Regorafenib Eye Drops: Investigation of Efficacy and Safety in Neovascular Age Related Macular Degeneration: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Regorafenib Eye Drops: Investigation of Efficacy and Safety in Neovascular Age Related Macular Degeneration (NCT02222207), a randomized phase 2 study. The primary outcome is Change From Baseline in Best Corrected Visual Acuity (BCVA) as Measured by Early Treatment Diabetic Retinopathy Study (ETDRS) Letter Score at Study Week 4 for Study Part A.

2. Clinical Question

3. Trial Design

This was a randomized, quadruple-masked, parallel-group Phase 2 study of regorafenib eye drops in neovascular age-related macular degeneration. The registry lists enrollment of 52. The recorded study start is 2014-10, and the primary completion date is 2015-05. The current status is terminated. The reason for termination is not reported in the registry record.

The official title describes a combined Phase IIa / IIb study. The registry summary separates the objectives into Part A (Phase IIa) and Part B (Phase IIb). Part A was designed to assess whether regorafenib eye drops could improve visual acuity after 4 weeks and 12 weeks, and to evaluate safety and tolerability. Part B was intended to investigate how often the drops should be given and to assess visual outcomes, safety, and tolerability across different dosing schedules. These descriptions state study aims; they are not results.

Part A is described as regorafenib eye drops. The Part B regorafenib groups are described as using different drop doses and receiving sham intravitreal therapy once every 4 weeks. The ranibizumab group was described as receiving intravitreal ranibizumab once every 4 weeks with placebo eye drops. The record does not give the dose amounts, the randomization allocation ratio, or details about how the random sequence was generated or concealed. It also does not explain which parties were masked despite the quadruple-masking designation.

The registry lists 52 participants enrolled, but this figure is not an endpoint analysis denominator. The primary endpoint population is defined as the Full Analysis Set, which included participants who received at least one dose of study medication. The number of participants included in that set is not reported in the registry record. Further details about the conduct of the two study parts, recruitment, and reasons for termination are also not reported.

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: Study was planned to be conducted in 2 parts, Part A and B, in Part A 89 subjects were enrolled, of them 37 were screen failure and 52 were assigned to treatment, 1 subject was excluded from all analysis sets due to protocol deviations and 51 subjects were analyzed. Part B was not initiated and the study terminated following completion of Part A.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set (FAS): included participants who received at least one dose of study medication.

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 Change From Baseline in Best Corrected Visual Acuity (BCVA) as Measured by Early Treatment Diabetic Retinopathy Study (ETDRS) Letter Score at Study Week 4 for Study Part A, measured over Baseline, Week 4.

The primary endpoint is the change from baseline in best corrected visual acuity, measured using the Early Treatment Diabetic Retinopathy Study (ETDRS) letter score at Study Week 4 for Study Part A. Visual acuity is assessed using an ETDRS chart, with scores recorded at study visits. The registry states that a higher score represents better functioning. The endpoint therefore expresses change in a measured vision score over the interval from baseline to the Week 4 assessment; the record does not report the actual change observed.

Using a standardized letter score provides a quantitative continuous measure, allowing investigators to summarize participants’ scores with a mean and standard deviation. In general, a change score can describe how a measured outcome shifts from its starting value, while a comparison between groups can estimate how outcomes differed under their assigned regimens. The registry record does not provide group-level endpoint summaries or an estimated between-group contrast for this primary endpoint, so the magnitude, direction, and precision of any such contrast cannot be assessed.

The endpoint description says that for participants who dropped out or received rescue treatment, the last observation before dropout or rescue treatment was carried forward. This is an analysis rule for handling some missing or post-rescue measurements, not a statement that all participants had complete Week 4 data. Counts of participants with observed Week 4 measurements, dropout, or rescue treatment are not reported in the registry record. The defined population is the Full Analysis Set: participants who received at least one dose of study medication.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The statistical details in the registry record are sparse. The endpoint is continuous, is summarized by a mean, and identifies standard deviation as its dispersion measure. The description also names a Full Analysis Set and a last-observation-carried-forward rule for some participants with dropout or rescue treatment. It does not report the test or model used for the primary analysis, an effect estimate, a confidence interval, or a p-value. General explanations below describe what these methods mean; they do not imply that an unreported method was used in this study.

What does a mean change represent?

A continuous outcome can take a range of numerical values rather than placing each participant into a category. For this endpoint, the ETDRS letter score is recorded at visits, and the primary measure is its change from baseline to Week 4. In general, a group mean change describes the average change among the participants included in that analysis. It does not describe every participant’s individual response, and it can conceal variation in individual trajectories. The registry says a higher score represents better functioning, but without the observed group mean changes, the direction and size of the reported outcome cannot be evaluated.

A standard deviation describes the spread of individual scores around a group mean. It is not the same as the standard error or a confidence interval. The standard deviation reflects variation among observations; a standard error reflects uncertainty in an estimated mean and depends on both spread and the amount of information. No standard deviations or standard errors for the primary endpoint are reported in the registry record.

How would a group comparison be interpreted?

In general, a comparative trial analysis would estimate how the outcome differs between assigned groups. An unadjusted comparison uses the recorded group summaries without accounting for additional covariates. An adjusted analysis can incorporate specified participant or design characteristics, but the model and adjustment variables would need to be reported to interpret it. The registry record does not provide a primary outcome contrast or describe an adjusted analysis. It is therefore not possible to identify the analysis scale, assess covariate adjustment, or determine whether the endpoint was analyzed according to the planned allocation.

A confidence interval gives a range of values compatible with the data and analysis under its assumptions. Its width conveys precision: a wider interval represents more uncertainty about the effect estimate. Statistical significance and clinical importance are different questions. A test result addresses compatibility with a statistical null hypothesis, whereas clinical importance depends on the size and meaning of an outcome difference. The registry record reports neither a confidence interval nor a test result for the primary endpoint, and it does not specify a clinically important threshold.

Why does missing-data handling matter?

The endpoint description says the last observation before dropout or administration of rescue treatment was carried forward. In general, last observation carried forward fills a later missing measurement with an earlier observed value. This creates an analyzable value for that time point, but it relies on an assumption that the earlier measurement is a reasonable substitute for the unobserved later outcome. If outcomes would have changed after dropout or rescue treatment, carrying the earlier value forward may not represent the unobserved measurement. The direction and size of any resulting bias depend on the unobserved outcomes and the reasons data are missing.

The registry record does not say how many participants had missing Week 4 data, how many received rescue treatment, whether other missing-data methods were used, or whether sensitivity analyses were conducted. It does not report whether the analysis examined assumptions about missing outcomes. These omissions make it impossible to assess how missingness may have affected the primary endpoint estimate.

What can planning illustrations tell the reader?

Sample-size planning is distinct from analyzing observed trial outcomes. A planning illustration describes the number of participants per arm that might be needed under specified assumptions; it is not an estimate of treatment effectiveness, and it is not observed power. The registry’s planning note describes a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect expressed as a fraction of the observed effect. Those are assumptions for an illustration, not evidence that the original study was designed using those choices. The trial’s own sample-size justification is not reported in the registry record.

In general, power calculations depend on assumptions about the outcome variability, the effect to detect, the significance level, allocation, and analysis. Changing assumptions changes the planning result. An illustration based on an observed effect can also be sensitive to the uncertainty in that effect, particularly when the observed estimate is imprecise. It should not be read as a retrospective statement that the trial had a specified probability of detecting a true effect. No numerical planning illustration can resolve the absence of the primary endpoint results.

The record gives randomized allocation and a parallel design, but does not describe sequence generation, allocation concealment, analysis model, hypothesis-testing procedure, interim analysis, or statistical analysis plan. Those details are not reported in the registry record. Because the primary outcome results are also absent, statistical significance, precision, and robustness cannot be assessed from the listed endpoint specification alone.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Part A Regorafenib")
n   <- c(50)
m   <- c(1.18)
sp  <- c(7.55)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Part A Regorafenib  50  1.180  7.550  -0.966  3.326

11. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary endpoint for Part A and gives secondary objectives concerning vision, safety, and tolerability. Two secondary outcome descriptions specifically concern the percentage of participants with individual changes in BCVA from Study Week 4 to Week 12, and the percentage with a loss of at least 10 letters from baseline to Study Week 12. The record lists four outcome measures overall, but does not provide a complete account of all their results or their analysis.

When a study tests multiple endpoints, time points, or treatment comparisons, the chance of at least one apparently positive result can increase if each is assessed independently. General approaches to multiplicity include prespecifying a primary comparison, adjusting significance thresholds, or organizing tests in a hierarchy. The registry record does not report whether any multiplicity adjustment or testing hierarchy was used. It also does not report a statistical analysis plan, so the prespecified relationship among Part A, Part B, the time points, and the secondary outcomes cannot be determined.

For missing data, the primary endpoint description states that the last observation before dropout or rescue treatment was carried forward. It does not report the number of missing observations or the reasons for missingness. Sensitivity analyses and other missing-data approaches are not reported in the registry record. The Full Analysis Set is defined as participants who received at least one dose of study medication. The number analyzed in that set, and whether other populations such as an intention-to-treat or per-protocol population were used, are not reported.

The registry lists zero analyses for the primary outcome and indicates that fewer than two arms were available for it. Thus, the record supplies neither an analysis across groups nor a basis for evaluating multiplicity in reported test results. The presence of a primary endpoint definition does not establish that its results were analyzed or posted.

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: acute myocardial infarction (2.0%), ankle fracture (2.0%), visual acuity tests abnormal (2.0%).

For Part A regorafenib, the registry lists 51 participants at risk for serious adverse events, with 3 affected. It separately lists 51 participants at risk for other adverse events, with 11 affected. These categories are reported separately and should not be combined or interpreted as a count of unique participants. The registry does not define further how events were attributed or classified for these figures.

The listed serious adverse-event terms are acute myocardial infarction, ankle fracture, and visual acuity tests abnormal; each is reported as 2.0%. The record does not establish that these events were caused by regorafenib. An adverse event occurring during a trial is not, by itself, proof of a causal relationship to treatment. The record also does not provide comparative safety counts for the other listed regimens in the adverse-event summary.

Deaths are not reported in the registry record. The safety figures describe reported events in the Part A regorafenib group; they do not replace the missing primary visual-acuity analysis. Without comparative data, details about event timing, severity beyond the serious-event designation, and attribution, these counts cannot support a treatment-versus-comparator safety estimate.

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

The record establishes that a randomized, quadruple-masked, parallel-group Phase 2 study was planned to investigate topical regorafenib in neovascular age-related macular degeneration. It describes a Part A Week 4 visual-acuity endpoint, Part B dose-frequency objectives, and a ranibizumab regimen. It also records enrollment of 52 and a terminated status. These design features explain the clinical question the investigators set out to study, but they do not answer it.

The primary endpoint results are not reported in the registry record. Consequently, no estimate of visual-acuity change, comparison between treatment groups, uncertainty interval, or significance test can be interpreted. The record does not demonstrate that regorafenib improved vision, nor does it demonstrate that it did not. Absence of a posted endpoint analysis is not equivalent to a result showing no effect.

Likewise, the safety counts are descriptive reports for Part A regorafenib. They cannot establish whether the listed events were more or less common under another regimen, and they do not establish causation. The registry does not provide comparative safety estimates in the adverse-event summary. The reported serious-event terms and percentages should be read as registry entries, not as proof that treatment caused those events or as a full account of the study’s safety experience.

In general, a persuasive interpretation of a clinical trial requires estimates that connect the assigned groups to measured outcomes, with enough information to assess precision, missingness, analysis choices, and possible bias. This record gives some endpoint and design definitions but lacks primary outcome estimates and details of the analysis plan. The enrollment figure cannot fill that gap: the number enrolled does not reveal the group-specific outcome values or how precisely any effect was estimated.

The study may still be informative about the questions investigators intended to examine, the design used, and the reported safety entries. However, the registry record alone does not support a conclusion about efficacy, comparative benefit, or treatment-related harm. The termination reason, the trial’s sample-size justification, and a complete account of the results are not reported in the registry record.

14. Why This Trial Matters Statistically

This trial is statistically notable because the registry contains a defined primary outcome but no reported primary outcome analysis. That distinction matters: a protocol objective tells readers what investigators intended to measure, while an outcome estimate is needed to judge what the observed data indicate. Without the estimate, the statistical question remains unanswered in this record.

The study’s design also raises interpretive issues that depend on information not reported. Randomization and quadruple masking are recorded, but the sequence-generation and masking procedures are not described. The primary outcome population is defined as participants who received at least one dose, while the number analyzed is unavailable. These details affect how readers evaluate protection against bias and the relationship between enrollment and the analyzed population.

The Part A endpoint concerns a continuous score measured over time, and the record specifies a mean and standard deviation as summary measures. It also identifies a last-observation-carried-forward rule for participants who dropped out or received rescue treatment. Such a rule can influence estimates when later outcomes differ from earlier measurements, making transparency about missingness and sensitivity analyses important. Those details are not available in the record.

The objectives include multiple study parts, time points, dosing schedules, and safety outcomes. In general, clear reporting of the analysis hierarchy and multiplicity approach helps readers understand how confirmatory claims should be judged. The registry does not report that approach. The missing primary results prevent readers from assessing the treatment contrast, its precision, or the relationship between any result and the stated objectives.

These features make the record useful for understanding the intended design while also illustrating a limit of registry-based interpretation: a description of a trial cannot substitute for reported outcome estimates. Statistical conclusions require the actual analyzed data and enough methodological detail to understand their uncertainty.

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 interpreting this trial is that the registry does not report the primary endpoint results. Although it defines the Week 4 BCVA change, measurement scale, analysis population, and a missing-data rule, it gives no group summaries, contrast, confidence interval, or test result. This prevents evaluation of the main visual-acuity question.

The record lists enrollment of 52, but does not provide the number analyzed in the Full Analysis Set or the endpoint-specific denominators. It does not report the number of participants with missing measurements, dropout, or rescue treatment. The extent to which the stated last-observation-carried-forward rule affected the results therefore cannot be evaluated.

Design and analysis details are also limited. The registry records randomized allocation, quadruple masking, and a parallel model, but sequence generation, allocation concealment, masking procedures, and the primary statistical model are not reported. The registry does not state whether the analysis was adjusted, whether interim analyses occurred, or how multiple endpoints and time points were handled. The trial’s sample-size justification is not reported in the registry record.

The status is listed as terminated, but the reason is not reported. The registry does not provide enough information to determine how termination related to recruitment, safety, operational issues, or outcome findings. The adverse-event summary is limited to Part A regorafenib and does not provide comparative safety results for the other listed regimens. These gaps restrict both efficacy and safety interpretation; they should not be filled by assumptions about trial conduct or results.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Regorafenib Eye Drops: Investigation of Efficacy and Safety in Neovascular Age Related Macular Degeneration — NCT02222207.
• Registry record last updated 2016-09-08; status last verified 2016-07.
• Results first posted 2016-09-08.
• 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

NCT02222207 is a randomized, quadruple-masked, parallel-group Phase 2 study of regorafenib eye drops for treatment-naïve subjects with neovascular age-related macular degeneration. The registry lists enrollment of 52, a start date of 2014-10, primary completion in 2015-05, and a terminated status.

Part A’s primary endpoint was change from baseline in ETDRS best corrected visual acuity at Week 4. Part B was intended to examine different dosing schedules. The registry describes ranibizumab with placebo drops as a comparator regimen and sham intravitreal therapy with regorafenib in Part B. Primary endpoint results and the reason for termination are not reported in the registry record.

The record includes Part A regorafenib adverse-event counts, but no comparative safety analysis. It defines a Full Analysis Set and a last-observation-carried-forward rule for dropout or rescue treatment. The analysis methods, sample-size justification, multiplicity approach, and missing-data counts are not reported.