A Phase I/II Open-Label Study of Ipilimumab and GM-CSF Administered to Unresectable Stage IIIC and Stage IV Melanoma Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Phase I/II Open-Label Study of Ipilimumab and GM-CSF Administered to Unresectable Stage IIIC and Stage IV Melanoma Patients (NCT02009397), a na phase 1, phase 2 study. The primary outcome is Change in Immune-related Overall Response Rate (irORR).

2. Clinical Question

3. Trial Design

This is a Phase I/II, open-label, single-group study sponsored by the University of Louisville. The registry record gives the study status as completed, enrollment as 27, a start date of 2012-02, and primary completion of 2016-11. The title identifies the target population as people with unresectable stage IIIC or stage IV melanoma; the listed condition is metastatic melanoma.

The intervention is a combination of ipilimumab and GM-CSF. The arm description specifies IV ipilimumab followed by subcutaneous GM-CSF, for up to 4 cycles. No dose levels, dose-adjustment rules, or more detailed treatment schedule are reported in the registry record. The study has one listed arm, and no concurrent treatment or usual-care control group is described.

Open-label and masking none mean that the study is not described as blinded. The record lists allocation as NA and the model as single group. Thus, the design does not provide a randomized between-group comparison. Any change observed during the study would be a within-group observation, not an estimate of a treatment difference against a control arm.

The stated primary endpoint is change in immune-related overall response rate, recorded as a number of participants. Its assessment timing is baseline and 4 weeks (±1 week) following the last ipilimumab administration. The registry record does not report a protocol-level statistical plan, the primary endpoint analysis, or an analysis population. Although the study is marked completed, completion status alone does not supply those missing details or establish what results were observed.

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:

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 Change in Immune-related Overall Response Rate (irORR), measured over assessed at baseline and at 4 weeks (±1 week) following the last administration of Ipilimumab.

The primary endpoint is titled “Change in Immune-related Overall Response Rate (irORR)” and is recorded in participants. The assessment is planned at baseline and at 4 weeks (±1 week) following the last administration of ipilimumab. The word “change” indicates that the endpoint concerns a comparison across these assessment times within the study, but the registry record does not give the response criteria, the calculation rule, or the values at either assessment.

In general, a response-rate endpoint is used to describe how many participants meet a prespecified definition of response in a population and at a stated assessment time. The criteria are essential: they determine which observations count as responses and how ambiguous or changing findings are handled. For this registry entry, the underlying criteria and any rules for classifying participants are not reported in the registry record. The listed unit is a participant count, so no rate, proportion, or change can be reconstructed from the posted information.

The endpoint can describe response status at the specified assessments, but it does not by itself provide a randomized comparison or establish why a change occurred. No endpoint result or statistical analysis is reported in the registry record. Accordingly, the endpoint's title and timing identify what the study intended to assess, not what the study found.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The study design determines which statistical conclusions are available. This record describes a single-group study, with allocation listed as NA and no masking. There is no separate comparator arm. A single-group design can describe observations within the treated group, but it cannot estimate a randomized difference between that group and a concurrent control. In general, a before-and-after change may reflect treatment as well as time trends, disease course, other care, measurement variation, or changes in who remains available for assessment. These are interpretive possibilities, not reported events in this trial.

What does the endpoint count?

The endpoint title names immune-related overall response rate, while its recorded unit and parameter are participants and number. In general, a binary response classification assigns each assessed participant to a category such as response or no response under specified criteria. A count then records how many participants meet the response definition. A rate or proportion would also require a defined denominator. The registry record does not report the response criteria, denominator rules, response counts, or values at either assessment, so no rate or change can be derived.

For a change endpoint, the analysis also needs to specify how the two assessment times are compared and how participants without observations at one or both times are handled. The stated assessment timing is baseline and 4 weeks (±1 week) following the last ipilimumab administration. The exact analysis method, allowable assessment windows beyond that wording, and missing-observation rules are not reported in the registry record.

Why do confidence intervals matter?

In general, a confidence interval expresses the uncertainty around an estimate under a specified statistical method. Its width depends on the amount and variability of the data, as well as the method used. It helps readers distinguish a relatively precise estimate from one compatible with a broad range of values. No confidence interval or primary endpoint estimate is reported in the registry record, so the precision of the intended response assessment cannot be evaluated.

What does a p-value address?

In general, a p-value describes how compatible observed data are with a specified null hypothesis under the assumptions of a statistical test. It is not the probability that a treatment works, nor is it a measure of clinical importance. The interpretation depends on the hypothesis, analysis method, and data. No p-value, hypothesis, or test for the primary endpoint is reported in the registry record. The absence of a reported test does not establish whether one was planned or performed outside the record.

What does over-dispersion mean?

In general, over-dispersion occurs when the observed variability in count data exceeds what a chosen model assumes. If ignored, standard errors and confidence intervals can be misleading, and tests can be poorly calibrated. Whether this issue is relevant depends on the outcome and analysis model. The registry record does not report a model or variability estimate for the primary endpoint, so it is not possible to assess over-dispersion or say that a particular count model was used.

What can the safety counts establish?

For safety outcomes, the registry records how many participants were at risk and how many were affected in the listed categories. In general, counts should be interpreted alongside follow-up duration, event definitions, and the completeness of reporting. A zero recorded count means that no affected participants are listed for that category in the registry entry; it does not quantify the risk of events beyond the reported observation and definitions. Here, the record lists 26 at risk and 0 affected for both serious and other adverse events, but does not report event terms, follow-up duration, or a fuller safety analysis.

The registry lists no analyses. It does not report an analysis plan or statistical methods for the primary outcome. Therefore, no particular test, model, adjustment, or approach to uncertainty should be attributed to the study based on this 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("Ipilimumab and GM-CSF")
n      <- c(20)
events <- c(20)
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  Ipilimumab and GM-CSF  20  20  100.0  83.2  100.0  83.9  100.0  83.9  99.9

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists one primary outcome measure, change in immune-related overall response rate, and reports 0 analyses. It does not describe secondary endpoints or a family of statistical hypotheses. The analysis plan, including any planned comparisons or interim analyses, is not reported in the registry record. It is therefore not possible to determine whether multiplicity was addressed in the study's protocol or analyses. In general, when several outcomes or comparisons are tested, the chance of at least one apparently notable result can increase; prespecified procedures can account for that issue. This general point does not establish that multiple testing occurred in this study.

The record does not describe the primary endpoint analysis population. It also does not report the number assessed at baseline or at the later time, the number with paired assessments, exclusions, or reasons for missing data. These details matter because the participants contributing to an analysis may differ from the enrolled group. In general, missing observations can affect an estimate if availability is related to response or other participant characteristics. The direction and size of any such effect cannot be inferred without information about the missingness and the analysis approach.

No imputation method, sensitivity analysis, or other missing-data procedure is reported in the registry record. The 27 enrolled participants and the 26 listed as at risk for safety outcomes should not be assumed to represent identical analysis populations. The registry does not explain their relationship. With no endpoint counts or analysis description, the impact of missing data and the handling of analysis populations remain unknown.

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.

The registry lists the ipilimumab and GM-CSF group with 26 participants at risk for serious adverse events and 0 affected. For other adverse events, it also lists 26 at risk and 0 affected. These are counts in the posted record, not estimates from a comparison between treatment groups. No separate control group is described.

The death count is not reported in the registry record. The list of top serious adverse-event terms is empty, so no specific serious-event categories are identified there. This should not be rewritten as a reported death count of zero or as evidence that no event of any kind occurred. It means the record does not give that information in the corresponding entry.

In general, safety counts are interpreted in the context of how events were defined, how long participants were observed, and how complete the reporting was. Those details are not reported in the registry record. The study enrollment is listed as 27, while the safety risk count is 26; the record does not explain the difference. The counts describe what was posted, but do not on their own provide a full safety profile or a comparative estimate.

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

The record identifies a study of ipilimumab followed by GM-CSF in people with unresectable stage IIIC or stage IV melanoma. It gives the study as Phase I/II, open-label, single-group, and completed, with enrollment of 27. Its primary outcome is titled change in immune-related overall response rate and is timed at baseline and 4 weeks (±1 week) following the last ipilimumab administration.

Those details establish what the study was designed to examine at a broad level. They do not reveal the observed response counts, the size or direction of any change, or the precision of an estimate. The endpoint values and an analysis are not reported in the registry record. The meaning of the endpoint is also limited by the absence of response criteria and a stated analysis population.

The single-group design does not provide a randomized comparison with another treatment or a control. In general, a change observed within one group cannot by itself separate a treatment-related effect from other changes over time or differences in who was assessed. The record therefore does not establish a comparative effect. This is a design limitation, not a claim about an unreported result.

The safety entries record 0 affected among 26 at risk for both serious and other adverse events. The death count is not reported in the registry record, and no serious-event terms are listed. These entries are limited registry counts; they do not provide event definitions, follow-up duration, or a complete description of safety.

Overall, the record supports a description of the study design, treatment sequence, intended primary outcome, and posted safety counts. It does not support a numerical conclusion about the primary outcome, its statistical significance, or comparative effectiveness. A completed status does not replace the missing outcome results or analysis details.

14. Why This Trial Matters Statistically

This study illustrates an important distinction between a registered research question and a reported statistical result. The registry identifies a primary endpoint, its measurement unit, and assessment timing. Yet the outcome values and analysis are not reported in the registry record. Readers can identify what was intended to be measured without being able to estimate the observed change or assess its precision.

The single-group design also makes the comparison structure central to interpretation. Without a separate control group, a within-group change is not a randomized estimate of the difference between the combination and another treatment. This distinction matters whenever a response measure is described in language that may sound comparative: the design still determines which comparisons the data can support.

The record also separates enrollment from the safety population at risk: it lists 27 enrolled and 26 at risk for each reported safety category. Because the record does not explain that difference, it is a reminder that denominators should be tied to the specific outcome and population rather than assumed to equal enrollment. The primary endpoint population is not described.

Finally, the safety entries show why counts need context. The registry lists 0 affected for serious and other adverse events, but does not report follow-up duration, event definitions, or a death count. Clear reporting of analysis populations, outcome definitions, missing-data handling, and uncertainty would be needed to interpret those counts more fully. The statistical importance of this record lies in showing both what trial registration can document and what remains unavailable when results and methods are not reported.

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 important limitation for interpretation is that the registry record does not report the primary endpoint values or an analysis. Although the outcome is named and its assessment times are specified, response criteria, counts at each time, an estimate of change, and a measure of uncertainty are absent. This prevents a quantitative interpretation of the study's main question.

The study is single-group and open-label, with no concurrent comparator described. It therefore cannot provide a randomized treatment contrast. The registry record also does not describe the analysis population or the number of participants assessed at either endpoint time. Enrollment is 27, while the safety entries list 26 at risk; the record does not explain this difference.

Further endpoint-specific limitations include the absence of a response definition, rules for handling missing assessments, and a stated analysis method. The registry does not report a statistical plan, interim analyses, multiplicity handling, or sensitivity analyses. No conclusion about whether these procedures existed outside the registry entry can be drawn.

The safety information is limited to category-level counts: 0 affected among 26 at risk for serious adverse events and 0 affected among 26 at risk for other adverse events. The death count is not reported in the registry record, and no serious-event terms are listed. Follow-up duration and event definitions are also not reported, limiting interpretation of these counts.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Phase I/II Open-Label Study of Ipilimumab and GM-CSF Administered to Unresectable Stage IIIC and Stage IV Melanoma Patients — NCT02009397.
• Registry record last updated 2021-11-22; status last verified 2021-10.
• Results first posted 2021-11-22.
• 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

This completed, open-label Phase I/II study is listed as a single-group trial sponsored by the University of Louisville. The registry record gives enrollment as 27, with a start date of 2012-02 and primary completion of 2016-11. It concerns unresectable stage IIIC and stage IV melanoma, also listed as metastatic melanoma.

The intervention arm describes IV ipilimumab followed by subcutaneous GM-CSF, for up to 4 cycles. The primary endpoint is change in immune-related overall response rate, recorded as participants and assessed at baseline and at 4 weeks (±1 week) following the last ipilimumab administration.

The record reports no analyses or primary endpoint values. It lists 0 affected among 26 at risk for both serious and other adverse events. The death count is not reported in the registry record. Response criteria, analysis methods, and analysis populations are also not reported.