Efficacy and Safety of Lenvatinib (E7080/MK-7902) Plus Pembrolizumab (MK-3475) for Advanced Melanoma in Anti-Programmed Death-1/Programmed Death-Ligand 1 (PD-1/L1)-Exposed Participants (MK-7902-004/E7080-G000-225/LEAP-004): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety of Lenvatinib (E7080/MK-7902) Plus Pembrolizumab (MK-3475) for Advanced Melanoma in Anti-Programmed Death-1/Programmed Death-Ligand 1 (PD-1/L1)-Exposed Participants (MK-7902-004/E7080-G000-225/LEAP-004) (NCT03776136), a na phase 2 study. The primary outcome is Objective Response Rate (ORR).

2. Clinical Question

The clinical question concerns objective response after prior exposure to anti-PD-1/L1 therapy, rather than a randomized comparison between treatments. Response was assessed over a timeframe of up to approximately 55 months. A complete response required disappearance of all lesions. A partial response required at least a 30% decrease in the sum of target lesion diameters without progression in other lesions.

The registry describes a modified RECIST 1.1 approach that allowed up to 10 target lesions total, with up to 5 per organ. Blinded independent central review was used to assess the response endpoint, even though the study itself was open-label. That distinction matters: central review can standardize assessment of the endpoint, but it does not create a concurrent control group or make treatment assignment randomized.

The record does not report the observed objective response percentage or its confidence interval. It therefore identifies the question and the measurement rules, but does not permit a numerical answer about the response rate from the information recorded.

3. Trial Design

LEAP-004 is recorded as a phase 2, multicenter, open-label, single-group trial. The registry lists enrollment of 103 and status as completed. The recorded start date is 2019-01-30, and the primary completion date is 2023-10-11. Allocation is listed as NA, and masking is listed as none. These design features mean that the study was not a randomized, masked comparison of lenvatinib plus pembrolizumab against another treatment or a control.

The participants had advanced melanoma and prior exposure to an anti-PD-1/L1 agent. The intervention combined lenvatinib with pembrolizumab. The regimen description specifies lenvatinib 20 mg orally once a day and pembrolizumab 200 mg by intravenous infusion on Day 1 of each 21-day cycle. Pembrolizumab was to be given for up to 35 cycles, approximately 24 months. The description of lenvatinib treatment ends after “until progressive disease or an unac”; the remaining treatment-duration text is not reported in the registry record.

The primary endpoint was objective response rate, defined using confirmed complete or partial responses assessed by blinded independent central review. The primary population was participants who received at least one dose of study intervention. Listed secondary outcomes include progression-free survival, overall survival, duration of response, lenvatinib exposure measured by area under the concentration-time curve, participants experiencing at least one adverse event, and participants discontinuing study treatment due to an adverse event.

The brief summary states that no statistical hypothesis would be tested. A detailed statistical analysis plan, including any planned interim analyses or sample-size justification, is not reported in the registry record. The absence of a comparator limits the design's ability to separate treatment-associated outcomes from the natural course of disease, other care, or selection of participants. It also means the findings cannot be read as a direct estimate of the difference between this regimen and another approach.

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: All participants who received at least one dose of study intervention.

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 Objective Response Rate (ORR), measured over Up to approximately 55 months.

Objective response rate is the percentage of participants in the analysis population whose best qualifying response was a confirmed complete response or partial response. In this trial, complete response meant disappearance of all lesions. Partial response required at least a 30% decrease in the sum of target lesion diameters without progression in other lesions. Responses were assessed according to RECIST 1.1 by blinded independent central review, with the protocol's stated modification allowing up to 10 target lesions total and up to 5 per organ.

Response rate is used to describe the proportion of participants meeting a prespecified tumor-response definition. It is a binary outcome at the participant level: each participant either meets the confirmed response definition or does not. It does not, by itself, describe how long a response lasts, how quickly it occurs, or what happens to participants who do not meet the definition. Duration of response, progression-free survival, and overall survival are distinct outcomes listed separately in the registry.

The endpoint description specifies a 95% confidence interval as the measure of dispersion, but the observed response percentage and interval are not reported in the registry record. The stated timeframe is up to approximately 55 months. Without the observed estimate and its uncertainty interval, the endpoint definition alone cannot establish the response rate in the trial population.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a binary participant-level measure expressed as a percentage: a participant either had a confirmed complete or partial response under the stated criteria, or did not. The registry defines the analysis population as all participants who received at least one dose of study intervention. The outcome timeframe is up to approximately 55 months. The actual observed percentage is not reported in the registry record.

What does a confidence interval communicate?

In general, a confidence interval describes uncertainty around an estimated quantity. A narrower interval indicates greater precision under the statistical method and assumptions used; a wider interval indicates less precision. It is not a range containing a known proportion of individual participant outcomes, and it does not account for every possible source of bias. The registry identifies a 95% confidence interval for the primary endpoint, but does not report its limits or the method used to calculate it. The estimate's precision therefore cannot be assessed from this record.

For a percentage, the interval depends in part on the number of participants contributing to the analysis and the number meeting the response definition. The registry's primary population rule is stated, but it does not report the number analyzed for the endpoint or the number with a confirmed response. No response percentage or interval should be reconstructed in the absence of those results. The registry's enrollment figure is not, on its own, proof that every enrolled participant entered the primary analysis population.

What does blinded central review add?

In general, independent review can reduce the influence of investigators' expectations when a response assessment requires interpretation of imaging. The study is nevertheless recorded as open-label and unmasked. Blinded independent central review applies to the stated response assessment; it does not mean participants or site staff were masked to treatment, and it does not make the study randomized. The registry does not describe procedures for resolving disagreements between reviewers or other details of endpoint adjudication.

RECIST 1.1 supplies operational criteria for classifying tumor response. The record defines complete response as disappearance of all lesions and partial response as at least a 30% decrease in the sum of target lesion diameters without progression in other lesions. The protocol modification concerning the number of target lesions is also stated. These definitions help clarify what the endpoint counts, but the endpoint remains a summary classification. It does not show the size of change for every participant or indicate the duration of a response.

How should the single-group design affect interpretation?

In general, a single-group study can describe outcomes observed among participants receiving an intervention. Without a concurrent comparator, it cannot directly estimate the difference in outcomes that would have occurred under another treatment or control condition. Factors such as participant selection, disease course, and other care may contribute to outcomes. This is why a response percentage from a single group should not be interpreted as a randomized comparative effect.

The registry labels the model as single-group and allocation as NA, with no masking. The brief summary states that no statistical hypothesis would be tested. The registry record does not report a statistical analysis plan, a prespecified benchmark for response, or a justification for the enrollment target. It also does not report interim-analysis procedures. Those elements should not be inferred from the phase designation or from the fact that the trial is marked completed.

What can the listed secondary outcomes contribute?

Progression-free survival and overall survival are time-to-event outcomes, while duration of response concerns how long a response persists among participants who respond. Lenvatinib area under the concentration-time curve describes drug exposure. Adverse-event outcomes describe safety events and treatment discontinuation. These outcomes answer different questions and are not interchangeable with objective response rate. Their inclusion in the registry does not provide their results or explain how censoring, missing observations, or competing events were handled. Those analytic details are not reported in the registry record.

In general, time-to-event analyses need to account for participants whose event has not occurred by the end of observed follow-up or whose follow-up ends earlier. The registry's secondary-outcome list alone does not specify the methods used to handle those situations. No survival estimates or related uncertainty measures are reported in the registry record recorded for this trial.

What can the safety counts establish?

The registry lists counts of participants with serious adverse events, other adverse events, and deaths in the lenvatinib plus pembrolizumab group. Such counts describe recorded events within that group. Without a control group, they do not measure excess risk attributable to treatment. The record also does not supply event timing, duration, severity grading beyond the serious-event classification, or causal attribution for the listed counts. Percentages attached to selected serious-event terms provide descriptive frequency information but do not make those events comparable with another treatment.

Overall, the statistical information recorded is enough to identify the planned endpoint type and its stated confidence-interval measure, but not enough to reproduce or evaluate the primary estimate. A confidence interval, analysis population, and missing-data approach would all be relevant to judging precision and robustness; the necessary result details and methods are not reported in the registry record.

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("Lenvatinib + Pembrolizumab")
n      <- c(103)
events <- c(22)
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  Lenvatinib + Pembrolizumab  103  22  21.4  13.9  30.5  14.5  30.2  14.6  30.3

11. Multiplicity, Missing Data and Analysis Populations

The registry names objective response rate as the primary outcome and lists progression-free survival, overall survival, duration of response, lenvatinib area under the concentration-time curve, participants experiencing at least one adverse event, and participants discontinuing study treatment due to an adverse event as secondary outcomes. The brief summary states that no statistical hypothesis would be tested. A multiplicity procedure, such as adjustment of significance thresholds across outcomes, is not reported in the registry record. Since no hypothesis-testing plan or multiplicity adjustment is described, the listed endpoints should not be treated as a collection of confirmatory tests.

The primary analysis population is defined as all participants who received at least one dose of study intervention. The registry does not report the number included in the primary endpoint analysis, the number excluded, or the reasons for any exclusions. It also does not describe how missing response assessments, incomplete follow-up, or unevaluable cases were handled. An intention-to-treat population is not specified in the registry record recorded for this trial.

For the secondary time-to-event outcomes, censoring rules and methods for handling missing follow-up are not reported in the registry record. The record also does not state whether missing data were imputed for any outcome, or whether sensitivity analyses were planned. These omissions matter because choices about analysis populations and incomplete observations can affect both the estimated outcome and its uncertainty. They do not demonstrate that a particular method was or was not used; they mean that the method is not documented in the registry record.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

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: diarrhoea (4.9%), sepsis (3.9%), hyponatraemia (2.9%), abdominal pain (1.9%), nausea (1.9%).

The adverse-event record lists 48 participants with a serious adverse event among 103 at risk in the lenvatinib plus pembrolizumab group. It lists 101 participants with an adverse event among 103 at risk, and 86 deaths. These entries describe outcomes recorded in the single treatment group; they are not estimates of a difference between treatments. The registry record does not state the causes of death or establish that deaths were related to study treatment.

The most frequently listed serious-event terms include diarrhoea at 4.9%, sepsis at 3.9%, hyponatraemia at 2.9%, abdominal pain at 1.9%, nausea at 1.9%, and general physical health deterioration at 1.9%. These percentages describe the recorded frequency of the named serious events. They should not be read as a ranking of causal risks or as comparisons with other treatments. The record does not provide event timing, individual participant histories, or an attribution breakdown.

Serious adverse events and all adverse events are different categories, and a participant may experience more than one event. The counts alone do not reveal the total number of events, their duration, or how many led to treatment discontinuation. The registry lists discontinuation due to an adverse event as a secondary outcome, but its result is not reported in the registry record.

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

The trial record describes a phase 2 evaluation of lenvatinib plus pembrolizumab in participants with advanced melanoma previously exposed to anti-PD-1/L1 therapy. Its primary endpoint is a defined measure of confirmed objective response, assessed by blinded independent central review. The study design and endpoint definitions clarify what investigators intended to assess and in whom.

However, the observed objective response percentage and its 95% confidence interval are not reported in the registry record. The record therefore does not allow readers to determine the trial's response estimate or its precision. The endpoint description, enrollment figure, completion status, and selected adverse-event counts cannot be used to fill in that missing primary result.

Even if a response estimate were available, the single-group, open-label design would support a description of outcomes among treated participants, not a direct causal comparison with another treatment. Blinded central review can help standardize response classification, but it does not eliminate all sources of bias or provide a control group. The record's statement that no statistical hypothesis would be tested also cautions against treating the trial as a confirmatory test of a comparative claim.

The adverse-event counts and selected serious-event percentages are likewise descriptive. They do not establish how the safety profile compares with another option, identify causes of death, or show treatment attribution. The registry does not report the detailed analysis methods, missing-data procedures, or results for the listed secondary outcomes.

Thus, the record is informative about the study's population, treatment regimen, design, endpoint definition, and selected safety observations. It is not sufficient to quantify the primary response result or to support comparative conclusions. Keeping these distinctions clear separates the trial's stated question and methods from results that the registry record does not report.

14. Why This Trial Matters Statistically

Statistically, LEAP-004 illustrates why a clearly defined endpoint and a reported estimate are both necessary. The registry specifies objective response rate, its response criteria, the assessment method, a 95% confidence interval as the dispersion measure, and the primary analysis population. These details make the intended quantity understandable. But because the observed percentage and interval are not reported in the registry record, readers cannot evaluate either the magnitude of the estimate or its precision.

The single-group design also defines what can be learned. It can describe the outcomes observed in the treated group, but it does not produce a direct randomized contrast. This distinction is important when interpreting a response proportion: a percentage is not, by itself, an estimate of improvement over another treatment or over what would have occurred without the intervention.

The trial's use of blinded independent central review for response assessment raises a further statistical point. An assessment method may improve consistency in outcome classification while leaving other features of an open-label, single-group study unchanged. Measurement rigor and comparison design address different sources of uncertainty; one cannot substitute for the other.

Finally, the registry lists several secondary outcomes and selected adverse-event data, but does not report their results or detailed analysis methods. Outcome labels alone do not communicate the statistical evidence behind them. The missing primary estimate, interval, and analysis details limit independent assessment of the endpoint, while the lack of a comparator limits causal interpretation. These are central considerations in reading a phase 2 study, not merely technical details.

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 primary result needed to interpret the main clinical question—the observed objective response rate and its confidence interval—is not reported in the registry record. The endpoint definition and stated timeframe are available, but the number of participants with a confirmed response and the number analyzed are not. This prevents assessment of the estimate's magnitude and precision.

The design is single-group, open-label, and unmasked, with allocation listed as NA. There is no concurrent comparator arm, so the study cannot provide a randomized estimate of the difference between the regimen and another approach. Blinded independent central review is specified for response assessment, but it does not address all potential sources of bias associated with the overall design.

The regimen description is truncated after stating that lenvatinib would continue “until progressive disease or an unac”; the remainder of the treatment-duration rule is not reported in the registry record. The record also does not describe a statistical analysis plan, enrollment justification, interim analyses, missing-data handling, or multiplicity procedures. Results for the listed secondary endpoints are not reported in the registry record recorded for this trial.

Safety interpretation is constrained as well. The registry gives selected adverse-event counts and serious-event term percentages, but not event timing, causal attribution, detailed grading, or a comparison group. The listed death count does not identify causes. These limitations mean the record supports a description of selected observations, not a comparative conclusion about efficacy or safety.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Efficacy and Safety of Lenvatinib (E7080/MK-7902) Plus Pembrolizumab (MK-3475) for Advanced Melanoma in Anti-Programmed Death-1/Programmed Death-Ligand 1 (PD-1/L1)-Exposed Participants (MK-7902-004/E7080-G000-225/LEAP-004) — NCT03776136.
• Registry record last updated 2024-10-09; status last verified 2024-09.
• Results first posted 2024-10-09.
• 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

LEAP-004 (NCT03776136) is recorded as a completed, multicenter, open-label phase 2 trial with a single-group design. It enrolled 103 participants with advanced melanoma previously exposed to anti-PD-1/L1 therapy. The intervention combined lenvatinib and pembrolizumab; allocation is listed as NA and masking as none.

The primary endpoint was objective response rate, based on confirmed complete or partial response under modified RECIST 1.1, assessed by blinded independent central review. The primary analysis population was participants who received at least one dose of study intervention. The registry record does not report the observed primary endpoint result or its confidence interval. The brief summary states that no statistical hypothesis would be tested.

Listed secondary outcomes include progression-free survival, overall survival, duration of response, lenvatinib exposure, and adverse-event measures. Selected adverse-event counts and serious-event term percentages are recorded, but detailed comparative safety interpretation is not possible from this single-group record.