4.4), risk ratio 0.23 (0.03–1.75); unadjusted two-proportion z-test p = 0.104.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between PF-04136309 and the control. The interval gives the range of effects that remain compatible with the data.

Serum ALT at Baseline

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • PF-04136309: mean 132.20 versus 154.70 on control; difference -22.50 (95% CI -81.93 to 36.93), standardized effect d = -0.31; z-test p = 0.458.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between PF-04136309 and the control. The interval gives the range of effects that remain compatible with the data.

Serum AST at Baseline

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • PF-04136309: mean 96.60 versus 110.60 on control; difference -14.00 (95% CI -53.20 to 25.20), standardized effect d = -0.29; z-test p = 0.484.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between PF-04136309 and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists secondary outcomes that extend the assessment beyond the primary Week 4 ALT response. They include AST response at Week 4, ALT and AST measurements and changes across several weeks, a methacetin breath-test measure, an enhanced liver fibrosis test, and maximum observed plasma concentration of PF-04136309. These outcomes cover additional laboratory, liver-function, and pharmacokinetic questions. The posted secondary results include a mixture of endpoint types, but the registry record does not provide numerical results for every listed change-from-baseline measure.

The broad pattern should be read alongside the primary result, not as a separate confirmation of it. The posted AST response comparison also has small group counts and an interval that includes no difference. Baseline ALT and AST values describe the groups before treatment and are not treatment effects. The secondary endpoints therefore do not resolve the uncertainty in the primary comparison, and they address distinct outcomes rather than replicating the primary ALT response definition.

As a general statistical point, examining many outcomes creates more opportunities for apparently notable findings to arise by chance. If several tests are interpreted without adjustment, an isolated unadjusted result carries less weight than a result tied to a prespecified primary endpoint and an appropriate analysis plan. The registry record lists 13 posted secondary results, but it does not report a multiplicity adjustment or a hierarchy for interpreting them. Consequently, secondary findings are best treated as descriptive or exploratory unless a more complete analysis plan establishes otherwise.

The endpoint list can show what investigators intended to measure, but a listed outcome is not itself evidence of a treatment effect. Interpretation depends on the actual result, its uncertainty, the analysis population, and the extent to which the endpoint was prespecified. Because the registry does not report all of those details for every secondary measure, the secondary record should be used to understand the scope of assessment rather than to make a broad claim about efficacy.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Percentage of Participants With a Response in Serum Aspartate Aminotransferase (AST) Level From Baseline at Week 4
• Change From Baseline in Serum ALT at Weeks 1, 2, 3 and 4
• Serum ALT at Baseline
• Change From Baseline in Serum AST at Weeks 1, 2, 3 and 4
• Serum AST at Baseline
• Change From Baseline in Methacetin Breath Test (BreathID) at Weeks 1 and 4
• Change From Baseline in Enhanced Liver Fibrosis Test (ELF) at Week 4
• Maximum Observed Plasma Concentration (Cmax) of PF-04136309

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary because participants are classified as responders or nonresponders according to the stated ALT threshold. The group percentages estimate the proportion meeting that definition in each treatment group. A comparison of those proportions can be expressed as a risk difference: the response proportion in the PF-04136309 group minus the response proportion in the placebo group. A negative estimate means the observed response proportion was lower in the PF-04136309 group. The recalculated risk difference is -0.114.

What does a risk difference describe?

A risk difference uses the original proportion scale. It describes an absolute contrast between groups rather than a relative contrast. Its confidence interval gives a range of values compatible with the data and the calculation’s assumptions. Here, the interval is -0.489 to 0.262, so it includes a negative difference, no difference, and a positive difference. The estimate itself is not a guarantee of the difference that would occur in another study or in a broader population.

The same binary data can also be compared using an odds ratio or a risk ratio. These measures use different scales and should not be read as if they were risk differences. An odds ratio compares the odds of response between groups; a risk ratio compares the response proportions. The recalculated odds ratio is 0.583, with a confidence interval from 0.097 to 3.506, and the recalculated risk ratio is 0.688, with a confidence interval from 0.196 to 2.408. The intervals are broad, reflecting limited precision. A ratio estimate below one indicates a lower observed response measure in the PF-04136309 group relative to placebo, but the intervals include values on either side of the no-relative-difference value.

Why use Fisher’s exact test?

The registry reports Fisher’s exact test for the sponsor’s odds-ratio analysis. As a general explanation, Fisher’s exact test is often used for categorical outcomes when group counts are small; it evaluates the observed allocation of events across groups using the fixed margins of the comparison. The sponsor-reported odds ratio is 0.583, with a 95% confidence interval from 0.10 to 3.51, and p = 0.667. The recalculated analysis is a simple unadjusted calculation from the posted summary statistics, and its p-value is 0.554. Differences between inferential procedures can yield different p-values even when point estimates and interval limits are close. The registry does not report a complete analysis plan or enough detail to reconstruct every sponsor calculation.

What do the continuous outcomes show statistically?

For continuous measurements, the registry reports group means and standard deviations. The standard deviation describes variation among measurements within a group; it is not the uncertainty in the group mean. The recalculated mean difference is the PF-04136309 mean minus the placebo mean. At baseline, the ALT means were 132.2 and 154.7 international units per liter, respectively, and the estimated mean difference was -22.5, with a confidence interval from -81.93 to 36.93. The baseline AST means were 96.6 and 110.6 international units per liter, and the estimated mean difference was -14.0, with a confidence interval from -53.2 to 25.2. These are baseline descriptions, not estimates of treatment-related change.

As a general statistical point, baseline comparisons can describe how groups began, but a difference at baseline is not itself a treatment effect. For a follow-up treatment comparison, the analysis would need to use the relevant post-baseline outcome or change measure and an appropriate comparison. The registry lists change-from-baseline ALT and AST outcomes, but the posted secondary results included in the record do not give numerical results for those changes.

How should imputation and analysis populations be understood?

The primary population is described as the Full Analysis Set: randomized participants with a baseline value and at least one post-baseline value. The registry says missing data were imputed with last observation carried forward. As a general explanation, LOCF substitutes a participant’s last recorded observation for a later missing value. This can retain participants in an analysis when a later measurement is missing, but it relies on an assumption that the last observed value is an appropriate stand-in for the missing value. If outcomes change over time, that assumption may not hold. The record does not report the amount or pattern of missingness, sensitivity analyses, or the number of participants whose primary outcome was imputed.

These methods explain how to interpret the posted estimates, but they do not establish that all assumptions were met. The registry record does not report whether the analysis was adjusted for other variables, whether an interim analysis occurred, or the full statistical analysis plan. No conclusions about those unreported procedures can be drawn from the posted results.

11. Confidence Intervals and Precision

Precision concerns how narrowly the data locate an estimate. A confidence interval expresses uncertainty around an estimate under the method’s assumptions; it is not a range guaranteed to contain the true value. The primary risk-difference estimate is -0.114, and its interval extends from -0.489 to 0.262. Because that range includes negative and positive differences as well as no difference, it does not locate the direction of the group contrast with precision.

The odds-ratio interval is also broad: the recalculated estimate is 0.583, with limits of 0.097 and 3.506. In general, the no-relative-difference value for an odds ratio is one. The interval includes values below and above that reference, so the estimated relative association is uncertain. The sponsor-reported interval, from 0.10 to 3.51, similarly spans a broad range. The limits are rounded in the registry’s reported analysis, so they should be quoted as recorded.

The primary group counts are 12 and 11. With relatively few observations, changing the response classification of a participant can shift a group percentage meaningfully. This is one reason the point estimates should be considered alongside the intervals rather than read as definitive quantities. A confidence interval does not account for every possible limitation: it does not remove uncertainty from missing data, endpoint selection, conduct of the study, or the generalizability of the population.

For the baseline continuous outcomes, the mean-difference intervals are also wide: -81.93 to 36.93 for ALT and -53.2 to 25.2 for AST. Those baseline intervals describe uncertainty about group differences at baseline and do not estimate a treatment effect. Overall, the posted intervals emphasize limited precision, and the registry record does not report additional analyses that would narrow or otherwise qualify that uncertainty.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size figures are planning illustrations based on the observed effect, not the trial’s original design calculation. For these non-time-to-event outcomes, the figures are participants per arm, rather than a total across groups or a number of events. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The planning effect is the stated fraction of the observed effect. The trial’s own original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column describes the number of participants per arm that the illustration estimates would be needed for an 80% chance of detecting the specified effect under the stated assumptions, if that effect were truly present. The 90% power column gives the corresponding planning figure for a higher chance of detection. These are design probabilities under an assumed effect and statistical model; they do not tell how likely the treatment is to work. The values are not observed power.

Rows that plan for 100% of the observed effect use the full estimated effect as the target. Rows planning for 75% or 50% of the observed effect use smaller target effects. Smaller effects are harder to distinguish from random variation, so they require more participants per arm under otherwise unchanged assumptions. The displayed illustrations are especially sensitive to the observed effect because the trial groups are small and the effect estimate is uncertain. They are not predictions that a future study will produce the same effect, and they are not a substitute for a design calculation based on a justified target effect.

The sample-size curve is a visual companion to the planning figures: read it in the context of the same assumptions and effect scenarios, rather than as a second independent source of evidence about efficacy. The registry does not report the original protocol’s planning target, its assumed treatment difference, or any adjustments for missing outcomes or multiple endpoints. Those design choices therefore cannot be inferred from the planning illustrations.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.364; treatment proportion p₁ = 0.250; average p̄ = 0.307.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6522 = 1.2783.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6472 = 0.5447.
4. n = (1.2783 + 0.5447)² / (-0.1136)² = 257.4, rounded up to 258 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
p0 <- 0.363636363636364                          # control proportion
p1 <- 0.25                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1226797)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 258 (80% power), 345 (90% power)
 75% of observed effect: n per arm = 470 (80% power), 629 (90% power)
 50% of observed effect: n per arm = 1,083 (80% power), 1,449 (90% power)
power.prop.test: 257.4 
Simulated power at n = 258 per arm: 0.807 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The sponsor-reported primary analysis used Fisher’s exact test and expressed the comparison as an odds ratio. It reported an odds ratio of 0.583, a 95% confidence interval from 0.10 to 3.51, and p = 0.667. The simple unadjusted recalculation from the posted group summaries gives an odds ratio of 0.583, a confidence interval from 0.097 to 3.506, and p = 0.554. The estimated odds ratios and the interval limits are close, while the p-values are not identical.

The recalculation is not a replacement for the sponsor’s analysis. It is an unadjusted calculation from summary counts, and the registry does not report enough detail to establish that every inferential choice matches the sponsor’s implementation. For interpreting what the trial formally reported, the sponsor’s listed analysis is the registry analysis. The recalculation helps readers see the result on familiar scales, including the risk difference, but should be kept distinct from the reported test.

Both analyses show substantial uncertainty. The sponsor’s interval is wide, and the recalculated interval is also wide; neither confines the odds ratio to a narrow range. The p-values should not be interpreted as probabilities that the null hypothesis is true, nor as measures of clinical importance. The record does not report an explanation for the difference between the p-values or a full statistical analysis plan that would permit a detailed audit of the sponsor’s calculation.

15. Multiplicity, Missing Data and Analysis Populations

The primary analysis population is described as the Full Analysis Set, consisting of randomized participants with a baseline measurement and at least one post-baseline measurement. The registry also states that missing data were imputed using last observation carried forward. These details matter because the estimated response proportions depend on which participants are included and how missing outcome values are handled.

As a general statistical explanation, LOCF carries a participant’s last available measurement forward to represent a later missing measurement. This approach can be simple to apply, but it assumes that the last recorded value is a reasonable substitute for the unobserved value. If the outcome would have changed after that measurement, the imputed value may differ from the unobserved outcome. The registry record does not report how many outcome values were missing, the reasons for missingness, the timing of missing measurements, or sensitivity analyses using alternative assumptions.

The study has a primary endpoint and multiple secondary outcomes. As a general principle, testing or emphasizing many outcomes without accounting for multiplicity can increase the chance of a seemingly notable result arising by chance. The registry record does not report whether multiplicity was controlled, how primary and secondary outcomes were prioritized in the full analysis plan, or whether any secondary findings were designated exploratory. That missing information limits how strongly secondary comparisons should be interpreted.

The record identifies a Full Analysis Set but does not report a detailed definition of all analysis populations, the handling of protocol deviations, or whether the primary analysis was adjusted for covariates. The original statistical analysis plan, interim analyses, and sample-size justification are not reported in the registry record. These omissions do not prove that particular procedures were absent; they mean that the available record does not establish what procedures were used. The numerical findings should therefore be read with the documented population and LOCF approach in mind, while recognizing that important details about missingness and analysis choices remain unavailable.

16. 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

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: sinus bradycardia (8.3%), hand fracture (8.3%).

The safety results list 12 participants at risk in each group. Serious adverse events were reported for 2 participants in the PF-04136309 group and 0 in the placebo group. Other adverse events were reported for 8 participants in the PF-04136309 group and 3 in the placebo group. The registry lists sinus bradycardia and hand fracture among the top serious adverse-event terms, each at 8.3%. The record does not identify the group attribution for those terms in the information.

These are descriptive counts, not proof that an event was caused by the assigned treatment. Serious adverse events and other adverse events are distinct categories in the record; the categories should not be conflated. With small safety groups, a count can change noticeably with a small number of events, and the posted data do not precisely characterize uncommon harms.

Deaths are not reported in the registry record. The registry information does not provide enough detail to assess event timing, severity beyond the serious classification, relatedness to treatment, or the full clinical context. These figures describe reported events during the recorded study, not a complete estimate of safety in other populations or with longer follow-up.

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

The posted results answer a narrow question: what proportion of the analyzed participants met a specified ALT reduction threshold at Week 4 in each randomized group? The observed proportions were 25% for PF-04136309 and 36.36% for placebo. The recalculated risk difference was -0.114, with a confidence interval from -0.489 to 0.262. The estimate favors a lower response proportion in the PF-04136309 group in this sample, but the interval includes differences in either direction.

These findings do not establish that PF-04136309 improves or worsens health, nor do they show whether any laboratory change corresponds to a patient-important outcome. ALT is a laboratory measure, and the endpoint is a threshold-based response rather than a measure of symptoms, complications, or long-term liver health. The trial record does not report evidence connecting the specified Week 4 response threshold to those outcomes.

The data also do not establish equivalence or prove that the groups are identical. An uncertain estimate is not the same as a precise finding of no difference. The small analysis groups and broad confidence interval leave room for a range of underlying group differences. The reported p-value is not a measure of the probability that the treatment works, and it does not show whether a possible difference would be important to patients.

The result applies to the participants and outcome definition recorded for this study. The registry describes chronic hepatitis C infection with raised aminotransferases, but it does not provide enough detail to characterize all aspects of participant eligibility or representativeness. It records the study as terminated without a reason. Without fuller information about termination, missing data, conduct, and the analysis plan, the result should not be used to make a broader claim about efficacy or safety.

In short, the registry documents a small randomized comparison with a short-term laboratory endpoint and substantial statistical uncertainty. It is useful as a record of what was measured and reported, but it cannot by itself settle the comparative clinical value of the intervention.

18. Why This Trial Matters Statistically

This trial illustrates why the size of an estimate and the precision of an estimate must be considered together. The point estimate for the primary risk difference is negative, but its confidence interval spans negative and positive values. Reporting only the two response percentages would conceal how uncertain the comparison is; reporting only a p-value would also leave out the range of effect sizes compatible with the data.

It also shows how a threshold-defined outcome shapes interpretation. A percentage of responders is easy to state, but it compresses the underlying ALT measurements into a yes-or-no classification. The chosen cutoff determines who counts as a responder, and the registry record does not explain the rationale for that threshold. Continuous change outcomes can retain information that the binary classification discards, but the numerical change results are not included in the posted secondary results described in the record.

The distinction between the sponsor-reported analysis and an unadjusted recalculation is another useful statistical lesson. Similar effect estimates can accompany different p-values when the calculation methods or details differ. The sponsor’s listed analysis remains the reported trial analysis; a recalculation from summary data is a check or alternate description, not a replacement for the complete analysis.

Finally, the planning illustrations demonstrate that sample-size calculations depend on the effect assumed for planning. The smaller the target effect, the more participants per arm are needed under the stated assumptions. These illustrations should not be confused with evidence about treatment effectiveness or with the trial’s original design justification, which is not reported in the registry record. Together, these points make the record valuable for learning how design, endpoint definition, uncertainty, and analysis choices affect interpretation.

19. 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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The analysis groups are small: the primary outcome results include 12 participants in the PF-04136309 group and 11 in the placebo group. The safety counts use 12 participants at risk in each group. The registry record does not explain the difference between the efficacy and safety counts, so the denominators should be read as reported for their respective analyses rather than assumed to be interchangeable.

The study is recorded as terminated, but the reason is not reported in the registry record. That limits interpretation of whether the termination could have affected recruitment, follow-up, or completeness of outcome reporting. The record also does not report the original enrollment target or sample-size justification, so it is not possible to assess the intended precision from the original design information.

The primary outcome uses LOCF for missing data, but the amount and pattern of missingness and sensitivity analyses are not reported. The outcome is a binary response based on a 30% ALT reduction; the rationale for the threshold and its relationship to patient-important outcomes are not reported. The study includes multiple secondary endpoints, while the record does not report a multiplicity strategy or a complete hierarchy for interpreting them.

Further limitations include the absence of a full protocol and statistical analysis plan in the registry record. Details about participant characteristics, adherence, treatment exposure, reasons for discontinuation, and the relationship of adverse events to treatment are not reported in the information available. These gaps do not demonstrate that the trial lacked appropriate procedures, but they constrain what can be concluded from the registry record alone. The short-term laboratory endpoint and limited precision also restrict broader inference about longer-term outcomes.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Safety And Efficacy Of Oral PF-4136309 In Patients With Chronic Hepatitis C Infection And Abnormal Liver Enzymes — NCT01226797.
• Registry record last updated 2023-07-27; status last verified 2022-09.
• Results first posted 2023-07-27.
• 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.

23. Record Summary

The registry describes a randomized, quadruple-masked, placebo-controlled phase 2 study of oral PF-04136309 500 mg twice daily in people with chronic hepatitis C infection and raised aminotransferases. It records enrollment of 24, a start date of 2011-01-17, a primary completion date of 2012-02-09, and a terminated status.

The primary endpoint was the percentage with an ALT response at Week 4, defined as a reduction of at least 30% from baseline. The posted proportions were 25% with PF-04136309 and 36.36% with placebo. The recalculated risk difference was -0.114, with a confidence interval from -0.489 to 0.262; the sponsor-reported odds-ratio analysis had a broad 95% confidence interval.

The record documents substantial uncertainty, an LOCF approach to missing primary outcome data, and several secondary outcomes. The reason for termination, original sample-size justification, multiplicity strategy, missingness details, and full analysis plan are not reported in the registry record.