Laser-Ranibizumab-Triamcinolone for Proliferative Diabetic Retinopathy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Laser-Ranibizumab-Triamcinolone for Proliferative Diabetic Retinopathy (NCT00445003), a randomized phase 3 study. The primary outcome is Change in Electronic Early Treatment Diabetic Retinopathy Study Visual Acuity Letter Score From Baseline to 14 Weeks.

2. Clinical Question

3. Trial Design

This was a phase 3, randomized, double-masked, parallel-group trial. The registry lists 333 participants enrolled and the study status as completed. The recorded start was 2007-03, and primary completion was 2009-10. The sponsor was Jaeb Center for Health Research. Further details about sites, recruitment, or the original statistical design assumptions are not reported in the registry record.

The three groups were sham injection, 0.5mg ranibizumab, and 4-mg triamcinolone acetonide. Sham injections were given at baseline and 4 weeks. Ranibizumab injections were given at baseline and 4 weeks. The triamcinolone group received the active injection at baseline and a sham injection at 4 weeks. All treatment groups also received focal/grid laser for diabetic macular edema 3 days to 10 days after the injection. The registry describes the study as evaluating injections adjunctive to panretinal photocoagulation; the exact panretinal photocoagulation regimen is not reported in the registry record.

The eye-level structure matters for interpreting group counts. Participants with two study eyes could have each eye enrolled in a different arm, while each arm included no more than one study eye for a given participant. The primary outcome description says that the number of eyes was equal to the number of participants in each arm. This design detail means the treatment comparisons are organized by study eye, with the participant contributing eyes to different groups in some cases. The record does not state further details about whether or how within-participant dependence was addressed in every analysis.

The stated primary outcome was change in visual-acuity letter score from baseline to 14 weeks. Secondary outcomes include visual acuity at a later time and retinal measurements, as well as additional treatment measures for diabetic macular edema. Detailed numerical results are available for only some of those listed secondary outcomes; other details are not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: Participants with 2 study eyes enrolled each eye in a different arm. Each treatment arm includes no more than 1 study eye for a given participant, and thus the numbers of eyes is equal to the number of participants in each arm.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Participants with 2 study eyes enrolled each eye in a different arm. Each arm includes no more than 1 study eye for a given participant, and thus the numbers of eyes is equal to the number of participants in each arm. Analysis followed intention to treat principle; eyes without 14-week data, the Last Observation Carried Forward method was used.

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 in Electronic Early Treatment Diabetic Retinopathy Study Visual Acuity Letter Score From Baseline to 14 Weeks, measured over baseline to 14 weeks.

The primary endpoint was change in electronic Early Treatment Diabetic Retinopathy Study visual-acuity letter score from baseline to 14 weeks. Visual acuity was assessed using the E-ETDRS test, with scores on a scale from 0, the worst score, to 97, the best score. A change score describes how the measured letter score at follow-up differs from the participant’s baseline score. A positive group mean indicates an average increase in score from baseline, while a negative group mean indicates an average decrease.

Visual acuity is used because the registry’s central clinical question concerns vision loss after panretinal photocoagulation. It is a direct measure of the visual function being considered in that question, rather than an anatomical measurement of the retina. This makes it relevant to the study’s stated aim, while the retinal imaging outcomes provide different kinds of information. Neither type of endpoint alone captures every possible benefit or harm.

The primary outcome is reported as a mean with standard deviation. The mean describes the average change in each group, and the standard deviation describes how dispersed individual changes were around that average. The posted group means were -4.0 for sham injection, 1.0 for 0.5mg ranibizumab, and 2.0 for 4-mg triamcinolone acetonide. These are group summaries, not predictions about an individual participant’s result. The registry specifies an intention-to-treat analysis, but the complete description of how missing 14-week outcome data were handled is not reported in the registry record.

7. Results Posted in the Registry

• 0.5mg Ranibizumab: mean 1.00 versus -4.00 on control; difference 5.00 (95% CI 1.80 to 8.20), standardized effect d = 0.40; z-test p = 0.002.
• 4-mg Triamcinolone Acetonided: mean 2.00 versus -4.00 on control; difference 6.00 (95% CI 2.78 to 9.22), standardized effect d = 0.47; 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.

Total Optical Coherence Tomography Retinal Volume

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • 0.5mg Ranibizumab: mean 9.30 versus 9.70 on control; difference -0.40 (95% CI -1.02 to 0.22), standardized effect d = -0.22; z-test p = 0.210.
  • 4-mg Triamcinolone Acetonided: mean 7.90 versus 9.70 on control; difference -1.80 (95% CI -2.29 to -1.31), standardized effect d = -1.23; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 0.5mg Ranibizumab and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for 4-mg Triamcinolone Acetonided than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change in Visual Acuity From Baseline

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • 0.5mg Ranibizumab: mean -4.00 versus -6.00 on control; difference 2.00 (95% CI -3.28 to 7.28), standardized effect d = 0.11; z-test p = 0.457.
  • 4-mg Triamcinolone Acetonided: mean -5.00 versus -6.00 on control; difference 1.00 (95% CI -3.54 to 5.54), standardized effect d = 0.06; z-test p = 0.666.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 0.5mg Ranibizumab and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 4-mg Triamcinolone Acetonided and the control. The interval gives the range of effects that remain compatible with the data.

Change in Optical Coherence Tomography Retinal Volume

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • 0.5mg Ranibizumab: mean -0.40 versus 0.10 on control; difference -0.50 (95% CI -0.91 to -0.09), standardized effect d = -0.42; z-test p = 0.016.
  • 4-mg Triamcinolone Acetonided: mean -1.30 versus 0.10 on control; difference -1.40 (95% CI -1.81 to -0.99), standardized effect d = -1.16; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for 0.5mg Ranibizumab than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for 4-mg Triamcinolone Acetonided than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover more than one domain: visual acuity at a later follow-up, optical coherence tomography measures of retinal volume and central subfield thickness, and additional treatments for diabetic macular edema. Seven secondary outcomes are listed in the registry, but detailed numerical records in the available data cover only some of them. Further numerical results or analysis details are not reported in the registry record.

Across the detailed results, the retinal measurements at 14 weeks generally show lower group means in the active-injection arms than in the sham arm. For the later visual-acuity outcome, the recalculated comparisons are less conclusive: their confidence intervals include zero. This is a different follow-up interval from the primary outcome and should not be treated as a direct substitute for it. The secondary results add context about anatomical outcomes and later vision, but they do not change the definition or timeframe of the primary endpoint.

Secondary outcomes are often numerous and can involve different measures, follow-up times, and analysis populations. When many comparisons are examined, some may appear noteworthy by chance even if there is no underlying difference. The registry record does not report a multiplicity adjustment or a prespecified hierarchy for interpreting the secondary comparisons. Consequently, unadjusted secondary p-values carry less weight than a prespecified primary analysis, and the secondary pattern is best treated as supportive or exploratory rather than as a set of independent confirmatory conclusions.

Different secondary denominators also indicate that the available outcome data vary across measures. Those differences may reflect outcome-specific availability, but reasons and handling rules are not reported in the registry record. The outcomes should therefore be interpreted in their own stated populations and timeframes, rather than assuming identical coverage across all measures.

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

• Additional Treatments for Diabetic Macular Edema
• Change in Optical Coherence Tomography Central Subfield Thickness
• Total Optical Coherence Tomography Retinal Volume
• Change in Visual Acuity From Baseline
• Eyes With Anti-vascular Endothelial Growth Factor Treatment for Diabetic Macular Edema
• Number of Eyes With Additional Number of Treatments for Diabetic Macular Edema
• Change in Optical Coherence Tomography Retinal Volume

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: it is a numerical letter score, and the reported group summary is a mean. A mean difference compares the average outcome in one group with the average outcome in another. For the simple recalculation, the comparison is expressed as the injection group’s mean change minus the sham group’s mean change. A positive estimate therefore indicates a higher average change score in the injection group. This direction describes the arithmetic of the endpoint; it is not, by itself, a conclusion about overall clinical value.

What does the confidence interval describe?

A confidence interval expresses the statistical uncertainty around an estimated difference. The 95% intervals for both recalculated primary comparisons are entirely above zero. Under the assumptions of the calculation, this indicates that the estimates are not especially compatible with a zero difference. The interval also communicates a range of effect sizes compatible with the data and method, rather than only a single point estimate. It does not mean that 95% of individual participants had changes inside that range, nor does it include every source of uncertainty in trial conduct or analysis.

Why are there two sets of primary estimates?

The recalculated comparisons use posted group means, standard deviations, and group sizes to produce simple unadjusted comparisons. The registry’s reported results use ANCOVA and are described as mean differences in final values. ANCOVA is a regression-based approach that can compare groups while accounting for covariates included in the model. The registry does not identify the complete covariate specification in the information. Because the methods differ, the estimated differences and confidence intervals need not match exactly. The ANCOVA estimates are the analyses reported by the sponsor; the recalculations are a separate, unadjusted summary-based view.

A p-value summarizes how incompatible the observed data are with a specified null model, given the assumptions of the analysis. It is not the probability that the null hypothesis is true, and it does not measure the probability that a result will replicate. The recalculated unadjusted p-values for the primary comparisons are 0.002 and <0.001. The sponsor-reported ANCOVA p-values are <.001 for both comparisons. These should not be treated as interchangeable, because they arise from different calculations.

Why does spread matter?

The standard deviation describes how variable the observed changes are within a group. Larger spread means individual outcomes are more dispersed around the group mean. When spread is large relative to the group difference, an estimated mean difference will generally be less precise unless the analysis includes more information or more observations. The primary outcome standard deviations are 14.0, 11.0, and 11.0 for sham, ranibizumab, and triamcinolone, respectively. Those values help put the average differences in context, but they do not show the shape of the outcome distribution or whether there are influential observations.

General statistical explanation: a mean-based comparison is most straightforward to interpret when the mean is a useful summary of the outcome distribution and the model assumptions are reasonable. The registry record does not report diagnostic checks, a detailed modeling specification, or sensitivity analyses for the primary endpoint. It is therefore not possible to assess those aspects from the reported summaries alone.

How should the eye-level structure be considered?

Some participants contributed two study eyes, and the two eyes could be allocated to different arms. The record states that each arm contained no more than one study eye per participant. This arrangement avoids placing both eyes from one participant in the same arm, but two eyes from one person may still share characteristics. The registry record does not report the full analysis details needed to determine exactly how any correlation between a participant’s eyes was handled in each model. That issue is relevant to the precision of eye-level comparisons.

The registry identifies the primary analysis as intention to treat. In general, intention-to-treat analysis aims to retain participants or assigned units in their randomized groups for analysis. The primary outcome description is truncated after mentioning eyes without 14-week data, so the exact missing-data rule is not reported in the registry record. No particular imputation method or assumption about missing outcomes should be inferred from the available description.

11. Confidence Intervals and Precision

The primary recalculated mean difference for 0.5mg ranibizumab versus sham is 5.0 letter-score points, with a 95% confidence interval from 1.801 to 8.199. For 4-mg triamcinolone acetonide versus sham, it is 6.0 points, with a 95% confidence interval from 2.777 to 9.223. Both intervals are above zero, while their widths also show that the data do not identify a single exact difference. The intervals describe uncertainty in the estimated group averages under the unadjusted calculation, not the range of individual outcomes.

The sponsor’s ANCOVA estimates have 95% confidence intervals from 2.2 to 9.0 for ranibizumab versus sham, and from 3.2 to 10.1 for triamcinolone versus sham. These intervals also lie above zero. The differences between the ANCOVA and recalculated intervals reflect that the analyses are not identical; the registry does not report enough model detail to attribute the differences to a particular adjustment or assumption.

Precision should be considered alongside the observed group variation and the outcome timeframe. The primary outcome covers baseline to 14 weeks, and each group’s change-score standard deviation is reported. A confidence interval around a mean difference is not a guarantee that the true effect lies within that interval. It quantifies sampling uncertainty under the analysis assumptions, while possible limitations in outcome availability, modeling, and the eye-level structure are separate considerations. Details needed to assess some of those issues are not reported in the registry record.

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 participants per arm, not total event counts. They are illustrations calculated from the observed effect rather than the trial’s original design justification. The assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The planning scenarios use 100%, 75%, or 50% of the observed effect as the effect to detect. The original trial’s own sample-size assumptions are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% probability of detecting the stated effect under the planning assumptions, if that effect and the assumptions hold. The 90% power column gives the corresponding planning number for a 90% probability. These are design calculations, not descriptions of what happened in this completed trial. They are not observed power.

The 75% and 50% scenarios represent smaller target effects than the full observed effect. Smaller effects are harder to distinguish from random variation, so they require more participants per arm under the same planning assumptions. The figures should be read as conditional planning illustrations: they depend on the observed estimate being a reasonable basis for a future target and on the simplified assumptions being suitable. They do not establish that a future study would obtain the same effect, or that the original investigators planned the trial using these calculations.

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 = 5.000; pooled standard deviation σ = 12.653.
2. n = 2 × (1.96 + 0.842)² × 12.653² / 5.000² = 100.5, rounded up to 101 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 <- 5                      # observed difference in means
sigma <- 12.6531641932982                     # 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(445003)
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 = 101 (80% power), 135 (90% power)
 75% of observed effect: n per arm = 179 (80% power), 240 (90% power)
 50% of observed effect: n per arm = 403 (80% power), 539 (90% power)
power.t.test: 101.5 
Simulated power at n = 101 per arm: 0.801 (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 reports the sponsor’s primary comparisons from ANCOVA as mean differences in final values. The ranibizumab comparison is 5.6, with a 95% confidence interval from 2.2 to 9.0 and p <.001. The triamcinolone comparison is 6.7, with a 95% confidence interval from 3.2 to 10.1 and p <.001. These are the trial’s reported model-based analyses.

The recalculated comparisons use the posted group means and standard deviations to estimate unadjusted differences in mean change. They are 5.0 for ranibizumab versus sham and 6.0 for triamcinolone versus sham, with their corresponding unadjusted confidence intervals. The estimates are close in direction and broad scale, but they are not identical to the ANCOVA results. A final-value ANCOVA and a simple comparison of change-score summaries can differ because they are different estimators and may account for baseline information differently.

The registry does not report the full ANCOVA specification, including all covariates and modeling details. The recalculation therefore cannot reproduce the sponsor’s analysis from the posted summary statistics. The sponsor’s p-values should be understood as results of the reported ANCOVA, while recalculated p-values are unadjusted checks based on summary data. The registry record indicates no discrepancy flag, but this does not make the methods interchangeable or remove the need to distinguish the two analyses.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates more than one outcome, comparison, or follow-up time. Even if each test uses a conventional significance threshold, conducting many tests increases the chance that at least one result will appear statistically notable by chance. This is why a prespecified primary endpoint is important: it identifies the main question to be interpreted, while secondary findings ordinarily need more caution unless a testing hierarchy or adjustment plan was specified.

The registry lists multiple secondary outcomes, and the posted results include comparisons across treatment groups and follow-up measures. A multiplicity correction, gatekeeping strategy, or other formal plan for controlling the overall error rate is not reported in the registry record. The primary and secondary results should therefore not be read as if every p-value had the same confirmatory status. The reported primary ANCOVA results address the designated primary endpoint; secondary p-values are less definitive without a stated multiplicity plan.

The primary outcome description identifies an intention-to-treat analysis, but the registry text available for the outcome is incomplete after it begins describing eyes without 14-week data. The method for handling missing primary outcomes is not reported in the registry record. Specific imputation methods, assumptions about missingness, or sensitivity analyses should not be inferred. The record also does not provide a complete account of missing-data handling for each secondary endpoint.

Analysis populations are not fully described beyond the primary outcome’s intention-to-treat statement and the eye-level details. Some participants could contribute eyes to different treatment arms, and the registry says that each arm included no more than one study eye per participant. The exact modeling approach for dependence between eyes, as well as the participant-level population used for every secondary outcome, is not reported in the registry record. These omissions limit assessment of how the analysis accounted for the trial’s structure and outcome availability.

Details about interim analyses, a complete statistical analysis plan, protocol deviations, and sensitivity analyses are also not reported in the registry record. Their absence from the information does not establish that such procedures did or did not occur; it means that their role in the interpretation cannot be assessed from this record.

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: abdominal pain (0.9%), angina pectoris (0.9%), cerebrovascular accident (0.9%), cholelithiasis (0.9%), convulsion (0.9%).

The registry reports serious adverse events affected 11 participants in the sham-injection group, 15 in the 0.5mg ranibizumab group, and 12 in the 4-mg triamcinolone acetonide group. The corresponding numbers at risk are 133, 116, and 115. Other, non-serious adverse events affected 57, 50, and 66 participants, respectively, with the same group-specific numbers at risk as listed for those categories. These are reported counts; no additional rates or comparisons are calculated.

The registry lists several serious adverse-event terms at 0.9%: abdominal pain, angina pectoris, cerebrovascular accident, cholelithiasis, convulsion, and coronary artery disease. The record does not provide further detail in these data about severity, timing, relatedness to treatment, or how the terms were distributed among groups. Death counts are not reported in the registry record.

Adverse-event counts are not, by themselves, a complete comparison of safety. The at-risk counts differ by group, and the registry summary does not provide enough detail to characterize event duration, recurrence, attribution, or the full clinical context. These results should be read as a registry summary of reported events, not as a comprehensive assessment of relative safety.

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

The primary results show that the posted average visual-acuity change at 14 weeks was higher in each injection group than in the sham-injection group. The simple unadjusted mean differences are positive, and the confidence intervals for both comparisons are above zero. The sponsor’s reported ANCOVA comparisons also have confidence intervals above zero. These statements describe the measured endpoint, observed groups, and statistical uncertainty in the reported analyses.

They do not establish what an individual participant would experience. Group averages can coexist with a wide range of individual outcomes, as reflected by the reported standard deviations. Nor do these estimates alone establish whether any difference is important to participants or outweighs potential harms. The posted primary outcome concerns a specific visual-acuity scale and a specific follow-up interval; it does not answer every question about vision, retinal anatomy, treatment burden, or longer-term outcomes.

The trial compares each active injection strategy with sham injection alongside laser care. It does not provide a direct randomized comparison between ranibizumab and triamcinolone in the primary comparisons. The numerical ordering of the group means should not be interpreted as establishing one active treatment as superior to the other.

The separate later visual-acuity outcome and retinal imaging outcomes provide additional, but distinct, information. Their measures, available group counts, and timeframes differ from the primary endpoint. Because a multiplicity plan and full missing-data methods are not reported in the registry record, secondary findings should be interpreted cautiously and should not be given the same weight as the designated primary analysis.

Overall, the registry results describe differences in average measured outcomes under the trial conditions. They do not by themselves establish the complete clinical balance of benefits and risks, explain results in groups not described in the registry record, or provide treatment advice. The record’s limitations in statistical-plan and outcome-handling detail also mean that some aspects of precision and robustness cannot be fully evaluated.

18. Why This Trial Matters Statistically

This trial raises several statistical issues that are common in clinical research. First, its primary outcome is a change score, while the sponsor’s reported analysis is an ANCOVA comparison of final values. These methods can use baseline information differently and produce estimates that are not numerically identical. Showing both the registry-reported analysis and a simple summary-based recalculation helps distinguish the sponsor’s model-based result from an unadjusted check.

Second, the unit of analysis requires attention. The treatment groups are organized by study eye, and a participant with two study eyes could contribute one eye to each of two arms. The registry’s statement that each arm contains no more than one eye per participant is important context, but full details on handling dependence between eyes are not reported. That affects how confidently the precision of eye-level estimates can be assessed.

Third, the study includes multiple secondary outcomes and follow-up intervals. Without a reported multiplicity plan, secondary p-values cannot all be treated as confirmatory evidence. This reinforces the importance of distinguishing a designated primary question from a wider set of supportive measurements.

Finally, the results illustrate that statistical significance and precision are related but different. A confidence interval can indicate the range of estimates compatible with the data and method, while clinical interpretation also depends on endpoint meaning, variation, missingness, safety, and the study’s broader design. The registry provides useful numerical results, but some analysis details needed for a fuller assessment are not reported in the registry record.

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.

Several limitations are specific to the information reported for this trial. The primary outcome description is incomplete: it states that the analysis followed the intention-to-treat principle and begins to mention eyes without 14-week data, but the remaining text is truncated. The missing-data rule and any sensitivity analyses are not reported in the registry record. This prevents a full assessment of how incomplete follow-up may have influenced the primary estimate.

The registry reports sponsor ANCOVA results but does not provide the full model specification in the available record. The covariates, handling of baseline measurements, and other modeling details are not reported. The summary-based recalculation is consequently a separate unadjusted analysis, not a reconstruction of the sponsor’s model.

The eye-level design also warrants caution. Some participants could contribute two eyes allocated to different arms. The record gives the allocation structure but does not report the exact method used to account for any correlation between eyes within the same participant in each analysis. The group counts for secondary measures also vary, and reasons for outcome-specific availability are not reported.

The registry lists seven secondary outcomes, but detailed results are not available for all of them in the information used for this interpretation. A multiplicity adjustment and a detailed prespecified hierarchy are not reported. The adverse-event summary gives group counts and selected terms but does not provide a full account of timing, treatment relatedness, or clinical context. These limitations restrict what can be concluded from the registry summaries without implying that unreported procedures or information were absent from the study itself.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Laser-Ranibizumab-Triamcinolone for Proliferative Diabetic Retinopathy — NCT00445003.
• Registry record last updated 2016-08-26; status last verified 2016-08.
• Results first posted 2011-07-13.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

23. Record Summary

The registry record describes a completed, randomized, double-masked, parallel-group phase 3 trial sponsored by Jaeb Center for Health Research. It lists enrollment of 333, a start of 2007-03, and primary completion in 2009-10. The groups received sham injection, 0.5mg ranibizumab, or 4-mg triamcinolone acetonide, with focal/grid laser for diabetic macular edema in all treatment groups.

The primary outcome was change in E-ETDRS visual-acuity letter score from baseline to 14 weeks. The posted group summaries and sponsor-reported ANCOVA analyses show positive mean-difference estimates for each active injection group versus sham. Secondary outcomes cover later visual acuity, retinal imaging, and additional treatment measures. Details on multiplicity, full missing-data handling, and some analysis specifications are not reported in the registry record.