A Study of MLN0264 in Participants With Cancer of the Stomach or Gastroesophageal Junction: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of MLN0264 in Participants With Cancer of the Stomach or Gastroesophageal Junction (NCT02202759), a na phase 2 study. The primary outcome is Overall Response Rate (ORR) Based on Response Evaluation Criteria in Solid Tumors (RECIST).

2. Clinical Question

The study was intended to assess the efficacy, safety and tolerability of MLN0264 in this clinical population. The primary endpoint focuses on tumor response: it counts participants whose best assessed response met the definition of complete response or partial response. It does not compare MLN0264 with another treatment or with a concurrent control group.

The registry record identifies the endpoint and its assessment schedule, but a numerical overall response rate is not reported in the registry record. Consequently, the record does not establish how many response-evaluable participants had a complete or partial response, nor how precise an estimated response percentage would be. The clinical question can be described from the study design, but the posted record does not supply the primary result needed to answer it quantitatively.

3. Trial Design

This was a Phase 2, single-group study of MLN0264. The registry record lists no masking and no allocation to different treatment groups. There is therefore no randomized comparison or concurrent control arm in the recorded design. Any description of outcomes concerns the participants receiving the study drug, rather than a contrast between treatment groups.

The recorded intervention was MLN0264 1.8 mg/kg by 30-minute intravenous infusion on Day 1 of each 21-day cycle. Treatment was planned for up to 1 year or until disease progression or unacceptable toxicity, up to 14 cycles. The record indicates that dose reduction, delay or discontinuation could occur for participants developing treatment-associated nonhematologic and other conditions, but the available arm description ends before completing that explanation. Further details are not reported in the registry record.

The primary endpoint was investigator-assessed overall response rate under RECIST version 1.1. Assessments were scheduled on Day 21, every other cycle, starting with Cycle 2, until disease progression, death or study closure, for up to 17 months. The response-evaluable population required measurable disease, at least 1 dose, and at least 1 post-baseline response assessment. This definition means the endpoint denominator was not simply specified as every participant enrolled.

Enrollment was 38. The study started on 2014-08-04, had primary completion on 2016-01-15, and its status is recorded as terminated. The reason for termination is not reported in the registry record. A total of 15 outcome measures are listed, and no analyses are listed. The record does not report a separate control group, a statistical analysis plan, or a numerical result for the primary endpoint.

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: Participants with a diagnosis of metastatic or recurrent adenocarcinoma of the stomach or gastroesophageal junction expressing Guanylyl Cyclase C (GCC) were enrolled in 1 treatment group, MLN0264 1.8 mg/kg, 30-minute IV infusion, Day 1 of each 21-day cycle.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Response-Evaluable population included all participants with measurable disease who received at least 1 dose of MLN0264 and had at least 1 post-baseline response assessment.

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: Safety population included all participants who received any amount of MLN0264.

6. Primary Endpoint

The registry lists the primary outcome as Overall Response Rate (ORR) Based on Response Evaluation Criteria in Solid Tumors (RECIST), measured over Day 21, every other cycle, starting with Cycle 2 until disease progression, death or study closure (up to 17 months).

Overall response rate is the percentage of participants in the response-evaluable population whose investigator-assessed response was complete or partial, according to RECIST version 1.1. A complete response requires disappearance of target and non-target lesions, no new lesions, and normalization of the tumor marker level. A partial response requires at least a 30% decrease in the sum of the diameters of target lesions, with no progression in non-target lesions and no new lesions.

This endpoint is used to describe the proportion of assessed participants who meet predefined tumor-response criteria. The criteria make the response classification explicit, while the percentage expresses the result relative to the defined analysis population. It is a binary outcome at the participant level: each participant either meets the complete-or-partial-response definition or does not.

The endpoint is not a measure of how long a response lasts, overall survival, or progression-free survival. Those are listed separately among the outcomes. Nor does a response percentage from a single-group study by itself estimate a comparative treatment effect against a control group.

The registry record specifies the endpoint, its criteria, population and assessment timing, but does not report the numerical response result. A response percentage, its denominator, and an uncertainty interval therefore cannot be described from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The study is recorded as single-group and unmasked, with no allocation to a comparator. This describes the structure of the investigation, not the statistical method used to analyze its outcomes. The registry record does not report a statistical analysis plan, model specification, or inferential procedure for the primary endpoint.

What does a percentage endpoint represent?

For an endpoint such as overall response rate, each participant in the analysis population is classified according to whether the response definition was met. The percentage expresses the share classified as having a complete or partial response. The denominator matters: changing which participants are included can change the estimated percentage even when the response classifications among assessed participants remain the same.

The registry definition makes the response-evaluable population conditional on measurable disease, receiving at least 1 dose, and having at least 1 post-baseline response assessment. In general, that kind of definition clarifies who contributes to the endpoint, but it also makes accounting for participants who do not meet the criteria important. The registry record does not report the size of this population, the response count, or how missing assessments were addressed.

Why is an uncertainty interval useful?

For a percentage estimated from a finite group, an interval communicates statistical uncertainty around the estimate. A narrow interval generally indicates greater precision than a wide interval, under the method used. Different methods can behave differently, particularly when the denominator or number of events is small. This is a general statistical point; the registry record does not report an interval or state which interval method would be used.

A p-value, when reported, addresses compatibility between data and a specified null model under assumptions. It is not the probability that a treatment works, nor does it describe the size or clinical importance of an effect. No primary-endpoint p-value or inferential analysis is listed in the registry record. In a single-group study, interpretation would also depend on what benchmark, if any, was chosen for a formal comparison; such a benchmark is not reported.

How does the design affect analysis?

Random allocation in a comparative study can support a fair comparison by balancing measured and unmeasured prognostic factors on average. This study has no randomized comparator group, so it cannot estimate a randomized between-group contrast. Its response percentage would be a description of outcomes in the response-evaluable participants, not a direct estimate of the difference between MLN0264 and another intervention.

Unmasking means investigators were not blinded according to the registry record. Response criteria are defined in advance in the record, which supports a consistent classification framework, but the record does not describe independent review, adjudication, or any safeguards intended to limit assessment bias. Those details are not reported in the registry record and should not be presumed.

What do the planning assumptions mean?

The record describes a sample-size planning illustration based on the observed effect, using 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. Such an illustration is a hypothetical planning exercise, not a report of what the trial was designed to enroll and not observed power. The recorded study itself is single-group, so the equal-allocation, two-arm assumption is not a description of its treatment allocation. Numerical planning estimates and the observed primary effect are not reported in the registry record available for this analysis.

In general, power calculations depend on assumptions about the effect, variability or event rate, significance level, allocation and analysis method. If those inputs differ from what is later observed, the planning result does not guarantee a particular precision or probability of statistical significance. A retrospective calculation based on an observed effect would likewise not replace an interval around the estimate or establish the reliability of the effect.

Why do missing data and follow-up matter?

Response assessments were scheduled from Cycle 2 and continued until disease progression, death or study closure, for up to 17 months. Participants may differ in how much assessment information is available when follow-up ends at different times. General statistical methods address incomplete observations through explicit assumptions or sensitivity analyses; the registry record does not identify such methods. The timing schedule alone does not tell readers how incomplete or unevaluable responses were treated.

Other listed outcomes involve time-to-event concepts, such as progression-free survival and overall survival. In general, those analyses must account for varying follow-up and participants who have not experienced the event by the end of observation. However, no analysis methods or numerical results for those outcomes are reported in the registry record. These general concepts explain what would be relevant to interpret such outcomes, not what was done in this study.

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("MLN0264 1.8 mg/kg (GCC Low)", "MLN0264 1.8 mg/kg (GCC Intermediate)", "MLN0264 1.8 mg/kg (GCC High)")
n      <- c(9, 14, 13)
events <- c(0, 2, 0)
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  MLN0264 1.8 mg/kg (GCC Low)  9  0  0.0  0.0  33.6  -0.0  29.9  0.3  30.8
ARM  MLN0264 1.8 mg/kg (GCC Intermediate)  14  2  14.3  1.8  42.8  4.0  39.9  4.3  40.5
ARM  MLN0264 1.8 mg/kg (GCC High)  13  0  0.0  0.0  24.7  0.0  22.8  0.2  23.2

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 15 outcome measures, including the primary overall response rate and several secondary outcomes. Examining multiple outcomes can raise a multiplicity issue: when many hypotheses are tested, the chance of at least one apparently notable result can increase. Statistical approaches may control that risk through prespecified testing sequences or adjusted thresholds, or may treat analyses as exploratory. The record does not report a multiplicity strategy, testing hierarchy, or statistical analysis plan. No particular approach should be inferred.

No analyses are listed in the registry record, and a numerical result for the primary endpoint is not reported. The record therefore does not provide p-values or estimates with which to evaluate whether multiplicity adjustments were applied. The listed outcomes should be understood as planned measures, not as evidence that each was analyzed or that a particular finding was obtained.

Missing-data handling is also not reported. The primary endpoint’s response-evaluable definition requires measurable disease, at least 1 dose, and at least 1 post-baseline response assessment. The registry record does not report the number of participants meeting those conditions, the number lacking assessments, or the treatment of participants whose response could not be evaluated. Those details matter because the analyzed population and assumptions about missing outcomes affect interpretation.

The record identifies 38 participants enrolled, but does not report an outcome-analysis population count or a numerical response denominator. It also does not describe whether any sensitivity analyses were planned to assess the influence of missing data or alternative population definitions. Consequently, the extent to which the response analysis might depend on exclusions or incomplete follow-up cannot be determined from the registry 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: diarrhoea (2.6%), dysphagia (2.6%), upper gastrointestinal hemorrhage (2.6%), gastric cancer (2.6%), tumour hemorrhage (2.6%).

For the MLN0264 1.8 mg/kg group, 38 participants were listed as at risk for serious adverse events, and 7 were listed as affected. For other adverse events, 38 were listed as at risk and 37 as affected. These counts describe participants recorded with events; they do not indicate how many separate events occurred.

The serious adverse event terms listed include diarrhoea, dysphagia, upper gastrointestinal hemorrhage, gastric cancer, tumour hemorrhage and anaemia, each reported as 2.6%. These terms may overlap within participants, so their percentages should not be added to obtain a total. The registry record does not provide the event-level detail needed to describe timing, duration, severity beyond the serious-event classification, or attribution for each term.

The number of deaths is not reported in the registry record. That absence should not be read as zero deaths. More broadly, the posted safety counts describe events recorded in this group; with no comparator group, they do not estimate a comparative safety difference.

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

The registry record establishes that a Phase 2, single-group study evaluated MLN0264 in previously treated participants with metastatic or recurrent GCC-expressing adenocarcinoma of the stomach or gastroesophageal junction. It defines investigator-assessed overall response under RECIST version 1.1 and describes the response-evaluable population and assessment schedule. These details make the intended primary question identifiable.

However, a numerical primary result is not reported in the registry record. There is no response percentage, response count, denominator for the primary analysis, or uncertainty interval to interpret. Accordingly, the posted record does not quantify the frequency of complete or partial responses or the precision of any response estimate.

Even if a response result were available, a single-group design would describe outcomes among participants treated in the study rather than establish a causal comparison with another treatment. No control group was recorded, and no randomized treatment contrast can be derived from this design. An observed outcome could reflect the intervention, characteristics of the enrolled population, disease course, assessment practices, or other factors; the study design does not separate these explanations through randomization.

The study also lists safety and other clinical outcomes, but listing an outcome does not establish its result. The serious adverse event counts and terms can be described as recorded, while the absence of a reported death count or other result must remain explicit. The termination status is recorded, but its reason is not reported.

Thus, the record is informative about study structure, eligibility for the response analysis, the endpoint definition, and some safety counts. It does not, on its own, provide the numerical evidence needed to characterize the primary response result or make a comparative effectiveness claim.

14. Why This Trial Matters Statistically

This study illustrates why statistical interpretation begins with the design and the population behind an endpoint. Overall response rate is not just a percentage detached from its denominator: here, the response-evaluable population is defined by measurable disease, treatment exposure, and a post-baseline assessment. Readers need both the result and the number of participants contributing to it to judge what the estimate describes.

The single-group design also makes the distinction between describing an outcome and estimating a treatment contrast especially important. A response percentage in one group can summarize observed outcomes, but a comparison with a concurrent randomized group would address a different question. Without that comparator, the registry record cannot support a randomized estimate of the difference between MLN0264 and another treatment.

The registry record demonstrates another practical limitation: a clearly specified endpoint is not a substitute for a posted result. It provides RECIST-based definitions and assessment timing, but does not report the numerical primary outcome. Statistical transparency requires both the planned measure and sufficient results to assess its magnitude and precision.

Finally, a terminated status should be read as a record status, not as an explanation. Without a reported reason, the status cannot be used to infer a safety concern, an efficacy finding, or an operational cause. Keeping those distinctions clear prevents study design details, endpoint definitions, and incomplete outcome reporting from being mistaken for evidence of a treatment effect.

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 registry record does not report a numerical overall response rate, response count, response denominator, or confidence interval. The listed endpoint and its definition are not enough to assess the size or precision of the result.

The design has no concurrent comparator and is not randomized. It therefore cannot provide a randomized comparison with another treatment. The study is also recorded as unmasked; the registry record does not report whether response assessments received independent review or other checks on assessment decisions.

The response analysis applies to a specifically defined response-evaluable population, but the number meeting that definition and the handling of participants without post-baseline assessment are not reported. Missing-data methods and sensitivity analyses are also not reported, leaving uncertainty about how incomplete assessments might affect the result.

The registry lists termination but does not report its reason. The arm description includes an incomplete sentence about treatment adjustments, so the full conditions governing dose reduction, delay or discontinuation are not available in the record. The record also lists secondary outcomes without numerical results in the registry entries. These limitations restrict interpretation of both the primary endpoint and the broader clinical outcome profile.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study of MLN0264 in Participants With Cancer of the Stomach or Gastroesophageal Junction — NCT02202759.
• Registry record last updated 2017-05-15; status last verified 2017-04.
• Results first posted 2017-05-15.
• 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

NCT02202759 is recorded as a Phase 2, single-group, unmasked study of MLN0264 in previously treated participants with metastatic or recurrent GCC-expressing adenocarcinoma of the stomach or gastroesophageal junction. Enrollment was 38. The study started on 2014-08-04, had primary completion on 2016-01-15, and is listed as terminated.

The primary endpoint was investigator-assessed overall response rate by RECIST version 1.1 in a response-evaluable population. The registry record specifies the response criteria and assessment schedule but does not report a numerical primary result or analysis method. It lists 15 outcome measures and no analyses. The reason for termination and the handling of missing response assessments are not reported in the registry record.