Ramucirumab and Pembrolizumab for the Treatment of EGFR Mutant Recurrent or Metastatic Non-small Cell Lung Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ramucirumab and Pembrolizumab for the Treatment of EGFR Mutant Recurrent or Metastatic Non-small Cell Lung Cancer (NCT04120454), a na phase 2 study. The primary outcome is Overall Response Rate.

2. Clinical Question

3. Trial Design

This was an investigator-sponsored phase 2 single-arm trial of ramucirumab and pembrolizumab in people with EGFR-mutant non-small cell lung cancer. The registry lists Ohio State University Comprehensive Cancer Center as the sponsor, enrollment of 6, and a completed status. The recorded start date is 2020-06-17 and the primary completion date is 2023-08-19.

The treatment group received ramucirumab and pembrolizumab. The regimen description says both were administered intravenously on day 1, with cycles repeating every 21 days for up to 35 cycles unless disease progression or unacceptable toxicity occurred. The record does not give details of treatment actually received by each participant, interruptions, discontinuations, or adherence.

Because this was a single-group trial, there was no randomized allocation to treatment alternatives and no concurrent control group. Masking was listed as none. These design features matter when interpreting outcomes: an observed response or safety event in the group cannot, by itself, establish how outcomes would have differed under another treatment or without this regimen. The design is suited to describing what was recorded in the treated group, but it does not provide a like-for-like treatment comparison.

The primary endpoint was overall response rate, assessed up to 2 years. The registry describes computed tomography scans every 2 cycles and tumor measurements using RECIST 1.1, with iRECIST also assessed. The record also lists secondary outcomes for adverse events, clinical benefit rate, progression-free survival, and overall survival. It lists 8 outcome measures but no analysis entries. The detailed statistical analysis plan, including the planned analysis population and handling of missing outcome assessments, is not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Overall Response Rate, measured over Up to 2 years.

Overall response rate is the primary endpoint. As a general statistical measure, it is the proportion of participants in an assessed population who have a complete or partial tumor response according to the specified response criteria. It condenses tumor measurements into a clinically interpretable response summary, while not describing how long a response lasts or whether it is associated with longer survival.

The registry specifies assessment up to 2 years. It describes computed tomography scans every 2 cycles, tumor measurements using RECIST 1.1, and assessment with iRECIST as well. The endpoint is expressed as a percentage of participants. These criteria provide a structured approach to classifying changes in measurable disease, rather than relying on an unstructured judgment of improvement.

The primary endpoint’s actual response count and percentage are not reported in the registry record. Nor does the record report the number assessed, the analysis population, or how missing or unevaluable scans were handled. As a result, the endpoint definition can be described, but its observed value and precision cannot be evaluated from the primary outcome information recorded. A percentage alone would also need its denominator and uncertainty to show how much information it carries, particularly in a small single-group study.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical methods determine how outcomes are summarized, which participants contribute to each analysis, and how uncertainty is represented. The registry record identifies an endpoint and assessment approach, but it does not report a detailed statistical analysis plan. The explanations below describe general concepts that help interpret this kind of study; they should not be taken as methods confirmed to have been used by the investigators.

What does an overall response rate estimate?

In general, an overall response rate is a binary outcome summarized as the fraction of an analysis group that meets the criteria for response. Each assessed participant is classified according to whether a response occurred within the specified assessment framework. A percentage makes this summary readily interpretable, but it depends on the denominator: the number assessed and the rules for participants without an evaluable assessment. The registry describes the primary measure as a percentage of participants but does not report the observed numerator, denominator, or missing-assessment rules.

Response classification relies on the specified tumor measurement criteria. Here, the registry describes computed tomography scans every 2 cycles, RECIST 1.1 measurements, and assessment using iRECIST. These are named assessment approaches in the record, but the record does not describe how discordant classifications, incomplete scans, or changes in assessment status were handled in the analysis.

Why is uncertainty important?

A point estimate is a single summary of the observed group. A confidence interval is a general statistical tool for expressing uncertainty around an estimate under a stated method and assumptions. A narrower interval generally indicates greater precision, while a wider interval indicates that a range of values remains compatible with the data and method. The interval does not eliminate uncertainty, and it does not by itself establish that an observed result is important or attributable to treatment.

For a binary percentage, precision depends on the response count and the size and definition of the assessed group. In a small study, a change in the outcome status of a participant can materially affect the estimate. The registry record does not report the primary response result or its confidence interval, so its magnitude and precision cannot be assessed. No interval should be inferred from enrollment alone.

What can a single-group design establish?

A single-group study describes outcomes in participants who received the study regimen. It has no concurrent randomized control group against which to estimate a difference. That means an observed outcome cannot be interpreted as a treatment contrast, and the design cannot isolate the contribution of ramucirumab from that of pembrolizumab. Historical comparisons, if attempted, would involve additional assumptions and are not described in the registry record.

Randomization is generally used to balance measured and unmeasured prognostic factors between comparison groups on average. Without randomized allocation and a comparator, differences between the study group and an external benchmark could reflect differences in eligibility, follow-up, assessment, or other factors rather than treatment. No such external comparison is reported in the registry record.

How should analysis populations be considered?

An analysis population specifies which participants are included in an outcome calculation. For a response endpoint, possible approaches can differ in their treatment of participants who do not have an evaluable scan or who stop treatment before assessment. These choices can affect the denominator and the resulting percentage. The registry record does not identify the primary analysis population or explain how unevaluable or missing assessments were treated. The enrollment count therefore should not be assumed to be the response denominator.

Follow-up outcomes require further detail. Progression-free survival and overall survival are time-to-event outcomes in general: their analysis usually accounts for the time until an event or the last known follow-up, with appropriate treatment of censoring. The registry lists these outcomes as secondary, but the analysis method, event definitions, follow-up completeness, and censoring procedures are not reported in the registry record.

What do planning calculations mean?

Sample-size calculations are planning tools. They describe the amount of information a hypothetical design may need under stated assumptions about the effect, significance level, allocation, and statistical approximation. The registry’s planning assumptions describe a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and effects expressed as fractions of an observed effect. These are planning illustrations, not evidence that the completed trial had a particular power.

The record describes the calculations as based on the observed effect, but the observed primary response effect is not reported in the registry record. Accordingly, those planning illustrations cannot fill the gap in the outcome reporting. In general, power is a design-stage property tied to assumptions; it is not a measure of how convincing a result is after a study has been completed. It should not be described as observed power.

The record states that time-to-event planning calculations use a total event count, while other calculations are expressed as participants per arm for 80% power or other listed planning targets. Such calculations concern hypothetical designs, not the observed sample or results of this single-group trial. The record does not state that these illustrations were the investigators’ original design justification or that they were used to plan this study.

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("Treatment (Ramucirumab, Pembrolizumab)")
n      <- c(6)
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  Treatment (Ramucirumab, Pembrolizumab)  6  0  0.0  0.0  45.9  0.0  39.0  0.4  41.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists several outcomes: overall response rate as primary, and adverse events, clinical benefit rate, progression-free survival, and overall survival among the secondary outcomes. When a study tests or interprets multiple outcomes, multiplicity can arise because the chance of at least one apparently notable finding may increase across repeated statistical tests. General approaches include designating a primary endpoint in advance, adjusting inference across tests, or treating secondary findings as exploratory. The registry record does not report a multiplicity adjustment or a detailed plan for interpreting multiple outcomes.

The record lists 8 outcome measures and no analysis entries. It does not report which outcomes were analyzed, the statistical tests used, or whether any analysis was prespecified or conducted after examining the data. The presence of listed outcomes alone does not show that all were measured or analyzed.

Missing-data handling is also not reported in the registry record. For the response endpoint, interpretation would require knowing how participants without an evaluable scan were treated and which participants formed the analysis denominator. For follow-up outcomes, the record does not describe censoring or completeness of follow-up. These omissions prevent assessment of how missing observations may have influenced the reported results.

The analysis populations are not reported in the registry record. It is therefore unclear whether outcome summaries were based on all enrolled participants, those who started treatment, those who had an assessment, or another defined group. The response outcome itself is not reported, further limiting evaluation of its analysis. These are reporting gaps, not evidence that a particular method was or was not used.

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: encephalopathy (33.3%), aspartate aminotransferase increase (16.7%), hypertension (16.7%), pericardial effusion (16.7%), pleural effusion (16.7%).

The registry records serious adverse events in the treatment group: 4 participants were affected among 6 at risk. It also lists other adverse events affecting 6 among 6 at risk, and a death count of 6. These are registry-recorded counts. The record does not establish that the study treatment caused each event or death, and the death count should not be interpreted as a treatment-related death count without further information.

The listed serious adverse-event terms include encephalopathy at 33.3%, and aspartate aminotransferase increase, hypertension, pericardial effusion, pleural effusion, and pulmonary embolism, each at 16.7%. These percentages describe the reported terms as recorded; the information does not show whether a participant could have experienced more than one term. They should not be added together to infer a total event rate.

Interpretation is limited because the registry record does not give the timing, duration, grade, relatedness assessment, or management of these events. It also does not clarify how the death count relates to event reporting or follow-up. Counts in a small treated group are descriptive and do not provide a comparative estimate of safety versus another regimen.

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

The registry describes a phase 2 single-group study of ramucirumab and pembrolizumab in EGFR-mutant recurrent or metastatic non-small cell lung cancer. It specifies overall response rate as the primary endpoint and describes how tumor response was to be assessed. However, the primary response result is not reported in the registry record. The efficacy outcome that would answer the study’s central question therefore cannot be characterized from the recorded primary endpoint information.

The listed safety data document serious adverse events, other adverse events, and deaths in the treatment group. They are descriptive observations, not proof that the treatment caused those outcomes. Without a concurrent comparison group, the record cannot quantify whether outcomes differ from those under another treatment or from the course of disease without this regimen.

The design also cannot distinguish the separate effects of ramucirumab and pembrolizumab. The intervention was the combination, and the registry does not describe a component-specific comparison. Even a reported response rate would have represented outcomes in this group under the stated assessment approach, rather than a randomized estimate of treatment benefit.

The enrollment count of 6 indicates that the study involved a small group, but it does not supply the missing response denominator or outcome result. The registry record also does not report confidence intervals for the primary endpoint, analysis populations, or missing-data procedures. Those gaps limit assessment of both the magnitude and precision of any efficacy estimate.

In short, the record documents the trial’s design, planned response measure, treatment schedule, and some safety counts. It does not report the primary response result, and it does not support a comparative or causal conclusion about the treatment. The listed outcomes and planning illustrations should not be treated as substitutes for results.

14. Why This Trial Matters Statistically

This trial raises several statistical issues that are important when reading early-phase clinical research. A single-group design can describe what happened among treated participants, but it does not provide a randomized contrast. The distinction matters because descriptive outcomes and comparative treatment effects answer different questions. Without a concurrent comparator, the record cannot show how outcomes would have differed under another approach.

The primary endpoint is a percentage, which can be easy to communicate but needs its numerator, denominator, and uncertainty for meaningful interpretation. The registry identifies overall response rate and an assessment framework, yet does not report the observed response result. The enrollment figure cannot replace an outcome denominator, and a percentage without an uncertainty measure would be difficult to assess in a small study.

Outcome reporting also matters across the full set of endpoints. The record lists several secondary outcomes as well as the primary response measure, but it does not provide analysis entries or a detailed statistical plan. Without reported methods for analysis populations, missing data, and multiplicity, readers cannot determine how choices in those areas shaped any outcome summary.

Finally, the safety figures are useful as descriptive registry information but cannot establish causation or comparative safety. Event counts and listed terms require context about timing, severity, relatedness, and overlap. Together, these considerations show why design, endpoint definitions, complete results, and uncertainty reporting are all needed to interpret a clinical trial statistically.

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 limitation of the registry record for efficacy interpretation is that it does not report the primary overall response rate result. The response count, assessed denominator, and confidence interval are not reported in the registry record. The endpoint definition and assessment schedule alone cannot show what response was observed or how precise an estimate would be.

The study was single-group, with no randomized comparator. This prevents a direct estimate of how the combination compares with another treatment and limits causal interpretation. The record also does not support separating the contribution of either medicine in the combination.

Enrollment was 6, so any group-level estimate would have limited information and could be sensitive to individual outcomes. The registry record does not report participant characteristics, the analysis population, scan evaluability, or missing-data handling. It is not possible to determine whether all enrolled participants contributed to each outcome.

Although the registry lists progression-free survival, overall survival, clinical benefit rate, and adverse events, it does not provide the detailed analyses for these outcomes in the record described. Follow-up duration and censoring procedures are not reported. For safety, event timing, severity grading, relatedness, and participant-level overlap are also not reported. These gaps restrict interpretation of both efficacy and harms and should not be filled by assumptions.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Ramucirumab and Pembrolizumab for the Treatment of EGFR Mutant Recurrent or Metastatic Non-small Cell Lung Cancer — NCT04120454.
• Registry record last updated 2025-07-11; status last verified 2025-07.
• Results first posted 2025-07-11.
• 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 NCT04120454, a completed phase 2, investigator-sponsored, single-group study of ramucirumab and pembrolizumab in EGFR-mutant recurrent or metastatic non-small cell lung cancer. Enrollment was 6. Treatment was described as intravenous administration on day 1, repeating every 21 days for up to 35 cycles if progression or unacceptable toxicity did not occur.

Overall response rate was the primary endpoint, with assessment up to 2 years using computed tomography every 2 cycles, RECIST 1.1, and iRECIST. The primary response result is not reported in the registry record. The record lists secondary outcomes that include adverse events, clinical benefit rate, progression-free survival, and overall survival, and records adverse-event counts and terms for the treatment group. It lists no analysis entries. The single-group design does not provide a randomized treatment comparison.