Itacitinib + Everolimus in Hodgkin Lymphoma: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Itacitinib + Everolimus in Hodgkin Lymphoma (NCT03697408), a non-randomized phase 1, phase 2 study. The primary outcome is Phase II: Efficacy of Itacitinib in Combination With Everolimus.

2. Clinical Question

The question is descriptive of response within the study population, rather than a direct estimate of how the combination compares with another treatment. The registry also lists secondary efficacy outcomes covering overall response rate, partial response, stable disease, duration of response, progression-free survival, and overall survival. Those outcomes broaden the kinds of disease response and time-to-event measures considered, but their outcome labels alone do not establish that estimates have been posted.

The registry record does not report the observed CR percentage or its 95% confidence interval. As a result, the central efficacy question cannot be answered from the posted results described in the record. The population and endpoint define what was intended to be evaluated; they are not themselves evidence of the observed response.

3. Trial Design

This is an open-label Phase I/II study with non-randomized allocation and a single-group model. The registry lists classical Hodgkin lymphoma as the condition and describes enrollment of subjects with relapsed or refractory disease. The sponsor is the University of Pennsylvania. The study start date is 2019-02-11, the primary completion date is 2024-05-20, and the status is active, not recruiting.

The treatment is the combination of itacitinib and everolimus. Three dose cohorts are described: Cohort -1 received itacitinib 200 mg once daily with everolimus 5 mg once daily; Cohort 1, identified as the starting dose, received itacitinib 300 mg once daily with everolimus 5 mg once daily; and Cohort 2 received itacitinib 400 mg once daily with everolimus 5 mg once daily. The registry record does not report how participants were assigned among these cohorts, whether dose decisions followed a particular escalation procedure, or the detailed operational rules for changing or stopping treatment.

Open-label means masking is listed as none: treatment assignment was not blinded. Non-randomized means the registry does not describe random assignment to treatment groups. Because the model is single group and no independent comparator is listed, differences between dose cohorts cannot be interpreted as randomized treatment effects. Cohort membership could reflect factors other than dose, and the registry record does not report enough detail to assess those factors.

The record identifies a Phase II primary efficacy outcome and also includes a Phase I component in the study title and phase listing. It does not report the protocol’s separate objectives for each phase or the rules used to move between phases. The enrollment figure is 23, but the registry record does not report a breakdown of enrollment by cohort or an analysis population for the efficacy endpoint. The study is active, not recruiting; this status does not by itself indicate that final efficacy results are available.

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.

Phase I (Dose Finding)

Phase II (Treatment)

Analysis population for the primary outcome, as defined in the registry: Efficacy will be assessed by CR rate, defined as the percentage of subjects achieving Complete Response (CR) as their best 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.

Population: Cohorts into which subjects with relapsed/refractory classical Hodgkin lymphoma (cHL) were enrolled. No subjects were enrolled into Cohort -1 (starting dose of itacitinib 200 mg in combination with everolimus 5 mg).

6. Primary Endpoint

The registry lists the primary outcome as Phase II: Efficacy of Itacitinib in Combination With Everolimus, measured over 2 Years.

The primary endpoint is the Phase II efficacy of itacitinib in combination with everolimus, measured as the percentage of subjects achieving complete response (CR) as their best response. The stated timeframe is 2 Years, and the planned measure includes a 95% confidence interval. The registry describes the endpoint as a CR rate among subjects with relapsed or refractory cHL.

A response proportion is useful for describing how many participants in a defined study population meet an outcome criterion. Using best response focuses on the strongest response recorded for each subject during the specified assessment period; the registry record does not report the criteria for determining CR, the assessment schedule, or how missing or unevaluable response assessments are handled.

A confidence interval communicates the precision of an estimated response percentage. In general, a wider interval indicates greater uncertainty about the population value compatible with the observed data, while a narrower interval indicates greater precision. The interval does not remove the limitations of a single-group, non-randomized design, and it does not establish a treatment effect relative to an unobserved control group.

The registry record does not report the observed CR percentage or its confidence interval. Consequently, the endpoint definition explains what was intended to be measured, but the posted record does not allow the magnitude or precision of the observed CR rate to be assessed.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The study’s design determines which statistical conclusions are reasonable. This trial is open-label, non-randomized, and described as single group. In general, randomization helps make treatment groups comparable with respect to both measured and unmeasured characteristics. Without random assignment and a separate control group, observed outcomes cannot isolate the effect of treatment from other possible explanations. The three dose cohorts are regimen groups, not randomized controls. The registry record does not report a statistical method for making causal comparisons between them.

What does a response percentage represent?

The primary endpoint is the percentage of subjects whose best response is CR during the stated timeframe of 2 Years. Conceptually, such an estimate uses a count of subjects meeting the response definition relative to a specified analysis population. The registry record does not report either the observed count or the resulting percentage, nor does it identify the analysis population in enough detail to determine who was included in the calculation. The response criteria and assessment procedures are also not reported in the registry record.

The endpoint is a proportion, not a time-to-event measure. Its interpretation depends on consistent outcome assessment and a clear rule for handling participants whose response cannot be determined. The registry record does not report how missing evaluations, early discontinuation, or unevaluable responses were handled. Without these details, it is not possible to assess whether the endpoint estimate, if calculated, would depend on assumptions about unobserved outcomes.

How should the confidence interval be understood?

A confidence interval expresses statistical uncertainty around an estimate. In general, it is a range calculated by a method intended to reflect the variability that would arise across repeated samples under the method’s assumptions. A confidence interval is not a guarantee that the true value lies in the particular interval, and it does not account automatically for bias from study design, incomplete follow-up, or outcome measurement.

The registry specifies a 95% confidence interval for the primary endpoint, but the registry record does not report the interval or the method used to calculate it. The observed percentage is also not reported, so the precision of the primary result cannot be assessed. A confidence interval around a single-group response estimate would describe uncertainty in that response estimate; it would not create a comparison with another treatment.

What do the secondary outcomes add?

The listed secondary outcomes include overall response rate, partial response, stable disease, duration of response, progression-free survival, and overall survival. Response categories describe status or response during assessment, whereas duration and survival outcomes involve time. In general, time-to-event analyses account for the time until an event or the end of observation, and can incorporate participants whose event has not been observed by the analysis cutoff. The registry record does not report the event definitions, censoring rules, analysis methods, or estimates for these outcomes.

The record lists 7 outcome measures and 0 analyses. That means the registry record does not contain posted analyses in the information described. It does not establish whether analyses were performed outside the registry or whether results exist elsewhere. No model, adjustment strategy, subgroup analysis, or interim analysis is reported in the registry record.

How do the safety counts differ from an efficacy analysis?

The adverse-event information is presented as counts of subjects at risk and affected within cohorts, plus death counts. Counts are useful for describing what the record reports, but their interpretation depends on definitions, observation time, and whether people can be counted in multiple event categories. Those details are not reported in the registry record. The counts do not by themselves estimate a rate over time or support a comparison between dose groups.

The listed serious-event terms have percentages, including shingles at 33.3% and fever at 10.0%. The registry record does not state the denominator or detailed counting rule for these term-level percentages. They should therefore be retained as reported and not reinterpreted as a common risk measure across cohorts.

What do planning calculations mean?

The described planning illustration uses a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. For time-to-event outcomes, the stated method gives the total number of events using Schoenfeld; other planning outputs are described as participants per arm. These are planning assumptions, not details of the trial’s own design, and any resulting sample sizes are illustrations rather than observed power. The registry record does not report the trial’s sample-size justification or its own statistical design assumptions. A two-arm, equal-allocation planning setup also differs from the actual single-group, non-randomized design, so it should not be read as evidence that the trial enrolled randomized arms.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary CR-rate endpoint and multiple secondary efficacy outcomes: overall response rate, partial response, stable disease, duration of response, progression-free survival, and overall survival. Considering several outcomes can create a multiplicity issue: when many hypotheses are tested, the chance of at least one apparently notable result may increase. In general, a prespecified testing hierarchy or an adjustment procedure can address some multiplicity concerns. The registry record does not report whether any such strategy was planned or used, so no adjustment or control of type I error should be assumed.

The record also does not report whether there were interim analyses, subgroup analyses, or prespecified comparisons among dose cohorts. Details about hypothesis tests, confidence-interval methods, model specifications, and analysis cutoffs are not reported in the registry record. The record lists 0 analyses, and it does not provide inferential results for the primary or secondary outcomes.

Missing-data handling is important for a response percentage because participants without an evaluable response may affect the analysis population and the estimate. The registry record does not report how missing assessments, withdrawal, or unevaluable response status were treated. It also does not report an intention-to-treat, per-protocol, safety, or other analysis-population definition. The enrollment of 23 does not, by itself, establish how many participants contributed to each endpoint.

For time-to-event outcomes, methods usually require rules for defining events and censoring participants whose event status is not observed during follow-up. Those rules, along with follow-up completeness, are not reported in the registry record. These omissions limit assessment of potential bias and precision; they do not establish that any particular method was or was not used outside the registry record.

11. 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: shingles (33.3%), fever (10.0%), sinus tachycardia (5.0%), enterocolitis (5.0%), sepsis (5.0%).

The safety entries are cohort-specific counts. Cohort 1 (Starting Dose) lists 3 subjects at risk for serious adverse events and 1 affected; for other adverse events, 3 are listed at risk and 3 affected. The death count is 1. Cohort 2 lists 20 at risk and 6 affected for serious adverse events, 20 at risk and 20 affected for other adverse events, and 7 deaths. Cohort -1 lists zero at risk and zero affected in both event categories, and zero deaths.

These figures describe the registry entries and are not adjusted comparisons. Cohort -1’s zero at-risk count does not show that no event could occur in that cohort; it indicates that the registry lists no subjects at risk in those entries. The record does not report the timing, exposure duration, event severity grading rules, or follow-up associated with these counts. It also does not explain whether one subject can contribute to more than one adverse-event term.

The serious-event terms are listed with percentages: shingles, 33.3%; fever, 10.0%; sinus tachycardia, 5.0%; enterocolitis, 5.0%; sepsis, 5.0%; and upper respiratory infection, 5.0%. Their denominators and counting rules are not reported in the registry record. These entries should be read as reported, without treating them as directly comparable risks across cohorts or as a complete account of every adverse event.

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

The record establishes that an open-label, non-randomized Phase I/II study evaluated itacitinib in combination with everolimus in subjects with relapsed or refractory cHL. It describes three dose regimens and identifies CR as the Phase II primary efficacy endpoint. This information defines the clinical and statistical question, but it does not answer that question.

The key efficacy result—the percentage of subjects whose best response was CR—and its 95% confidence interval are not reported in the registry record. The secondary outcome labels also do not include corresponding estimates. Consequently, the posted record does not establish the observed response frequency, the precision of that response estimate, or outcomes for response duration, progression-free survival, or overall survival.

The safety entries provide descriptive counts by cohort, including counts affected by serious and other adverse events and deaths. They do not establish that a treatment caused an event, and the available information does not support a comparison of event risk between the cohorts. Differences in group size, follow-up, and other factors could matter; the registry record does not provide enough information to evaluate them. The term-specific percentages likewise lack reported denominators and counting rules.

A single-group study can describe outcomes among the participants studied, but it cannot by itself show what would have happened to a comparable group receiving a different treatment or no study treatment. Without a control group, observed outcomes cannot be attributed uniquely to the combination. The non-randomized cohort structure also does not support interpreting differences among regimens as treatment effects.

Accordingly, the record supports a description of the study design, planned outcome, and posted safety counts, but not a conclusion that the combination is effective, ineffective, safer, or less safe than another option. Any such conclusion would require results and comparative evidence that are not reported in the registry record.

13. Why This Trial Matters Statistically

This trial is statistically informative as an example of how study design shapes the claims an endpoint can support. The primary CR-rate outcome is a proportion, and its planned confidence interval would describe the precision of the estimated response percentage in the study population. But precision and comparability are different issues: even a precise estimate from a single group would not supply the missing counterfactual needed for a treatment comparison.

The three listed regimens make dose description an important part of the study record. Yet the cohorts are non-randomized, and the registry does not report how participants entered each cohort or the rules governing dose selection. Statistical comparisons across those cohorts could therefore reflect differences in participants or study conduct as well as differences in regimen. The cohort labels alone do not establish a dose-response relationship.

The record also illustrates why outcome definitions and outcome results must be distinguished. It lists CR as the primary endpoint and multiple secondary outcomes, but does not report their estimates or analyses. A reader can identify the intended domains of efficacy assessment without being able to assess observed efficacy. Similarly, safety counts are useful descriptive information, but counts without relevant follow-up and denominator definitions do not provide a complete comparative safety analysis.

Finally, the registry’s active, not recruiting status and its recorded primary completion date provide study-status context, not a statistical conclusion. The absence of posted analyses means uncertainty remains about the planned efficacy question. For clinical researchers, this distinction helps prevent a study’s rationale, structure, or endpoint list from being mistaken for evidence about its outcome.

14. 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 observed CR percentage or its 95% confidence interval. It also does not report estimates for the secondary efficacy outcomes or analyses for any listed outcome. Thus the planned endpoint cannot be used to assess the magnitude or precision of response from this record.

The single-group, non-randomized design has no separate control arm. It cannot support a randomized comparison, and the dose cohorts are not a like-for-like control comparison. The registry record does not report how participants were assigned to cohorts, the decision rules for dose selection, or cohort-specific enrollment for efficacy. Those omissions constrain interpretation of any between-cohort differences.

The registry record does not report detailed CR criteria, response-assessment timing, analysis-population definitions, missing-data procedures, or follow-up completeness. It also does not report event definitions or censoring rules for time-to-event outcomes. These details are needed to evaluate how outcomes were classified and how participants with incomplete observation contributed to estimates.

Safety counts are presented without reported exposure duration or enough detail about event ascertainment and denominators to interpret them as rates. The record does not clarify the denominator for the percentages attached to serious-event terms, or whether individuals may appear under multiple terms. The counts should therefore be treated as descriptive entries rather than comparative estimates.

The registry record lists 0 analyses and does not report the statistical plan, multiplicity approach, interim analyses, or sample-size justification. The status is active, not recruiting, but this does not supply the missing results. These limitations describe what can be assessed from the registry record; they do not establish whether additional information exists outside it.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Itacitinib + Everolimus in Hodgkin Lymphoma — NCT03697408.
• Registry record last updated 2026-06-23; status last verified 2026-06.
• Results first posted 2025-05-30.
• 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.

18. Record Summary

NCT03697408 is an open-label, non-randomized Phase I/II single-group study of itacitinib with everolimus in subjects with relapsed or refractory classical Hodgkin lymphoma. The sponsor is the University of Pennsylvania. The registry lists enrollment of 23, a start date of 2019-02-11, primary completion on 2024-05-20, and status active, not recruiting.

Three dose cohorts are listed, with itacitinib doses of 200 mg, 300 mg, and 400 mg once daily, each combined with everolimus 5 mg once daily. The primary Phase II endpoint is the percentage achieving CR as best response over 2 Years, with a planned 95% confidence interval. Secondary outcomes include overall response rate, partial response, stable disease, duration of response, progression-free survival, and overall survival.

The record includes cohort-level safety counts, but does not report the primary efficacy estimate, its confidence interval, or analyses for the listed outcomes. The registry record does not report the detailed analysis plan, missing-data rules, or analysis populations.