|
Activity Number:
|
557
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 3, 2016 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Consulting
|
|
Abstract #320538
|
|
|
Title:
|
Analysis of Eyelid Position in Ophthalmologic Plastic Surgery Research
|
|
Author(s):
|
Jonathan Grotts*
|
|
Companies:
|
|
|
Keywords:
|
Multivariate statistics ;
Design of experiments ;
Multiple comparisons ;
Biostatistics
|
|
Abstract:
|
Ophthalmologic plastic surgery for pathologic upper eyelid droop (Ptosis) is a common procedure for oculoplastic surgeons. The ophthalmologic literature lacks consensus on the measurement of the upper eyelid and the statistical techniques for assessing surgical results. We propose methods for the measurement of the eyelid and methods for comparing surgical procedures of eyelid retraction surgery. Data from 30 eyes that underwent Muller's muscle conjunctival resection were used to design a simulation study that assesses the efficacy of a multivariate statistics model in discerning the performance of surgical techniques. Eyelid height was assumed to follow a multivariate normal distribution and the difference in eyelid position pre- and post-surgery was assessed using multivariate analysis of variance. Eyelid position change along the eyelid curve was assessed using linear regression while controlling for the false discovery rate. This is a unique application of well-established statistical techniques. The results of this simulation study can be used to properly design future research that evaluates the differences in surgical techniques for pathologic upper eyelid droop.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2016 program
|
