Neo-DIANA: Neoadjuvant Treatment for EGFR Mutated Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Neo-DIANA: Neoadjuvant Treatment for EGFR Mutated Patients (NCT04512430), a na phase 2 study. The primary outcome is Overall Response.

2. Clinical Question

The planned clinical question concerns tumor response following neoadjuvant treatment in a selected population: patients with locally advanced, potentially resectable NSCLC and EGFR mutations. The registry defines overall response as complete response plus partial response. Target lesions were to be assessed using RECIST v1.1 and MRI. The stated observation period runs from the end of neoadjuvant treatment until the last follow-up, assessed up to 36 months.

This is a single-group study, rather than a comparison of the regimen with a control treatment. Its design can describe outcomes among enrolled participants, but without a concurrent comparator it cannot separate treatment-associated outcomes from other explanations, such as the natural course of disease or differences in participant characteristics. The registry describes the trial as phase II and open-label, with no masking.

The record reports enrollment of 4 participants, while its brief summary describes a plan to enroll 26. The trial status is terminated. No primary response count, response rate, or treatment-effect estimate is reported in the registry record. Consequently, the clinical question is stated, but the posted results do not provide an efficacy analysis with which to answer it.

3. Trial Design

Neo-DIANA is registered as a phase II trial of neoadjuvant treatment for patients with EGFR-mutated NSCLC. Its official title describes carboplatin, pemetrexed, bevacizumab and atezolizumab for locally advanced and potentially resectable disease. The record identifies Fundación GECP as the sponsor. The design is open-label, non-randomised and single-group; allocation is listed as not applicable, and masking is listed as none.

The experimental arm is called Neo-Adjuvant Immunotherapy. The description specifies intravenous atezolizumab, bevacizumab, carboplatin and pemetrexed, with treatment to start within 1-3 days from enrollment. It describes 3 cycles at 21-day (+/- 3 days) intervals prior to surgery. The arm description is incomplete after the word “Befor,” so additional details beyond the text recorded cannot be established.

The registry records a start date of 2020-12-02 and a primary completion date of 2024-07-19. The study status is terminated. Enrollment is recorded as 4 participants; the brief summary says 26 patients were planned. The record does not state why the study was terminated or explain the difference between the planned enrollment and recorded enrollment.

Because everyone is assigned to one group and the study is not randomized, the design does not support a like-for-like comparison between treatment groups. The registry record does not report a protocol-based sample-size justification, the reason for the enrollment target, or whether the target was revised. It also does not report whether interim analyses were planned or conducted. These details should not be inferred from the phase designation or from the recorded enrollment.

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

Analysis population for the primary outcome, as defined in the registry: Intention to treat

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 Overall Response, measured over From date of end of neoadjuvant treatment until the date of last follow up, assessed up to 36 months.

The primary outcome is titled Overall Response and is measured as a count of participants. Its description identifies objective response rate as the measure of antitumor activity. Under the stated RECIST v1.1 criteria for target lesions, complete response means disappearance of all target lesions. Partial response means at least a 30% decrease in the sum of the longest diameters of target lesions. Overall response combines complete and partial response. Progressive disease is described as at least a 20% increase in the sum of target-lesion diameters. The registry says lesions were assessed by MRI.

Objective response is used to summarize whether participants meet a prespecified tumor-shrinkage category during the defined assessment period. It expresses response as a participant-level outcome rather than as a continuous change in tumor size. The stated timeframe begins at the end of neoadjuvant treatment and continues until the date of last follow-up, assessed up to 36 months.

The endpoint description names the intention-to-treat population. However, the registry record does not report the number of participants with complete response, partial response, or overall response, nor does it report an estimated response rate or uncertainty interval. The outcome definition is therefore available, but its observed result is not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the response outcome represent?

Overall response is a categorical outcome based on whether a participant meets the criteria for complete or partial response. The registry describes lesion assessment using RECIST v1.1 and MRI. Complete response is defined as disappearance of all target lesions; partial response as at least a 30% decrease in the sum of their longest diameters. The two categories together define overall response. The record also describes progressive disease using at least a 20% increase in the sum of target-lesion diameters.

In general, a binary outcome classifies each participant into one of two broad states for the analysis, such as having or not having the event being counted. The registry’s outcome is listed as a participant count. An estimated response proportion would require the relevant participant counts and a defined denominator. Neither a response count nor an analyzed denominator for this endpoint is reported in the registry record, so an outcome estimate cannot be reconstructed from the listed enrollment alone.

Why does uncertainty matter?

In general, an estimate from a clinical study is subject to sampling variability: another group of participants could produce a different estimate, even if recruited and assessed in a similar way. A confidence interval is a range of values compatible with the data under a specified statistical method. Its width communicates precision, while the point estimate describes the central result. These are general statistical concepts; the registry record does not report a confidence interval or an estimate for overall response.

For a participant-level binary outcome, the amount of information depends on the observed outcome count and the number of participants assessed. Here, the recorded enrollment is 4, but no primary response count or analysis is reported. It is therefore not possible to assess the observed response frequency, quantify its uncertainty, or determine whether any planned analysis was carried out. No p-value for the primary outcome is reported.

What can a single-group design estimate?

In general, a single-group study can describe outcomes in the participants who received the study regimen. It has no concurrent control group from which to estimate a treatment contrast. Differences between a study outcome and an external expectation can reflect differences in eligibility, care, measurement, follow-up, or other factors, as well as treatment. Without a randomized comparison, those possibilities cannot be separated by the study design alone.

Randomization is a method for assigning participants to comparison groups so that, on average, measured and unmeasured characteristics are not deliberately concentrated in one group. This trial is described as non-randomised and single-group, so a randomized between-group contrast is not part of the recorded design. The statistical plan beyond these design details is not reported in the registry record.

How should planning illustrations be understood?

The planning assumptions attached to sample-size illustrations specify a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They describe the effect to detect as a stated fraction of the observed effect. For participant outcomes, such illustrations are expressed as participants per arm; time-to-event illustrations are expressed as a total number of events using the Schoenfeld approach.

These assumptions describe planning illustrations, not the trial’s own design. The actual trial is a single-group study, not an equally allocated two-arm comparison. Sample-size illustrations are not observed power and should not be interpreted as a finding about the trial. The registry record does not report a protocol-based sample-size justification or identify an analysis that generated an observed primary-outcome effect. Since the primary outcome analysis is not reported, a planning illustration cannot substitute for a response estimate from participants.

In general, over-dispersion matters when outcomes vary more than a statistical model assumes; if ignored, estimated uncertainty can be too small. The primary outcome is binary and no dispersion estimate or model is reported. The registry record does not provide enough information to say whether over-dispersion was assessed or whether any alternative model was used. No specific inferential method for the primary response outcome is reported in the registry record.

What information is needed for an inferential result?

An inferential result generally requires a stated analysis population, outcome data, an analysis method, and a measure of uncertainty or a test tied to the clinical question. For a comparative question, the design also needs a valid comparator and a method for estimating the between-group contrast. The record names an intention-to-treat population for the outcome but does not report the response data or the statistical analysis. The absence of these details means that readers cannot verify an estimate, assess its precision, or evaluate whether the analysis followed a prespecified plan.

10. Multiplicity, Missing Data and Analysis Populations

The registry identifies one primary outcome measure, Overall Response, but records zero analyses. It does not report a multiplicity adjustment or explain how multiple comparisons, endpoints, time points, or subgroup analyses were handled. No such analyses should be assumed from the phase designation or the outcome description.

The primary outcome names an intention-to-treat population. The record does not report how that population was operationalized, how participants with missing response assessments were handled, or what denominator was used for an efficacy analysis. It also does not report the amount or pattern of missing outcome data, whether participants were excluded from any analysis, or whether sensitivity analyses were conducted. These details are not reported in the registry record.

In general, missing outcome information can affect both the estimate and its uncertainty, especially if the chance that data are missing is related to participants’ outcomes or characteristics. Analysis choices such as excluding participants with missing assessments, imputing outcomes, or using another approach can lead to different interpretations. No method for addressing missing primary-outcome data is reported, so the effect of missingness cannot be assessed.

The registry does not describe an interim analysis plan, stopping boundary, or final statistical analysis plan. It also does not state whether the primary outcome was analyzed before termination. The status is recorded as terminated, but the reason and any consequences for the planned analysis are not reported in the registry record. In the absence of these details, readers cannot determine how multiplicity, missingness, or analysis-population decisions may have affected the intended inference.

11. 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: right lung hernia (25.0%).

The experimental group lists 4 participants at risk for serious adverse events, with 1 participant affected. The listed serious event term is right lung hernia, with 25.0% shown. The same group lists 4 participants at risk for other adverse events and 4 affected. Deaths are recorded as 0.

These figures are descriptive counts in the registry record. The serious-event count concerns participants with an event, not necessarily the total number of event episodes. The record does not state the timing, duration, severity grading details, outcome, or whether the serious event was considered related to treatment. A listed event term does not by itself establish causation.

Safety counts also need the study context: the record describes a single group and enrollment of 4, and the trial status is terminated. The counts do not provide a comparison with another treatment group, and the record does not report additional detail to characterize risk across a broader population. The posted safety figures should therefore be read as the events recorded for this group, not as a comparative estimate or proof about the regimen’s safety.

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

The registry record describes a phase II study designed to evaluate objective response after neoadjuvant carboplatin, pemetrexed, bevacizumab and atezolizumab in participants with locally advanced, potentially resectable NSCLC with EGFR mutations. It records an enrollment of 4 and a terminated status. It also provides some safety counts for the experimental group.

What the record does not establish is the primary efficacy result. No count of complete responses, partial responses, or overall responses is reported, and there is no response-rate estimate or uncertainty interval. The study’s stated aim is not itself a result. Similarly, lack of a reported response analysis does not mean that no participant responded; the registry record does not report that information.

The design also limits what any single-group outcome could mean. Without a concurrent control group, observed outcomes would describe participants receiving the regimen but would not, on their own, establish what outcomes would have been under a different treatment. The absence of randomization further means there is no randomized treatment contrast to interpret.

The safety figures are likewise limited. They identify recorded event counts in the study group but do not state whether events were attributed to treatment or compare those counts with another group. No causal conclusion follows from the event listing alone.

Thus, the posted results support a factual account of the study’s design, enrollment, status and recorded adverse events. They do not supply the primary response analysis or enough methodological detail to assess its precision, missing-data handling, or statistical plan. The difference between intended and recorded enrollment is documented, but the reason for it is not reported in the registry record.

13. Why This Trial Matters Statistically

This trial raises a clinically focused statistical question: how to describe objective response after a neoadjuvant regimen in a population defined by locally advanced, potentially resectable NSCLC and EGFR mutation. Its endpoint is specified using RECIST v1.1, which makes the response categories explicit rather than relying on an undefined judgment of improvement.

The record also illustrates why design and results must be read together. A single-group, open-label, non-randomised phase II study can be structured to observe outcomes in people receiving a regimen, but it cannot supply a randomized comparison. This distinction matters when moving from a description of outcomes to a claim about comparative treatment effects.

Enrollment and reporting are also central to interpretation. The registry lists 4 enrolled participants, while the brief summary describes 26 as planned, and the status is terminated. Because the primary response analysis is not reported, readers cannot use the endpoint definition alone to determine the observed response or its precision. A clearly stated outcome is valuable, but it does not replace the outcome data and analysis needed to answer the research question.

Finally, the record separates efficacy from safety information. Serious and other adverse-event counts can describe what was recorded among participants, but without attribution or a comparison group they do not establish a treatment-related risk difference. The case emphasizes the importance of transparent outcome reporting, statistical methods, and explanations for deviations between planned and recorded study conduct.

14. 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 trial-specific limitation in the registry record is that the primary response outcome has no reported analysis. Although the endpoint and its assessment criteria are described, no response count, response rate, confidence interval, or test is given. The clinical question therefore cannot be answered from the posted efficacy results.

The study is single-group, non-randomised and open-label. There is no concurrent comparator for estimating a treatment contrast, and the design does not provide randomized balancing of participant characteristics. These features restrict causal and comparative interpretation, even if outcome results were available.

The enrollment is recorded as 4, while the brief summary states that 26 patients were planned. The status is terminated. The record does not explain the enrollment difference, give the reason for termination, or state how these circumstances affected the analysis. The recorded enrollment alone does not indicate why the trial ended.

Several statistical details are not reported in the registry record: the protocol-based sample-size justification, the primary analysis method, missing-data handling, multiplicity procedures, interim analyses, and the detailed definition of analysis populations. The outcome names an intention-to-treat population, but the record does not provide the corresponding analyzed denominator or response data.

Safety reporting is also limited to the listed counts and serious-event term. Attribution, timing and further clinical details are not reported. Taken together, these gaps mean that the posted record supports description of trial conduct and recorded events, but not a precise efficacy assessment or a comparative benefit-risk conclusion.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Neo-DIANA: Neoadjuvant Treatment for EGFR Mutated Patients — NCT04512430.
• Registry record last updated 2025-04-02; status last verified 2025-04.
• Results first posted 2025-04-02.
• 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.

18. Record Summary

Neo-DIANA is a phase II, open-label, non-randomised, single-group study sponsored by Fundación GECP. It concerns neoadjuvant carboplatin, pemetrexed, bevacizumab and atezolizumab for locally advanced, potentially resectable NSCLC with EGFR mutations. The registry records 4 participants enrolled, a planned enrollment of 26 in the brief summary, and a terminated status.

The primary outcome is Overall Response, defined through RECIST v1.1 and assessed by MRI, with the outcome population identified as intention to treat. No primary response analysis is reported in the registry record. Safety listings report 1 participant with a serious adverse event among 4 at risk, 4 with other adverse events among 4 at risk, and 0 deaths. A serious event term is listed as right lung hernia, 25.0%.

The record does not report the reason for termination, the response results, or several details of the statistical plan and missing-data handling.