Assess the Efficacy/Safety of Intravitreal Ranibizumab in Patients With Vision Loss Due to Choroidal Neovascularization.: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Assess the Efficacy/Safety of Intravitreal Ranibizumab in Patients With Vision Loss Due to Choroidal Neovascularization. (NCT01840410), a randomized phase 3 study. The primary outcome is Change From Baseline in Best-corrected Visual Acuity (BCVA) in Study Eye to Month 2.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group, Phase 3 study with a planned 12-month duration. The official title describes a double-masked, sham-controlled, multicenter study. The registry metadata lists masking as triple. The record does not identify which groups of people were masked, so these descriptions cannot be reconciled further from the registry information.

The study compared 0.5 mg ranibizumab intravitreal injections with sham injection in patients with visual impairment due to CNV. In the ranibizumab group, injections began at baseline and subsequent injections were given as needed according to disease activity. In the sham-control group, the baseline procedure was sham. If treatment was needed at Month 1, sham was administered; at Month 2, participants could switch to open-label ranibizumab as needed. This change in treatment strategy matters when interpreting later comparisons: the primary endpoint was assessed at Month 2, while the treatment options could change after baseline.

The registry reports enrollment of 183. The study start is recorded as 2013-09, primary completion as 2015-11, and status as completed. The primary endpoint was change from baseline in BCVA in the study eye to Month 2. The registry also lists secondary measures involving visual acuity, retinal structure, fluid, leakage, and rescue treatment. Detailed eligibility criteria, allocation ratios, and the trial's original sample-size justification are not reported in the registry record.

The primary analysis population was the full analysis set, described as all randomized participants, with only participants who had data at both baseline and Month 2 analyzed. The arm counts in the primary results are 118 for ranibizumab and 57 for sham control. These are the analyzed counts for this endpoint and should not be interpreted as the total randomized 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.

Before assignment: A total of 183 participants were enrolled. Of these, 178 adults were randomized in a 2:1 ratio and considered for analysis. There were 5 adolescent participants, non-randomized, who received open-label treatment and were not included in the analyses. Therefore, the number enrolled = 183 differs from the participant flow number started = 178.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The full analysis set (FAS) was considered for the analysis. The FAS included all participants who were randomized to treatment. Only participants, with available data at both baseline and Month 2, were analyzed.

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) in Study Eye to Month 2, measured over Baseline, Month 2.

The primary endpoint was change from baseline in best-corrected visual acuity (BCVA) in the study eye to Month 2, measured in letters. BCVA is a standardized assessment of how many letters a participant can read on a visual acuity chart under the testing conditions. The registry describes testing in a sitting position using Early Treatment Diabetic Retinopathy Study (ETDRS)-like charts, with an initial testing distance of 4 meters.

Change from baseline expresses the follow-up measurement relative to each participant's starting measurement. The registry specifies that a positive change indicates improvement. Comparing average changes between randomized groups provides a way to estimate the difference in short-term visual acuity outcomes under the assigned treatment strategies.

This endpoint is useful for a randomized comparison because it is a continuous measure, so the analysis can represent both the direction and average size of change rather than only classifying participants as improved or not improved. The endpoint concerns the study eye and the Month 2 assessment; it does not summarize every aspect of vision, longer-term outcomes, or individual experiences. The registry lists other visual and anatomical outcomes, but BCVA change to Month 2 is the designated primary measure described in the record.

7. Results Posted in the Registry

• Ranibizumab: mean 9.50 versus -0.40 on control; difference 9.90 (95% CI 6.96 to 12.84), standardized effect d = 1.01; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Number of Participants With Requirement for Rescue Treatment at Month 1

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Ranibizumab: 0.0% (0/119) versus 1.7% (1/58) on control; risk difference -1.7 percentage points (95% CI -5.1 to 1.6); unadjusted two-proportion z-test p = 0.151.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Ranibizumab and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists secondary outcomes spanning additional BCVA assessments, retinal thickness and volume, the presence of intra-retinal or subretinal fluid, active chorioretinal leakage, letter-gain categories, and rescue treatment. These measures address related but distinct aspects of visual acuity, retinal anatomy, disease activity, and treatment use. They can add context to the primary BCVA comparison, but they do not measure the same outcome or necessarily answer the same question.

Detailed numerical results are not reported in the registry record for most of the listed secondary outcomes. The available rescue-treatment result concerns Month 1: 0 of 119 participants in the ranibizumab group and 1 of 58 in the sham-control group were reported as requiring rescue treatment. The unadjusted risk difference is -0.017, with a 95% confidence interval from -0.051 to 0.016 and p = 0.151. This estimate is not statistically distinct from zero at conventional levels based on the reported unadjusted test, and its interval includes differences in either direction.

The primary result and the secondary outcomes should be considered together only with attention to their different measures, time points, and levels of reporting. The secondary endpoint list alone cannot establish that anatomical or other outcomes followed a particular pattern. For most listed secondary measures, the results needed to characterize such a pattern are not reported in the registry record.

Secondary tests also raise a multiplicity issue: when several outcomes or comparisons are examined, the chance of at least one apparently unusual result can increase. The registry record does not report a multiplicity adjustment for the secondary analyses. Consequently, any unadjusted secondary p-values, where reported, carry less confirmatory weight than a prespecified primary analysis with a defined inferential role. Secondary outcomes can still be informative, but they are better treated as supporting or exploratory evidence unless an analysis plan establishes otherwise.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Change From Baseline in BCVA in Study Eye up to Month 2
• Change From Baseline in Central Subfield Thickness (CSFT) in Study Eye
• Change From Baseline in Central Subfield Volume (CSFV) in Study Eye
• Number of Participants With Presence of Intra-retinal Fluid in Study Eye Compared to Baseline
• Number of Participants With Presence of Subretinal Fluid in Study Eye Compared to Baseline
• Number of Participants With Presence of Active Chorioretinal Leakage
• Average Change From Baseline in BCVA
• Number of Participants With ≥ 1, ≥ 5, ≥ 10 and ≥ 15 Letters Gain or Reaching 84 Letters

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: each participant's BCVA change is measured in letters, and the analysis estimates group means and a between-group contrast. Continuous outcomes preserve information about the magnitude and direction of measured change. A mean difference is expressed in the same units as the outcome, so the reported contrast is in letters. It represents the modeled difference between groups, not a count of participants who improved.

Why use a repeated-measures model?

The registry says that the primary data were analyzed using mixed model repeated measures (MMRM). In general, a repeated-measures model is used when outcomes are collected at scheduled visits and the analysis needs to represent measurements over time. It can model the relationship among a participant's repeated measurements rather than treating each visit as an unrelated observation. The registry describes scheduled visit as a fixed effect, although the primary endpoint is the change to Month 2.

The listed model also includes treatment group and a category for the underlying pathophysiologic mechanism—angloid streaks versus others—as fixed-effect factors. Centered baseline BCVA is included as a continuous covariate. In general, including a baseline measure can account for differences in starting values and improve the precision of an estimated follow-up contrast. Centering means expressing the baseline covariate relative to a reference value used by the model; the reference value and further implementation details are not reported in the registry record.

The model includes treatment group by visit and visit by centered baseline BCVA interactions. In general, an interaction allows the association of one model term with the outcome to vary across levels of another term. Here, the listed treatment-by-visit term allows modeled treatment differences to vary by visit, while the visit-by-baseline term allows the relationship between baseline BCVA and outcome to vary by visit. The record does not give additional detail about the model's covariance structure, estimation procedure, or diagnostic checks.

What does the reported mean difference represent?

The registry reports a mean difference (net) from a mixed-model analysis, along with a 95% confidence interval and p-value. A modeled mean is an estimate produced by the specified statistical model, rather than necessarily the raw arithmetic average of all observed values. The displayed arm-level least-squares means are 9.5 letters for ranibizumab and -0.4 letters for sham control. The reported net difference is 9.94 letters. The modeled contrast is the principal comparison for interpreting the primary result.

The unadjusted recalculation uses the posted arm summaries to estimate a difference in means and its uncertainty. It relies on an approximate pooled standard deviation reconstructed from the reported standard errors and sample sizes. It does not incorporate the model terms described for the sponsor's MMRM. In general, adjustment and repeated-measures modeling may produce estimates or uncertainty that differ from a simple summary-statistic calculation. The recalculated result is therefore best treated as a separate, approximate check on the scale of the group contrast.

What do the p-value and confidence interval say?

A p-value summarizes how incompatible the observed data are with a specified null model, assuming the statistical model and its assumptions are appropriate. It is not the probability that the treatment has no effect, nor does it quantify the chance that the reported estimate is correct. The reported p-value for the primary analysis is <0.001. The recalculated unadjusted p-value is also <0.001, but it comes from a different, simpler analysis.

A confidence interval gives a range of values compatible with the data and analysis under a repeated-sampling interpretation. Its width reflects statistical precision: narrower intervals indicate more precise estimates than wider intervals, all else equal. The reported 95% interval for the mixed-model contrast is 6.97 to 12.91 letters. It describes uncertainty in the estimated group mean difference, not the spread of individual participant outcomes.

Why does over-dispersion matter in general?

Over-dispersion is a general concern for count or binary data when the observed variability exceeds what a simple probability model expects. It can make standard errors too small if ignored, leading to confidence intervals that are too narrow and p-values that appear more compelling than warranted. The primary BCVA endpoint is continuous, and the registry does not report an over-dispersion adjustment for it. This concept is more relevant to some count or binary outcomes and should not be assumed to have affected the primary analysis.

The registry's analysis population included randomized participants with available data at both baseline and Month 2. In general, restricting an analysis to people with observed measurements can affect interpretation if missingness is related to outcomes or treatment. The record does not state how missing data were handled beyond specifying which participants were analyzed, nor does it report sensitivity analyses for missing outcomes. Model details, protocol deviations, and checks of assumptions are also not reported in the registry record.

11. Confidence Intervals and Precision

The sponsor-reported mean difference is 9.94 letters, with a 95% confidence interval from 6.97 to 12.91. This interval conveys uncertainty in the estimated average contrast between the groups under the reported mixed-model analysis. It does not describe the range of individual participant changes, and it should not be read as guaranteeing that a future study's estimate will fall within these limits.

The interval lies on the positive side of zero, while the reported p-value is <0.001. Together, these statistics indicate that the fitted model estimated a positive difference and that the data were not compatible with a zero contrast under the model at the conventional levels represented by the reported test. Statistical precision is not the same as certainty about every clinical implication: the interval concerns one endpoint, one assessment time, and the analyzed population.

The recalculated unadjusted estimate is 9.9 letters, with a 95% confidence interval from 6.961 to 12.84. Its reported unadjusted p-value is <0.001. The recalculated interval is based on summary statistics and an approximate pooled standard deviation, rather than the MMRM covariates and repeated-measures structure. Its precision should therefore be interpreted as belonging to that simplified calculation, not as an additional model-based interval for the sponsor's analysis.

The primary analysis used 118 ranibizumab participants and 57 sham-control participants with the required baseline and Month 2 data. The unequal analyzed counts are relevant context for interpreting precision, but the registry record does not give a separate precision assessment by subgroup or a sensitivity analysis for missing measurements. Neither confidence interval describes variability in safety outcomes or uncertainty at later follow-up times.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are illustrations based on the observed primary effect, not the trial's original design calculation. The registry record does not report the trial's own sample-size assumptions or justification. For these illustrations, the stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; each planning scenario targets a specified fraction of the observed effect.

The columns for 80% and 90% power describe the number of participants per arm that the illustration estimates would be needed to detect the chosen effect size under those assumptions. In general, power is the probability of detecting an effect of the specified size if that effect is present and the assumed design and analysis conditions hold. The 90% power column represents a higher target probability of detection than the 80% column, and therefore has larger participant counts for each listed effect scenario.

The effect scenarios are planning for 100%, 75%, and 50% of the observed effect. Smaller effects need more participants to detect with the same target power and significance level. These counts are not observed enrollment or analyzed group sizes. This is not observed power: it is a planning illustration calculated from the observed effect, and it does not establish the probability that this completed trial detected its true effect.

The stated convention is participants per arm for continuous and other non-time-to-event outcomes; time-to-event calculations, when present, give total events. The primary endpoint is continuous, so its planning counts are per arm. The assumptions of equal allocation and normal approximation belong to the illustration and should not be mistaken for undocumented features of the original trial's design.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 9.900; pooled standard deviation σ = 9.841.
2. n = 2 × (1.96 + 0.842)² × 9.841² / 9.900² = 15.5, rounded up to 16 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- 9.9                      # observed difference in means
sigma <- 9.84124569162897                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(1840410)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 16 (80% power), 21 (90% power)
 75% of observed effect: n per arm = 28 (80% power), 37 (90% power)
 50% of observed effect: n per arm = 63 (80% power), 84 (90% power)
power.t.test: 16.5 
Simulated power at n = 16 per arm: 0.786 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The registry's reported primary analysis is a mixed-model analysis with a mean difference (net) of 9.94 letters, a 95% confidence interval of 6.97 to 12.91, and p < 0.001. This is the sponsor-reported analysis for the primary endpoint. It uses the MMRM described in the record, including scheduled visit, treatment group, pathophysiologic mechanism category, centered baseline BCVA, and the listed interactions.

The unadjusted recalculation from the posted arm summaries estimates a mean difference of 9.9 letters, with a 95% confidence interval of 6.961 to 12.84 and p < 0.001. It is a simpler calculation based on arm-level summaries and an approximate pooled standard deviation. It does not reproduce the sponsor's specified repeated-measures model or its covariate structure.

The two estimates are close in magnitude, but they are not identical. Their confidence intervals also come from different calculations. The registry record does not give a further explanation for the numerical differences, so they should not be attributed to a particular modeling choice beyond the documented distinction between the mixed-model analysis and the unadjusted recalculation. The recalculation is useful as a statistical cross-check, but it is not a substitute for the sponsor's reported analysis.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary endpoint and lists secondary outcomes, with 14 outcome measures recorded and 13 secondary results posted. Testing multiple outcomes can increase the chance of a nominally small p-value arising by chance when each test is considered separately. The registry record does not report whether a multiplicity-control procedure was specified or applied, nor does it describe a hierarchy or gatekeeping strategy among the secondary outcomes. The rescue-treatment comparison is explicitly an unadjusted recalculation; an adjustment for the other secondary tests is not reported.

The primary population is described as the full analysis set: all randomized participants were included in the set, but only participants with available data at both baseline and Month 2 were analyzed for the primary endpoint. The displayed primary counts are 118 for ranibizumab and 57 for sham control. This definition makes clear that the primary endpoint analysis was based on observed data at both required assessments. The record does not report the number or characteristics of participants lacking one or both measurements, reasons for missingness, or a sensitivity analysis assessing how missing data might affect the estimate.

MMRM is the reported primary method, but the registry does not specify its covariance structure, the precise method used to handle missing repeated measurements, or the assumptions made about the missing-data process. The analysis description should therefore not be expanded into a claim that missing outcomes were handled in a particular way beyond what is stated. Additional details about protocol deviations, per-protocol analyses, interim analyses, and the statistical analysis plan are not reported in the registry record.

These reporting limits matter because analysis populations, missing measurements, and multiple comparisons affect how strongly results can be interpreted. The reported primary model and its interval remain the central statistical evidence for the designated endpoint, while unadjusted secondary findings should be read with greater caution.

16. 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: faecaloma (1.9%), pyrexia (1.9%), urosepsis (1.9%), rheumatic disorder (1.9%), hepatocellular carcinoma (1.9%).

The adverse-event record separates participants by treatment exposure: ranibizumab, sham with ranibizumab, and sham without ranibizumab. Serious adverse events were reported for 9 of 119 participants in the ranibizumab group, 4 of 52 in the sham-with-ranibizumab group, and 0 of 7 in the sham-without-ranibizumab group. Other adverse events were reported for 42 of 119, 19 of 52, and 4 of 7 participants, respectively. These are participant counts within the recorded groups; they are not rates adjusted for exposure time.

The sham groups reflect different treatment histories, including whether participants received ranibizumab, so they should not be treated as a single unchanged exposure group. The record lists serious-event terms including faecaloma, pyrexia, urosepsis, rheumatic disorder, hepatocellular carcinoma, and oliguria, each at 1.9%. It does not provide a causal attribution for these events in the information. Death counts are not reported in the registry record.

Safety counts describe events observed in this study and do not by themselves establish that an event was caused by a treatment. The small sham-without-ranibizumab group also means its count should be read in the context of the reported group size, without treating zero recorded serious events as proof that no risk exists.

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

The primary analysis estimates a positive average difference in BCVA change at Month 2 between the ranibizumab and sham-control groups. The sponsor-reported mixed-model mean difference is 9.94 letters, with a 95% confidence interval from 6.97 to 12.91 and p < 0.001. The arm-level least-squares means are 9.5 letters for ranibizumab and -0.4 letters for sham control. These results describe the analyzed group's average endpoint under the trial's specified treatment strategies.

The result does not mean that every participant experienced a change equal to the group mean, or that all participants improved. A group average can coexist with substantial variation among individual outcomes, and the registry record does not provide the distribution needed to describe that variation in detail. The interval quantifies uncertainty in the estimated group contrast, not the range of likely individual responses.

The primary endpoint is limited to the study eye and the change from baseline to Month 2. It does not establish the size or persistence of a difference at later times. The sham-control strategy could include open-label ranibizumab from Month 2, so later comparisons would need to be interpreted in light of those treatment changes. The posted primary result also does not answer every question about retinal anatomy, rescue treatment, safety, or outcomes beyond the measured endpoint.

The registry record reports a statistically clear model-based contrast, but statistical significance is not the same as a complete assessment of clinical importance, treatment burden, long-term effects, or individual benefit and risk. Those judgments require additional context and outcomes not contained in the primary comparison. No medical advice follows from these group-level statistics.

18. Why This Trial Matters Statistically

This trial illustrates several important statistical features of clinical research. First, the primary endpoint is a continuous measure of change from baseline, reported in its original unit of letters. That makes the group contrast interpretable as an average difference in the measured outcome rather than only a binary classification.

Second, the trial's primary analysis uses MMRM and includes baseline BCVA, visit, treatment group, and specified interactions. This makes the reported result a model-based estimate rather than a simple comparison of raw arm summaries. Comparing it with an unadjusted recalculation demonstrates why statistical methods need to be read alongside the estimate: two analyses can target a similar group contrast while using different information and assumptions.

Third, the confidence interval complements the p-value by conveying the range of values compatible with the model and observed data. The primary estimate is accompanied by both measures, allowing readers to consider direction, size, and precision rather than treating a threshold test as the whole result.

Finally, the record highlights interpretation issues beyond the primary test. Participants in the sham group could switch to open-label ranibizumab, the primary analysis required observed data at both baseline and Month 2, and multiple secondary outcomes were recorded without a reported multiplicity strategy. These details affect how results across time, analysis populations, and outcomes should be weighed. A careful statistical reading separates the designated primary finding from supportive or incompletely reported secondary evidence.

19. 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 endpoint is assessed at Month 2, so it provides a short-term comparison within a study planned for 12 months. The registry record does not report the primary estimate for later follow-up in the information described, and the primary result alone cannot establish how the group contrast changed over time. Later treatment changes are relevant: sham-control participants could switch to open-label ranibizumab at Month 2 on an as-needed basis.

The primary analysis includes participants with available measurements at both baseline and Month 2. The registry does not report the extent or reasons for missing primary measurements, or sensitivity analyses for missing data. The record also does not provide the model covariance structure or other implementation details needed to fully reproduce the MMRM.

Although the official title describes a double-masked study, the registry metadata lists triple masking. The record does not identify the masked parties, so the masking description cannot be clarified further. The allocation ratio and detailed eligibility criteria are also not reported in the registry record.

Most listed secondary outcomes do not have numerical results in the registry record. The multiplicity strategy for secondary testing is not reported, so secondary findings that are unadjusted should not carry the same confirmatory weight as the designated primary analysis. Safety groups also reflect different treatment exposures, and the sham-without-ranibizumab group includes 7 participants; its event counts therefore have limited context for broad comparisons. Death counts are not reported in the registry record.

The registry does not report the trial's original sample-size justification, interim analyses, or further statistical-plan details. The planning figures based on the observed primary effect are illustrations and cannot resolve these missing design details.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Assess the Efficacy/Safety of Intravitreal Ranibizumab in Patients With Vision Loss Due to Choroidal Neovascularization. — NCT01840410.
• Registry record last updated 2016-08-26; status last verified 2016-08.
• Results first posted 2016-08-26.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

23. Record Summary

NCT01840410 is a completed randomized, parallel-group Phase 3 study of intravitreal ranibizumab versus sham control for visual impairment due to CNV. The registry reports enrollment of 183 and a planned 12-month study. The primary endpoint was change from baseline to Month 2 in BCVA in the study eye, measured in letters.

The sponsor-reported MMRM analysis estimated a mean difference (net) of 9.94 letters, with a 95% confidence interval of 6.97 to 12.91 and p < 0.001. The primary analysis included participants with available data at both baseline and Month 2. A simpler unadjusted recalculation from arm summaries estimated a mean difference of 9.9 letters.

The registry lists secondary visual, anatomical, disease-activity, rescue-treatment, and safety outcomes. Numerical results for most secondary outcomes are not reported in the registry record. The original sample-size justification, multiplicity procedure, and several implementation details of the statistical analysis are also not reported.