This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Study Evaluating the Safety Of HKI-272 (Neratinib) In Subjects With Advanced Non-Small Cell Lung Cancer (NCT00266877), a non-randomized phase 2 study. The primary outcome is Objective Response Rate for Neratinib in Patients With Non-small Cell Lung Cancer.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00266877 |
| Phase | Phase 2 |
| Condition | Carcinoma, Non-Small-Cell Lung, Lung Neoplasms |
| Allocation | Non-Randomized |
| Design model | Single Group |
| Masking | None (open label) |
| Enrollment | 172 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Puma Biotechnology, Inc. |
| Results posted | Yes |
2. Clinical Question
Population
The study concerned subjects with advanced non-small cell lung cancer. The registry describes three groups based on previous treatment and patient characteristics: prior Tarceva or Iressa with an EGFR mutation, prior Tarceva or Iressa without an EGFR mutation, and no prior EGFR tyrosine kinase inhibitor treatment. The third group was described as having adenocarcinoma, a smoking history of no more than 20 pack-years, and current non-smoking status; an EGFR mutation was not required for that group. The primary endpoint population is called modified ITT in the record.
Intervention
Participants received HKI-272, also called neratinib in the endpoint descriptions. The registry record does not report a comparator treatment or a placebo group. Further details of dose and administration are not reported in the registry record.
Comparator
This was a nonrandomized, single-group study, not a randomized comparison between treatment arms. The three named groups represent different prior-treatment or eligibility characteristics, not like-for-like control groups. Any differences across those groups would not by themselves isolate a treatment effect.
Primary question
The primary endpoint was objective response rate assessed by independent radiologists using RECIST v1.0. It was intended to count complete and partial responses according to specified tumor-imaging criteria. The registry record gives the endpoint definition and a 90% confidence interval designation, but does not report the observed response result or its interval. Therefore the magnitude and precision of the response estimate cannot be described from the registry record.
3. Trial Design
The record describes a phase 2 study of HKI-272, or neratinib, in subjects with advanced non-small cell lung cancer. It lists a nonrandomized allocation, no masking, and a single-group model. The intervention is the drug HKI-272. The registry record lists enrollment as 172 and gives a study start of 2005-12, primary completion of 2009-01, and status as completed. These details describe the registered study; they do not provide an outcome estimate.
Three groups are described according to prior EGFR tyrosine kinase inhibitor treatment and tumor or smoking characteristics. Two groups had disease progression following at least 12 weeks of Tarceva or Iressa, with one group having an EGFR mutation demonstrated at screening and the other not having one. The third group had no prior EGFR tyrosine kinase inhibitor treatment and was characterized by adenocarcinoma, a smoking history of no more than 20 pack-years, and current non-smoking status. The record does not report random assignment among these groups. They should not be interpreted as randomized treatment arms or as a controlled comparison.
The registry record's description of the primary endpoint population uses the term modified ITT and says participants were randomized and had taken at least one dose of neratinib; it also calls this population equivalent to the safety population. That use of “randomized” is in tension with the record's nonrandomized allocation and single-group design. The reason for this inconsistency is not reported in the registry record. The exact number of participants included in the endpoint analysis is not reported in the registry record.
The registry lists clinical benefit rate, duration of response, and progression-free survival as secondary outcomes. Their numerical results and analysis details are not reported in the registry record. The sample-size rationale, recruitment targets for each group, treatment schedule, and any planned interim analyses are also 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.
Overall Study
| Stage | Prior Tarceva or Iressa With EGFR Mutation | Prior Tarceva or Iressa w/o EGFR Mutation | No Prior EGFR Tyrosine Kinase Inhibitor Treatment |
|---|---|---|---|
| STARTED | 91 | 48 | 28 |
| COMPLETED | 0 | 0 | 0 |
| NOT COMPLETED | 91 | 48 | 28 |
Reasons for not completing this period:
| Reason | Prior Tarceva or Iressa With EGFR Mutation | Prior Tarceva or Iressa w/o EGFR Mutation | No Prior EGFR Tyrosine Kinase Inhibitor Treatment |
|---|---|---|---|
| Death | 1 | 1 | 1 |
| Adverse Event | 6 | 4 | 1 |
| Physician Decision | 2 | 1 | 1 |
| Withdrawal by Subject | 3 | 1 | 1 |
| Disease Progression | 72 | 37 | 23 |
| Symptomatic Deterioration | 6 | 3 | 1 |
| Hospitalization | 1 | 0 | 0 |
| Concomitant Radiotherapy | 0 | 1 | 0 |
Analysis population for the primary outcome, as defined in the registry: modified ITT: Subjects who were randomized and who had taken at least 1 dose of neratinib; equivalent to the safety population
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.
| Characteristic | Unit | Prior Tarceva or Iressa With EGFR Mutation | Prior Tarceva or Iressa w/o EGFR Mutation | No Prior EGFR Tyrosine Kinase Inhibitor Treatment | Total |
|---|---|---|---|---|---|
| Participants analysed | 91 | 48 | 28 | 167 | |
| Age, Customized: < 60 years | Participants | 45 | 24 | 13 | 82 |
| Age, Customized: >= 60 years | Participants | 46 | 24 | 15 | 85 |
| Sex: Female, Male: Female | Participants | 74 | 26 | 18 | 118 |
| Sex: Female, Male: Male | Participants | 17 | 22 | 10 | 49 |
6. Primary Endpoint
The registry lists the primary outcome as Objective Response Rate for Neratinib in Patients With Non-small Cell Lung Cancer, measured over From first dose date to progression/death or last tumor assessment, up to three years..
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | 90% Confidence Interval |
| Unit | percentage of participants |
| Endpoint classification | Binary Endpoint |
The primary endpoint was objective response rate for neratinib in patients with non-small cell lung cancer. It was defined as a percentage of participants and assessed by independent radiologists using RECIST v1.0. The record describes complete response as disappearance of all target lesions. Partial response required at least a 30% decrease in the sum of the longest diameters of target lesions, with no progression in non-target lesions and no new lesions.
Objective response rate is used to describe the proportion of an assessed group meeting a prespecified tumor-response definition. An independent radiographic assessment can reduce reliance on a treating investigator's unblinded judgment, although the record does not describe the review procedures beyond identifying independent radiologists. Response is a tumor-imaging outcome; it does not, by itself, describe how long a response lasts, whether disease progression is delayed, or whether participants live longer. Duration of response and progression-free survival are listed separately as secondary outcomes.
The endpoint timeframe was from first dose to progression or death, or the last tumor assessment, up to three years. The registry specifies a 90% confidence interval for the endpoint, but does not report the response count, analyzed denominator, point estimate, or interval limits. Thus, the endpoint's definition is available, but its observed result and precision are not reported in the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The design information establishes that this was a phase 2, nonrandomized, single-group study with no masking. It does not establish how often participants had an objective response. Although the primary endpoint is defined and a confidence interval level is specified, no primary response estimate or confidence interval limits are reported in the registry record. A numerical assessment of the endpoint's magnitude or precision is therefore not possible from this record.
That distinction matters: an endpoint definition explains what would count as a response, while an outcome result reports how many participants met that definition and how uncertain the estimate is. The registry provides the first, but not the second. The same limitation applies to the listed secondary outcomes of clinical benefit rate, duration of response, and progression-free survival; their numerical results are not reported in the registry record.
The three groups differ in prior therapy and eligibility characteristics. They are not randomized control groups, so comparisons among them would be vulnerable to differences in prognosis, treatment history, and other characteristics. The study's single-group structure also means the record does not provide a concurrent comparator against which to interpret the response endpoint. This is a design limitation for causal comparison, not evidence for or against an effect.
The record gives serious adverse event counts for each named group and lists several serious event terms with percentages. Those figures provide information about reported safety events, but they do not replace the missing response result. The registry record does not give a complete account of all safety outcomes in the fields described, and serious adverse events are only one category of safety information.
The endpoint population description also contains an unresolved inconsistency: it refers to participants who were randomized, whereas the study design is listed as nonrandomized and single-group. The record says this population is equivalent to the safety population, but does not explain the wording or provide the endpoint denominator. This limits clarity about exactly which participants contributed to the primary endpoint.
Overall, the record allows a reader to understand the study's broad design, the response criteria, the endpoint timeframe, and selected safety figures. It does not report the primary response result, confidence interval values, or secondary outcome results. No conclusion about the observed response rate or its precision can be drawn from the registry record alone.
9. Statistical Methods Explained
What does a confidence interval convey?
In general, a confidence interval describes uncertainty around an estimated quantity under the statistical method used to construct it. For a response percentage, the interval would show a range of values compatible with the observed data and that method. A narrower interval indicates greater statistical precision than a wider interval, though precision is not the same as freedom from bias. The registry record specifies a 90% confidence interval for the primary endpoint but does not report its bounds or the response estimate. Its actual width and implications therefore cannot be assessed.
What is an objective response rate?
In general, an objective response rate is a proportion based on a defined event: meeting the criteria for complete or partial response. Here, the record identifies independent radiographic review and RECIST v1.0 criteria. A proportion requires both a count of participants meeting the response definition and a denominator of assessed participants. Neither the primary response count nor the analyzed denominator is reported in the registry record. The enrollment figure alone cannot be substituted for the endpoint denominator, because enrollment and analysis populations need not be identical.
Why does the study design affect interpretation?
In general, randomization helps balance measured and unmeasured participant characteristics between comparison groups, on average. This study is listed as nonrandomized and single-group, so there is no randomized control group in the record. The three named groups have different eligibility and prior-treatment descriptions. Differences in their outcomes, if reported, could reflect those characteristics as well as other differences; they would not constitute a randomized estimate of a treatment contrast. The record explicitly cautions that the groups are not a like-for-like control comparison.
Masking is listed as none. In general, when treatment assignment is known, expectations can affect some aspects of care or assessment. Independent radiographic review may help limit some assessment influences, but the registry record does not describe the review process in enough detail to determine how effectively potential bias was managed. No masking means the record does not document blinding of participants or study personnel.
What does the endpoint timeframe mean?
The primary endpoint timeframe runs from first dose to progression or death, or to the last tumor assessment, up to three years. In general, a participant's observation can end because an event occurs or because follow-up ends without a documented event. The last-assessment provision indicates that the timing of available tumor assessments matters to endpoint evaluation. The registry does not report how missing or unevaluable assessments were handled, the visit schedule, or the number of participants followed for each duration. Those details are not reported in the registry record.
What is over-dispersion, and is it relevant?
In general, over-dispersion occurs when observed variation is greater than expected under a statistical model's assumptions. It can matter for count outcomes or clustered data when a model assumes less variability than the data contain; standard errors may then be too small if the extra variation is ignored. The primary outcome is described as a percentage of participants, and the record does not report a model-based analysis or an over-dispersion adjustment. Whether over-dispersion was assessed is not reported in the registry record. This concept should not be taken to imply that such an issue occurred in this study.
What can be said about sample-size planning?
In general, sample-size calculations depend on an assumed effect, a significance level, allocation, and a statistical method. The planning description associated with this record specifies a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; it describes the effect to detect as a stated fraction of the observed effect. These are planning assumptions, not observed trial results, and they are not a report of the trial's original design rationale. The record does not report the trial's own sample-size justification. No planning count or observed response effect is reported in the registry record, so no such values can be evaluated. Any planning illustration should not be described as observed power.
What does the record's analysis population wording imply?
The primary outcome population is called modified ITT and is described as participants who were randomized and had taken at least one dose, with an asserted equivalence to the safety population. In general, an analysis-population definition is important because exclusions or eligibility requirements can change the denominator and the interpretation of an estimate. Here, the word “randomized” conflicts with the recorded nonrandomized, single-group design. The record does not explain this discrepancy or give the number analyzed. The population label therefore cannot resolve uncertainty about the primary endpoint denominator.
The registry lists no analyses in the analysis count. That does not establish what statistical work may have occurred outside the registry record; it means the record does not present analysis details in that field. The statistical plan, handling of multiplicity, missing-data methods, and any sensitivity analyses are not reported in the registry record. In general, without those details and without endpoint estimates, it is not possible to judge the robustness of the findings or reproduce the primary analysis.
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.
| Arm | Participants | Events | Observed % | Clopper-Pearson 95% CI | Wilson 95% CI | Bayesian 95% credible interval |
|---|---|---|---|---|---|---|
| Prior Tarceva or Iressa With EGFR Mutation | 91 | 3 | 3.3% | 0.7% to 9.3% | 1.1% to 9.2% | 1.2% to 9.2% |
| Prior Tarceva or Iressa w/o EGFR Mutation | 48 | 0 | 0.0% | 0.0% to 7.4% | 0.0% to 7.4% | 0.1% to 7.3% |
| No Prior EGFR Tyrosine Kinase Inhibitor Treatment | 28 | 1 | 3.6% | 0.1% to 18.3% | 0.6% to 17.7% | 0.8% to 17.8% |
R code and output
arm <- c("Prior Tarceva or Iressa With EGFR Mutation", "Prior Tarceva or Iressa w/o EGFR Mutation", "No Prior EGFR Tyrosine Kinase Inhibitor Treatment")
n <- c(91, 48, 28)
events <- c(3, 0, 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 Prior Tarceva or Iressa With EGFR Mutation 91 3 3.3 0.7 9.3 1.1 9.2 1.2 9.2
ARM Prior Tarceva or Iressa w/o EGFR Mutation 48 0 0.0 0.0 7.4 0.0 7.4 0.1 7.3
ARM No Prior EGFR Tyrosine Kinase Inhibitor Treatment 28 1 3.6 0.1 18.3 0.6 17.7 0.8 17.811. Multiplicity, Missing Data and Analysis Populations
The record lists one primary outcome, objective response rate, and three secondary outcomes: clinical benefit rate, duration of response, and progression-free survival. When multiple outcomes are examined, multiplicity can arise because repeated statistical tests increase the chance of at least one apparently notable result under a set of null hypotheses. In general, a prespecified testing strategy or adjustment can address this issue. The registry record does not report a multiplicity strategy, a statistical analysis plan, or numerical results and tests for the listed outcomes. No conclusion about whether or how multiplicity was addressed is possible.
Missing-data methods are also not reported in the registry record. The primary endpoint definition refers to progression, death, or the last tumor assessment, but the record does not state how missing scans, incomplete follow-up, unevaluable responses, or withdrawals were treated. The endpoint denominator and the number with missing assessments are not reported. Without these details, it is not possible to determine how incomplete observation affected the response estimate.
The endpoint population is called modified ITT and is described as including participants who were randomized and took at least one dose. The record also lists nonrandomized allocation and a single-group model. The inconsistency is not explained. The record says the endpoint population is equivalent to the safety population, but does not report a count for either analysis population. The actual inclusion and exclusion rules beyond the brief description are not reported in the registry record.
These omissions do not demonstrate that a particular analysis choice was made incorrectly. They limit the reader's ability to reconstruct the analysis, assess the impact of incomplete data, or determine which participants contributed to each endpoint.
12. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Prior Tarceva or Iressa With EGFR Mutation | 33 | 91 | 36.3% |
| Prior Tarceva or Iressa w/o EGFR Mutation | 21 | 48 | 43.8% |
| No Prior EGFR Tyrosine Kinase Inhibitor Treatment | 14 | 28 | 50.0% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Prior Tarceva or Iressa With EGFR Mutation | 91 of 91 |
| Prior Tarceva or Iressa w/o EGFR Mutation | 46 of 48 |
| No Prior EGFR Tyrosine Kinase Inhibitor Treatment | 26 of 28 |
Most frequent serious adverse event terms
| Event term | Organ system | Prior Tarceva or Iressa With EGFR Mutation | Prior Tarceva or Iressa w/o EGFR Mutation | No Prior EGFR Tyrosine Kinase Inhibitor Treatment |
|---|---|---|---|---|
| Pleural effusion | Respiratory, thoracic and mediastinal disorders | 7 of 91 | 4 of 48 | 1 of 28 |
| General physical health deterioration | General disorders | 5 of 91 | 3 of 48 | 3 of 28 |
| Non-small cell lung cancer | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 4 of 91 | 3 of 48 | 1 of 28 |
| Dyspnoea | Respiratory, thoracic and mediastinal disorders | 4 of 91 | 1 of 48 | 3 of 28 |
| Diarrhoea | Gastrointestinal disorders | 2 of 91 | 1 of 48 | 2 of 28 |
| Nausea | Gastrointestinal disorders | 4 of 91 | 0 of 48 | 1 of 28 |
| Vomiting | Gastrointestinal disorders | 2 of 91 | 1 of 48 | 2 of 28 |
| Dehydration | Metabolism and nutrition disorders | 1 of 91 | 2 of 48 | 2 of 28 |
| Pneumonia | Infections and infestations | 0 of 91 | 3 of 48 | 0 of 28 |
| Back pain | Musculoskeletal and connective tissue disorders | 1 of 91 | 1 of 48 | 1 of 28 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Prior Tarceva or Iressa With EGFR Mutation | Prior Tarceva or Iressa w/o EGFR Mutation | No Prior EGFR Tyrosine Kinase Inhibitor Treatment |
|---|---|---|---|---|
| Diarrhoea | Gastrointestinal disorders | 85 of 91 | 41 of 48 | 25 of 28 |
| Nausea | Gastrointestinal disorders | 52 of 91 | 24 of 48 | 16 of 28 |
| Fatigue | General disorders | 36 of 91 | 19 of 48 | 7 of 28 |
| Decreased appetite | Metabolism and nutrition disorders | 35 of 91 | 16 of 48 | 11 of 28 |
| Vomiting | Gastrointestinal disorders | 36 of 91 | 14 of 48 | 9 of 28 |
| Abdominal pain | Gastrointestinal disorders | 36 of 91 | 14 of 48 | 5 of 28 |
| Dyspnoea | Respiratory, thoracic and mediastinal disorders | 26 of 91 | 13 of 48 | 8 of 28 |
| Cough | Respiratory, thoracic and mediastinal disorders | 28 of 91 | 5 of 48 | 8 of 28 |
| Asthenia | General disorders | 22 of 91 | 9 of 48 | 6 of 28 |
| Rash | Skin and subcutaneous tissue disorders | 16 of 91 | 8 of 48 | 9 of 28 |
Serious events with the highest arm-level rate: general physical health deterioration (10.7%), dyspnoea (10.7%), pleural effusion (8.3%), diarrhoea (7.1%), vomiting (7.1%).
The registry record lists serious adverse event information for the three named groups. For the group with prior Tarceva or Iressa and an EGFR mutation, it records 33 participants affected among 91 at risk. For the group with prior Tarceva or Iressa without an EGFR mutation, it records 21 affected among 48 at risk. For the group with no prior EGFR tyrosine kinase inhibitor treatment, it records 14 affected among 28 at risk. These are group-specific counts; they should not be combined to construct a total.
The listed serious event terms include general physical health deterioration and dyspnoea, each reported as 10.7%; pleural effusion, 8.3%; and diarrhoea, vomiting, and dehydration, each 7.1%. The registry record does not provide further context for these percentages in the posted event-term list, such as a separate count for each term. The percentages therefore should be read as reported rather than reverse-engineered into counts.
Serious adverse events are not the same as all adverse events, and these figures do not describe every possible safety outcome. The record does not report deaths in the group fields, nor does it provide enough detail to interpret event timing, duration, or causal attribution. The groups differ in eligibility and prior-treatment characteristics and are not randomized comparisons, so their figures should not be treated as a controlled comparison of safety.
13. What the Result Does, and Does Not, Mean
The record establishes that a phase 2 study evaluated HKI-272, also called neratinib, in advanced non-small cell lung cancer, and it defines the primary response endpoint using independent radiographic assessment and RECIST v1.0. It also identifies three clinically distinct groups based on prior therapy, EGFR mutation status, and other eligibility characteristics. These details help clarify what the study set out to assess and who the groups were intended to include.
However, the primary endpoint's observed response rate is not reported in the registry record. The response count, endpoint denominator, and confidence interval limits are also not reported. Consequently, the record does not allow a reader to state the frequency of objective response or how precise its estimate was. The listed secondary outcomes likewise have no numerical results in the registry record.
The study's nonrandomized, single-group design does not furnish a randomized control comparison. The group descriptions do not create a like-for-like control, because they are defined by different treatment histories and participant characteristics. Therefore, even if group-specific outcomes were available, the record's design would require caution in attributing differences to neratinib rather than to differences between the groups.
The serious adverse event figures provide a limited description of reported safety events in the named groups. They do not establish a full safety profile, and they do not answer the missing efficacy-result question. The record does not provide details such as event timing or a causal assessment in these fields.
The appropriate reading is therefore bounded: study design, eligibility-group descriptions, endpoint criteria, timeframe, and selected serious adverse event information are available. The primary result, its precision, and the analysis details needed to evaluate it are not reported in the registry record. Absence of those results in the record is not itself evidence for or against an effect.
14. Why This Trial Matters Statistically
This study is statistically informative as an example of why endpoint definitions and endpoint results must be distinguished. The registry record defines objective response using independent radiographic review and RECIST v1.0, and states the endpoint timeframe and confidence interval level. Yet without the response estimate, denominator, and interval limits, a reader cannot assess either the observed magnitude or its precision. A clear definition is necessary for interpretation, but it cannot substitute for the data summary.
The record also illustrates how study design constrains claims. A nonrandomized, single-group study can describe outcomes among participants treated in that study, but it does not create a randomized comparison with an untreated or alternative-treatment group. The three groups are differentiated by prior therapy and eligibility characteristics. Their labels should not be mistaken for a design that balances prognostic factors or supports a direct treatment contrast.
Population definitions matter as well. The primary endpoint population is described as modified ITT and includes wording about randomization, while the design is recorded as nonrandomized. This discrepancy, together with the absent endpoint denominator, makes it difficult to determine exactly how the analysis population was formed. Clear alignment among design, eligibility, and analysis-population descriptions is important for reproducibility.
Finally, the record lists secondary outcomes and selected serious adverse event information but does not provide the statistical plan, missing-data approach, or numerical results for the primary and secondary outcomes. These omissions show why registry summaries are useful for locating planned questions and study structure but may not contain enough information to evaluate an estimate fully. Statistical interpretation depends on both the design and accessible outcome data.
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 principal limitation for interpreting efficacy is that the primary endpoint result is not reported in the registry record. There is no reported response count, analyzed denominator, point estimate, or confidence interval limits. The secondary outcomes are listed without numerical results. Thus, the record does not permit assessment of response magnitude, uncertainty, or the relationship between response and the other listed outcomes.
The design is nonrandomized and single-group, with no masking. The named groups differ in prior treatment and eligibility features, and the record cautions that they are not like-for-like controls. Comparisons across them would not have the protection against confounding associated with random allocation. The record does not report a comparator treatment or placebo group.
There is also a reporting inconsistency: the endpoint population description refers to randomized participants, while the study allocation is listed as nonrandomized. The reason is not reported. The exact endpoint population size and detailed inclusion rules are also not reported in the registry record.
Other limitations of interpretability include the absence of a reported statistical analysis plan, missing-data methods, multiplicity strategy, and details of any sensitivity analyses. The registry record does not explain how unevaluable imaging assessments or incomplete follow-up were handled. It also does not report the trial's sample-size justification. The available serious adverse event figures are selective and do not provide a complete account of all safety outcomes or event context.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: Study Evaluating the Safety Of HKI-272 (Neratinib) In Subjects With Advanced Non-Small Cell Lung Cancer — NCT00266877.
- Registry record last updated 2018-04-13; status last verified 2018-04.
- Results first posted 2018-04-13.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
19. Record Summary
The registry record describes a completed phase 2, nonrandomized, single-group study of HKI-272, or neratinib, in advanced non-small cell lung cancer. It lists enrollment as 172 and identifies three groups based on prior EGFR tyrosine kinase inhibitor treatment, mutation status, and other eligibility characteristics. The primary endpoint was objective response rate assessed by independent radiologists under RECIST v1.0, with a 90% confidence interval specified and a timeframe from first dose through progression or death, or last tumor assessment, up to three years.
The record lists clinical benefit rate, duration of response, and progression-free survival as secondary outcomes. It also includes group-specific serious adverse event counts and selected event-term percentages. The primary response result, confidence interval limits, secondary outcome results, statistical plan, and missing-data methods are not reported in the registry record. The endpoint population's reference to randomization is inconsistent with the recorded nonrandomized design, and the record does not explain the discrepancy.