Docetaxel and Cisplatin in Treating Patients With Stage III or Stage IV Non-Small Cell Lung Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Docetaxel and Cisplatin in Treating Patients With Stage III or Stage IV Non-Small Cell Lung Cancer (NCT00118131), a na phase 2 study. The primary outcome is Overall Tumor Response Rate.

2. Clinical Question

3. Trial Design

This was a phase II, single-group study of docetaxel plus cisplatin in chemotherapy-naive patients with stage IV or select stage IIIB non-small cell lung cancer. The registry lists an enrollment of 49 and records the study status as terminated. The start is recorded as 2003-12 and primary completion as 2010-02. The sponsor was the University of Medicine and Dentistry of New Jersey.

Allocation is listed as NA, and masking as none. There is no randomized control group described in the record. The findings therefore pertain to the treatment group enrolled in this study; they cannot be interpreted as a comparative estimate of the combination against another regimen or usual care. Characteristics of a control population are not reported in the registry record.

The regimen used cycles defined as intervals of 28 days. Docetaxel was scheduled at 35 mg/m2 per day on Days 1, 8 and 15, and cisplatin at 25 mg/m2 per day on those same days. The recorded total doses for a cycle were 105 mg/m2 for docetaxel and 75 mg/m2 for cisplatin. Docetaxel was always to be given before cisplatin. These are the planned administration details in the registry; treatment adherence, dose modifications, and exposure actually received are not reported in the registry record.

The primary endpoint was overall tumor response rate, with a timeframe recorded as 7 years. The registry states that the analysis was performed on the first 47 patients and that the study was terminated before 2 patients met the pre-specified time point. Three secondary outcomes are listed: time to progressive disease, 1-year survival rate, and median survival time. Although four outcome measures are recorded, the registry record does not report statistical analysis entries for them. The reason for termination and the protocol-level basis for the planned enrollment are not reported.

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: Analysis was performed on the first 47 patients. Study was Terminated before 2 of the patients met the pre-specified time point.

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 Overall Tumor Response Rate, measured over 7 years.

The primary endpoint, overall tumor response rate, concerns the percentage of participants experiencing either a complete response or a partial response. The registry describes the response criteria as RECIST v1.0 for target lesions assessed by MRI. A complete response means disappearance of all target lesions. A partial response is defined as a >=30% decrease in the sum of the longest diameters of target lesions. The overall response combines complete and partial responses.

Response is a binary outcome at the participant level: a participant either meets the defined response criterion or does not. Reporting the proportion meeting the criterion can describe tumor response in the studied group. The endpoint does not, by itself, describe how long a response lasts, whether disease later progresses, or survival. Time to progressive disease, 1-year survival rate, and median survival time are listed separately as secondary outcomes.

The registry records a 7-year timeframe for the primary endpoint, but does not explain in detail how assessments were scheduled or how the timeframe was applied to each participant. It also does not report the number with complete or partial response, the resulting percentage, or uncertainty around that estimate. Without those results, the endpoint definition can be understood, but the observed response rate and its precision cannot be assessed from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record identifies a percentage endpoint and a single-group design, but contains no statistical analysis entries. The methods below explain how such data are generally interpreted; they do not describe unreported procedures as if they were used in this trial.

What does a response percentage represent?

For a binary endpoint, each participant is classified according to whether the stated event occurred. The response percentage represents the share of the analyzed population meeting the response definition. Here, the event is complete or partial response under the listed RECIST criteria. The registry describes the endpoint and says the analysis used the first 47 patients, but it does not give the event count or percentage. The result itself therefore cannot be reconstructed from the record.

A percentage is most informative when its denominator and analysis population are clear. In this record, the described population and the note about patients who had not reached the pre-specified time point are relevant to interpretation, but the handling of those patients is not specified. The registry also does not state whether all patients with available assessments were analyzed, how unevaluable assessments were classified, or whether the response assessment was confirmed. Those details are not reported in the registry record.

What would a confidence interval add?

In general, a confidence interval expresses the uncertainty around an estimated effect or percentage that arises from sampling variability under the statistical model. A narrower interval indicates greater precision under that model; a wider interval indicates less precision. It does not guarantee that the estimate is free from bias, and it does not account automatically for limitations such as selection, missing observations, or measurement error.

No confidence interval for the response rate is reported in the registry record. Without the estimate and its uncertainty, readers cannot judge how compatible the data are with a range of response rates. A point estimate alone, even if it were available, would not show precision. Nor would a confidence interval by itself establish a causal treatment effect in a single-group study.

Why does the single-group design matter?

In general, a control group allows outcomes under different conditions to be compared within a study. Random allocation can help make the groups comparable on measured and unmeasured characteristics, while masking can reduce some forms of bias in assessment or care. This trial is listed as single-group, with allocation NA and masking none. It therefore has no internal randomized comparison. A response rate in the treated group, if reported, would be descriptive of that group and could not alone show what would have happened under another treatment or without the study regimen.

Single-group studies can still describe feasibility, observed outcomes, and safety experience. Their interpretation depends on the population enrolled, the endpoint definition, follow-up, completeness of outcome assessment, and the context in which outcomes are measured. The registry record does not report enough information to assess all these features. The distinction is between describing observed outcomes and estimating a comparative treatment effect.

What do the sample-size assumptions mean?

General planning calculations translate an assumed effect and a chosen statistical design into an illustrative sample size. The record states that its planning illustration uses a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect expressed as a fraction of the observed effect. These are planning assumptions, not evidence that this single-group trial used a two-arm design or was planned using those assumptions. The registry record does not report the trial's own sample-size justification or statistical plan.

A planning sample size is not observed power. It cannot establish whether a completed study had adequate power, and it does not measure the probability that a particular result is true. Such calculations depend on assumptions about the effect, variability, error rates, allocation, and analysis. The record does not provide a reported observed response estimate or the calculation outputs in the statistical analysis entries, so no trial-specific power conclusion can be drawn from this information.

Why can over-dispersion matter?

In general, over-dispersion occurs when observed variability is greater than a statistical model assumes. If a model underestimates variability, standard errors can be too small and confidence intervals too narrow; inferential tests may then appear more decisive than warranted. The relevance of over-dispersion depends on the outcome and model. The primary endpoint is a binary response, but the registry record does not identify a fitted model or report a variance assessment. It would be inappropriate to claim that over-dispersion was tested or corrected.

For time-to-event outcomes such as time to progressive disease, methods generally need to account for follow-up duration and censoring, when a participant's event time is not observed during the relevant follow-up. The registry lists time to progressive disease, but does not report its estimate, censoring rules, model, or analysis population. The same limitation applies to the listed survival outcomes: their names do not disclose how they were analyzed.

What can be inferred from the absence of analysis entries?

The record lists 0 analyses. This means no statistical analysis entries are present in the registry record; it does not prove that investigators performed no analyses outside that record. There are no posted p-values, confidence intervals, model specifications, or adjusted results to evaluate. The interpretation must therefore remain limited to the design and descriptive entries actually recorded. General statistical concepts can explain what those missing results would have helped readers assess, but cannot substitute for them.

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("Docetaxel and Cisplatin")
n      <- c(47)
events <- c(10)
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  Docetaxel and Cisplatin  47  10  21.3  10.7  35.7  12.0  34.9  12.0  35.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists the primary outcome of overall tumor response rate and secondary outcomes of time to progressive disease, 1-year survival rate, and median survival time. Multiple endpoints create a multiplicity issue in general: when several hypotheses are tested, the chance of at least one apparently positive result can increase if each is judged independently. Statistical plans may address this through a prespecified hierarchy or adjustment, but the record does not report such a plan or any multiplicity adjustment. No test results are posted, so the practical impact of multiplicity cannot be assessed.

The primary-outcome population is described as the first 47 patients, and the record says the trial was terminated before 2 patients met the pre-specified time point. This indicates that the endpoint analysis did not include all enrolled patients as described in the registry, but the record does not explain exactly how inclusion was determined or how the remaining outcome information was treated. It does not state whether the endpoint was missing for those patients, whether follow-up continued, or whether any imputation or sensitivity analysis was used. The fact that a time point was not met should not be equated automatically with a particular missing-data mechanism.

The registry does not report an intention-to-treat definition, a per-protocol population, rules for unevaluable response assessments, or a missing-data analysis. It also does not explain whether the 7-year endpoint timeframe applied uniformly or how incomplete follow-up was handled. These matters are important because analysis choices can affect both the estimated response proportion and its uncertainty. Without those details and without outcome results, readers cannot judge whether missing data or multiplicity materially influenced the findings.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: dyspnea (shortness of breath) (10.2%), diarrhea patients without colostomy (6.1%), supraventricular arrhythmias (svt/atrial fibrillation/flutter (4.1%), fever (in the absence of neutropenia, where neutropenia is defined as agc<1.0 x 10e9/l) (4.1%), nausea (4.1%).

The safety entries describe a group titled Docetaxel and Cisplatin, with 49 at risk for serious adverse events and 18 affected. For other adverse events, the record lists 49 at risk and 49 affected. It also records 45 deaths. These counts describe registry entries; they do not, by themselves, establish that an event was caused by the study drugs or indicate when it occurred.

The listed serious adverse event terms and percentages are dyspnea (shortness of breath), 10.2%; diarrhea patients without colostomy, 6.1%; supraventricular arrhythmias (SVT/atrial fibrillation/flutter, 4.1%; fever in the absence of neutropenia, where the record defines neutropenia as AGC<1.0 x 10e9/L, 4.1%; nausea, 4.1%; and infection without neutropenia, 4.1%. These are the terms and percentages recorded, not a comparison against another group.

The record does not report event-level timing, duration, severity grading, treatment attribution, or the criteria used to determine relatedness. It also does not give a comparator safety group. The entries should therefore be read as descriptive safety information, not as a causal estimate of risk or a basis for comparing regimens.

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

The record establishes that a phase II, single-group study evaluated weekly docetaxel with weekly cisplatin in chemotherapy-naive patients with stage IV or select stage IIIB non-small cell lung cancer. It defines overall tumor response using complete and partial responses and describes the population used for the primary analysis. It also records serious and other adverse event counts, selected serious adverse event terms, and deaths.

It does not report the primary response count or rate. There is no posted confidence interval or test result for the primary endpoint, and no statistical analysis entries are listed. As a result, the record cannot quantify the observed response or show how precisely it was estimated. It also cannot support a conclusion about statistical significance for the primary endpoint.

The absence of a comparator is central to interpretation. Even if the response result were available, an outcome in a single treatment group would not provide a randomized estimate of the difference between the combination and another treatment. Differences in patient characteristics, outcome assessment, follow-up, or other influences could affect outcomes. The registry record does not provide a basis for separating those influences from the treatment experience.

The listed progression and survival outcomes are not accompanied by results or analysis details. Their presence in the registry should not be mistaken for evidence about the outcomes. Similarly, safety counts and percentages are descriptive entries. Without attribution and comparative information, they do not establish how much risk was caused by treatment.

The record states that the study was terminated before 2 patients reached the pre-specified time point. It does not give the reason for termination or explain the consequences for endpoint assessment and analysis. This limits interpretation of completeness and follow-up. The supported conclusion is therefore about what the registry documents—the design, treatment schedule, endpoint definition, and recorded safety information—not a conclusion that the regimen does or does not have clinical benefit.

14. Why This Trial Matters Statistically

This trial illustrates a basic distinction in clinical statistics: an endpoint definition is not an endpoint result. The registry describes overall tumor response in terms of complete or partial response, but does not report how many participants met that definition or the resulting rate. Without the estimate and its uncertainty, readers cannot assess the magnitude or precision of the primary outcome.

The study also demonstrates why design details shape what a result can mean. A single-group study can describe outcomes in the enrolled group, but it has no concurrent randomized comparison to help distinguish treatment-associated outcomes from other influences. Allocation is listed as NA and masking as none. Those design features do not invalidate descriptive information, but they constrain comparative interpretation.

Analysis populations and follow-up also matter. The registry says the primary analysis used the first 47 patients and notes that the trial ended before 2 patients met the pre-specified time point. Without an explanation of how those patients' data were handled, readers cannot determine the implications for missing outcome information or representativeness of the analysis population. The record does not state the statistical plan or report analysis entries.

Finally, the safety counts demonstrate the difference between recording events and estimating treatment-related risk. Serious and other adverse events are listed for the treatment group, but no comparator or attribution details are reported. These data can describe what the registry recorded, while leaving causal interpretation unresolved. Together, the record shows why clear reporting of estimates, uncertainty, analysis populations, and comparison groups is essential for sound statistical interpretation.

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.

Several trial-specific limitations follow directly from the registry record. The primary response result is not reported, so the response count, percentage, and precision cannot be assessed. Although the outcome definition and 7-year timeframe are stated, details of assessment timing and the handling of participants who did not reach the pre-specified time point are not reported.

The study is listed as single-group, with allocation NA and masking none. There is no like-for-like control group for estimating comparative outcomes. The registry record also does not report the reason for termination, the trial's own sample-size justification, or the statistical plan. It lists 0 analyses, so no model results, confidence intervals, p-values, or adjusted estimates are available in the record.

The primary analysis population is described as the first 47 patients, while the record states that the study ended before 2 patients met the pre-specified time point. The inclusion criteria for that analysis, the treatment of incomplete assessments, and the handling of missing data are not reported. These omissions prevent assessment of whether outcome availability could have affected the estimate.

Safety information is also limited to registry counts and selected terms with percentages. Details about event timing, severity grading, attribution to treatment, and follow-up are not reported. The record does not describe a comparison group for safety. The listed secondary outcomes have no accompanying estimates or analysis details. These limitations restrict interpretation to the study's documented design and descriptive entries.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Docetaxel and Cisplatin in Treating Patients With Stage III or Stage IV Non-Small Cell Lung Cancer — NCT00118131.
• Registry record last updated 2023-08-15; status last verified 2023-07.
• Results first posted 2013-11-25.
• 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

NCT00118131 is a phase II, single-group study of weekly docetaxel and cisplatin in chemotherapy-naive patients with stage IV or select stage IIIB non-small cell lung cancer. The registry records enrollment of 49, allocation as NA, masking as none, and status as terminated. The primary endpoint is overall tumor response rate, defined using complete or partial response under RECIST v1.0. The record says the primary analysis used the first 47 patients and that the study ended before 2 patients met the pre-specified time point.

The primary response result and statistical analysis entries are not reported in the registry record. Safety entries include 18 affected for serious adverse events, 49 affected for other adverse events, and 45 deaths. The record does not provide a concurrent comparator or enough analysis detail to support comparative or causal conclusions.