Efficacy and Safety Evaluation of IBI308 in Treatment of Patients With Relapsed/Refractory Classical Hodgkin's Lymphoma: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety Evaluation of IBI308 in Treatment of Patients With Relapsed/Refractory Classical Hodgkin's Lymphoma (NCT03114683), a na phase 2 study. The primary outcome is Objective Response Rate (ORR) Assessed According to the Revised International Working Group Response Criteria for Malignant Lymphoma in 2007(IWG 2007) by the Independent Radiological Review Committee (IRRC)..

2. Clinical Question

3. Trial Design

NCT03114683 is recorded as a completed, multicenter, single-arm phase II study of IBI308 in patients with relapsed or refractory classical Hodgkin's lymphoma. The registry lists an enrollment of 96. The study started on 2017-03-30, and its primary completion date is 2019-09-12. These dates describe the registry record; they do not give the duration of follow-up for each participant.

With a single group and no randomized allocation, the study describes outcomes among participants who received the intervention rather than estimating a treatment contrast against a concurrent control group. The record lists no masking. It does not report a comparator arm, allocation procedure, or details about how participants entered the study. The listed arm description is empty.

The primary outcome is objective response rate assessed according to the revised 2007 International Working Group criteria by an independent radiological review committee. The listed timeframe is up to 2 years. The brief summary also names complete response, partial response, disease control rate, duration of response, progression-free survival, and safety as study aims. However, the record lists one outcome measure, and does not give results or analysis details for these other aims.

Further protocol information, including eligibility criteria, dosing, visit schedules, and the rationale for the enrollment target, is not reported in the registry record. The phase designation alone does not establish which design or analysis decisions were made.

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 Objective Response Rate (ORR) Assessed According to the Revised International Working Group Response Criteria for Malignant Lymphoma in 2007(IWG 2007) by the Independent Radiological Review Committee (IRRC)., measured over Up to 2 years.

The primary endpoint is objective response rate, expressed as the percentage of participants with an overall response. Under the listed 2007 International Working Group criteria, overall response is the combination of complete response and partial response. Complete response is described as disappearance of all target lesions. Partial response requires at least a 50% decrease in the sum of the products of diameters of up to 6 largest dominant masses, with no increase in the size of other nodes. Assessment was by CT and PET and was assigned by an independent radiological review committee.

Response rate is a binary-outcome summary: each participant is classified as having met or not met the response definition within the assessment process, and the group result is expressed as a percentage. It is used to describe the frequency of a defined response, rather than the time until an event. A confidence interval communicates uncertainty around the estimated response percentage; it does not account for every possible source of bias or make a single-arm result comparative.

The registry lists a 95% confidence interval and a timeframe of up to 2 years. It does not report the response estimate, the confidence-interval limits, or details of how the endpoint was analyzed.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Several general statistical ideas help frame the registry record, but the record does not report the full analysis plan or the numerical primary-endpoint result. The explanations below distinguish general principles from study-specific information.

What does a response percentage describe?

For a binary endpoint, each participant is classified according to whether a defined event or condition occurred. Here, the endpoint definition combines complete and partial response under the stated criteria. A response percentage describes the share of the analyzed group meeting that definition. Its interpretation depends on how the analysis population was defined, how assessments were handled when unavailable, and the assessment schedule. Those details are not reported in the registry record.

The endpoint is assessed by an independent radiological review committee, according to the title. Independent review can help separate endpoint assessment from the treating team's judgments, but the record does not describe the committee's procedures, whether assessments were blinded, or how disagreements were resolved. The study itself is listed as having no masking; that does not establish whether any separate review process was masked.

What does a confidence interval add?

As a general statistical concept, a confidence interval expresses uncertainty in an estimate under a specified statistical method. For a response percentage, the estimate is a proportion and the interval gives a range around that estimate. The interval's width depends on information such as the number of participants contributing to the analysis and the observed response pattern, as well as the method used. A 95% confidence interval is listed for this endpoint, but the estimate, interval limits, analysis denominator, and interval method are not reported in the registry record. Therefore the interval cannot be interpreted or checked.

A confidence interval does not mean that the true value has a 95% probability of lying in the particular calculated interval under the usual frequentist interpretation. Rather, the confidence level describes the long-run behavior of the method under its assumptions. Nor does an interval resolve design limitations: it quantifies sampling uncertainty, not selection bias, outcome misclassification, or the absence of a comparator.

Why does the single-group design matter?

In a randomized comparison, an analysis can estimate a contrast between assigned groups, subject to the design and analysis assumptions. In a single-group study, the response percentage instead describes the enrolled group. There is no internal control group to estimate what would have occurred to a comparable group under a different condition. Historical or external comparisons would require separate data and careful assumptions; none is reported in the registry record. This is why the endpoint should not be read as a randomized treatment effect.

The registry lists no masking. Masking can, in general, limit the influence of knowledge about assignment on some study procedures or assessments. In this study there is no listed randomized assignment to mask, and the record does not explain masking for outcome review or other procedures. The independent review committee is named as the assessor, but its masking status is not reported.

What do the planning assumptions mean?

The planning assumptions describe an illustration based on an observed effect, not the study's original design. They specify a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect expressed as a fraction of the observed effect. For time-to-event illustrations, the stated quantity is total events; other illustrations refer to participants per arm. These are general planning conventions, not evidence that the trial used two arms or had a randomized comparison. The study is recorded as single-group, and no numerical planning results or original sample-size justification are reported in the registry record. Such illustrations are not observed power and should not be interpreted as results from participants.

In general, a sample-size calculation depends on assumptions about the effect to detect, variability or event frequency, error rates, allocation, and analysis method. A calculation can illustrate how those assumptions relate to a target sample size, but it cannot establish that a study is adequately powered for every question. The registry record does not report the assumptions behind its enrollment of 96 or a formal power calculation.

Why can over-dispersion matter?

For outcomes modeled as counts or rates, over-dispersion means that variation in the observed data is greater than a model assumes. If ignored, standard errors may be too small and confidence intervals too narrow. This is a general consideration for count-based analyses; the listed primary endpoint is a percentage, and the registry does not report a count-model analysis or any assessment of over-dispersion. No claim about its role in this study can be made.

Likewise, the record does not state whether the primary analysis was adjusted, how multiple outcomes were handled, or what statistical tests were used. The endpoint title and its confidence-interval label do not supply those missing methodological details.

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("Sintilimab")
n      <- c(96)
events <- c(82)
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  Sintilimab  96  82  85.4  76.7  91.8  77.0  91.1  77.0  91.1

11. Multiplicity, Missing Data and Analysis Populations

The brief summary names several study aims: objective response rate, complete response, partial response, disease control rate, duration of response, progression-free survival, and safety. The registry lists one outcome measure, with objective response rate as the primary endpoint. It does not report a testing hierarchy, multiplicity adjustment, or plan for interpreting several endpoint tests together. These details are not reported in the registry record.

In general, evaluating multiple outcomes or making repeated statistical tests can increase the chance of at least one apparently notable result arising by chance. A prespecified hierarchy or adjustment can help control that issue, but the suitable approach depends on the aims and analysis plan. No particular approach can be attributed to this study from the registry record.

The record also does not report how missing response assessments were handled, how many participants contributed to the primary analysis, or the analysis population definition. These choices matter because the denominator and treatment of unavailable assessments can affect a percentage estimate. No missing-data method, sensitivity analysis, or imputation procedure is reported. Without these details—and without a numerical endpoint result—neither the impact of missing data nor the robustness of the primary estimate can be assessed.

The registry does not report interim analyses, stopping rules, or a statistical analysis plan. Their presence or absence should not be inferred from the completed status or from the phase designation.

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: pneumonitis (7.3%), lung infection (3.1%), pneumonia (2.1%), upper respiratory tract infection (2.1%), death (2.1%).

The registry's adverse-event group is labeled Sintilimab. It lists 96 participants at risk for serious adverse events and 24 affected by serious adverse events. For other adverse events, it lists 96 at risk and 96 affected. The record also lists 3 deaths. These are reported counts; the registry does not explain the relationship between the intervention label IBI308 and the adverse-event group label Sintilimab.

The serious-event terms listed with percentages are pneumonitis, 7.3%; lung infection, 3.1%; pneumonia, 2.1%; upper respiratory tract infection, 2.1%; death, 2.1%; and pleural effusion, 1.0%. The registry record does not provide further detail about event definitions, severity grading, timing, duration, or whether participants could contribute more than one event term. The term list should not be assumed to represent mutually exclusive participant groups.

Counts and percentages describe reported events in the study group; without a concurrent comparator they do not estimate an excess risk attributable to the intervention. The record does not report a causal assessment or enough detail to interpret the listed terms beyond their recorded frequencies.

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

The record establishes that a completed, multicenter, single-arm phase II study enrolled 96 patients with relapsed or refractory classical Hodgkin's lymphoma and assessed objective response rate using criteria specified in the registry. It also provides selected adverse-event counts and serious-event terms. These details describe the study's scope and some of its reporting, but they are not a complete account of clinical outcomes.

The record does not report the primary response-rate estimate or the limits of its 95% confidence interval. It also does not give numerical results for the additional outcomes named in the brief summary. As a result, the posted information does not permit an assessment of the observed response frequency, the precision of that estimate, or those other outcomes.

Even if a response percentage were available, a single-group result would describe participants in the study rather than establish a comparison with an alternative. A treatment effect is a contrast, and this record has no concurrent control group. This is a general interpretation point, not a judgment about the study's conduct or the value of its findings.

The safety counts similarly describe events recorded in the study group. They do not alone determine whether an event was caused by treatment, and they cannot establish how event frequency compares with another group. The registry lacks the additional contextual information needed for those interpretations.

Accordingly, the appropriate statistical reading is limited: the design, endpoint definition, listed timeframe, enrollment, and reported safety figures can be described, while the unreported efficacy result and analysis details remain unknown. No treatment recommendation follows from these registry entries.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of the distinction between an endpoint definition and an endpoint result. The registry specifies objective response rate, the response criteria, the independent review committee, and a 95% confidence interval. But it does not report the estimate or interval. A well-defined outcome can clarify what a study intended to measure, while still leaving readers unable to evaluate the observed result when the numerical estimate is absent.

The single-group design also makes the target of inference important. A response percentage in one enrolled group is descriptive; it is not a randomized contrast. Readers need to distinguish a summary of observed outcomes from evidence about differences between treatment options. This distinction applies broadly to clinical studies, regardless of the particular disease or intervention.

The registry additionally shows why reporting methods matter. The analysis denominator, missing-data handling, multiplicity plan, and confidence-interval method affect how an estimate should be understood. Those elements are not reported in the registry record. Safety reporting is likewise easier to interpret when the event definitions, assessment procedures, and relationship between event counts and participant counts are clear.

The posted information therefore supports careful questions about reporting completeness and interpretation, rather than a conclusion about efficacy. The listed design and safety details are useful context, but they cannot replace the missing primary result or a comparator-based analysis.

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 principal limitation for interpreting efficacy is that the registry record does not report the objective response rate or its 95% confidence interval. Without these, the observed frequency and its precision are unknown. The record also does not report numerical results for the other outcomes mentioned in the brief summary.

The single-arm design has no concurrent control group, so it cannot provide a direct randomized comparison. The record lists no masking, and does not describe the independent review committee's procedures or masking status. The listed assessment timeframe is up to 2 years, but participant-level follow-up duration and assessment schedules are not reported.

Further limitations arise from missing reporting detail. The registry does not report the primary analysis population, endpoint denominator, missing-assessment handling, statistical method for the confidence interval, multiplicity strategy, or original sample-size justification. Eligibility details, intervention dosing, and the arm description are also not provided in the record. These omissions limit evaluation of reproducibility and of how broadly results might apply.

The safety figures are limited to listed counts and terms. Definitions, timing, severity grading, causal assessments, and event-level detail are not reported. The adverse-event group label differs from the intervention label, and the registry does not explain that difference. These limitations constrain interpretation of the safety entries as well as comparison with other groups.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Efficacy and Safety Evaluation of IBI308 in Treatment of Patients With Relapsed/Refractory Classical Hodgkin's Lymphoma — NCT03114683.
• Registry record last updated 2020-12-07; status last verified 2020-11.
• Results first posted 2020-12-07.
• 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

NCT03114683 is a completed multicenter, single-arm phase II study evaluating IBI308 in patients with relapsed or refractory classical Hodgkin's lymphoma. The registry lists enrollment of 96, no masking, and an objective response rate primary endpoint assessed by an independent radiological review committee under the 2007 International Working Group criteria. The stated timeframe is up to 2 years.

The record does not report a primary response-rate estimate, confidence-interval limits, or analysis details. It lists selected adverse-event counts and serious-event terms, with the adverse-event group labeled Sintilimab. No concurrent comparator is listed, so the study does not provide a randomized treatment contrast.