Rucaparib vs Placebo Maintenance Therapy in Metastatic and Recurrent Endometrial Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Rucaparib vs Placebo Maintenance Therapy in Metastatic and Recurrent Endometrial Cancer (NCT03617679), a randomized phase 2 study. The primary outcome is Progression Free Survival (PFS).

2. Clinical Question

This is a time-to-event question: it concerns how long participants remain alive without recorded disease progression, rather than the proportion with a particular status at one fixed visit. The registry identifies overall survival and the incidence of treatment-emergent adverse events as secondary outcomes. Those outcomes address different questions from progression-free survival and should not be treated as substitutes for it.

The population and treatment context matter when interpreting the endpoint. The brief summary specifies maintenance therapy after 1-2 prior lines, but the registry record does not report detailed eligibility criteria, prior-treatment composition, or other participant characteristics. The posted medians are therefore descriptive of the trial groups as recorded, not a guarantee of outcomes in other populations or treatment settings.

3. Trial Design

The registry describes a randomized, double-blind, parallel-group phase II study. Participants were assigned to maintenance treatment with rucaparib or placebo, and the arm descriptions specify 1:1 randomization. The registry lists 39 participants in the active ingredient arm and 40 in the placebo arm. The enrollment field reports 79.

The study title and brief summary place the comparison in metastatic and recurrent endometrial cancer after prior therapy. The listed condition is metastatic endometrial cancer, and the brief summary describes treatment after 1-2 prior lines. More complete eligibility criteria, the exact disease and treatment history of participants, and the method used to generate or conceal random allocation are not reported in the registry record.

Double masking means the registry characterizes the study as blinded to two groups of people, but it does not identify those groups or describe how masking was maintained. The trial is labeled parallel, indicating that the two treatment groups are compared as separate arms rather than in a crossover design. The registry does not report the treatment schedule, follow-up visit schedule, adherence, discontinuation rules, or permitted subsequent treatments.

The trial status is completed. The recorded start date is 2019-03-06 and the primary completion date is 2023-10-31. The registry identifies University of Colorado, Denver as sponsor. These record details describe the study’s registration and timeline; they do not by themselves establish how all enrolled participants were included in each analysis.

The primary outcome was progression-free survival, with a timeframe listed as up to 48 months. Overall survival and incidence of treatment-emergent adverse events are named as secondary outcomes. The registry record does not report a detailed statistical analysis plan, analysis populations, interim analyses, or sample-size justification. The registered enrollment should not be interpreted as evidence that the study was designed to have a particular statistical power.

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 Progression Free Survival (PFS), measured over Up to 48 months..

The primary endpoint, progression-free survival, measures time from cycle 1 day 1 until disease progression or death. Progression was defined using RECIST 1.1 criteria. The endpoint combines two clinically important events: documented progression and death before documented progression. The registry lists a timeframe of up to 48 months.

The registry reports this endpoint as a median time in months for each arm, accompanied by a 95% confidence interval. A median time summarizes the point by which half of the relevant time-to-event distribution has experienced the event, subject to the analysis and censoring rules used. Those detailed rules are not reported in the registry record.

In general, a time-to-event endpoint can use information about both when an event occurs and how long participants are observed without an event. Participants whose event time is not observed during follow-up may be censored, but the registry record does not describe censoring procedures or follow-up completeness. Such details are important because the median and its uncertainty depend on the observed event-time data and the analysis method.

Progression-free survival is used to describe the duration of time without progression or death. It differs from overall survival, which is separately listed as a secondary outcome, and from adverse-event outcomes, which describe safety. The endpoint definition clarifies what event is counted, but it does not by itself establish the size or statistical certainty of a treatment comparison.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a time-to-event measure. Each participant’s event time is defined by the first recorded progression under RECIST 1.1 criteria or death, measured from cycle 1 day 1. A time-to-event analysis is useful when participants can have events at different times and may have unequal observation periods. Unlike a simple event proportion, it can account for the timing of events and for participants whose event has not been observed by the end of their available follow-up. The registry record does not describe the specific handling of those participants.

What does a median time summarize?

A median time is the point at which the estimated event-time distribution reaches its midpoint. It is a summary of a distribution, not a statement that every participant experienced the event at that time. The median is also not the same quantity as a hazard ratio: the median gives a time point, while a hazard ratio compares event rates over time under a model. The registry posts medians for both arms but does not report a comparative hazard ratio for progression-free survival.

For the active ingredient arm, the reported median is 28.1 months and the lower confidence bound is 12.8 months; the upper confidence bound is not reported. For placebo, the median is 8.7 months and the confidence interval is 5.4 to 16.7 months. A confidence interval is a measure of estimation uncertainty produced by a statistical procedure. It is not a range containing every participant’s event time, and it does not itself provide a direct test of the difference between two arms. The incomplete interval for the active arm prevents a full reading of its reported uncertainty from the registry result.

Why are arm medians not a complete comparison?

Comparing two medians can provide a descriptive contrast, but it does not supply the uncertainty of a treatment-effect estimate. A formal comparison would require an analysis designed for the time-to-event outcome, along with information about events and follow-up. A hazard ratio or survival-curve comparison could account for the pattern of events across follow-up; the registry does not post such a result. No new comparison can be recovered from the two median values alone without additional data and assumptions.

In general, the proportional-hazards model used for a hazard ratio assumes that the relative event rate is adequately represented by a constant ratio over time. If that assumption is unsuitable, one hazard ratio may not summarize the treatment contrast well. Whether proportional hazards were assessed, what model was used, and whether any alternative analyses were planned are not reported in the registry record. This general point does not imply that the assumption was or was not met in this trial.

What does over-dispersion mean for count outcomes?

General statistical explanation: over-dispersion occurs when count data vary more than a simple model assumes. If present, standard errors from an overly restrictive model may be too small, making confidence intervals appear more precise than warranted. This concept can matter for some count-based outcomes, but the posted primary endpoint is time-to-event, and the registry does not report a count model or an over-dispersion assessment for the trial. It should not be inferred that over-dispersion was present or that a particular method was used.

How should planning calculations be read?

General statistical explanation: a sample-size calculation asks what study size might be needed under stated assumptions to detect a chosen effect with a selected error rate and power. The planning illustrations associated with this trial are based on the observed effect, use a two-sided significance level of 0.05, equal allocation, and a normal approximation; their target effect is a stated fraction of the observed effect. For time-to-event outcomes, the calculation is expressed as a total number of events using the Schoenfeld approach. These are planning illustrations, not the trial’s original design justification, and not observed power. The registry record does not report the trial’s own sample-size justification or statistical design assumptions.

The distinction between a planning illustration and observed power is important. Observed power is not a useful substitute for an estimated effect and its uncertainty after results are available. A planning calculation under hypothetical assumptions cannot show that the completed trial had adequate information for every outcome. The registry record does not provide the event totals or inferential results needed to assess the precision of a comparative time-to-event analysis.

What is not reported about the analysis?

The registry record does not report the analysis population, detailed censoring rules, missing-data procedures, model specification, or a statistical test for the primary outcome. It also does not report whether assumptions were assessed, whether sensitivity analyses were conducted, or how competing events were handled. These are not minor details: time-to-event estimates depend on definitions of events and follow-up, while inferential results depend on the chosen model and analysis population. Without these details, interpretation should remain descriptive and tied to the posted summaries.

10. Multiplicity, Missing Data and Analysis Populations

The registry names overall survival and incidence of treatment-emergent adverse events as secondary outcomes, alongside the primary progression-free survival outcome. It does not report a multiplicity strategy, such as a prespecified adjustment or a hierarchy for interpreting multiple statistical tests. In general, testing several outcomes can increase the chance of at least one apparently notable result arising by chance. Whether and how that issue was addressed in the trial analysis is not reported in the registry record.

The registry lists three outcome measures overall and two secondary outcomes, but does not post statistical analyses for them. No comparative results for overall survival are included in the outcome information. The adverse-event record lists counts, but does not give a comparative statistical test. These gaps mean that secondary outcomes cannot be used to corroborate or qualify an inferential conclusion about the primary endpoint.

Missing-data handling is not reported in the registry record. For progression-free survival, the record also does not specify censoring rules, the analysis population, event counts, or how participants with incomplete follow-up were handled. For other outcomes, it does not describe whether all randomized participants were included, how missing outcome assessments were treated, or whether sensitivity analyses were performed.

Randomization can support a fair comparison when groups are analyzed as planned, but the registry record does not identify the analysis population or provide enough detail to determine how the randomized groups contributed to each outcome. The record also does not report interim analyses or a statistical analysis plan. These absences should be treated as reporting limitations, not evidence that a particular procedure was or was not used.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: thrombocytopenia (5.1%), anemia (2.6%), neutropenia (2.6%), nausea (2.6%), elevated alt/ast (2.5%).

The adverse-event record lists serious adverse events for 3 participants in the active ingredient group, with 39 at risk, and for 1 participant in the placebo group, with 40 at risk. It lists other adverse events for 37 participants in the active ingredient group and 27 in the placebo group. Deaths are recorded as 1 in each group. These are counts as posted; no percentages or comparative estimates are calculated.

Serious adverse events are distinct from the broader category of other adverse events in the record. The listed counts do not show event severity beyond the serious classification, timing, duration, recurrence, or whether an event was judged related to treatment. A death count alone does not identify its cause or establish treatment attribution. The registry does not provide an exposure-adjusted analysis or a statistical comparison of these safety counts.

The registry also lists serious-event terms with percentages: thrombocytopenia, 5.1%; anemia, 2.6%; neutropenia, 2.6%; nausea, 2.6%; and elevated ALT/AST, 2.5%. The denominator and arm attribution for these term-specific percentages are not reported in the registry record. They should therefore not be interpreted as arm-specific rates or as a complete description of all adverse events.

Safety counts are descriptive and are affected by how events were defined, collected, and followed. The registry record does not provide those detailed procedures. The counts alone cannot establish that a treatment caused an event or quantify a causal difference between groups.

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

The posted primary results describe median progression-free survival in each randomized group: 28.1 months for the active ingredient arm and 8.7 months for the placebo arm. The registry also gives a confidence interval lower bound of 12.8 months for the active arm, without an upper bound, and a confidence interval from 5.4 to 16.7 months for placebo. These data convey the reported arm-specific summaries, but not a complete inferential comparison.

The record does not post a hazard ratio, p-value, or other statistical test for the primary endpoint. It therefore does not establish the statistical significance or precision of a between-arm treatment effect. Nor do the posted medians alone establish that the difference between groups is causal, durable, or applicable outside the trial population. The registry’s brief summary describes maintenance treatment after 1-2 prior lines, while detailed eligibility and participant characteristics are not reported.

The safety record lists serious adverse events, other adverse events, and deaths by arm, but the counts do not establish treatment causation. The listed serious-event terms have percentages without a reported denominator or arm attribution. These safety data should be understood as registry summaries rather than a complete comparative safety analysis.

In general, a randomized design is intended to support comparisons between assigned groups, but interpreting those comparisons also requires the analysis population, outcome definitions, missing-data rules, and statistical methods. The registry record does not report those details for the primary result. A completed study status does not imply that all planned outcomes or analyses have been posted.

The appropriate reading is therefore limited: the registry provides arm-level median progression-free survival and selected adverse-event counts, while leaving key comparative analyses and methods unreported. This does not mean that the treatment was or was not effective. It means that the posted registry results are insufficient to make a definitive statistical claim about the comparative treatment effect.

13. Why This Trial Matters Statistically

This trial is statistically informative as an example of the difference between an arm-level summary and a comparative treatment-effect estimate. The posted primary outcome gives a median for each group, but a direct comparison requires more than placing those two values side by side. A hazard ratio, a test of the time-to-event distributions, or another prespecified comparative method would convey additional information about the treatment contrast and its uncertainty. Such an analysis is not posted in the registry record.

The confidence intervals also illustrate why uncertainty matters. The placebo interval is reported with both bounds, while the active arm has a lower bound but no upper bound in the posted result. The estimates can be described as recorded, but the missing upper bound constrains interpretation of the active arm’s precision. This is a reporting limitation, not a basis for filling in an unreported value.

The randomized, double-blind design identifies an intended structure for comparing treatment groups. Yet design labels alone do not reveal the analysis population, follow-up completeness, censoring choices, or handling of missing data. Those details are especially relevant for time-to-event outcomes, where the timing and observation of events contribute to the estimate.

The record also helps distinguish outcome domains. Progression-free survival, overall survival, and treatment-emergent adverse events address different questions. The registry names the latter two as secondary outcomes, but does not post their comparative analyses. Safety counts can describe reported events, but cannot replace a formal analysis or establish causality.

Finally, planning calculations should not be confused with evidence about the completed study’s observed power. A planning illustration is conditional on assumptions and a hypothetical target effect; it does not supply missing event information or a treatment-effect confidence interval. The central statistical lesson is to separate descriptive results, inferential comparisons, planning exercises, and evidence that is not reported.

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 primary result is incomplete as a comparative time-to-event analysis. The registry reports arm-specific medians, but does not post a hazard ratio, p-value, or other inferential comparison. The active ingredient arm’s confidence interval has a reported lower bound but no upper bound. The record does not give event counts, survival estimates at specific times, or the pattern of censoring, limiting assessment of the information underlying the medians.

Details needed to assess analysis validity are not reported in the registry record. These include the analysis population, censoring rules, missing-data procedures, statistical model, handling of protocol deviations, and sensitivity analyses. The registry does not report the statistical analysis plan, sample-size justification, interim analyses, or multiplicity strategy. It is not possible to determine from these omissions whether a method was used but not posted or was not used.

The registry offers limited context for generalizability. Its brief summary refers to metastatic and recurrent endometrial cancer after 1-2 prior lines, while the condition field lists metastatic endometrial cancer. Detailed eligibility criteria and participant characteristics are not reported. Treatment schedule, adherence, discontinuation, subsequent treatment, and follow-up completeness are also not described in the outcome information.

Safety reporting is similarly limited. The record lists counts and selected serious-event terms, but does not report the denominator or arm attribution for the term-specific percentages. It also does not provide event-level detail, exposure-adjusted rates, or a comparative safety analysis. The death counts do not establish cause or treatment relationship.

These limitations constrain interpretation of the posted registry results. They should not be treated as evidence for a particular unreported analysis or as proof that a treatment effect is absent or present.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Rucaparib vs Placebo Maintenance Therapy in Metastatic and Recurrent Endometrial Cancer — NCT03617679.
• Registry record last updated 2026-03-24; status last verified 2026-03.
• Results first posted 2024-07-01.
• 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.

18. Record Summary

The registry record describes a completed, randomized, double-blind, parallel-group phase II study of rucaparib versus placebo maintenance therapy for metastatic and recurrent endometrial cancer. The brief summary places maintenance treatment after 1-2 prior lines of therapy. The record lists 79 enrolled participants and reports 39 in the active ingredient arm and 40 in the placebo arm.

The primary outcome is median progression-free survival, defined from cycle 1 day 1 to progression under RECIST 1.1 criteria or death, with a timeframe of up to 48 months. The posted medians are 28.1 months for the active ingredient arm and 8.7 months for placebo. The active arm’s interval upper bound is not reported, and no comparative hazard ratio or statistical test is posted.

Overall survival and treatment-emergent adverse events are named as secondary outcomes. The adverse-event record lists serious events, other events, deaths, and selected serious-event terms. The registry does not report the statistical analysis plan, analysis populations, missing-data procedures, or multiplicity approach, so the posted results support descriptive interpretation rather than a complete inferential assessment.