A Study of Lorlatinib in ALK Inhibitor-Treated ALK-Positive NSCLC in China: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of Lorlatinib in ALK Inhibitor-Treated ALK-Positive NSCLC in China (NCT03909971), a na phase 2 study. The primary outcome is Percentage of Participants With Objective Response (Cohort 1).

2. Clinical Question

3. Trial Design

This was a Phase 2, multicenter, open-label, dual-cohort study of lorlatinib monotherapy in China. The registry lists a parallel model, no masking, and allocation as not applicable. It describes the study as completed, with enrollment of 109. The recorded start date is 2019-04-28, and the primary completion date is 2020-08-10. These registry entries describe the study’s structure and status; they do not provide evidence of a comparative treatment effect.

The intervention was lorlatinib 100 mg orally once daily, continuously, given as four 25 mg tablets. The primary outcome was objective response in Cohort 1. Objective response was defined as a best overall confirmed complete or partial response under RECIST version 1.1, with disease progression assessed by independent central radiology. The specified primary assessment period began at Cycle 1 Day 1 and continued to documented progression, up to 67 weeks.

The registry also lists objective response in Cohort 2 as a secondary outcome. Other secondary outcomes include progression-free survival assessed by independent central review and by investigators, overall survival, intracranial objective response assessed by both methods, and duration of response assessed by both methods. These are distinct outcomes and assessment approaches; their inclusion does not establish that results were reported for them.

The design information does not describe a randomized comparator. The registry’s allocation entry is not applicable, and the study is open-label. Therefore, the record describes outcomes observed in the study cohorts rather than a randomized contrast between lorlatinib and a control treatment. Details about the criteria separating the cohorts and the rationale for their structure are not reported in the registry record.

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: The study enrolled 109 participants, with 67 in Cohort 1 and 42 in Cohort 2.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The analysis population included all enrolled participants who received at least 1 dose of lorlatinib.

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 With Objective Response (Cohort 1), measured over From Cycle 1 Day 1 to documented progression of disease by ICR (up to 67 weeks).

The primary endpoint is the percentage of Cohort 1 participants with an objective response. A participant counted as having an objective response if the best overall confirmed response was complete response or partial response under RECIST version 1.1. Complete response was defined as disappearance of target and non-target lesions, with pathological lymph nodes reduced to less than 10 mm in short axis. Partial response required at least a 30% decrease in the sum of the longest dimensions of target lesions relative to the baseline sum.

Objective response is a binary outcome at the participant level: each person either meets the stated response definition or does not. Reporting the percentage expresses how often the defined response occurred in the analysis population. The registry specifies a 95% confidence interval as the measure of uncertainty around the endpoint. A confidence interval, in general, describes a range of values compatible with the data under the statistical method used; it does not guarantee that the true value lies within that particular interval.

The endpoint is assessed by independent central radiology, which provides a review approach distinct from investigator assessment. The registry specifies the assessment window as starting at Cycle 1 Day 1 and ending at documented progression by independent central review, up to 67 weeks. The primary percentage and confidence interval are not reported in the registry record. As a result, the definition and assessment method are available, but the numerical endpoint result and its precision cannot be interpreted from this record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry defines the primary endpoint as a percentage and specifies a 95% confidence interval. The primary response result itself is not reported in the registry record, so there is no estimate or interval to interpret. The general statistical concepts below explain how this type of endpoint and uncertainty measure are ordinarily read; they do not add unreported results or establish which computational details were used in this study.

What does a percentage endpoint represent?

For a binary outcome, each participant is classified according to whether the defined event occurred. In this study, the event was a best overall confirmed complete or partial response under RECIST version 1.1. The percentage describes the share of participants in the analysis population who meet that definition. It is not a measure of how much an individual participant’s disease changed, and it does not on its own compare outcomes with another treatment.

The response definition matters because classification depends on prespecified criteria. Complete response required disappearance of target and non-target lesions, with pathological lymph nodes reduced to less than 10 mm in short axis. Partial response required at least a 30% decrease in the sum of the longest dimensions of target lesions relative to the baseline sum. Confirmation is part of the registry’s definition of the best overall response. A percentage calculated using a different response definition, assessment schedule, or analysis population could answer a different question.

How should the confidence interval be understood?

In general, a confidence interval conveys statistical uncertainty about an estimated quantity. A narrower interval indicates greater precision under the method used, while a wider interval indicates less precision. The interval does not describe the range of outcomes for individual participants, and it does not show that all values within it are equally plausible. Its interpretation depends on the analysis method and the assumptions underlying that method.

The registry specifies a 95% confidence interval for the primary percentage but does not report its endpoints. It also does not report the statistical procedure used to construct that interval. Therefore, readers cannot assess its width, whether it includes particular response percentages, or how the estimate’s precision relates to the study population. No new interval or estimate can be reconstructed from the information recorded about the endpoint because the primary response count is absent.

Why does the assessment method matter?

The primary response assessment used independent central radiology. The registry also lists investigator assessments for some secondary outcomes. In general, central review can help apply a consistent assessment process across cases, while investigator assessment reflects the treating study team’s evaluations. These are different measurement approaches, not interchangeable labels. The record does not report the agreement between assessors, the handling of disagreements, or any analysis comparing their results.

The endpoint timeframe runs from Cycle 1 Day 1 to documented progression by independent central review, up to 67 weeks. A defined timeframe helps specify which observations contribute to an endpoint. It does not by itself explain the timing of every assessment, what happened when an assessment was unavailable, or how observations after treatment discontinuation were handled. Those operational details are not reported in the registry record.

What does the study structure allow readers to assess?

The study is described as Phase 2, multicenter, open-label, and dual-cohort, with a parallel model and allocation listed as not applicable. General statistical interpretation distinguishes an estimate within a cohort from a treatment contrast between randomized groups. A cohort-level percentage can describe the observed frequency of an outcome in that cohort, but a causal comparison requires an appropriate comparator and methods that address differences between groups. This record does not describe a randomized control group or a like-for-like control comparison.

Open-label means masking was absent according to the registry. In general, knowledge of treatment assignment can influence some assessments or study processes, although independent central assessment may provide a separate review for specified outcomes. The registry does not report procedures that would quantify or eliminate any influence of open-label conduct. The design details should therefore be considered alongside the endpoint’s assessment method rather than treated as proof that assessments were biased or unbiased.

What can planning calculations say?

The record describes sample-size calculations as planning illustrations based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It states that the effect to detect is a stated fraction of the observed effect. These calculations are planning illustrations, not observed power and not results from a randomized comparison in this study. The numerical planning outputs are not reported in the registry record for this account, and no additional sample-size calculation can be inferred.

In general, a planning calculation asks how many participants might be needed under specified assumptions to detect a target effect with a chosen statistical operating characteristic. It is not a measure of the probability that the study’s finding is correct, nor does it establish that the actual design had those assumptions. The registry does not report the trial’s own sample-size justification, so the planning illustration should not be represented as the study’s design rationale.

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("Cohort 1")
n      <- c(67)
events <- c(47)
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  Cohort 1  67  47  70.1  57.7  80.7  58.3  79.8  58.3  79.8

11. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary objective-response outcome for Cohort 1 and a secondary objective-response outcome for Cohort 2. It also lists progression-free survival, overall survival, intracranial objective response, and duration of response, with some outcomes assessed by independent central review and others by investigators. The record lists 28 outcome measures. With multiple outcomes and assessment approaches, readers should distinguish the prespecified primary question from secondary analyses rather than treating every endpoint as an equivalent confirmatory test.

In general, testing several hypotheses can increase the chance that at least one result appears statistically notable by chance. Statistical plans may address this through a prespecified testing sequence or other multiplicity procedures. Whether any such approach was used, and whether the analyses were intended to be confirmatory or exploratory, are not reported in the registry record. The record also does not report an analysis plan that would clarify how the different outcomes were prioritized.

The primary analysis population included enrolled participants who received at least one dose of lorlatinib. This definition is reported, but the record does not describe the handling of missing response assessments, participants who discontinued, or other missing endpoint information. It does not report imputation methods, sensitivity analyses, or the number of participants with evaluable primary endpoint data. General statistical interpretation treats missing outcomes as important because the estimated percentage can depend on how missing observations are handled.

The registry does not report a statistical plan for subgroup analyses, covariate adjustment, interim analyses, or missing-data sensitivity analyses. These details should not be inferred from the Phase 2 designation, the endpoint list, or the sample-size planning illustration. In the absence of the primary outcome estimate and analysis details, the record supports interpretation of the stated endpoint definition and population, but not a fuller assessment of multiplicity control or the robustness of the numerical 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: pneumonia (11.9%), pyrexia (4.8%), respiratory failure (4.8%), hyperglycaemia (3.0%), cerebral infarction (3.0%).

The registry reports serious adverse event counts by cohort: Cohort 1 lists 23 affected among 67 at risk, and Cohort 2 lists 16 affected among 42 at risk. These are counts in the registry record; they do not establish that an event was caused by lorlatinib. The record also lists 28 deaths for Cohort 1 and 26 for Cohort 2, but does not provide details about attribution or the circumstances of those deaths.

The listed serious adverse event terms with percentages are pneumonia, 11.9%; pyrexia, 4.8%; respiratory failure, 4.8%; hyperglycaemia, 3.0%; cerebral infarction, 3.0%; and pneumonitis, 3.0%. The record does not specify cohort attribution for these listed percentages in the information available for this account. These figures should therefore be read as registry-reported safety summaries, not as evidence that a particular event was treatment-related or as a comparison with another treatment.

In general, adverse event counts describe events recorded under a study’s reporting procedures; causal attribution requires separate assessment. The registry entry does not provide event timing, severity grading, relatedness assessments, exposure-adjusted rates, or detailed participant-level information. The safety figures are informative about what the registry reports, but they do not support a complete assessment of safety or a causal comparison.

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

The study asks a defined question: what percentage of Cohort 1 had a confirmed complete or partial response under RECIST version 1.1, assessed by independent central radiology? The registry describes the population, response criteria, and assessment window. It does not report the primary percentage or confidence interval. That absence means the numerical answer and its precision cannot be determined from the registry record.

The registry also identifies lorlatinib as the intervention and gives the schedule as 100 mg orally once daily, continuously. These treatment details describe what was studied; they do not establish that treatment caused any observed outcome. The record describes an open-label, dual-cohort Phase 2 study, not a randomized comparison with a control treatment. It therefore does not provide a basis for estimating a comparative treatment effect from the information recorded.

Objective response is a defined outcome, not a complete summary of all aspects of cancer outcomes. The registry separately lists progression-free survival, overall survival, intracranial response, and duration of response as secondary outcomes. Numerical results for these outcomes are not reported in the registry record. The existence of an outcome listing should not be mistaken for a reported finding.

The safety summaries record serious adverse events and deaths by cohort, along with selected serious event terms and percentages. They do not, on their own, establish causation or provide a comparison against another treatment. The available record also lacks details needed to interpret missing assessments, multiplicity handling, and other aspects of analysis.

Overall, the record supports a description of the study design, primary endpoint definition, analysis population, and selected safety counts. It does not support a conclusion about the size or precision of the primary response result, comparative efficacy, or causal safety effects. Those limits reflect what is not reported in the registry record, rather than a claim about findings that may have been reported elsewhere.

14. Why This Trial Matters Statistically

This trial is statistically notable for the way its primary question is defined alongside a nonrandomized, open-label, dual-cohort structure. Its primary endpoint is a participant-level binary response outcome, with a clear RECIST-based definition and independent central radiology assessment. Those details make the target quantity understandable: the frequency of confirmed complete or partial response in the specified Cohort 1 analysis population.

The distinction between defining an endpoint and reporting its result is central to interpreting clinical trial records. Here, the registry provides the endpoint definition, the analysis population rule, and the confidence-interval type, but not the response percentage or interval. Without those numerical results, statistical precision and the observed response frequency cannot be evaluated. A carefully described endpoint is not a substitute for its estimate.

The dual-cohort design also illustrates why comparisons require attention to allocation and comparator structure. The record lists allocation as not applicable and does not describe a randomized control comparison. Cohort 2 has its own secondary response outcome, but the registry does not establish that the cohorts are comparable or intended to serve as controls for each other. Descriptive cohort outcomes and randomized treatment contrasts answer different statistical questions.

Finally, the multiple outcome listings and distinct assessment methods make analysis transparency relevant. The record names a range of secondary outcomes, but does not report the multiplicity strategy or important missing-data procedures. These omissions limit evaluation of how endpoint findings were prioritized and how robust they may be. The trial therefore provides an example of how registry design details can clarify the intended question while incomplete numerical results and analysis methods constrain 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.

The primary limitation for statistical interpretation is that the Cohort 1 objective-response percentage and its 95% confidence interval are not reported in the registry record. The record defines the endpoint but does not provide the estimate needed to assess response frequency or precision. Numerical results for the listed secondary outcomes are also not reported in the registry record.

The study is open-label and has no randomized control comparison described. Cohort 2 is not identified as a control group, and the record does not explain how cohort membership was determined or what distinguishes the cohorts. Consequently, no like-for-like comparative effect can be inferred from the study structure described in the registry.

The registry specifies an analysis population consisting of enrolled participants who received at least one dose, but does not report the number contributing evaluable data for the primary endpoint or how missing assessments were handled. It also does not report missing-data sensitivity analyses, the statistical procedure for the confidence interval, or the details of endpoint assessment schedules beyond the stated timeframe.

The outcome listing includes 28 outcome measures, but the registry record does not report a multiplicity strategy, statistical analysis plan, interim analyses, or sample-size justification for the trial. The listed planning illustration assumptions do not establish the trial’s own design rationale. Safety information is also limited: serious event counts and selected terms are present, but attribution, timing, relatedness, and cohort attribution for the listed percentages are not specified in the record information.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study of Lorlatinib in ALK Inhibitor-Treated ALK-Positive NSCLC in China — NCT03909971.
• Registry record last updated 2025-11-05; status last verified 2025-10.
• Results first posted 2021-10-26.
• 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 describes NCT03909971 as a completed Phase 2, multicenter, open-label, dual-cohort study of lorlatinib monotherapy in China for ALK inhibitor-treated, locally advanced or metastatic ALK-positive non-small cell lung cancer. Enrollment was 109. The intervention schedule was 100 mg orally once daily, continuously, as four 25 mg tablets.

The primary outcome was the percentage of Cohort 1 participants with a confirmed complete or partial response under RECIST version 1.1, assessed by independent central radiology. The primary analysis population included enrolled participants who received at least one dose. The primary response percentage and 95% confidence interval are not reported in the registry record. Secondary outcomes include response in Cohort 2, survival, progression, intracranial response, and duration of response.

The study does not describe a randomized control comparison. The registry records serious adverse event counts by cohort and selected serious event terms, but does not provide enough information to infer causation. Key statistical details, including missing-data handling and multiplicity procedures, are not reported in the registry record.