A Study for Participants With Small-Cell Lung Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study for Participants With Small-Cell Lung Cancer (NCT01025284), a non-randomized phase 2 study. The primary outcome is Part A: Percentage of Participants Achieving an Overall Response (Overall Response Rate).

2. Clinical Question

The question is descriptive: it concerns the proportion of Part A participants who met the response definition. The registry record does not report the observed number of responders or the resulting percentage, so it does not establish the magnitude or precision of that proportion. It also does not give a randomized control group against which to compare response.

3. Trial Design

This is a phase 2 study sponsored by Eli Lilly and Company, listed as completed in the registry record. The recorded study start is 2009-12 and primary completion is 2012-07. Enrollment is listed as 64. The condition is small cell lung cancer, and the official title specifies extensive-stage disease.

The record describes two study parts. Part A evaluated LY2523355 at 8 mg/m² per dose, administered intravenously as a 1-hour infusion on Days 1, 5, and 9 of each 21-day cycle. Treatment was described as continuing until disease progression or unacceptable toxicity. Part B evaluated 5 or 6 mg/m² per dose on Days 1, 2, and 3 of each 21-day cycle, with G-CSF support administered subcutaneously beginning on Day 4. The Part B treatment description is incomplete in the registry record after its statement about when treatment continued.

The registry lists the allocation as non-randomized, masking as none, and model as single-group. Although the record distinguishes Part A and Part B and lists Part B dose groups, those features do not create a randomized control comparison. Differences between groups could reflect participant characteristics, study procedures, or other factors that are not controlled by random assignment.

The primary endpoint is Part A overall response rate. The listed secondary outcomes include progression-free survival in both parts; clinical benefit rate in Part A; overall response rate in Part B; and pharmacokinetic measures of LY2523355, with metabolite measurement also listed for Part A. The record lists 11 outcome measures, but does not report analysis results for these outcomes.

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.

Before assignment: This is a nonrandomized, open-label, 2-part study.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All participants who received at least 1 dose of study drug in Part A.

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.

Population: All participants who received at least 1 dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Part A: Percentage of Participants Achieving an Overall Response (Overall Response Rate), measured over Date of enrollment to date of measured progressive disease up to 99.6 weeks.

The primary endpoint is the percentage of Part A participants achieving an overall response. The registry defines an overall response as complete response (CR) or partial response (PR), classified by investigators according to Response Evaluation Criteria in Solid Tumors (RECIST) guidelines. CR is defined as disappearance of all target and non-target lesions. PR is defined as at least a 30% decrease in the sum of the longest diameters of target lesions. The response rate is defined as the number of participants with CR or PR divided by the total number treated, multiplied by 100.

This endpoint expresses response as a proportion of the treated population. In general, a binary response endpoint can provide a readily interpretable summary of how many participants met a specified response criterion. It does not describe how long a response lasted, and by itself it does not establish that treatment caused the responses. The registry lists the Part A population as all participants who received at least 1 dose of study drug. Its stated timeframe is date of enrollment to date of measured progressive disease, up to 99.6 weeks.

The registry record defines the endpoint but does not report its observed numerator, denominator, percentage, or confidence interval. Consequently, the endpoint’s observed value and precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The statistical information in a registry record has two distinct roles: it can describe how an outcome is defined, and it can report what was observed. Here, the primary endpoint definition is present, but the observed primary result is not reported in the registry record. The endpoint is a percentage, so the underlying outcome is whether each participant did or did not meet the CR-or-PR response definition. A percentage summarizes the number meeting that definition relative to the stated analysis population.

What does the confidence interval describe?

The primary endpoint lists a 90% confidence interval as its dispersion measure, but no interval limits are reported. In general, a confidence interval represents uncertainty around an estimate under the assumptions of the analysis method. A narrower interval indicates greater precision than a wider interval, while the interval’s location describes the range of values compatible with the data and method. Without the reported estimate and interval limits, neither the response estimate nor its precision can be assessed.

A confidence interval is not a guarantee that the true value lies within a particular set of limits, and it does not address every source of uncertainty. For example, it does not automatically resolve bias from participant selection, outcome assessment, missing observations, or lack of a control group. Those design and data issues require separate consideration.

How should a binary response measure be read?

For a binary outcome, participants are classified according to whether the event occurred. Here, the event is achieving CR or PR under the stated RECIST definitions. The numerator is the number classified as having an overall response, and the denominator is the number treated in the Part A endpoint population. The registry describes that calculation but does not report either count or the resulting percentage. It would therefore be inappropriate to infer a value from enrollment or from the safety group counts.

The primary endpoint population is all participants who received at least 1 dose of study drug in Part A. That is a treatment-exposed population, rather than all enrolled participants across both parts. The record does not give the actual number included in the primary endpoint analysis or describe how participants with missing response assessments were handled.

What does over-dispersion mean in general?

In general, over-dispersion occurs when observed variability is greater than a statistical model assumes. A model that ignores over-dispersion can understate uncertainty, making confidence intervals too narrow or tests too optimistic. This concept is relevant to some count and proportion models, but the registry record does not report the model used for the primary endpoint, any over-dispersion assessment, or any adjustment for it. It is therefore not possible to say whether over-dispersion was relevant to the sponsor’s analysis.

What do the planning assumptions mean?

The planning illustration assumptions are described as a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They use a fraction of the observed effect as the effect to detect. In general, a sample-size calculation depends on assumptions about the effect, variability, significance level, power, allocation, and analysis method. Changing those assumptions can change the resulting planning estimate. These illustrations are not the trial’s own design justification; the registry record does not report the study’s sample-size justification.

The listed assumptions do not make this trial a two-arm randomized comparison. The registry describes a non-randomized, single-group model, and does not describe a like-for-like control comparison. A planning illustration using equal allocation between two arms is a hypothetical calculation, not a description of the study’s actual allocation or an observed result. Sample-size illustrations are planning quantities, not observed power. Observed power is not a substitute for reporting an estimate and its confidence interval.

What analysis details are not reported?

The registry record lists the endpoint definition and timeframe, but does not report the primary analysis method, any covariate adjustment, interim analysis procedures, or a statistical analysis plan. It also does not describe how missing endpoint data were treated, whether response assessments were independently reviewed, or whether the listed outcomes were tested in a prespecified order. Each of those details can affect how estimates and uncertainty should be interpreted, but none can be inferred from the endpoint definition alone.

For safety, the record gives numbers at risk and numbers affected for serious and other adverse events by listed group, as well as percentages for selected serious-event terms. These figures are descriptive. No inferential safety analysis or confidence intervals are reported in the registry record, so formal comparisons between the groups cannot be reconstructed from the listed values.

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("Part A")
n      <- c(38)
events <- c(1)
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  Part A  38  1  2.6  0.1  13.8  0.5  13.5  0.6  13.5

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 11 outcome measures spanning response, progression-free survival, clinical benefit, and pharmacokinetic measures. It does not report an analysis plan explaining how multiple outcomes or multiple statistical tests were handled. Whether any adjustment for multiplicity was planned, or whether a hierarchy of endpoints was used, is not reported in the registry record. Without that information, the listed outcomes should not be interpreted as a set of independently confirmatory tests.

The primary endpoint definition identifies the Part A population as all participants who received at least 1 dose of study drug in Part A. The record does not report the number analyzed for the endpoint, the number with missing response assessments, or how missing assessments were classified or handled. The approach to missing data for the secondary outcomes is also not reported in the registry record. This prevents assessment of whether the analysis denominator differed from the intended population or whether missingness could have influenced the estimate.

No analysis results are listed in the registry record, including results for the primary endpoint. The statistical analysis plan, interim analyses, model specifications, and any sensitivity analyses are not reported in the registry record. These absences do not establish that such procedures were not conducted; they mean that their presence and methods cannot be determined from the record.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: mucosal inflammation (50.0%), dyspnoea (37.5%), pneumonia (25.0%), neutropenia (12.5%), atrial fibrillation (12.5%).

The registry lists serious adverse-event counts for Part A - 8 mg/m²/Day, Part B - 5 mg/m²/Day, and Part B - 6 mg/m²/Day. The corresponding numbers at risk are 38, 18, and 8; the numbers affected by serious adverse events are 8, 8, and 8. For other adverse events, the numbers affected are 35, 18, and 7, with the same respective group counts at risk. These are counts, not comparative risk estimates.

The listed serious-event terms and percentages are mucosal inflammation, 50.0%; dyspnoea, 37.5%; pneumonia, 25.0%; neutropenia, 12.5%; atrial fibrillation, 12.5%; and asthenia, 12.5%. The record does not specify in the listed information which group or denominator applies to these term percentages, so they should not be assigned to a particular group. Death counts are not reported in the registry record.

In general, adverse-event counts describe events recorded among participants at risk; they do not alone establish that treatment caused an event. The non-randomized design and absence of a described control group also limit comparative interpretation. The registry does not report uncertainty intervals for these safety figures.

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

The registry record establishes what the study set out to measure: Part A overall response, defined as complete or partial response under RECIST, among participants who received at least 1 dose. It also describes the two study parts, the LY2523355 regimens, the recorded study design, and selected safety counts. These details help define the question and the context in which the study was conducted.

The record does not report the observed primary endpoint result. It therefore does not show how many Part A participants achieved response, what percentage that represented, or how precisely that percentage was estimated. Results for the listed secondary outcomes are also not reported in the registry record. The treatment’s effect cannot be quantified from the endpoint definition, enrollment total, or adverse-event counts.

The design matters for what any response result could establish. The study is listed as non-randomized, unmasked, and single-group, with no separate control treatment described. Such a design does not provide a randomized estimate of the difference between LY2523355 and a comparator. Comparisons between the study parts or Part B dose groups are not like-for-like randomized comparisons.

In general, an observed response proportion in a single-group study can describe the participants assessed, but it cannot by itself distinguish a treatment effect from other explanations. The record also does not give the primary endpoint’s confidence interval limits, analysis details, or missing-data handling, so the robustness and precision of a potential estimate cannot be evaluated.

The serious and other adverse-event figures are descriptive counts for the listed groups. They do not alone establish that treatment caused the events, and the listed serious-event term percentages are not linked to a group in the information reported. The registry record should therefore be read as a description of the study design, endpoint definitions, and selected safety information—not as a complete report of efficacy or comparative safety results.

14. Why This Trial Matters Statistically

This study illustrates why endpoint definitions and endpoint results must be read separately. The registry precisely describes the Part A response criterion and the treated population, but does not report the observed response proportion or its 90% confidence interval. A well-specified outcome does not substitute for an estimate, and without the estimate and uncertainty interval, readers cannot assess its magnitude or precision.

It also highlights the importance of matching statistical interpretation to study design. The record identifies a non-randomized, unmasked, single-group model. Its two parts and listed dose groups do not amount to randomized treatment comparisons. That distinction remains important even when registry records present outcomes for multiple groups: group labels alone do not establish comparability.

The safety information provides counts of participants affected and selected serious-event percentages, but does not supply uncertainty intervals or a group assignment for the selected event-term percentages. Keeping those descriptive data separate from causal or comparative claims is a central statistical discipline.

Finally, planning calculations should not be mistaken for trial results or for the original design rationale. The stated planning assumptions concern a hypothetical equal-allocation, two-arm calculation using a fraction of an observed effect. The registry record does not report the trial’s sample-size justification, and planning illustrations are not observed power. Together, these features show why a sound statistical reading requires attention to what is defined, what is estimated, what is missing, and what the design can support.

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 main limitation for interpreting the primary outcome is that its observed result is not reported in the registry record. The record defines overall response and identifies the Part A endpoint population, but does not give the responder count, analysis denominator, percentage, or confidence interval. Results for the listed secondary outcomes are also not reported.

The design is recorded as non-randomized, unmasked, and single-group, with no separate control treatment described. Therefore, the study record does not support a randomized comparison between treatment options. Part A and Part B also differ in regimen descriptions, and Part B includes two listed dose groups; they should not be treated as randomized, like-for-like controls.

The registry lists enrollment as 64 but does not state how many participants entered each part for the primary endpoint analysis. The safety information gives group-specific numbers at risk, but those figures cannot be assumed to be the primary endpoint denominators. Missing response assessments, the handling of missing data, and sensitivity analyses are not reported in the registry record.

Other details that could clarify interpretation are also absent: the primary statistical analysis method, any covariate adjustment, interim analyses, multiplicity procedures, and the trial’s sample-size justification. The Part B treatment description is incomplete after its statement about treatment continuing. For safety, deaths are not reported, and the group or denominator for the listed serious-event term percentages is not specified in the information recorded.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study for Participants With Small-Cell Lung Cancer — NCT01025284.
• Registry record last updated 2019-09-17; status last verified 2019-09.
• Results first posted 2017-12-04.
• 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

NCT01025284 is a completed phase 2 study sponsored by Eli Lilly and Company, with enrollment listed as 64. The registry records a study start of 2009-12 and primary completion of 2012-07. It concerns participants with small-cell lung cancer, with the official title specifying extensive-stage disease.

The record describes LY2523355 treatment in Part A and Part B, with G-CSF support in Part B. Allocation is listed as non-randomized, masking as none, and model as single-group. The primary endpoint is Part A overall response rate, defined by CR or PR under RECIST among participants who received at least 1 dose. The endpoint result, its confidence interval limits, and results for the secondary outcomes are not reported in the registry record.

Adverse-event counts are listed for three regimen groups, and selected serious-event terms have percentages. These figures are descriptive and do not provide a randomized safety comparison.