Viscocannula-Assisted Reinversion of Implantable Collamer Lens: Comparison of Postoperative Outcomes With the Fellow Eyes
CORRESPONDENCE Viscocannula-Assisted Reinversion of Implantable Collamer Lens: Comparison of Postoperative Outcomes With the Fellow Eyes
CONFLICT OF ...
CORRESPONDENCE Viscocannula-Assisted Reinversion of Implantable Collamer Lens: Comparison of Postoperative Outcomes With the Fellow Eyes
CONFLICT OF INTEREST DISCLOSURES: ALL AUTHORS have completed and submitted the ICMJE Form for Disclosure of Potential Conflicts of Interest and none were reported.
REFERENCE EDITOR: IN THE RECENTLY PUBLISHED STUDY BY KUMAR AND
associates, the authors compare the postoperative outcomes of eyes with accidental intraoperative inversion of implantable collamer lens (ICL) with fellow eyes with a normal implantable collamer lens.1 Two sets of comparisons are presented in the article: (1) within eyes over successive time points and (2) between eyes at specific time points. Regarding the former, the authors applied the correct statistical test to account for the repeated measurements on the same eye at different time points. However, regarding the latter, they did not appreciate the need to account for the clustering of eyes within the same individual. When comparing reinverted and fellow eyes at each time point, they describe using the Mann–Whitney U test, which is not appropriate because it fails to account for the clustering effect. Assuming the first normal and reinverted eye data that are listed in Table 11 correspond to the same individual, we conducted a reanalysis of the study data using the Wilcoxon signed-rank test and provided readers with the correct P values in the Table below. There was no significant difference between the 2 groups with respect to uncorrected visual acuity, central corneal thickness, or anterior chamber depth. Although this does not amend the interpretation, it is still imperative to use appropriate statistical techniques that produce correct P values. CARRIE HUISINGH GERALD MCGWIN JR
Birmingham, Alabama
1. Kumar DA, Agarwal A, Prakash G, et al. Viscocannulaassisted reinversion of implantable collamer lens: comparison of postoperative outcomes with the fellow eyes. Am J Ophthalmol 2012;153(1):62– 67.
REPLY WE READ WITH INTEREST THE CORRESPONDENCE OF HUIS-
ingh and McGwinn regarding the use of the statistical tests in the analysis of our recent study.1 In the analysis, we considered the reinverted eyes as the treatment group and used fellow eyes as the control group. We treated the data as unpaired and used the nonparametric Mann–Whitney U test for comparison between the 2 groups at various time points. The Wilcoxon signed-rank test is a frequently used nonparametric test for paired data (eg, consisting of pretreatment and posttreatment measurements) based on independent units of analysis.2 Hence, we used it for the comparison of outcomes in the phakic intraocular lens reinverted eyes (before and after viscocannula reinversion). It also was reported that this test cannot be used for paired comparisons arising from clustered data (eg, if paired comparisons are available for each of 2 eyes of an individual).2 Although the Mann–Whitney U test is ubiquitous in statistical practice for the comparison of measures of location for 2 samples where the assumption of normality is questionable, there have been reports in the literature in which the Mann–Whitney U test has been used comfortably for fellow eye comparisons in which the fellow eye was taken as the control.3,4
TABLE. Comparison of the Use of the Wilcoxon Signed-Rank and Mann–Whitney U Tests in the Statistical Analysis of Postoperative Outcomes of Eyes with Visocannula-Assisted Reinversion of Implantable Collamer Lens P Value, Wilcoxon Signed-Rank Test (from Reanalysis)
UCVA CCT ACD
P Value, Mann-Whitney U Test (from Article)
1 Month
6 Months
24 Months
1 Month
6 Months
24 Months
.6875 1.0000 .7500
.6875 1.0000 .7500
.6875 1.0000 .7500
.611 NS .915
.611 NS .915
.611 NS .915
ACD ⫽ anterior chamber depth; CCT ⫽ central corneal thickness; NS ⫽ no significant difference; UCVA ⫽ uncorrected visual acuity.