Cabozantinib-S-Malate and Erlotinib Hydrochloride in Treating Patients With Previously Treated Metastatic Non-Small Cell Lung Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Cabozantinib-S-Malate and Erlotinib Hydrochloride in Treating Patients With Previously Treated Metastatic Non-Small Cell Lung Cancer (NCT01866410), a na phase 2 study. The primary outcome is Objective Response Rate.

2. Clinical Question

In plain terms, the study asks how often participants treated with the combination had a complete or partial response during the stated assessment period. It does not directly estimate how the combination compares with another treatment, because the registry describes a single-group design. Any response proportion would describe the observed participants and their follow-up under this study, rather than establish what would have happened to similar participants under a different treatment.

3. Trial Design

This is a phase II, completed, single-group trial sponsored by the National Cancer Institute. The registry records enrollment of 37 participants and study dates from 2013-05-20 to primary completion on 2018-03-30. The title and official title describe cabozantinib with erlotinib in advanced or previously treated non-small cell lung cancer, with the official title specifying EGFR-mutant disease that progressed on EGFR tyrosine kinase inhibitor therapy.

All participants were assigned to the treatment group described in the record: cabozantinib-s-malate and erlotinib hydrochloride. Treatment was oral, with cabozantinib-s-malate daily and erlotinib hydrochloride once daily on days 1-28. Courses were described as repeating every 28 days in the absence of progression or unacceptable toxicity. The registry lists laboratory biomarker analysis in addition to the two drugs. It does not describe a separate control group, and masking is listed as none.

The primary outcome is objective response rate, with an endpoint timeframe of up to 2 years. The registry describes response according to RECIST v1.1, with complete response defined as disappearance of all target lesions and partial response defined as at least a 30% decrease in the sum of the longest diameter of target lesions. Overall response combines those categories. MRI is specified as the assessment method.

Other listed outcomes include tumor doubling time, adverse events, best response, progression-free survival, and overall survival. The registry lists 10 outcome measures and 2 analyses, but further details about their analysis populations and methods are not reported in the registry record. The design is suitable for describing outcomes among treated participants; without a concurrent comparison group, differences attributable to treatment cannot be isolated from other explanations.

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 Objective Response Rate, measured over Up to 2 years.

Objective response rate is the proportion of participants classified as having a complete or partial response according to the stated tumor-response criteria. The registry defines complete response as disappearance of all target lesions and partial response as at least a 30% decrease in the sum of the longest diameter of target lesions. The response assessment is described as using RECIST v1.1 and MRI, with a timeframe of up to 2 years.

This endpoint provides a categorical summary of tumor change: each participant is classified by response status rather than by the size of a continuous change alone. Combining complete and partial responses gives a single overall response measure. In general, such an endpoint is used to describe the share of participants meeting a prespecified response definition, which can be informative in an early-phase study focused on observed tumor response.

The registry lists the primary measure as a number with a 95% confidence interval, but the response count, response percentage, and interval are not reported in the registry record. Therefore, the size of the observed response rate and its precision cannot be assessed from the posted primary outcome information. The definition alone does not establish whether responses occurred, how many participants had them, or how durable any response was.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the primary endpoint count?

Objective response rate is a binary outcome at the participant level: a participant is classified as having an overall response or not, using the specified response criteria. The registry defines overall response as complete response plus partial response. Complete response means all target lesions disappear; partial response means at least a 30% decrease in the sum of the longest diameter of target lesions. The assessment is described as RECIST v1.1 by MRI, with a timeframe of up to 2 years.

For a binary outcome, the response rate is ordinarily the number of participants meeting the response definition divided by the number evaluated under the analysis rules. That is a general description, not a reconstruction of this trial's result. The registry record does not report the response count, denominator used for the primary analysis, or estimated rate. It therefore does not allow the rate to be checked or interpreted numerically.

How should a confidence interval be read?

A confidence interval expresses uncertainty around an estimate. In general, a narrower interval indicates greater precision, while a wider interval indicates less precision. A 95% confidence interval is listed for the primary outcome, but its endpoints and the estimate are not reported in the registry record. Without them, precision cannot be evaluated. A confidence interval is not a guarantee that the true value lies within a particular interval, nor does it by itself resolve limitations in the study design.

Why does the single-group design matter?

The study model is single group, allocation is recorded as NA, and masking is listed as none. In general, a single-group study can describe outcomes among participants receiving the study regimen, but it does not provide a randomized contrast with another group. A response rate observed in one group cannot by itself distinguish an effect of treatment from other influences, such as the characteristics of enrolled participants or the natural course of disease. This is a design limitation, not a defect that can be corrected by calculating a confidence interval.

What does the planning illustration represent?

The sample-size assumptions are explicitly described as a planning illustration computed from the observed effect, not the trial's own design. They specify a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. For time-to-event outcomes, the planning quantities are total events; for other outcomes, they are participants per arm. These calculations are hypothetical planning quantities, not observed results and not evidence that the trial was designed with those assumptions. The registry record does not report a sample-size justification for the trial itself. A planning illustration based on an observed effect also does not replace an independent estimate of uncertainty or establish that a future study will reproduce that effect.

Why can event counts differ in interpretability?

Binary outcomes such as response classify participants into categories, while time-to-event outcomes such as progression-free survival involve both whether an event occurred and when it occurred. In general, time-to-event analyses may account for participants whose event time is not observed during follow-up through censoring methods. The registry lists progression-free survival and overall survival as secondary outcomes, but the analysis methods, event definitions, follow-up summaries, and numerical results are not reported in the registry record.

For adverse events, counts describe how many participants were affected under the registry's reporting categories. Serious adverse events and other adverse events are distinct report groupings. A participant may experience more than one event, so event-term percentages should not automatically be treated as percentages of unique participants unless the reporting convention makes that clear. General adverse-event comparisons also depend on exposure time, definitions, and collection methods; those details are not reported in the registry record.

What is not specified about the statistical plan?

The record lists 10 outcome measures and 2 analyses, but it does not provide the full statistical analysis plan, analysis populations, missing-data rules, or interim-analysis details. It also does not report whether the primary endpoint was analyzed by intention-to-treat, by evaluable participants, or under another rule. These distinctions can affect denominators and interpretation. They should not be inferred from the outcome title or from the treatment description.

In general, statistical interpretation combines an estimate, its uncertainty, the design that generated it, and the rules used to define the analysis. For this trial, the primary estimate and interval are absent from the registry result information. The available methods description therefore supports understanding what the outcome was intended to measure, but not independent numerical evaluation of the outcome.

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("Cabozantinib-s-malate, Erlotinib Hydrochloride")
n      <- c(37)
events <- c(4)
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  Cabozantinib-s-malate, Erlotinib Hydrochloride  37  4  10.8  3.0  25.4  4.3  24.7  4.4  24.8

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 10 outcome measures and 2 analyses, including objective response rate, tumor doubling time, adverse events, best response, progression-free survival, and overall survival. Considering multiple outcomes can raise multiplicity concerns: in general, the more statistical comparisons or tests made, the greater the chance that at least one result appears notable by chance. A prespecified testing hierarchy or adjustment can address some multiplicity concerns, but the statistical plan and any multiplicity adjustment are not reported in the registry record. The presence of several listed outcomes does not establish that formal hypothesis tests were performed for each.

The registry identifies the primary endpoint and its timeframe, but does not report the primary outcome count, analysis denominator, or response estimate. It also does not specify the primary analysis population or how missing response assessments were handled. In general, missing outcome data may affect both the estimated proportion and its precision, especially if participants with missing assessments differ from those with observed assessments. The record does not state whether missing participants were counted as nonresponders, excluded, or handled in another way.

Details about interim analyses, stopping rules, protocol deviations, and analysis populations are not reported in the registry record. These omissions prevent readers from determining whether the posted analysis followed a prespecified statistical plan. The listed sample-size assumptions describe a planning illustration rather than the trial's own design justification, so they do not fill that gap. No conclusion about the handling of multiplicity or missing primary outcome data should be inferred from the available registry description.

12. 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: diarrhea (24.3%), lipase increased (10.8%), serum amylase increased (10.8%), nausea (8.1%), hypertension (8.1%).

The treatment group lists 37 participants at risk for serious adverse events and 25 affected. For other adverse events, the record lists 37 at risk and 37 affected. These are participant counts in the registry's safety categories; the counts do not by themselves establish event severity beyond the category or a causal relationship to treatment. The record also lists 32 deaths, without a cause or timing breakdown in the safety information.

The most frequent serious adverse event terms listed are diarrhea at 24.3%, lipase increased at 10.8%, serum amylase increased at 10.8%, nausea at 8.1%, hypertension at 8.1%, and vomiting at 5.4%. These percentages are reported as event-term figures. They should not be added together: a participant may have experienced more than one term, and the record does not state that the categories are mutually exclusive.

Safety interpretation depends on definitions, collection period, exposure, severity grading, and attribution. Those details are not reported in the registry record. The posted counts describe reported events in this group; they do not establish how the regimen compares with another treatment or whether an individual event was caused by either drug.

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

The registry describes a phase II study of cabozantinib-s-malate with erlotinib hydrochloride in a single group of participants with advanced EGFR-mutant non-small cell lung cancer after progression on EGFR tyrosine kinase inhibitor therapy. It specifies an objective response endpoint based on RECIST v1.1 assessments by MRI and a timeframe of up to 2 years. These details explain the intended clinical question and how response was defined.

The primary response estimate and its 95% confidence interval are not reported in the registry record. As a result, the posted primary outcome information does not show how many participants had a complete or partial response, the size of the response rate, or how precise that estimate was. The response definition alone is not a result and cannot support a conclusion about the observed frequency of response.

The study has no separate comparison group in the registry description. Therefore, even a reported response proportion would describe outcomes among participants treated in this study, rather than establish the difference between the combination and another treatment. The registry's safety counts provide descriptive information about serious and other adverse events, but they do not determine whether events were caused by treatment or how safety compares with an alternative.

The record does not report the complete statistical analysis plan, analysis populations, missing-data methods, or interim-analysis details. These gaps limit independent assessment of how outcomes were analyzed. The conclusions that can be drawn are correspondingly narrow: the registry documents the study design, endpoint definition, and selected safety counts, while the primary response result and several details needed for fuller statistical interpretation are not reported in the registry record.

14. Why This Trial Matters Statistically

This trial illustrates why a clearly defined endpoint and a reported numerical result are both necessary for statistical interpretation. The registry specifies objective response rate, the response categories, the assessment method, and the timeframe. Those definitions allow readers to understand what the primary measure was intended to capture. However, because the response estimate and confidence interval are not reported in the registry record, readers cannot assess either the observed response frequency or its precision.

The single-group design is another important statistical feature. It permits descriptive reporting of outcomes among participants receiving the combination, but it does not create a randomized comparison. This distinction helps prevent an observed outcome from being mistaken for a comparative treatment effect. The design and the missing primary result together make it especially important to separate what the registry documents from what cannot be inferred.

The record also shows how outcome lists and safety summaries require careful reading. Multiple outcomes do not reveal whether multiplicity was addressed, and event-term percentages do not necessarily represent distinct groups of participants. Counts, denominators, definitions, and analysis rules all shape what a statistic means. Several of those analysis details are not reported in the registry record.

Finally, planning calculations should be distinguished from trial design and observed evidence. The sample-size assumptions are labeled as an illustration based on the observed effect, rather than as the trial's own design. Such calculations can help frame future planning, but they do not supply the missing response estimate, show that the trial had a particular level of power, or validate a treatment effect. This distinction is useful when interpreting registry records that include both outcome reporting and planning information.

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 primary limitation for interpreting efficacy is that the objective response rate and its 95% confidence interval are not reported in the registry record. Without the estimate, response count, and analysis denominator, the primary endpoint cannot be evaluated numerically. The record defines the endpoint but does not establish the observed outcome.

The design is single group, with no separate comparator and no masking. This limits the ability to attribute observed outcomes specifically to the combination or to compare it fairly with another regimen. The enrolled group may also differ from other patient groups in ways that affect outcomes; the registry information does not permit those differences to be assessed.

The registry identifies 37 enrolled participants, but does not report the primary analysis population or the handling of missing response assessments. It also does not report assessment frequency, response-review procedures, or the detailed statistical analysis plan. These gaps limit assessment of the response denominator, potential assessment differences, and adherence to prespecified analysis methods.

Safety information is descriptive, and the record does not provide a causal attribution breakdown, exposure-adjusted rates, or the definitions and collection details needed for fuller comparison. The listed 32 deaths are not accompanied by cause or timing information in the safety summary. The top serious adverse event terms are useful for identifying reported categories, but do not by themselves establish comparative risk.

Although secondary outcomes are listed, their numerical results and analytic details are not present in the registry information summarized by the record. Multiplicity handling, missing-data rules, interim analyses, and the trial's own sample-size justification are also not reported in the registry record. These limitations constrain both efficacy and safety interpretation.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Cabozantinib-S-Malate and Erlotinib Hydrochloride in Treating Patients With Previously Treated Metastatic Non-Small Cell Lung Cancer — NCT01866410.
• Registry record last updated 2019-05-16; status last verified 2019-04.
• Results first posted 2019-05-16.
• 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

NCT01866410 is a completed phase II, single-group trial sponsored by the National Cancer Institute. The registry records enrollment of 37 participants and a study start date of 2013-05-20, with primary completion on 2018-03-30. It evaluates cabozantinib-s-malate with erlotinib hydrochloride in advanced EGFR-mutant non-small cell lung cancer after progression on EGFR tyrosine kinase inhibitor therapy.

The primary endpoint is objective response rate by RECIST v1.1, assessed by MRI, over a timeframe of up to 2 years. The response estimate and 95% confidence interval are not reported in the registry record. Safety information lists 25 participants affected by serious adverse events, 37 affected by other adverse events, and 32 deaths. The registry does not describe a control group, and key analysis details are not reported in the registry record.