Lapatinib for Treatment of Ductal Carcinoma In Situ (DCIS) of the Breast: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Lapatinib for Treatment of Ductal Carcinoma In Situ (DCIS) of the Breast (NCT00857714), a na na study. The primary outcome is Number of Patients Where Gene Signature Was Obtained..

2. Clinical Question

This is therefore not a direct comparison of lapatinib with another treatment or with no treatment. Its registered primary outcome concerns obtaining a gene signature, rather than a direct measure of tumor response, recurrence, or clinical benefit. The registry record also lists toxicity associated with short therapy as a secondary outcome. It does not report results for the primary outcome, participant characteristics, or the secondary outcome beyond the posted serious adverse event figures. The study's stated aim and its registered endpoint should be kept distinct: the aim refers to evaluating therapy using a gene signature, while the primary endpoint specifically counts whether a signature was obtained.

3. Trial Design

The registry record describes NCT00857714, titled “Lapatinib for Treatment of Ductal Carcinoma in Situ (DCIS) of the Breast,” with Indiana University as sponsor. The study is listed as single-group and unmasked. Allocation and phase are recorded as NA. Its status is terminated. The recorded start is 2009-04, and primary completion is recorded as 2010-08.

Enrollment is recorded as 1. The intervention is lapatinib, and the safety group is labeled “1500 mg Lapatinib for 14-21 Days.” The primary outcome is the number of patients where a gene signature was obtained, with a timeframe of up to 60 days. The registry also lists toxicity associated with short therapy with lapatinib as a secondary outcome. It records 2 outcome measures and 0 analyses.

Because the design is single-group and no comparator is recorded, the study does not estimate a between-group treatment contrast. Its structure can describe observations in the treated group, but cannot separate an intervention effect from other explanations for an observed outcome. The allocation entry of NA does not establish random assignment, and the record does not give a reason for termination. It also does not report a protocol-level statistical plan, sample-size justification, or details of any interim analyses. These absences limit what can be inferred about how the study was intended to operate beyond the registered design and endpoints.

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

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 Number of Patients Where Gene Signature Was Obtained., measured over Up to 60 days.

The primary endpoint is the number of patients for whom a gene signature was obtained. It is specified as a participant count, with a timeframe of up to 60 days. The description says the signature was intended to identify a gene signature denoting the effect of lapatinib therapy in breast cancer cell lines and to assess the therapy's effect in patients with DCIS using that signature as a surrogate marker.

The endpoint therefore concerns whether the gene signature was obtained, not the magnitude of a clinical outcome. In general, a surrogate marker is used as an indirect indicator of a biological or clinical process; a surrogate does not automatically establish that a treatment changed a patient-centered outcome. The registry record does not provide validation evidence for this signature or define a threshold for interpreting it. It also does not report the number of participants with a signature obtained.

That distinction matters for interpretation. Counting signature acquisition can describe whether the planned measurement was available, but by itself it cannot show whether the signature changed, whether it predicts clinical outcomes, or whether lapatinib caused a change. Those questions require outcome definitions and results that are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record describes a single-group study, not a randomized comparison. This distinction determines what kinds of statistical conclusions are available. A comparison between treatment groups can estimate a contrast between those groups, subject to the design and analysis. A single-group study has no such internal contrast. It can report what happened among participants observed in the group, but it cannot, on its own, distinguish an intervention effect from natural history, measurement variation, or other influences.

What does the primary outcome count?

The primary endpoint is a participant count: the number of patients where a gene signature was obtained within up to 60 days. The outcome is described as binary in the registry record, meaning that each participant's status can be considered as having or not having the specified event. A count of participants with an event is not the same as a measure of how large a biological response was. The registry does not report an outcome count, a proportion, or an analysis of this endpoint.

In general, binary outcomes are often described using event counts and denominators, and may be analyzed with methods suited to proportions or event probabilities. Which method is appropriate depends on the design, amount of data, endpoint definition, and analysis plan. The registry record does not report a statistical method for the primary endpoint, so no particular inferential model or adjustment should be attributed to the study.

What can a confidence interval tell readers?

In general, a confidence interval conveys uncertainty around an estimated quantity. Its width depends on the data and the method used; it is not a guarantee that the true value lies within the displayed interval. With limited observations, estimates can be imprecise, and a point estimate alone can conceal that uncertainty. No confidence interval for the primary outcome is reported in the registry record. Thus, readers cannot assess the precision of a primary endpoint estimate from this entry.

How should the planning assumptions be read?

The record describes a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It describes effects to detect as stated fractions of the observed effect. These are planning assumptions, not a description of the actual single-group design: the registry lists no comparator group. The illustration's sample sizes are planning quantities, not observed trial results and not observed power. No planning sample-size values or justification are reported in the registry record.

In general, a sample-size calculation estimates the amount of information that a proposed design might need under specified assumptions. It is sensitive to the anticipated effect, variability or event probability, allocation, and statistical method. When the assumptions do not match the actual design or endpoint, the illustration may not describe the study's operating characteristics. A planning calculation cannot substitute for a result, and it does not show whether the study had adequate precision after enrollment.

Why does the single-group structure matter?

Without a control group, there is no direct estimate of how the endpoint would differ under an alternative condition. The primary endpoint is also a measurement-availability outcome: obtaining a signature. That can be useful for describing whether a measurement was achieved, but it does not itself quantify a treatment response. The registry description calls the signature a surrogate marker; general statistical reasoning cautions that a surrogate needs evidence supporting its relationship to outcomes of interest. Such validation details are not reported in the registry record.

The record lists 0 analyses. That means no analysis results are posted in the registry entry; it does not establish which analyses may or may not have been conducted outside the entry. No analysis population, adjustment method, missing-data procedure, or handling of multiple outcomes is reported in the registry record. Consequently, readers should not infer a prespecified statistical analysis plan from the endpoint descriptions alone.

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("1500 mg Lapatinib for 14-21 Days")
n      <- c(1)
events <- c(1)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  1500 mg Lapatinib for 14-21 Days  1  1  100.0  2.5  100.0  20.7  100.0  15.8  98.7

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 2 outcome measures: a primary outcome concerning obtaining a gene signature and a secondary outcome concerning toxicity associated with short therapy with lapatinib. It does not report a multiplicity strategy, such as how interpretation would account for testing more than one outcome. In general, when multiple outcomes are examined, the chance of at least one seemingly notable result can depend on the number and relationship of the analyses. No adjustment or hierarchy beyond the labels “primary” and “secondary” is reported.

Missing-data handling is not reported in the registry record. In general, a missing endpoint measurement can affect both the denominator and the interpretation of an event rate. This is particularly relevant to an endpoint defined by whether a gene signature was obtained: the record does not explain whether failure to obtain a signature would be counted as not obtained, treated as missing, or handled in another way.

The registry does not report an analysis population, exclusions, a rule for incomplete follow-up, or an imputation method. It records 0 analyses, so no outcome analysis or population definition is posted. The enrollment entry is 1, but the registry does not explain how that entry relates to completeness of endpoint data. Without these details and the primary outcome result, the extent and consequences of missing data cannot be assessed.

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: wound complication (100.0%).

The serious adverse event entry is for the group labeled “1500 mg Lapatinib for 14-21 Days.” It records 1 participant at risk and 1 affected. Wound complication is listed as the top serious term at 100.0%. These are the posted registry figures; they should be read as counts and a percentage within the recorded group, not as a reliable estimate for a broader population.

The registry also records 1 at risk and 1 affected in the other adverse-event fields. The record does not provide further detail about those events in the registry record. A serious adverse event is a safety classification, and its presence does not by itself establish that the study intervention caused it. The registry entry does not report an attribution assessment or contextual details for the wound complication.

The small enrollment recorded as 1 means the safety information is highly limited. A percentage based on a very small denominator can appear definitive while conveying little about the frequency that would occur in other participants. The record does not support a comparative safety assessment because it lists no control group.

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

The record establishes that a study of lapatinib for DCIS was registered as single-group, had enrollment recorded as 1, and was later listed as terminated. Its primary endpoint was the number of patients where a gene signature was obtained within up to 60 days. The registry describes the signature as a surrogate marker intended to assess therapy in patients, drawing on work in breast cancer cell lines.

What the record does not establish is whether the gene signature was obtained, whether it changed, or whether it tracked a clinical outcome. No primary outcome result is reported in the registry record. There is also no posted analysis estimate or precision measure. The stated study purpose is not itself evidence that the intended assessment was completed or that the signature functions as a valid surrogate.

The safety entry reports a serious adverse event for the recorded group, with wound complication listed at 100.0%. These data are descriptive and limited to the registry's recorded group. They do not establish causation or permit comparison with another treatment, because no comparator is recorded.

In general, an observed result from a single-group study can motivate further study or describe what occurred in that group, but it cannot provide the same causal evidence as a suitable comparative design. Here, the lack of a posted primary result further restricts interpretation. The registry entry supports conclusions about the study's recorded design, purpose, status, and limited safety figures—not conclusions about treatment efficacy, surrogate validity, or the expected balance of benefits and harms.

14. Why This Trial Matters Statistically

This study is statistically instructive because its stated aim and registered primary endpoint are not identical. The aim concerns assessing lapatinib therapy using a gene signature as a surrogate marker, while the primary endpoint counts whether the signature was obtained. The distinction between collecting a measurement and demonstrating a treatment effect is central to interpreting clinical research. Measurement availability can be necessary for analysis, but it does not by itself answer whether a treatment changes a meaningful outcome.

The single-group design also clarifies why a study result, even if posted, would need careful interpretation. Without a comparator, observed outcomes cannot be directly contrasted with outcomes under an alternative condition. This limits causal interpretation independently of the statistical method used. The registry does not report an analysis plan that could resolve this design limitation.

The entry also illustrates the importance of result completeness. The primary outcome is defined, but its result and precision are not reported in the registry record. A study's endpoint description and enrollment information cannot replace the outcome data needed to estimate what happened. The posted serious adverse event figures are similarly constrained by the small recorded enrollment and absence of a control group.

Finally, planning assumptions should be separated from the actual design and observed evidence. The planning illustration refers to two-arm allocation, while the registered study is single-group. Its assumptions are not observed outcomes or proof of power. Reading these elements separately helps prevent planning calculations, endpoint intentions, and safety counts 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 major limitation is the absence of a reported result for the primary endpoint. The registry record defines the outcome but does not report how many patients had a gene signature obtained. It also does not provide an effect estimate or uncertainty interval, so the primary outcome's observed value and precision cannot be assessed.

Enrollment is recorded as 1, and the design is single-group with no comparator. Those features severely limit both precision and causal interpretation. The registry does not report participant characteristics, including whether the enrolled participant had ER-negative DCIS, the subgroup emphasized in the study purpose. It also does not explain why the study was terminated.

The endpoint's interpretation is limited by the absence of reported validation details for the gene signature as a surrogate marker. The record does not define how unsuccessful signature acquisition or missing measurements were handled. No analysis population, missing-data strategy, multiplicity procedure, or statistical analysis plan is reported. The entry records 0 analyses.

Safety information is also limited. Although the serious adverse event fields record 1 participant at risk and 1 affected, the record supplies little context beyond the wound complication term. It does not provide an attribution assessment or a comparison group. These constraints mean the safety figures should remain descriptive and should not be generalized as a population risk estimate.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Lapatinib for Treatment of Ductal Carcinoma In Situ (DCIS) of the Breast — NCT00857714.
• Registry record last updated 2015-07-08; status last verified 2015-06.
• Results first posted 2015-07-08.
• 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

NCT00857714 is a terminated, single-group study sponsored by Indiana University, with enrollment recorded as 1. The intervention is lapatinib; the safety group is labeled “1500 mg Lapatinib for 14-21 Days.” The primary outcome is the number of patients where a gene signature was obtained within up to 60 days. The stated purpose focuses particularly on ER-negative DCIS and describes the signature as a surrogate marker.

The registry lists 2 outcome measures and 0 analyses. It does not report the primary outcome result or a reason for termination. The serious adverse event entry records 1 at risk and 1 affected, with wound complication listed as the top serious term at 100.0%. The single-group design and missing primary result leave the record unable to establish a treatment effect or the precision of the primary endpoint.