Study of Romiplostim for Chemotherapy Induced Thrombocytopenia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Romiplostim for Chemotherapy Induced Thrombocytopenia (NCT02052882), a na phase 2 study. The primary outcome is Percentage of Participants Who Achieved Platelet Counts of ≥ 100,000/mcL.

2. Clinical Question

The broader study summary also asks whether romiplostim would allow patients to receive at least 2 further cycles of chemotherapy without thrombocytopenia. That question is part of the stated study rationale, but it is not the named primary endpoint. The registry record does not report a result for that question. The record lists “Number of Participants Evaluated for Toxicity” as a secondary outcome, but it does not provide a toxicity-evaluation result. Thus, the registry describes the intended clinical questions and intervention, but leaves the outcome findings unavailable for interpretation.

3. Trial Design

This is an open-label Phase II study of romiplostim for isolated chemotherapy-induced thrombocytopenia. Its design is classified as single-group. Allocation is listed as NA, and masking is listed as none. These features mean the registry record does not describe randomized assignment or a blinded comparison. The listed enrollment is 60.

The intervention was weekly subcutaneous romiplostim. The arm description specifies a starting dose of 2 mcg/kg and weekly titration according to CBC and platelet counts, with a target platelet count of 150,000-200,000/mcL. It also states that treatment could be held up to 16 days if a participant developed an intercurrent medical illness. These are treatment-description details; the registry record does not report how often doses were changed or held, or how many participants followed each aspect of the dosing approach.

The registry record gives a study start date of 2014-01-30 and a primary completion date of 2023-11-13, and lists the study status as completed. These dates describe the record’s study timeline; they do not provide the timing of individual participant follow-up or outcome assessment beyond the stated primary endpoint timeframe.

The summary frames the research question partly as romiplostim compared with waiting for platelet recovery. However, the recorded design has one group and no like-for-like control arm. Consequently, the study design can describe outcomes among participants treated with romiplostim, but it does not provide a concurrent untreated comparison. Any contrast with spontaneous recovery would require evidence beyond a single-group outcome count. The registry record does not report a protocol, detailed statistical analysis plan, sample-size justification, interim analyses, or analysis populations.

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

Reasons for not completing this period:

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 Percentage of Participants Who Achieved Platelet Counts of ≥ 100,000/mcL, measured over within 3 weeks after treatment.

The primary endpoint is the percentage of participants who achieved platelet counts of at least 100,000/mcL within 3 weeks after treatment. It converts an individual platelet-count threshold and a defined follow-up window into a proportion of participants meeting the response criterion. The endpoint description says that the primary therapeutic response is assessed by platelet count within that period.

A threshold-based endpoint can make a clinical question easier to communicate: it identifies whether participants crossed a stated platelet-count level within the specified timeframe. It does not, by itself, describe the full distribution of platelet counts, how quickly any change occurred, or how long a response lasted. Those questions require additional outcome definitions and results.

As a general statistical point, a percentage is most informative when its numerator and denominator are clear. For this endpoint, the registry record does not report the number of participants meeting the threshold, the percentage, or the analysis population used to calculate it. The enrollment of 60 is not necessarily the denominator for an endpoint result, because the number assessed and the handling of missing measurements are not reported. The primary endpoint result is therefore not available for estimating the response rate or its precision.

The study summary also mentions the possibility of receiving further chemotherapy cycles without thrombocytopenia. That is a distinct question from achieving the platelet-count threshold within 3 weeks, and the registry record does not report a result for it.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a single-group design estimate?

The recorded design is single-group, open-label, and has no masking. In general, a single-group study can describe outcomes among participants who receive the intervention. It does not directly estimate a between-group contrast because there is no concurrent control group in the registry design. Platelet counts can change over time for reasons other than the intervention; without a control group, the observed course cannot separate those influences from changes associated with treatment.

The study summary names waiting for platelet recovery as a conceptual alternative. That does not make waiting a study comparator: the registry lists one group, Romiplostim. A comparison with an external or historical expectation would need a defined source, comparable participants, and an analysis plan. Such a comparator or analysis is not reported in the registry record.

What does the endpoint measure?

The primary outcome is a participant-level threshold response: whether platelet count reached at least 100,000/mcL within 3 weeks after treatment. The registry describes the result as a percentage of participants. In general, this type of endpoint turns a continuous measurement into a yes-or-no classification using a specified threshold and time window. That can give the outcome a direct interpretation, but it also means the percentage does not show how far above or below the threshold individual counts were.

To estimate that percentage, an analysis needs a numerator—the participants meeting the criterion—and a denominator—the participants included in the endpoint analysis. It also needs a rule for participants without a measurement in the time window. The registry record reports none of these endpoint counts or rules. The listed enrollment of 60 is not a substitute for the endpoint denominator.

How should uncertainty be understood?

General statistical explanation: an estimate from a sample is subject to sampling variability. A confidence interval represents uncertainty around an estimate under the assumptions of its statistical method. A narrow interval usually indicates greater precision than a wide interval, but precision does not establish causality or remove design limitations. Intervals also depend on the sample and analysis population actually used.

No primary endpoint estimate, confidence interval, or analysis is reported in the registry record. Consequently, the response level and its precision cannot be assessed. No numerical uncertainty measure should be inferred from the enrollment figure alone.

What role do planning calculations play?

General statistical explanation: sample-size planning asks how many observations a future study may need to detect an effect under selected assumptions. The registry’s planning description refers to a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect defined as a stated fraction of an observed effect. It also distinguishes totals of events for time-to-event calculations from participants per arm for other calculations.

Those are planning assumptions, not a description of the completed study’s single-group design. A planning illustration is not observed power and does not show whether a result is clinically important. The numerical planning outputs, the observed effect used as an input, and a sample-size justification for the actual study are not reported in the registry record. The description therefore cannot be used to infer that the study had a particular power or that it met a planned target.

What is the role of analysis choices?

General statistical explanation: analysis choices determine which participants count in an estimate, how repeated or missing measurements are handled, and what uncertainty method is used. For a threshold endpoint, the timing rule and the treatment of participants without an in-window platelet count can change the denominator and the resulting percentage. Prespecifying these decisions helps readers distinguish an intended analysis from decisions made after outcome data are available.

The registry record does not report the statistical analysis plan, the analysis population, or missing-data methods. It lists 0 analyses. There is therefore no basis in this record to describe an adjusted model, a confidence-interval method, or a strategy for departures from the planned assessment window. The result itself is also not reported, so recalculation from posted summary statistics is not possible. No recalculated estimate is available to compare with a sponsor analysis.

Why does the design matter alongside the analysis?

Statistical methods can quantify uncertainty in the observed data, but they cannot create a randomized comparison where none was recorded. In general, a model or interval around a single-group response can describe the treated group under its assumptions; it cannot, by itself, establish what would have happened to the same participants without treatment. The registry record’s open-label, single-group classification is therefore central when interpreting any future-reported response estimate.

The absence of a reported analysis does not mean that no analysis occurred outside the registry. It means that the registry record does not provide an analysis for readers to evaluate. The record also does not report interim analyses, endpoint-specific missingness, or multiplicity procedures. These are important reporting details because they explain how the reported results were selected and how robust their interpretation may be.

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("Romiplostim")
n      <- c(60)
events <- c(56)
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  Romiplostim  60  56  93.3  83.8  98.2  84.1  97.4  84.1  97.3

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 2 outcome measures: the primary platelet-count response and the secondary outcome “Number of Participants Evaluated for Toxicity.” It does not report results for either outcome. It also lists 0 analyses. Thus, there is no reported set of outcome estimates from which to assess whether the primary endpoint was analyzed as planned or whether secondary findings were considered supportive or exploratory.

Multiplicity concerns arise when several outcomes, time points, or statistical tests are examined. In general, conducting multiple tests can increase the chance of a nominally noteworthy result unless the analysis plan addresses that issue. The registry record does not report a multiplicity strategy, a hierarchy among outcomes beyond identifying the primary endpoint, or interim analyses. It is not possible to infer that a particular adjustment was or was not performed outside the registry record.

The record does not describe missing-data methods or the primary endpoint analysis population. It does not give the number of participants with platelet measurements during the endpoint window, the number excluded from analysis, or reasons for missing assessments. Without those details, an endpoint denominator and the potential influence of missing observations cannot be assessed. Enrollment of 60 alone does not establish how many participants contributed to the primary endpoint.

General statistical context: missingness can matter when the likelihood of an unavailable measurement is related to a participant’s condition, treatment, or outcome. Different assumptions about unavailable measurements can lead to different estimates. The registry record does not specify assumptions or sensitivity analyses. It also does not report whether all enrolled participants were included in an analysis population. These omissions limit reproducibility and make it difficult to judge how representative a reported estimate would be, if one were available.

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 non-serious adverse event terms

The registry lists 60 participants at risk and 0 affected in the serious adverse-event category for the Romiplostim group. It lists 60 at risk and 6 affected in the other adverse-event category. The record also lists 53 deaths. These entries should be read as separate registry counts rather than as a complete account of individual clinical courses.

The serious adverse-event figure is a reported count, not proof that no serious event occurred outside the record’s reporting scope or period. No serious adverse-event terms are listed. The other adverse-event category is not described in enough detail to identify event types, timing, severity, or attribution. The registry record does not report whether deaths were related to treatment, occurred during follow-up, or had particular causes. The death count alone does not establish treatment causation.

General statistical context: safety counts are easier to interpret when the observation period, definitions, completeness of reporting, and relationship to treatment are clear. Those details are not reported in the registry record. The listed at-risk counts do not supply that missing context, and the safety entries should not be treated as comparative estimates because the study has no recorded control group.

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

The study is a completed, open-label, single-group Phase II investigation of weekly romiplostim in patients with isolated chemotherapy-induced thrombocytopenia. Its primary endpoint is clearly defined as the percentage of participants reaching at least 100,000/mcL within 3 weeks after treatment. The record also describes a dose-titration approach and lists safety counts.

However, the registry record does not report the primary endpoint result. It therefore does not show what percentage reached the threshold, how many participants were assessed, or how precise an estimate might be. The listed enrollment of 60 cannot answer those questions. Nor does the record report whether participants received at least 2 further chemotherapy cycles without thrombocytopenia, a question stated in the study summary.

The design does not include a concurrent comparator. General interpretation: a treated-group outcome can describe what happened among those participants, but a single-group study cannot directly distinguish an intervention-associated change from the natural course or other influences. The summary’s mention of waiting for platelet recovery does not constitute an observed control group in the registered design.

The safety entries report 0 affected participants in the serious adverse-event category, 6 in the other adverse-event category, and 53 deaths, with 60 participants listed at risk in each adverse-event category. The record does not provide the event terms, timing, causes, or treatment relationship needed to interpret those counts fully.

Accordingly, the registry record describes a clinical question and study design but does not support a conclusion about the size or precision of the primary endpoint response, a comparative treatment effect, or the cause of reported deaths. These are limits of what the record reports, rather than findings about the results of analyses that are not included.

14. Why This Trial Matters Statistically

This trial illustrates why endpoint definition and result reporting need to be read together. The primary endpoint specifies a platelet-count threshold and a follow-up window, making the intended response criterion understandable. But without the number meeting the criterion, the analysis denominator, or an uncertainty estimate, the response cannot be quantified or judged for precision.

The design classification is equally important. The study is single-group and open-label, with no recorded comparator. The study summary’s question about improvement compared with waiting captures a clinical motivation, but the registered design does not make that comparative estimate. This distinction helps prevent a treated-group observation from being mistaken for evidence of a between-group effect.

General statistical context: an endpoint estimate and its uncertainty address different questions. The estimate describes the observed response in the analyzed participants; an interval communicates uncertainty under a specified method. Neither alone resolves confounding or replaces a control group. Here, the registry record reports neither the endpoint estimate nor an interval, so both magnitude and precision remain unavailable.

The record also highlights the value of transparent analysis details. Reporting the analysis population, missing-data handling, outcome definitions, and multiplicity approach would let readers assess how the endpoint was constructed and whether alternative assumptions might change its interpretation. Those details are not reported in the registry record. The completed status and enrollment count do not substitute for outcome reporting.

Finally, safety data require context as well as counts. The listed adverse-event and death figures are potentially important, but the record does not include terms for serious events or explain timing and treatment relationship. Statistical interpretation therefore depends not only on numerical summaries but also on clear definitions and reporting of how observations were collected.

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 efficacy from the registry record is that the primary endpoint result is not reported. The record gives the endpoint definition and timeframe but no response percentage, numerator, denominator, or confidence interval. It also does not state how many participants had an evaluable platelet measurement within 3 weeks after treatment.

The single-group design limits comparative interpretation. There is no concurrent control group in the registry record, despite the study summary’s reference to waiting for platelet recovery. The record therefore cannot provide a direct comparison between romiplostim and a waiting-only group.

The registry does not report the primary analysis population, missing-data handling, detailed statistical analysis plan, sample-size justification, interim analyses, or multiplicity procedures. The listed enrollment of 60 does not resolve these gaps. The planning description gives general assumptions, but its numerical outputs and the observed effect used for planning are not reported in the registry record.

The safety information is also limited. The record lists 0 serious adverse events among 60 at risk, 6 participants with other adverse events among 60 at risk, and 53 deaths, but does not report serious-event terms. It does not explain the timing or causes of deaths or their relationship to treatment. The safety counts therefore lack the context needed for attribution or comparison.

The registry describes dose titration and a treatment-hold allowance, but does not report participant-level dosing, adherence, treatment duration, or the frequency of dose changes and holds. It also does not report results for the stated question about further chemotherapy cycles without thrombocytopenia. These missing details constrain interpretation of both treatment exposure and outcomes.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Study of Romiplostim for Chemotherapy Induced Thrombocytopenia — NCT02052882.
• Registry record last updated 2024-12-27; status last verified 2023-11.
• Results first posted 2024-12-27.
• 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 describes NCT02052882, “Study of Romiplostim for Chemotherapy Induced Thrombocytopenia,” an open-label Phase II, single-group study sponsored by Memorial Sloan Kettering Cancer Center. It lists an enrollment of 60, a start date of 2014-01-30, a primary completion date of 2023-11-13, and a completed status.

The intervention was weekly subcutaneous romiplostim, beginning at 2 mcg/kg with weekly titration toward a platelet count of 150,000-200,000/mcL. The primary endpoint was the percentage achieving platelet counts of at least 100,000/mcL within 3 weeks after treatment. The registry record does not report the primary endpoint result or an analysis of it.

The record lists 2 outcome measures and 0 analyses. Safety entries list 0 serious adverse events, 6 participants with other adverse events, and 53 deaths; the record does not report event terms or the causes and treatment relationship of deaths. There is no concurrent control group, and key analysis and missing-data details are not reported.