Chemotherapy for Participants With Lymphoma: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Chemotherapy for Participants With Lymphoma (NCT00436280), a na phase 2 study. The primary outcome is Percent of Participants With Progression Free Survival (PFS) After 1 Year Treatment.

2. Clinical Question

The study also listed outcomes concerning response, progression-free survival (PFS), overall survival, event-free survival, biomarkers and enzastaurin pharmacokinetics. These are different questions: some describe disease status over time, while others concern response categories, biological features or drug exposure. Their inclusion does not make the study a controlled comparison, and the registry record does not report numerical results for them in the information available for this analysis.

3. Trial Design

This was an open-label, single-group phase 2 study of enzastaurin with R-GEMOX in participants with relapsed DLBCL. The registry lists Eli Lilly and Company as sponsor, enrollment of 68, and the study status as completed. Allocation is listed as not applicable and masking as none. These design features mean the listed study regimen was not compared with a concurrent randomized control group.

The primary endpoint was the percentage of participants with PFS after 1 year of treatment. The registry defines the time origin as the first dose of study drug and the event as measured progressive disease or death from any cause. The endpoint description says PFS was estimated from the distribution of PFS times using Kaplan-Meier estimates. Participants not known to have died by the data cut-off and without documented progressive disease were censored at their last progression-free disease assessment.

The registry describes the primary analysis population as participants who received at least 1 dose, but also calls them “all randomized participants.” That phrasing sits uneasily with the single-group model and allocation listed as not applicable; the record does not explain the discrepancy. It additionally reports that 14 participants were censored for the primary outcome. The reason for censoring for each participant and the completeness of follow-up are not reported in the registry record.

Other outcomes included response rate, PFS at later follow-up points, overall and event-free survival, biomarker-related PFS analyses, and pharmacokinetic measures. These outcomes broaden the study’s descriptive scope, but do not supply a control group or resolve the uncertainty about treatment effects relative to another option. The registry record does not report the detailed statistical analysis plan, eligibility criteria, treatment schedule, or sample-size justification.

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.

Before assignment: Reasons reported are for discontinuation from study treatment.

Period 1: Induction

Reasons for not completing this period:

Period 2: Consolidation

Reasons for not completing this period:

Period 3: Maintenance

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All randomized participants who received at least 1 dose of study drug. Participants censored =14

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 Percent of Participants With Progression Free Survival (PFS) After 1 Year Treatment, measured over First Dose of Study Drug to Measured Progressive Disease or Death from Any Cause at 1 Year.

The primary endpoint is the estimated percentage of participants who remained free of measured progressive disease or death from any cause through 1 year after their first dose of study drug. It is a time-to-event outcome expressed as a rate at a specified follow-up time. The registry says it was estimated using the Kaplan-Meier distribution of PFS times rather than simply treating every participant without a recorded event as event-free.

In general, a time-to-event method can use information from participants with different lengths of follow-up. A participant with no recorded event may be censored at the last assessment at which progression-free status was known. Censoring means that the event time is not observed within the available follow-up; it does not establish that the event never occurred. The method relies on assumptions about how censoring relates to the chance of an event, and the registry record does not report analyses testing those assumptions.

PFS combines measured progression and death from any cause into the endpoint event. This makes it a broader measure of time without documented progression or death than a response measure, which classifies tumor response. The endpoint may describe disease control over follow-up, but in a single-group study it cannot by itself establish what would have happened under a different treatment. The primary estimate and its 95% confidence interval are not reported in the registry record, so the magnitude and precision of the result cannot be assessed from the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is a time-to-event measure reported as a percentage at 1 year. Its time origin is the first dose of study drug. The event is the first measured progressive disease or death from any cause. The registry describes the estimate as a Kaplan-Meier rate derived from the distribution of overall PFS times.

What does Kaplan-Meier estimation do?

General explanation: Kaplan-Meier estimation summarizes the probability of remaining free of the defined event over follow-up while accounting for participants whose event time is not observed. It updates the estimated event-free proportion as event times occur. Participants who have not had an event by their last known assessment can contribute information up to that point, after which their follow-up is censored. The method is useful when follow-up lengths vary, but it does not remove the need to describe follow-up completeness or examine whether censoring may be informative.

The registry says that participants not known to have died by the data cut-off and without progressive disease were censored at their last progression-free disease assessment. This describes the stated censoring rule. It does not tell readers why each participant stopped contributing follow-up, whether the reasons were related to prognosis, or how the censoring pattern affected the estimate. Those details are not reported in the registry record.

How should the confidence interval be read?

The primary outcome specifies a 95% confidence interval. General explanation: a confidence interval expresses sampling uncertainty around an estimate, under the statistical method and its assumptions. It is not a guarantee that the true value lies within a particular calculated interval. Its width helps convey precision. The numerical confidence limits are not reported in the registry record, so no assessment of the primary estimate’s precision is possible from this information.

The endpoint is described as a rate or percentage at a particular follow-up time, not as the proportion of the original group known to have avoided an event under complete observation. Kaplan-Meier estimation is intended to incorporate censored follow-up. It should not be interpreted as eliminating missing-outcome concerns: censoring is a statistical treatment of incomplete event-time information, and the validity of the estimate depends on assumptions about that process.

What can a single-group result establish?

General explanation: an outcome rate in a treated group describes what was observed under that study’s conditions. A treatment effect is a contrast between outcomes under different treatment strategies. A concurrent comparison group can support such a contrast, subject to design and analysis assumptions; a single-group study cannot make that direct within-trial comparison. Differences from an external benchmark may be affected by differences in eligibility, follow-up, outcome assessment or other factors. No external comparator is identified in the registry record.

Open-label means masking was listed as none. General explanation: knowledge of treatment can potentially affect subjective assessments, participant reporting, or decisions about evaluation. The endpoint includes measured progressive disease, but the registry does not report the assessment procedures or whether outcome assessors were independent. The record therefore does not permit a detailed evaluation of possible assessment bias.

What do the planning assumptions mean?

The stated sample-size assumptions describe a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They also state that the effect to detect is a stated fraction of the observed effect. For time-to-event outcomes, the assumptions describe a total number of events using the Schoenfeld method; other outcomes use participants per arm. These are assumptions for planning illustrations, not a description of this trial’s single-group design, and not observed power. The numerical planning results and the trial’s own sample-size justification are not reported in the registry record.

Recalculated results, if available, would be simple unadjusted calculations from posted summary statistics rather than a replacement for the sponsor’s analysis. No recalculated primary estimate is reported in the registry record, and no sponsor analysis result for the primary endpoint is included in the information. The record therefore supports an explanation of the named methods, but not independent verification of a numerical result.

What is not specified?

The registry record does not report the detailed analysis plan, the method used to calculate the confidence interval, planned handling of competing risks, or prespecified sensitivity analyses. It also does not state whether interim analyses were conducted or provide a sample-size justification. These omissions limit the ability to evaluate whether the reported analysis followed a prespecified approach, beyond the brief endpoint description.

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("Enzastaurin + R-GEMOX")
n      <- c(68)
events <- c(11)
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  Enzastaurin + R-GEMOX  68  11  16.2  8.4  27.1  9.3  26.7  9.3  26.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists multiple secondary outcomes: overall response, PFS at later follow-up points, overall survival, event-free survival, biomarker-related PFS assessments and pharmacokinetic measures. Testing or estimating many outcomes can create multiplicity concerns. General explanation: when several hypotheses are examined, the chance of at least one apparently notable result can increase if each is interpreted without regard to the others. Prespecified outcome hierarchies or multiplicity adjustments can help clarify how such findings should be interpreted.

The registry record does not report a multiplicity strategy, an outcome hierarchy, or whether secondary analyses were adjusted. The number of outcome measures is listed as 11, and the record lists 2 analyses, but it does not explain the relationship between those counts or identify a correction procedure. Numerical secondary-outcome results are not reported in the record, so no conclusions about their magnitude or statistical uncertainty are possible.

For the primary outcome, the record states that 14 participants were censored and gives a rule based on last progression-free disease assessment. Censoring is part of time-to-event analysis, but the record does not provide a fuller account of missingness, follow-up completeness, or reasons for censoring. It also does not report sensitivity analyses addressing alternative assumptions about participants with incomplete follow-up.

The primary population is described as all randomized participants who received at least 1 dose. Because the design is also described as single-group with allocation not applicable, the population wording is ambiguous. The registry record does not explain this discrepancy or report how participants were handled if they did not receive treatment. These population and missing-data details matter when judging which participants contributed to the analysis and how broadly the estimate applies.

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.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pyrexia (7.4%), ovarian fibroma (4.8%), thrombocytopenia (2.9%), general physical health deterioration (2.9%), infection (2.9%).

The registry separates serious adverse events from other adverse events. For the Enzastaurin + R-GEMOX group, 68 participants were listed as at risk for serious adverse events, and 30 were listed as affected. For other adverse events, 68 were listed as at risk and 68 as affected. These category-level figures should not be conflated: they refer to different event groupings and do not indicate that every affected participant had a serious event.

The listed serious-event terms and percentages are pyrexia, 7.4%; ovarian fibroma, 4.8%; thrombocytopenia, 2.9%; general physical health deterioration, 2.9%; infection, 2.9%; and sepsis, 2.9%. These are percentages attached to listed terms. The registry record does not provide the corresponding counts in the information, and it does not establish whether participants could appear under more than one term. The listed terms should therefore not be added together or interpreted as mutually exclusive categories.

No deaths figure is reported for this group in the registry record. These summaries describe reported events in this study and do not establish how event rates compare with another treatment or with the underlying disease. The record does not provide enough detail to assess event timing, duration, severity beyond the serious-event classification, or attribution to study treatment.

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

The study was designed to estimate PFS at 1 year among participants treated with enzastaurin plus R-GEMOX. The registry defines the event as measured progressive disease or death from any cause and describes a Kaplan-Meier approach that censors participants at their last known progression-free assessment when no event is recorded. This is the intended interpretation of the primary outcome.

The registry record does not report the primary PFS estimate or its 95% confidence interval. As a result, the posted information does not show the observed 1-year PFS rate or how precisely it was estimated. It also does not support a claim of statistical significance or a quantitative statement about the size of an outcome. The same limitation applies to the numerical findings for the listed secondary outcomes, which are not reported in the registry information available for this analysis.

Even with a numerical estimate, the single-group design would describe outcomes in the treated group rather than directly quantify a treatment effect against a concurrent control. The study has no like-for-like control arm in its registry design. Thus, an outcome rate alone could not establish what would have happened to comparable participants under a different regimen, nor isolate the contribution of enzastaurin from the other drugs in R-GEMOX.

The safety listings document reported serious-event terms and group-level affected figures, but do not provide a controlled comparison of safety. The event percentages do not establish causation, and the available registry entries do not show timing, attribution, or overlap among listed terms. Overall, the record describes the study question, design and endpoint method, but the absence of numerical efficacy results and the lack of a comparator constrain what can be concluded about outcomes.

14. Why This Trial Matters Statistically

This trial illustrates an important distinction between an outcome definition and an outcome result. The registry specifies PFS at 1 year, the time origin, the event definition, the Kaplan-Meier method and the censoring rule. Those details make the intended estimand more interpretable than a bare label such as “PFS.” But the numerical estimate and confidence interval are not reported in the registry record, so readers cannot assess the size or precision of the result.

It also highlights how design limits the questions that statistical analysis can answer. A single-group phase 2 study can describe outcomes in participants receiving a regimen and can examine additional response, survival, biomarker and pharmacokinetic questions. Without a concurrent control, however, it cannot provide a direct randomized estimate of the difference attributable to treatment. This is a design limitation, not something that a more elaborate analysis of the same single group can remove.

The record also shows why analysis-population language matters. “All randomized participants” appears in the primary population description, while the study is classified as single-group and allocation is not applicable. Explicit clarification would help readers understand who was analyzed. Similarly, the report of 14 censored participants is useful context, but fuller information on follow-up and censoring reasons would help evaluate the time-to-event estimate.

Finally, the study lists several additional outcomes without a reported multiplicity plan or numerical results in the registry information. Statistical interpretation depends not only on which methods are named, but also on complete estimates, uncertainty, populations and analysis decisions. These features are especially important when a study has multiple outcomes and no control group.

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 main limitation for interpreting the primary outcome is that the registry record does not report its numerical estimate or 95% confidence interval. The record therefore gives the endpoint definition and method but not the result’s magnitude or precision. Numerical findings for the listed secondary outcomes are also not reported in the record.

The single-group design has no concurrent control, so it cannot yield a direct within-trial comparison with another treatment. The open-label design also means masking was listed as none. The registry record does not describe the procedures for assessing progression or whether outcome assessors were independent, leaving the possibility of assessment-related influences difficult to evaluate.

The primary population description says “all randomized participants who received at least 1 dose,” while the registry classifies the study as single-group and allocation as not applicable. This inconsistency is not explained. The record notes 14 censored participants but does not report detailed censoring reasons, follow-up completeness, or sensitivity analyses for missing event-time information.

The record lists multiple secondary outcomes but does not report a multiplicity approach or an outcome hierarchy. It also does not report a detailed statistical analysis plan, interim-analysis information, sample-size justification, or numerical planning results. These details would be relevant to judging prespecification and the context for any estimated findings, but are not reported in the registry record.

Finally, the safety information is limited to group-level affected figures and listed event terms with percentages. The registry record does not provide event timing, treatment attribution, or enough detail to determine overlap among terms. No deaths figure is reported for the group.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Chemotherapy for Participants With Lymphoma — NCT00436280.
• Registry record last updated 2020-08-06; status last verified 2020-07.
• Results first posted 2020-08-06.
• 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, single-group phase 2 study evaluated enzastaurin with rituximab, gemcitabine and oxaliplatin in relapsed DLBCL. The registry lists enrollment of 68 and identifies PFS after 1 year as the primary outcome. PFS was defined from first dose to measured progressive disease or death from any cause and was estimated using Kaplan-Meier methods. The record says 14 participants were censored.

The primary estimate and its 95% confidence interval are not reported in the registry record. The study had no concurrent control group, and the primary population wording referring to randomized participants is not reconciled with the single-group classification. The registry lists additional response, survival, biomarker and pharmacokinetic outcomes, as well as serious adverse-event terms, but the information summarized in the record does not support a controlled treatment-effect estimate.