Comparison of the Treatments of Obinutuzumab + Venetoclax Versus Obinutuzumab + Chlorambucil in Patients With Chronic Lymphocytic Leukemia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Comparison of the Treatments of Obinutuzumab + Venetoclax Versus Obinutuzumab + Chlorambucil in Patients With Chronic Lymphocytic Leukemia (NCT02242942), a randomized phase 3 study. The primary outcome is Progression Free Survival (PFS) Based on Investigator Assessment According to IWCLL Criteria.

2. Clinical Question

The clinical question is framed as a comparison of efficacy and safety, rather than as a comparison against no treatment. Both groups received obinutuzumab; the treatment contrast is the addition of venetoclax versus chlorambucil. The trial is described as prospective, multicenter, randomized, open-label, and Phase III. Its stated population is specifically previously untreated participants with chronic lymphocytic leukemia and coexisting medical conditions, so the findings should be interpreted in that trial context.

The primary endpoint uses investigator assessment. A secondary progression-free survival outcome used an Institutional Review Committee assessment. The registry also lists response and minimal residual disease outcomes, among other secondary measures. These help describe different aspects of disease status, but they do not replace the primary comparison or make the trial population broader than the one enrolled.

3. Trial Design

This was a randomized, parallel-group, open-label Phase III trial sponsored by Hoffmann-La Roche. The registry record lists an enrollment of 445 and describes a multicenter study in previously untreated chronic lymphocytic leukemia with coexisting medical conditions. The two main treatment groups were obinutuzumab plus venetoclax and obinutuzumab plus chlorambucil. A separate safety run-in group receiving obinutuzumab plus venetoclax is also listed in the safety results.

For the two main regimens, the descriptions specify obinutuzumab for 6 cycles and the other drug for 12 cycles; cycles comprised 28 days. The brief summary describes time on study treatment as approximately one year and follow-up as up to 9 years. The primary progression-free survival timeframe is baseline until disease progression or death, up to approximately 3.75 years. These are distinct descriptions of treatment duration and outcome follow-up, not interchangeable measures.

The primary analysis population was defined as all randomized participants. The posted outcome records show 216 participants in each main treatment group for the primary endpoint. Those outcome counts need not match the registry's enrollment figure: enrollment and an endpoint-specific analysis population can reflect different record definitions or availability. The record does not report a reconciliation of these counts, and it does not report the original sample-size justification or detailed allocation procedures.

Masking was none, so the trial was open-label. The primary endpoint was progression-free survival assessed by investigators according to International Workshop on Chronic Lymphocytic Leukemia criteria. A secondary progression-free survival endpoint used Institutional Review Committee assessment. Other listed outcomes include overall response, complete response, minimal residual disease negativity in peripheral blood and bone marrow, and overall survival.

The registry lists the study as completed. Dates for study start and primary completion are recorded, but the record does not describe the timing or conduct of interim analyses. It also does not report details of stratification, allocation concealment, or the complete statistical analysis plan. Those omissions limit what can be concluded about design choices beyond the features explicitly recorded.

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: ITT population was defined as all randomized participants.

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 Progression Free Survival (PFS) Based on Investigator Assessment According to IWCLL Criteria, measured over Baseline until disease progression or death up to approximately 3.75 years.

The primary endpoint was progression-free survival, measured from randomization to the first occurrence of disease progression or death from any cause. Investigators assessed progression according to the International Workshop on Chronic Lymphocytic Leukemia 2008 criteria. The registry describes signs of progression that include changes in circulating lymphocytes, new or enlarging lymph nodes or other lesions, enlargement of the liver or spleen, and transformation to a more aggressive histology.

Progression-free survival is a time-to-event outcome: it incorporates both whether an event occurred and how long participants remained free of progression or death. This is useful when the timing of disease progression or death is central to the research question and participants can have different lengths of follow-up. General statistical point: time-to-event methods can use information from participants whose event has not been observed by the end of follow-up, provided censoring and other analysis assumptions are handled appropriately. The registry record does not report the detailed censoring rules.

The posted primary result is a hazard ratio with a 95% confidence interval and a Log Rank p-value. The arm-specific median estimates are not fully reported: the chlorambucil group's record contains a lower confidence bound of 31.1 months, while the median values and remaining bounds are absent. Therefore, the registry record does not support a complete comparison of median progression-free survival. The hazard ratio is the available comparative summary, and its interpretation depends on which group is used as the reference in the analysis.

7. Results Posted in the Registry

• Obinutuzumab + Chlorambucil vs Obinutuzumab + Venetoclax: hazard ratio 0.35 (95% CI 0.23–0.53), reported p < 0.001 (as reported in the registry).

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Progression Free Survival (PFS) Based on Institutional Review Committee (IRC)-Assessments According to International Workshop on Chronic Lymphocytic Leukemia (IWCLL) Criteria

• Endpoint type: Time to event: compared as a hazard ratio.
• Test: Hazard ratio as reported by the sponsor (Log Rank); it was not recalculated.
• Result:
  • Obinutuzumab + Chlorambucil vs Obinutuzumab + Venetoclax: hazard ratio 0.33 (95% CI 0.22–0.51), reported p < 0.001 (as reported in the registry).
• Interpretation:
  • The 95% confidence interval excludes no difference (a ratio of 1), so the hazard of the event is statistically lower for Obinutuzumab + Chlorambucil vs Obinutuzumab + Venetoclax than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants With an Overall Response (OR) at Completion of Treatment, as Determined by the Investigator According to IWCLL Criteria

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Obinutuzumab + Venetoclax: 84.7% (183/216) versus 71.3% (154/216) on control; risk difference 13.4 percentage points (95% CI 5.7 to 21.1), risk ratio 1.19 (1.07–1.32); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Obinutuzumab + Venetoclax than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants With a Complete Response Rate (CRR) at the Completion of Treatment Assessment as Determined by the Investigator According to IWCLL Criteria

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Obinutuzumab + Venetoclax: 49.5% (107/216) versus 23.1% (50/216) on control; risk difference 26.4 percentage points (95% CI 17.7 to 35.1), risk ratio 2.14 (1.62–2.83); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for Obinutuzumab + Venetoclax than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover more than one aspect of disease status: committee-assessed progression-free survival, investigator-assessed response and complete response, minimal residual disease in blood and bone marrow, and overall survival. Among the secondary outcomes with numerical comparative results recorded in detail, the overall pattern is consistent with the primary result's report of a difference between treatment groups. The reported response proportions are numerically higher for the venetoclax-containing regimen, and the committee-assessed time-to-event result is statistically significant under its reported analysis.

These endpoints complement rather than replace the primary investigator-assessed progression-free survival analysis. Committee assessment provides a distinct assessment of progression; response measures disease status at a specified completion-of-treatment assessment; and minimal residual disease and overall survival address other outcomes. Each has its own timing, definition, and analysis. Results for these measures should not be collapsed into a single claim about treatment effect.

The registry lists 22 secondary outcomes, but the full numerical results for every listed secondary outcome are not reported in the registry record. It also does not report a multiplicity adjustment strategy. When many outcomes are tested, the chance of obtaining at least one small p-value under a collection of null hypotheses can increase. General statistical point: this is why secondary p-values, especially those not adjusted for multiple comparisons, are usually considered less confirmatory than a prespecified primary endpoint.

The sponsor's reported analyses should be distinguished from unadjusted recalculations of individual binary outcomes. The registry does not give sufficient detail to evaluate all analysis choices for every secondary measure. The overall pattern is informative, but it should be interpreted with the endpoint definitions, limited reporting, and multiplicity uncertainty in view, rather than as a collection of independent confirmations.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Progression Free Survival (PFS) Based on Institutional Review Committee (IRC)-Assessments According to International Workshop on Chronic Lymphocytic Leukemia (IWCLL) Criteria
• Percentage of Participants With an Overall Response (OR) at Completion of Treatment, as Determined by the Investigator According to IWCLL Criteria
• Percentage of Participants With a Complete Response Rate (CRR) at the Completion of Treatment Assessment as Determined by the Investigator According to IWCLL Criteria
• Percentage of Participants With Minimal Residual Disease (MRD) Negativity in Peripheral Blood as Measured by Allele-Specific Oligonucleotide Polymerase Chain Reaction (ASO-PCR) at Completion of Treatment
• Percentage of Participants With MRD Negativity in Bone Marrow as Measured by ASO-PCR at Completion of Treatment
• Overall Survival (OS)
• Percentage of Participants With MRD Negativity in Peripheral Blood as Measured by ASO-PCR at Completion of Combination Treatment Assessment
• Percentage of Participants With MRD Negativity in Bone Marrow as Measured by ASO-PCR at Completion of Combination Treatment Assessment

9. Statistical Interpretation

10. Statistical Methods Explained

What does a hazard ratio describe?

General explanation: a hazard ratio compares the event rates over follow-up between groups, conditional on participants remaining event-free up to each time. It is a relative time-to-event measure, not a difference in median survival time and not a ratio of the numbers of participants who experienced events. A hazard ratio near 1 indicates similar estimated hazards under the model; values on either side of 1 indicate different relative hazards, with direction determined by the group coding and reference. For this trial, the registry reports the primary contrast as a hazard ratio of 0.35 and the Institutional Review Committee contrast as 0.33. The record does not explicitly state the hazard-ratio numerator and reference group, so the values should be quoted with that limitation.

What does the Log Rank method contribute?

The registry identifies the Log Rank method for both progression-free survival comparisons. General explanation: the Log Rank test compares the observed and expected event experience between groups across follow-up, accounting for the timing of events and censoring. Its p-value evaluates evidence against the null hypothesis of no difference in the event experience, subject to the method's assumptions. It is not a probability that the null hypothesis is true, and it does not tell readers whether an estimated difference is clinically important. The primary reported p-value is p < 0.001. Detailed information about the test's assumptions, censoring rules, or any supporting model is not reported in the registry record.

Why are medians and hazard ratios different summaries?

A median time-to-event is the time by which half of the analyzed population is estimated to have experienced the event, under the survival curve. A hazard ratio summarizes relative event rates across follow-up rather than a specific time point. The registry's primary result does not include complete arm-specific medians: only a lower confidence bound of 31.1 months is recorded for the chlorambucil group, and the other median fields are absent. The hazard ratio is therefore the available comparative summary, not a substitute for unreported median values. A confidence bound alone should not be presented as an observed median.

How should the response comparisons be read?

For the secondary overall response and complete response outcomes, the registry reports group percentages and sponsor analyses using the Cochran-Mantel-Haenszel method. General explanation: this method compares categorical outcomes between groups while accounting for specified strata when such strata are part of the analysis. The registry does not report the stratification details, so the adjustment structure cannot be assessed from this record. The sponsor's reported differences in response rates and confidence intervals are the primary inferential results for those outcomes. Unadjusted recalculations from posted group summaries can be useful as checks, but they need not equal an analysis that accounts for stratification or uses a different analysis population.

The outcome percentages are proportions observed at the completion-of-treatment assessment, specified as 3 months after treatment completion, at approximately 15 months. They are not time-to-event outcomes. Their interpretation is tied to that assessment time and the registry's endpoint definitions. A difference in proportions describes the contrast at that assessment; it does not by itself describe the duration of response or later disease status.

What do confidence intervals and p-values add?

General explanation: a confidence interval gives a range of values reasonably compatible with the data and analysis assumptions at its stated confidence level. A narrow interval indicates greater statistical precision than a broad interval, though precision does not establish clinical importance. A p-value describes how unusual the data, or more extreme data, would be under the specified null model; it does not measure the probability that the result occurred by chance in an everyday sense. The reported primary interval is 0.23 to 0.53, and the reported p-value is p < 0.001. The registry's own analysis should be distinguished from unadjusted recalculations based on summary figures.

For binary outcomes, an unadjusted recalculation from group proportions can differ from the sponsor's stratified analysis. Differences can arise because the analyses use different methods, adjustments, or underlying records. The registry lists sponsor analyses for the secondary binary endpoints, so those are the relevant reported analyses. The record does not give enough detail to recreate the sponsor's full analysis independently.

What can be inferred about analysis populations?

The primary population is defined as all randomized participants, which is an intention-to-treat definition. The posted primary outcome lists 216 participants per main group. The safety record uses different denominators for the two main groups and includes a separate safety run-in group. These denominators belong to different recorded analyses and should not be combined or assumed to represent the same population. The record does not explain these differences, nor does it report details of exclusions, missing outcome data, censoring, or sensitivity analyses.

Finally, statistical significance and design power answer different questions. The posted p-values describe the observed analyses; planning illustrations use assumed effects to show what sample sizes or event counts would be needed under stated assumptions. Such planning values do not establish the probability that this completed trial detected a true effect, and they do not replace the trial's reported analysis.

11. Confidence Intervals and Precision

The primary hazard-ratio estimate is 0.35, with a 95% confidence interval from 0.23 to 0.53. The interval excludes 1, and the reported p-value is p < 0.001. Under the reported analysis, this indicates a relatively precise estimate of a difference in the hazard ratio scale, though the interval still allows a range of possible effect sizes. The direction of that comparison depends on the group coding, which the registry record does not explicitly describe.

The secondary Institutional Review Committee progression-free survival estimate has a 95% confidence interval from 0.22 to 0.51 around a hazard ratio of 0.33. The interval also excludes 1 and the reported p-value is p < 0.001. Since this is a distinct assessment of progression, it provides related evidence but should not be conflated with the primary investigator assessment.

For the primary endpoint, complete arm-specific median estimates and confidence intervals are not reported in the registry record. The chlorambucil group includes a lower bound of 31.1 months, but that bound is not a complete median estimate or interval. Missing median information limits interpretation of absolute time on the progression-free survival scale and prevents a full descriptive comparison of group medians.

General explanation: a confidence interval reflects statistical uncertainty under the analysis and its assumptions. It does not incorporate every source of uncertainty, such as outcome misclassification, missing-data mechanisms, or limitations in generalizability. It also does not establish whether a difference is clinically important. The registry does not report enough methodological detail to assess all these sources of uncertainty. The confidence intervals should therefore be read alongside the endpoint definitions, analysis population, and limitations of the record.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning illustrations translate assumed effects into either total event counts for time-to-event outcomes or participants per arm for binary outcomes. For progression-free survival, the figures are total events, not participants per arm. For the response outcomes, the figures are participants per arm. These quantities are not interchangeable: a time-to-event analysis depends on accumulating events, while a binary-outcome illustration specifies the number of participants needed in each group.

The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to a stated fraction of the observed effect. The illustrations show planning at 100%, 75%, and 50% of the observed effect, with columns for 80% and 90% power. In plain language, the 80% power column gives the estimated event count or per-arm participant count for an 80% chance of detecting the assumed effect under those assumptions, if that effect is real. The 90% column uses a higher target chance of detection. The registry's original sample-size assumptions and justification are not reported in the registry record.

Across the planning scenarios, smaller assumed effects require more information: they need more participants per arm for binary outcomes or more total events for time-to-event outcomes. This is a general consequence of trying to distinguish a smaller difference from random variation. The required amounts are illustrations based on the observed effect and stated assumptions, not a reconstruction of the trial's original design.

These figures are not observed power. They are prospective planning illustrations, and they do not describe the probability that the completed trial detected an effect after its results were known. The actual inferential evidence comes from the posted estimates, confidence intervals, and sponsor analyses.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

d is the total number of events needed (Schoenfeld's formula) with 1:1 allocation and proportional hazards.

Worked calculation for this trial

1. Hazard ratio HR = 0.350, so ln(HR) = -1.0498.
2. d = 4 × (1.96 + 0.842)² / [ln(0.350)]² = 28.5, rounded up to 29 events in total for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
hr <- 0.35                              # observed hazard ratio
events_needed <- function(power, frac = 1) ceiling(round(4 * (z_a + qnorm(power))^2 / log(hr^frac)^2, 6))   # Schoenfeld, 1:1 allocation
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: events = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(events_needed(0.80, f), big.mark = ","), format(events_needed(0.90, f), big.mark = ",")))

# Simulation: given d total events under proportional hazards, events in the treatment arm are Binomial(d, hr / (1 + hr)).
# The score (log-rank type) statistic is (D1 - d / 2) / sqrt(d / 4).
set.seed(2242942)
d    <- events_needed(0.80)
reps <- 20000
D1 <- rbinom(reps, d, hr / (1 + hr))
z  <- (D1 - d / 2) / sqrt(d / 4)
cat(sprintf("Simulated power with %s events: %.3f (%d replicates)\n", format(d, big.mark = ","), mean(abs(z) > z_a), reps))

Output from running the code

100% of observed effect: events = 29 (80% power), 39 (90% power)
 75% of observed effect: events = 51 (80% power), 68 (90% power)
 50% of observed effect: events = 114 (80% power), 153 (90% power)
Simulated power with 29 events: 0.800 (20000 replicates)

The simulation uses the fact that, with d events in total and proportional hazards, the number of events in the treatment arm is binomial. It is an approximation that conditions on the total number of events, and it should land close to the target power.

14. Analyses Reported by the Sponsor

The sponsor's reported primary analysis is a Log Rank hazard-ratio comparison. It gives an estimate of 0.35, a 95% confidence interval from 0.23 to 0.53, and p < 0.001, and is classified as a superiority analysis. This is the analysis to use when describing the trial's reported primary result. The registry does not explicitly state the ratio's numerator and reference group, so its direction should not be inferred from the numerical estimate alone.

The same principle applies to the secondary progression-free survival comparison: the sponsor reports a hazard ratio of 0.33, a 95% confidence interval from 0.22 to 0.51, and p < 0.001. For the secondary response outcomes, the sponsor reports Cochran-Mantel-Haenszel analyses. Those analyses include reported differences in response rates and p-values, and can differ from simple recalculations based on the posted group percentages because the methods and analysis details may differ.

Recalculated comparisons, where available, are simple unadjusted calculations from posted summary statistics. They are useful as an independent descriptive check, not a replacement for the sponsor's analysis. If a recalculated estimate or p-value differs from the sponsor's result, the sponsor's own analysis takes precedence. The registry does not report enough detail to reproduce the full sponsor analysis, including all adjustment and data-handling choices.

15. Multiplicity, Missing Data and Analysis Populations

The registry record identifies a primary progression-free survival endpoint and a broad set of secondary outcomes. It does not report a multiplicity strategy describing whether or how the significance threshold was adjusted across secondary endpoints. Without such a strategy, individual secondary p-values should be treated as less confirmatory because testing multiple outcomes can increase the chance of apparently strong findings even when some underlying effects are absent. The posted secondary results remain useful, but they do not all carry the same inferential weight as the designated primary analysis.

The primary analysis population is defined as all randomized participants. This supports an intention-to-treat description, but the registry does not report detailed rules for handling participants who lacked an endpoint assessment, discontinued treatment, or had incomplete follow-up. Missing-data methods, censoring details, and sensitivity analyses are not reported in the registry record. For time-to-event endpoints, the handling of follow-up and censoring can affect estimates; for response outcomes assessed at a specified time, missing assessments can affect the analyzed proportions.

The registry also does not report the original sample-size justification, detailed analysis plan, interim-analysis procedures, or the full assumptions behind the sponsor's analyses. The planning illustrations based on observed effects do not fill these gaps. They describe hypothetical planning requirements under stated assumptions, rather than the trial's original design rationale.

These omissions do not invalidate the posted results, but they limit independent assessment of prespecification, analysis robustness, and the risk of selective emphasis among outcomes. The primary reported result is more clearly identified than the secondary results; complete interpretation still depends on methodological details that are not reported in the registry record.

16. 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: febrile neutropenia (23.1%), pyrexia (15.4%), thrombocytopenia (7.7%), bradycardia (7.7%), myocardial infarction (7.7%).

The safety record lists serious adverse events for the two main treatment groups and the separate safety run-in group. Serious adverse events were reported for 90 of 214 participants at risk in the obinutuzumab plus chlorambucil group, 104 of 212 at risk in the obinutuzumab plus venetoclax group, and 10 of 13 at risk in the safety run-in group. Deaths are listed as 17, 20, and 2, respectively. These are descriptive counts within the recorded safety populations, not adjusted comparisons of risk.

The registry also lists serious adverse-event terms, including febrile neutropenia, pyrexia, thrombocytopenia, bradycardia, myocardial infarction, and diarrhoea, with percentages. The record does not explain the denominator or event-counting details for these term percentages in the excerpted results, so they should be interpreted cautiously. Serious adverse event counts do not by themselves establish that an event was caused by treatment, and the registry record does not provide a comparative statistical analysis of these safety figures.

The safety denominators differ from the primary endpoint group counts, and a separate run-in group is included. These populations should not be combined or treated as interchangeable. The figures are a summary of reported serious events and deaths, not a full account of treatment tolerability or all adverse events.

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

The posted primary analysis reports a statistically significant progression-free survival comparison under the sponsor's Log Rank analysis. The estimate is a hazard ratio of 0.35 with a 95% confidence interval from 0.23 to 0.53 and p < 0.001. The registry classifies the analysis as superiority. Since the registry does not explicitly state the hazard-ratio reference coding, the estimate should be reported as recorded rather than assigned a direction that the record does not establish.

The record also reports numerical differences in secondary response outcomes and a statistically significant committee-assessed progression-free survival comparison. These findings add context about outcomes measured at different times and by different assessment methods. They do not establish that every secondary outcome changed, that an effect persists beyond the reported follow-up, or that the outcomes have equal clinical importance.

A small p-value is evidence against a specified null model under the reported analysis; it does not measure how important an effect is to participants. A confidence interval conveys statistical precision but does not account for all possible bias or uncertainty. The incomplete median reporting, absent analysis details, unreported multiplicity approach, and unspecified missing-data methods limit a full evaluation of the results.

The record describes a trial in previously untreated chronic lymphocytic leukemia with coexisting medical conditions. Results should not automatically be generalized to people with different disease histories or characteristics. The trial comparison also concerns two regimens that both include obinutuzumab; it does not estimate the effect of either regimen versus no treatment or versus every other available approach.

These results are statistical findings from a clinical trial record, not individualized guidance. They describe the analyses and populations recorded and do not, alone, determine what treatment is appropriate for any particular person.

18. Why This Trial Matters Statistically

This trial raises a useful statistical question about how to interpret a time-to-event comparison when the registry gives a hazard ratio but does not provide complete arm-specific medians. The primary estimate and confidence interval provide comparative evidence on the hazard-ratio scale, while the incomplete median fields prevent a complete description of absolute progression-free survival times. Keeping those summaries distinct avoids treating a hazard ratio as a difference in median months.

The trial also illustrates why outcome assessment matters. The primary progression-free survival endpoint is based on investigator assessment, while a secondary endpoint uses an Institutional Review Committee assessment. The results are related, but they come from different assessment processes and should not be treated as identical measurements. The response outcomes add another kind of evidence because they are proportions at a specified assessment rather than time-to-event comparisons.

Several methodological distinctions are important for reading the record: the intention-to-treat definition, outcome-specific denominators, sponsor-reported analyses, unadjusted recalculations, and planning illustrations all serve different purposes. In particular, planning figures derived from observed effects are not observed power and do not reveal the trial's original design rationale.

Finally, the registry lists many secondary outcomes but does not report a multiplicity strategy or complete results for every measure. This makes the distinction between a designated primary endpoint and a broad secondary outcome set consequential. Statistical interpretation depends not just on whether individual p-values are small, but also on prespecification, analysis methods, precision, and the limits of what the record documents.

19. 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 primary endpoint's arm-specific median estimates are incomplete. The chlorambucil group has a lower confidence bound of 31.1 months recorded, but the median and upper bound are absent; the corresponding venetoclax-group median information is not reported in the registry record. The primary comparison is therefore available as a reported hazard ratio rather than a complete median-time comparison. The hazard-ratio reference coding is also not made explicit, limiting directional interpretation of the estimate from this record alone.

The registry does not report the original sample-size rationale, detailed allocation procedures, censoring rules, missing-data methods, interim-analysis procedures, or the full statistical analysis plan. It does not report a multiplicity strategy for the broad set of secondary outcomes. These omissions make it difficult to assess prespecification, the handling of incomplete observations, and how strongly secondary results should be interpreted.

The recorded enrollment differs from the endpoint-specific group counts, and the safety denominators differ from the primary outcome counts. The record does not reconcile these populations. The safety results also include a separate safety run-in group, and the term-level adverse-event percentages lack accompanying denominator details in the record excerpt. The safety counts are descriptive and do not provide a formal comparative safety analysis.

The open-label design means participants and investigators were not masked, as recorded. The registry does not provide information to assess how this feature may have affected assessments or other trial processes. The study population is specific to previously untreated participants with chronic lymphocytic leukemia and coexisting medical conditions, limiting direct generalization beyond that context.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Comparison of the Treatments of Obinutuzumab + Venetoclax Versus Obinutuzumab + Chlorambucil in Patients With Chronic Lymphocytic Leukemia — NCT02242942.
• Registry record last updated 2025-11-06; status last verified 2025-11.
• Results first posted 2019-10-01.
• 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.

23. Record Summary

This completed, randomized, open-label, parallel-group Phase III trial compared obinutuzumab plus venetoclax with obinutuzumab plus chlorambucil in previously untreated chronic lymphocytic leukemia with coexisting medical conditions. The registry lists enrollment of 445 and defines the primary analysis population as all randomized participants.

The primary endpoint was investigator-assessed progression-free survival from randomization to disease progression or death. The sponsor reported a hazard ratio of 0.35, a 95% confidence interval from 0.23 to 0.53, and p < 0.001 using a Log Rank method. The registry classifies the result as superiority, but does not make the hazard-ratio reference direction explicit. Complete arm-specific median results are not reported.

Secondary outcomes include committee-assessed progression-free survival, response, complete response, minimal residual disease, and overall survival. Safety results list serious adverse events and deaths for the main treatment groups and a separate safety run-in group. The registry does not report the full analysis plan, missing-data methods, or a multiplicity strategy, so these results should be interpreted within the limits of the recorded information.