Sorafenib and Anastrozole in Treating Postmenopausal Women With Metastatic Breast Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Sorafenib and Anastrozole in Treating Postmenopausal Women With Metastatic Breast Cancer (NCT00217399), a na phase 1, phase 2 study. The primary outcome is Complete Response + Partial Response + Stable Disease > 24 Weeks.

2. Clinical Question

The study asks whether sorafenib given with anastrozole can be administered to women with advanced or metastatic breast cancer, and whether the combination is associated with clinical benefit as defined by the protocol. It is a Phase I/II trial, so its stated aims include studying side effects and identifying a sorafenib dose, as well as assessing how well the combination works. The registry record describes the population as female patients with advanced or metastatic breast cancer and identifies the intended treatment population as postmenopausal women with metastatic breast cancer.

The primary question is about the proportion of participants meeting a composite clinical-benefit definition, not about a direct comparison between treatments. Because there is no control group, the study record cannot establish how outcomes under the combination compare with outcomes under another treatment or with an untreated course. The available record also does not report an observed endpoint count, an uncertainty interval, or an adjusted analysis. The question can therefore be described from the endpoint definition, but the answer cannot be quantified from the reported results.

3. Trial Design

This is a completed Phase I/II, single-group trial sponsored by the National Cancer Institute (NCI). The registry lists enrollment as 35, and records the study start as 2005-06 and primary completion as 2009-07. Allocation is marked NA, and masking is listed as NONE. These design features mean the record does not describe randomized assignment or masking, and it does not include a contemporaneous control arm for a like-for-like comparison.

The listed interventions are sorafenib tosylate and anastrozole. The Phase I description says participants received oral sorafenib twice daily and oral anastrozole once daily on days 1-28. Courses were to repeat every 28 days in the absence of disease progression or unacceptable toxicity. It also describes dose escalation, with cohorts of 3-6 participants receiving escalating sorafenib doses until the maximum tolerated dose was determined. The registry text does not provide the complete definition of that dose-limiting outcome in the available description.

The registry identifies the study as Phase I/II, but the detailed Phase II procedures, dose selection, analysis plan, and transition criteria are not reported in the registry record. The stated primary outcome is a clinical-benefit measure assessed at 24 weeks. Secondary outcomes include the number of participants with adverse events and tumor marker analysis. The record lists 3 outcome measures and 0 analyses. It does not report an analysis population, participant flow, or how many participants contributed data to each outcome.

This design can describe outcomes and tolerability observed in the single treatment group, subject to the completeness of outcome reporting. It does not provide the randomized treatment contrast needed to estimate a comparative effect against a separate control group. Enrollment alone should not be treated as the number who completed treatment or had evaluable endpoint data; those details are not reported in the registry record.

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

Analysis population for the primary outcome, as defined in the registry: Female patients with advanced or metastatic breast cancer. The protocol was initiated with intention to treat every patient enrolled with a sorafenib and anastrozole combination.

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 Complete Response + Partial Response + Stable Disease > 24 Weeks, measured over 24 weeks.

The primary endpoint is “Complete Response + Partial Response + Stable Disease > 24 Weeks,” measured in participants, with a timeframe of 24 weeks. The registry describes clinical outcome assessment using Response Evaluation Criteria in Solid Tumors (RECIST) V1.0 and assessment by MRI or CT. Complete response is defined as disappearance of all target lesions. Partial response is described as a decrease of at least 30% in the sum of the longest diameter of target lesions. Stable disease is a tumor that is neither growing nor shrinking. The protocol description defines clinical benefit using complete response, partial response, or stable disease sustained beyond 24 weeks.

This composite is used to summarize whether participants had tumor response or maintained stable disease for the specified period. Combining response categories can capture clinical outcomes that are not limited to tumor shrinkage: stable disease may meet the endpoint when it persists for the required duration. The endpoint is therefore a threshold-based participant count rather than a continuous measure of tumor change. Its meaning depends on the stated response definitions, assessment timing, and availability of imaging and follow-up.

The registry record does not report the number meeting the endpoint, the number assessed, or an estimate of the endpoint’s uncertainty. It also does not report details such as the handling of participants without an assessment by the stated timeframe. The endpoint’s definition is available, but its observed result cannot be evaluated from the reported information.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes the study as single-group, with allocation marked NA and masking marked NONE. It reports a Phase I/II design and a Phase I dose-escalation component. The record does not report a detailed statistical analysis plan, a sample-size justification, interim analyses, or the criteria used for selecting the dose carried forward. Those details should not be inferred from the trial’s phase labels or from its enrollment.

What does a single-group design estimate?

In general, a single-group design can describe outcomes observed among participants who receive the study regimen. It does not provide a concurrent control outcome against which to estimate a treatment difference. Random allocation can help balance known and unknown factors between groups; no randomized comparison is described in this record. Consequently, even a complete outcome count would be descriptive of the treated group, rather than a direct estimate of how the regimen compares with a control treatment.

The Phase I description uses cohorts of 3-6 participants and escalating sorafenib doses until the maximum tolerated dose is determined. Dose escalation is a method for assessing dose-related tolerability. The exact dose-limiting criteria are not available in the registry description, and the record does not report which dose was selected or the analysis leading to that selection. The Phase II details are also not reported in the registry record, so its dose and procedures should not be inferred.

How should the primary endpoint be understood?

The endpoint is a binary participant-level classification: a participant either meets the stated clinical-benefit definition or does not, based on response category and duration. The categories use RECIST V1.0 as described in the record, with imaging by MRI or CT. The threshold combines complete response, partial response, and stable disease lasting more than 24 weeks. In general, a composite endpoint can capture more than one clinically distinct state, but its interpretation depends on the exact category definitions and the duration requirement. Here, the classification rule is described, but the registry record does not report the number classified as meeting it or the number evaluated.

For a binary endpoint, a basic descriptive summary would report the number meeting the criterion and the denominator assessed. The denominator matters because participants may not all have an outcome assessment at the relevant time. The record lists enrollment as 35, but does not state that all enrolled participants contributed an endpoint assessment. No endpoint count or denominator is reported, so neither an observed rate nor its uncertainty can be interpreted.

What would uncertainty estimates mean?

In general, a confidence interval expresses the statistical uncertainty around an estimate and indicates a range of values compatible with the data under the method used. It does not remove design limitations, and it cannot repair missing outcome information or create a control comparison. No confidence interval for the primary endpoint is reported in the registry record. No standard error or other uncertainty estimate is reported either. Therefore, the precision of the endpoint estimate cannot be assessed from this record.

A p-value, in general, relates observed data to a specified null hypothesis under a statistical model. Its interpretation depends on the hypothesis, the analysis method, and whether the analysis was planned or selected after examining data. The registry lists 0 analyses and does not report a p-value or a statistical hypothesis for the primary endpoint. It would not be appropriate to infer statistical significance from the endpoint definition, enrollment, or safety counts.

What do the planning assumptions convey?

The record’s sample-size assumptions describe planning illustrations based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is described as a stated fraction of the observed effect. These assumptions are not described as the trial’s own design justification. The record identifies this study as single-group and does not report a randomized two-arm comparison; the illustration assumptions therefore should not be mistaken for the design actually recorded. No illustration result is included in the registry record reported for this trial.

In general, a sample-size calculation asks how many participants a hypothetical design would require under specified assumptions. Such a calculation is sensitive to the assumed effect, variability, allocation, significance level, and desired power. A planning illustration is not an observed outcome and is not a measure of what the completed trial established. The registry record does not report a prospective sample-size rationale or the assumptions used to plan enrollment of 35.

What is not available for checking?

The record does not report an endpoint analysis method, a missing-data method, an analysis population, or a protocol-defined hierarchy among outcomes. It lists 3 outcome measures and 0 analyses. The secondary outcomes include adverse events and tumor marker analysis, but detailed analysis procedures and tumor-marker results are not reported in the registry record. General statistical principles can explain what estimates and uncertainty would mean, but they cannot supply the absent trial results or analysis choices.

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("Sorafenib and Anastrozole")
n      <- c(35)
events <- c(35)
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  Sorafenib and Anastrozole  35  35  100.0  90.0  100.0  90.1  100.0  90.3  99.9

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 3 outcome measures, including the primary clinical-benefit endpoint and secondary outcomes for the number of participants with adverse events and tumor marker analysis. It records 0 analyses. No multiplicity strategy, outcome hierarchy, or adjustment for multiple statistical tests is reported in the registry record. Because inferential analyses are not listed, the record does not establish whether multiplicity adjustments were needed or used.

In general, when several outcomes or comparisons are tested, the chance of at least one false-positive result can increase if each is interpreted separately without regard to the others. Prespecifying a primary outcome and controlling or otherwise accounting for multiplicity can clarify how multiple findings should be interpreted. Here, the primary endpoint is identified, but the registry record does not report a broader analysis plan or how the secondary outcomes were to be interpreted alongside it. No statistical significance claims can be evaluated from the available record.

Missing-data handling is also not reported. The endpoint is assessed at 24 weeks, but the record does not state how participants without assessment at that time were classified, whether assessments outside the timeframe were used, or what follow-up was available. It does not report the number with evaluable endpoint data. Enrollment of 35 cannot be assumed to be the denominator for the primary endpoint.

The analysis population is not reported in the registry record. The protocol summary says there was an intention to treat every patient enrolled with the combination, but the available information does not specify how the endpoint analysis implemented that intention or handled participants who did not complete treatment or assessment. Those details are needed to understand which participants contribute to a result and how missing outcomes may affect its interpretation.

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 3% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: hand-foot syndome (34.3%).

The registry lists one treatment group, “Sorafenib and Anastrozole,” with 35 participants at risk for serious adverse events and 12 affected. For other adverse events, it lists 35 at risk and 35 affected. These are registry counts for separate safety categories; they should not be combined or treated as measures of treatment benefit. The record’s top serious term is written as “hand-foot syndome,” with 34.3% shown. The denominator for that percentage is not stated in the available information, so it should not be reconstructed from the group counts.

In general, an adverse-event count describes events recorded under the registry’s definitions and reporting rules. Serious adverse events are a subset defined by seriousness criteria, whereas other adverse events are reported separately. The counts do not by themselves show timing, duration, severity distribution, whether an event was considered related to treatment, or whether participants experienced multiple events. Those details are not reported in the registry record.

There is no control group, so the counts cannot be used as a randomized safety comparison against another regimen. The record also does not report detailed follow-up time or the methods used to collect adverse events. The figures are best read as descriptive safety information for the recorded treatment group, with important context and comparison details unavailable.

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

The registry record is useful for identifying what the trial set out to study: sorafenib combined with anastrozole in women with advanced or metastatic breast cancer, with a primary endpoint based on response or stable disease lasting more than 24 weeks. It also records a Phase I dose-escalation approach and selected adverse-event counts. These registry entries describe the study’s question and some of its recorded safety information.

The record does not report the primary endpoint result. It therefore does not show how many participants met the clinical-benefit definition, how many were assessed, or how precise an estimate would be. The absence of a reported result is not evidence that the endpoint was met or not met. It is a limit on what can be concluded from this registry record.

The single-group design also means that any observed outcomes would not constitute a randomized comparison with another treatment. A response or period of stable disease in the treated group could not, from this design alone, establish the effect of the combination relative to an alternative. Other features of the disease course, participant selection, follow-up, and treatment could matter, and comparative evidence is not presented in the record.

The safety counts provide descriptive information but do not establish a comparative safety profile. They do not show whether adverse events were attributed to sorafenib, anastrozole, their combination, or other causes. The record does not provide the detailed definitions, timing, or participant-level information needed for those interpretations.

Accordingly, the registry supports a careful account of the planned endpoint, regimen, design, and limited safety counts. It does not support a claim that the combination did or did not produce clinical benefit, a quantified treatment effect, or a comparison with another regimen. Those questions would require outcome results and analysis details not reported in the registry record.

14. Why This Trial Matters Statistically

This trial illustrates why a clear endpoint definition is not the same as an interpretable result. The registry specifies a composite clinical-benefit outcome using complete response, partial response, and stable disease beyond 24 weeks, and describes its assessment using RECIST V1.0 and MRI or CT. Without the observed count and assessment denominator, however, the endpoint’s frequency and precision cannot be evaluated. Statistical interpretation depends on both a clearly defined measure and reported data for that measure.

It also demonstrates the importance of matching the question to the design. A single-group Phase I/II study can describe treatment experience and support dose and safety assessment. Without a separate randomized comparator, it cannot directly quantify a comparative treatment effect. Readers should distinguish evidence about outcomes within a treatment group from evidence that one treatment changes outcomes relative to another.

The record also separates design information from results. It reports enrollment, timing, a dose-escalation description, and safety counts, but does not report a primary endpoint result or an analysis plan. Enrollment is not a substitute for an endpoint denominator, and a trial’s completion status does not establish what its results were. These distinctions matter when judging whether a numerical estimate is available and whether its uncertainty can be assessed.

Finally, the record’s limited safety figures show why denominators and event definitions matter. Serious and other adverse events are recorded separately, and the top serious term has a percentage without a stated denominator in the information available. Such figures are descriptive, not a controlled comparison. The trial is therefore a useful example of how design, endpoint definition, missing results, and reporting detail jointly determine what statistical conclusions are supportable.

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 most important trial-specific limitation for interpretation is that the registry record does not report the primary endpoint result, its assessment denominator, or an uncertainty estimate. The endpoint is defined at 24 weeks, but the information available does not establish how many participants had adequate imaging or follow-up to be classified. Enrollment is listed as 35 and should not be substituted for an endpoint analysis population.

The single-group design, with allocation marked NA and masking listed as NONE, provides no like-for-like control comparison. The record therefore does not offer a randomized estimate of benefit or harm relative to another treatment. The sample-size assumptions describe a planning illustration involving equal allocation between two arms, but the listed study model is single-group. The record does not report the trial’s own sample-size justification or explain how any illustration relates to its design.

Several operational details are not reported in the registry record. The available Phase I description is incomplete, including the definition of the maximum tolerated dose. Phase II procedures, dose selection, analysis populations, participant flow, and missing-data handling are not provided. The record also does not describe a multiplicity strategy or a detailed statistical analysis plan.

Safety interpretation is limited by the absence of detail about event definitions, attribution, timing, follow-up, and the denominator for the reported 34.3% serious term. Tumor marker analysis is listed as a secondary outcome, but results and analysis procedures are not reported. These omissions do not determine what the unreported results would be; they limit the conclusions that can be drawn from the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Sorafenib and Anastrozole in Treating Postmenopausal Women With Metastatic Breast Cancer — NCT00217399.
• Registry record last updated 2014-05-28; status last verified 2012-12.
• Results first posted 2013-02-12.
• 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

The registry record identifies a completed Phase I/II, single-group study of sorafenib with anastrozole for women with advanced or metastatic breast cancer. It lists enrollment as 35, sponsor National Cancer Institute (NCI), start 2005-06, and primary completion 2009-07. Allocation is marked NA and masking NONE.

The Phase I description includes oral sorafenib twice daily and oral anastrozole once daily on days 1-28, repeated in 28-day courses when disease progression or unacceptable toxicity does not occur. Cohorts of 3-6 participants received escalating sorafenib doses. The primary endpoint is complete response, partial response, or stable disease lasting more than 24 weeks, assessed using RECIST V1.0 by MRI or CT.

The registry lists 3 outcome measures and 0 analyses. It reports 12 participants affected by serious adverse events among 35 at risk, and 35 affected by other adverse events among 35 at risk. The primary endpoint result, its analysis denominator, and an inferential analysis are not reported in the registry record.