Characteristics of Design and Analysis of Ophthalmic Randomized Controlled Trials

ABSTRACT

Objective

To evaluate the recent practice of design and statistical analysis of ophthalmic randomized clinical trials (RCTs).

Design

Review of 96 ophthalmic RCTs.

Method

Two authors reviewed primary result papers published January 2020 through December 2021 in Ophthalmology, JAMA Ophthalmology, American Journal of Ophthalmology, and British Journal of Ophthalmology. Data were extracted and analyzed for the characteristics of design (one-eye design, two-eye design, paired-eye design, subject design), sample size and power, and statistical analysis for inter-eye correlation adjustment, missing data, and correction for multiplicity.

Main Outcome Measures

Characteristics of trial design and statistical analysis.

Results

Among 96 RCTs, 50 (52%) used one-eye design, 21 (22%) two-eye design, 10 (10%) paired-eye design, and 15 (16%) subject design. In 31 trials of two-eye design or paired-eye design, 18 (58%) trials had suboptimal analysis of data from both eyes by analyzing data from one eye (n=10), taking the average of two eyes (n=2), analyzing two eyes separately (n=1), ignoring inter-eye correlation (n=3), or not specifying how two-eye data were analyzed (n=2), and 13 trials (42%) properly adjusted the inter-eye correlation by using the mixed effects model (n=6), paired t-test (n=5), generalized estimating equations (n=1) or marginal Cox regression model (n=1). Among 96 trials, 75 (78%) provided both sample size and statistical power estimation, but only 16 (17%) trials described statistical test for sample size or power estimation. Missing data in primary outcome occurred in 86 (90%) trials with a median missing data rate of 8%, 32 (37%) trials applied statistical methods for missing data, including last value carried forward (n=10), multiple imputation (n=14) or other approaches (n=8). Among 25 trials with more than two arms, 16 (64%) corrected for multiplicity using Bonferroni procedure (n=8), Hochberg procedure (n=2), Gatekeeping procedure (n=2), or hierarchical procedure (n=4). Among 16 trials with multiple primary outcomes, 4 (25%) corrected for multiplicity by Bonferroni procedure.

Conclusion

There are opportunities for improvement in the design and statistical analyses of ophthalmic trials, particularly in the aspects of adjustment for inter-eye correlation, missing data and multiplicity. Continuing education in ophthalmology and vision research community may improve the quality of ophthalmic trials.