Ibrutinib and Brentuximab Vedotin in Treating Patients With Relapsed or Refractory Hodgkin Lymphoma: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ibrutinib and Brentuximab Vedotin in Treating Patients With Relapsed or Refractory Hodgkin Lymphoma (NCT02744612), a non-randomized phase 2 study. The primary outcome is Complete Response (CR) Rate.

2. Clinical Question

3. Trial Design

This was a multicenter phase II study of ibrutinib plus brentuximab vedotin in relapsed or refractory Hodgkin lymphoma. Its recorded allocation was nonrandomized, masking was absent, and the model was sequential. These design features matter when interpreting comparisons: the two dose groups were not formed through random allocation, and the registry specifically cautions that the arms are not a like-for-like control comparison.

Arm I used ibrutinib 420 mg by mouth once daily on days 1–21 and brentuximab vedotin 1.8 mg/kg intravenously on day 1. Arm II used ibrutinib 560 mg by mouth once daily on days 1–21 with the same brentuximab vedotin regimen. Cycles repeated every 21 days in the absence of disease progression or unacceptable toxicity. These details describe the recorded regimens; they do not establish that a dose difference caused any difference in outcomes.

The registry lists enrollment of 39, a start date of 2016-07-01, primary completion on 2021-03-03, and completed status. The record does not report a rationale for the planned enrollment, or enough detail to infer how the sequential transition between regimens was managed. The primary endpoint was complete response rate, with overall response rate listed as a secondary outcome. Numerical efficacy results are not reported in the registry record.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: 3 subjects didn't complete Cycle 1 and then were off treatment. So they are not evaluable for response.

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 Complete Response (CR) Rate, measured over Up to 8 months..

The primary endpoint was complete response rate, expressed as the percentage of evaluable participants with a confirmed complete response. The record says response was assessed using Cheson criteria based on the Lugano Classification, and gives a timeframe of up to 8 months. Confirmation is part of the endpoint definition: the target is not simply an initial indication of response, but a response meeting the specified complete-response criteria and confirmed according to the study definition.

A response proportion is a binary-outcome summary: each evaluable participant either meets the endpoint definition or does not. Reporting the proportion alongside a confidence interval helps distinguish the estimated response frequency from the uncertainty around that estimate. The registry describes an exact 95% confidence interval for the rate. However, neither the rate nor its interval is reported in the registry record, so the endpoint’s observed magnitude and precision cannot be assessed from this record.

The response population excludes 3 subjects who did not complete Cycle 1 and then went off treatment. That exclusion is material because the endpoint is defined among evaluable patients, rather than necessarily among all enrolled participants. The record does not report further rules for evaluability or for handling other missing response assessments.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

A binary endpoint records whether each participant meets a defined condition. For this study, the condition was a confirmed complete response under the stated Cheson criteria. The response rate is a proportion among evaluable participants. Its interpretation depends on both the endpoint definition and the population used as the denominator; excluding participants who are not evaluable can change the population to which the estimate applies.

A confidence interval expresses uncertainty around an estimate. In general, a 95% confidence interval is produced by a procedure designed to cover the underlying quantity at the stated rate over repeated applications under its assumptions. It is not a guarantee that a particular interval contains the true value, and it does not measure the probability that the treatment is effective. For a response proportion, the interval communicates how precisely the observed proportion estimates the response frequency in a comparable population.

The registry says that exact 95% confidence intervals were calculated for the complete response rate. An exact interval is a method for constructing uncertainty bounds for a binomial proportion without relying on a normal approximation to the sampling distribution. This can be useful when the amount of information is limited or the observed proportion is near the boundaries of its possible range. The record does not report the calculated interval limits or the response count, so the precision cannot be evaluated from the registry record.

The word exact describes the calculation procedure, not certainty about the endpoint definition, population, or generalizability. An interval can account for sampling variation under its statistical model, but it does not automatically account for selection into the evaluable population, measurement issues, missing data, or bias from nonrandom allocation. Those concerns require separate design and analysis information.

What does the study design permit?

Random allocation can help make treatment groups comparable with respect to both measured and unmeasured characteristics, on average. Here allocation was nonrandomized and the model was sequential. Thus, an observed difference between the two arms could be associated with the ibrutinib dose, but could also reflect differences in participant characteristics, timing, or other factors associated with assignment. The registry cautions that these arms are not a like-for-like control comparison. The record does not report an adjusted comparative analysis that would address such differences.

Masking was absent. In general, knowledge of treatment assignment can influence subjective aspects of care, assessment, or reporting. The degree to which this matters depends on the outcome and assessment procedures. The registry describes a confirmed response based on named criteria but does not report enough information to assess masking of response assessment or other safeguards against assessment bias.

How should planning illustrations be read?

The registry describes sample-size illustrations as planning calculations based on the observed effect, with a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. For non-time-to-event outcomes, such illustrations are expressed as participants per arm for 80% power or another stated planning target. These are planning illustrations, not observed power and not a report of the number of participants actually analyzed.

In general, a planning calculation asks how much information would be needed to detect a specified effect under stated assumptions. Its answer depends on the assumed effect, allocation, significance threshold, power target, and statistical approximation. A smaller effect to detect generally requires more information, all else equal. Such calculations do not establish that the planned study achieved the target, and they do not measure the probability that a result from a completed study is true.

The registry record does not report numerical illustration results or the observed effect used for those calculations. It also does not report the study’s own sample-size justification. The described illustrations therefore should not be mistaken for the trial’s design rationale or evidence of observed power. Their assumptions are planning assumptions rather than features that make the nonrandomized arms comparable.

What analysis details are not available?

The primary endpoint description names an exact interval procedure, but the registry record does not report a broader statistical analysis plan, model adjustments, interim analyses, or a detailed approach to missing outcome data. No inferential comparison between the dose groups is reported in the record. Without those details, it is not possible to assess whether other analyses were prespecified, how multiple endpoints were handled, or whether estimates were adjusted for differences among participants.

General statistical interpretation should separate estimation from comparison. A response proportion estimates the frequency of the endpoint in its analysis population. A comparison asks whether outcomes differ between groups and, for a causal interpretation, requires design and analysis assumptions that support attribution. A confidence interval around a single group’s proportion addresses sampling uncertainty for that estimate; it does not remove confounding or create a randomized comparison.

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("Arm I: Ibrutinib 420 mg PO QD + BV 1.8 mg/kg IV Q2", "Arm II: Ibrutinib 560 mg PO QD + BV 1.8 mg/kg IV Q")
n      <- c(3, 33)
events <- c(0, 12)
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  Arm I: Ibrutinib 420 mg PO QD + BV 1.8 mg/kg IV Q2  3  0  0.0  0.0  70.8  0.0  56.1  0.6  60.2
ARM  Arm II: Ibrutinib 560 mg PO QD + BV 1.8 mg/kg IV Q  33  12  36.4  20.4  54.9  22.2  53.4  22.2  53.5

11. Multiplicity, Missing Data and Analysis Populations

The registry identifies complete response rate as the primary outcome and overall response rate as a secondary outcome. When a study evaluates more than one endpoint, the chance of at least one apparently notable result can increase if each is tested separately without accounting for the set of analyses. Statistical approaches to multiplicity can control that issue, but the registry record does not report a multiplicity strategy or a hierarchy for interpreting outcomes. It also does not report inferential analysis results for these endpoints.

The record describes the complete response rate among evaluable patients and explicitly excludes 3 subjects who did not complete Cycle 1 and then went off treatment. This is an analysis-population rule recorded for response. The registry does not report further evaluability criteria, how other incomplete or missing response assessments were handled, or whether analyses using a broader population were performed.

In general, missing outcome data can affect an estimate when the chance that an outcome is unobserved is related to the outcome itself or to participant characteristics. Excluding participants can yield an estimate for the evaluable population, but its relevance to all enrolled participants depends on why data are missing and on the study question. The registry does not report imputation methods, sensitivity analyses, or reasons for missingness beyond the stated early discontinuations.

The registry record does not report a detailed analysis plan, interim analyses, or methods for handling multiplicity and missing data beyond the response-evaluability statement. These omissions limit assessment of how robust any endpoint conclusions would be to alternative analysis choices.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: colitis (5.6%), infections and infestations - other, specify (5.6%), febrile neutropenia (2.8%), diarrhea (2.8%), fever (2.8%).

The safety record gives serious adverse event counts by arm. In Arm I, 0 of 3 participants at risk were recorded as affected by a serious adverse event; in Arm II, 10 of 36 were recorded as affected. These are descriptive counts for the groups recorded, not a randomized comparison. The different group sizes and nonrandom allocation mean that a contrast between the figures cannot be interpreted as an isolated treatment-dose effect.

The record also lists other adverse events: 3 of 3 at risk in Arm I and 36 of 36 in Arm II were affected. These figures are separate from the serious adverse event counts and should not be combined with them. The registry lists deaths as 2 in each arm, but does not report their causes or whether they were considered related to treatment.

Selected serious event terms include colitis and infections and infestations—other, specify, each listed as 5.6%; febrile neutropenia, diarrhea, fever, and upper respiratory infection are each listed as 2.8%. The registry record does not give additional detail on event timing, recurrence, severity grading, or causal attribution. Counts and percentages describe recorded events; they do not by themselves establish that the study drugs caused them.

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

The registry record establishes that a phase II study evaluated a combination of ibrutinib and brentuximab vedotin in relapsed or refractory Hodgkin lymphoma, using two ibrutinib dose regimens. It also establishes that complete response rate was the primary endpoint, assessed among evaluable participants and defined using the named response criteria. These details clarify the study question, but the record does not report the numerical primary endpoint result.

Without the observed complete response rate and its confidence interval, the magnitude and precision of the response estimate cannot be judged. The registry also does not report a numerical overall response rate. Therefore, the record does not establish how often participants achieved either outcome. It cannot support a claim about the size of an effect or whether an effect was statistically distinguishable from a reference value.

The design does not support a straightforward causal comparison between the two dose regimens. Allocation was nonrandomized and sequential, and the registry explicitly states that the arms are not a like-for-like control comparison. Any difference in recorded outcomes could have explanations beyond the dose regimen itself. The registry record does not report a randomized comparison or an adjusted analysis that would resolve this limitation.

Safety figures document recorded events in the groups, including serious events, other events, and deaths. They do not establish causation, and the information recorded does not explain the cause of deaths or provide all details needed to compare safety across groups. These counts should be interpreted as descriptive rather than as proof that an outcome was caused by one regimen.

More generally, a study result applies most directly to the population and conditions represented by the study. The response population excludes subjects who did not complete Cycle 1 and went off treatment. The registry does not provide enough detail to determine how that exclusion, other missing assessments, or participant selection affects generalizability. The record supports a careful description of design and endpoint definitions, but not a conclusion that either regimen is superior or that the combination does or does not work.

14. Why This Trial Matters Statistically

This trial is statistically notable because it asks about response to a drug combination while recording two different ibrutinib regimens in a nonrandomized, sequential design. That distinction matters: a study can describe outcomes within each group, but the groups do not automatically provide a valid causal comparison. Randomization is one way to reduce systematic differences between groups; it was not used here, and the registry cautions that the arms are not a like-for-like control comparison.

The primary endpoint also illustrates the importance of defining an analysis population. Complete response rate was calculated among evaluable patients, and the record states that 3 subjects did not complete Cycle 1 and then went off treatment. The estimate, if reported, would therefore describe the evaluable population under the study’s definition. It should not be assumed to represent every enrolled participant without understanding the exclusions and missingness.

Precision is as important as the response estimate itself. The record says that an exact 95% confidence interval was calculated, which is an appropriate kind of uncertainty summary for a binary proportion. Yet neither the proportion nor interval is reported in the registry record. This prevents readers from assessing whether the estimate is precise or highly uncertain.

The study also underscores the distinction between a planning calculation and evidence from observed outcomes. Sample-size illustrations use stated assumptions, but they are not observed power and do not remedy limitations in allocation or analysis. Overall, the statistical importance lies in reading the design, endpoint population, uncertainty, and safety descriptions together, while recognizing that key efficacy results are absent from this registry record.

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 consequential limitation of the registry record is that it does not report the numerical complete response rate or its confidence interval, despite describing the endpoint and the calculation of an exact interval. The numerical overall response rate is also not reported. This prevents evaluation of efficacy magnitude, precision, and consistency across the named outcomes.

The study was nonrandomized and sequential, with no masking. The registry explicitly warns that the arms are not a like-for-like control comparison. This limits interpretation of differences between the ibrutinib dose groups, since the record does not establish that participant characteristics or other factors were balanced. A detailed adjusted analysis is not reported.

Response was assessed among evaluable participants, and the record excludes 3 subjects who did not complete Cycle 1 and then stopped treatment. The registry does not report additional evaluability rules, missing-data procedures, or sensitivity analyses. It is therefore not possible to assess how other unavailable response assessments were handled or how the exclusion affects the interpretation of the endpoint.

The record does not report the study’s sample-size justification, a detailed statistical analysis plan, interim analyses, or a strategy for multiplicity. It describes planning illustrations but does not give their numerical results or the effect used. Safety information is also limited: causes and treatment relationships for deaths, detailed event timing, and further event-level context are not reported. These limitations constrain interpretation of both comparative outcomes and the completeness of the safety picture.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Ibrutinib and Brentuximab Vedotin in Treating Patients With Relapsed or Refractory Hodgkin Lymphoma — NCT02744612.
• Registry record last updated 2026-11-06; status last verified 2026-10.
• Results first posted 2023-07-10.
• 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 describes a completed multicenter phase II study of ibrutinib plus brentuximab vedotin in relapsed or refractory Hodgkin lymphoma. The recorded design was nonrandomized, unmasked, and sequential. Arm I used ibrutinib 420 mg once daily; Arm II used ibrutinib 560 mg once daily. Both arms used brentuximab vedotin 1.8 mg/kg every 21 days.

Complete response rate was the primary endpoint, defined among evaluable participants using the stated response criteria, with an exact 95% confidence interval. The record says 3 subjects were not evaluable after not completing Cycle 1 and going off treatment. Numerical primary and secondary efficacy results are not reported in the registry record. Serious adverse event counts and selected event percentages are listed, but causal attribution and a valid dose-group comparison cannot be inferred from this nonrandomized design.