Hsin-Yi Chen1, Mei-Ling Huang. 1. Department of Ophthalmology, China Medical University Hospital, #2, Yuh-Der Road, Taichung City 404, Taiwan. hsin7850@url.com.tw
Abstract
BACKGROUND: We differentiated between normal and glaucomatous eyes in the Taiwan Chinese population based solely on the quantitative assessment of summary data reports from Stratus optical coherence tomography (OCT) by comparing their area under the receiver operating characteristic (ROC) curve. METHODS: One randomly selected eye from each of the 62 patients with early glaucomatous damage (mean deviation -2.8 +/- 1.8 dB) and from each of the 62 age- and sex-matched normal individuals were included in the study. Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head analysis results) were obtained by Stratus OCT. Twenty-one OCT parameters were included in a linear discriminant analysis (LDA) using forward selection and backward elimination to determine the best combination of parameters for discriminating between glaucomatous and healthy eyes based on ROC curve area. RESULTS: The average RNFL thickness was the best individual parameter for differentiating between normal eyes and glaucomatous eyes (ROC curve area 0.793). The maximum area under the ROC curve of six input parameters (average RNFL thickness; 10, 11, and 12 o'clock segment thicknesses; cup area; and vertical integrated rim area) generated by the forward selection method was 0.881. Whereas the maximum area under the ROC curve of 15 input parameters (average RNFL thickness; 1, 3, 4, 6, 8-10, 12 o'clock segment thicknesses; vertical integrated rim area; horizontal integrated rim area; disc area; cup to disc area ratio; cup to disc horizontal ratio; and cup to disc vertical ratio) generated by backward elimination method was 0.929. CONCLUSIONS: The performance of individual parameters obtained from Stratus OCT is fairly reliable for differentiating the early glaucomatous eyes from normal eyes. However, the discriminant power increases when LDA with forward selection and backward elimination methods is applied.
RCT Entities:
BACKGROUND: We differentiated between normal and glaucomatous eyes in the Taiwan Chinese population based solely on the quantitative assessment of summary data reports from Stratus optical coherence tomography (OCT) by comparing their area under the receiver operating characteristic (ROC) curve. METHODS: One randomly selected eye from each of the 62 patients with early glaucomatous damage (mean deviation -2.8 +/- 1.8 dB) and from each of the 62 age- and sex-matched normal individuals were included in the study. Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head analysis results) were obtained by Stratus OCT. Twenty-one OCT parameters were included in a linear discriminant analysis (LDA) using forward selection and backward elimination to determine the best combination of parameters for discriminating between glaucomatous and healthy eyes based on ROC curve area. RESULTS: The average RNFL thickness was the best individual parameter for differentiating between normal eyes and glaucomatous eyes (ROC curve area 0.793). The maximum area under the ROC curve of six input parameters (average RNFL thickness; 10, 11, and 12 o'clock segment thicknesses; cup area; and vertical integrated rim area) generated by the forward selection method was 0.881. Whereas the maximum area under the ROC curve of 15 input parameters (average RNFL thickness; 1, 3, 4, 6, 8-10, 12 o'clock segment thicknesses; vertical integrated rim area; horizontal integrated rim area; disc area; cup to disc area ratio; cup to disc horizontal ratio; and cup to disc vertical ratio) generated by backward elimination method was 0.929. CONCLUSIONS: The performance of individual parameters obtained from Stratus OCT is fairly reliable for differentiating the early glaucomatous eyes from normal eyes. However, the discriminant power increases when LDA with forward selection and backward elimination methods is applied.
Authors: L M Zangwill; C Bowd; C C Berry; J Williams; E Z Blumenthal; C A Sánchez-Galeana; C Vasile; R N Weinreb Journal: Arch Ophthalmol Date: 2001-07
Authors: Lelia A Paunescu; Joel S Schuman; Lori Lyn Price; Paul C Stark; Siobahn Beaton; Hiroshi Ishikawa; Gadi Wollstein; James G Fujimoto Journal: Invest Ophthalmol Vis Sci Date: 2004-06 Impact factor: 4.799
Authors: Bryce A Ford; Paul H Artes; Terry A McCormick; Marcelo T Nicolela; Raymond P LeBlanc; Balwantray C Chauhan Journal: Ophthalmology Date: 2003-06 Impact factor: 12.079
Authors: Tarek A El Beltagi; Christopher Bowd; Catherine Boden; Payam Amini; Pamela A Sample; Linda M Zangwill; Robert N Weinreb Journal: Ophthalmology Date: 2003-11 Impact factor: 12.079
Authors: Gadi Wollstein; Joel S Schuman; Lori L Price; Ali Aydin; Siobahn A Beaton; Paul C Stark; James G Fujimoto; Hiroshi Ishikawa Journal: Am J Ophthalmol Date: 2004-08 Impact factor: 5.258
Authors: Linda M Zangwill; Kwokleung Chan; Christopher Bowd; Jicuang Hao; Te-Won Lee; Robert N Weinreb; Terrence J Sejnowski; Michael H Goldbaum Journal: Invest Ophthalmol Vis Sci Date: 2004-09 Impact factor: 4.799
Authors: Kenneth C Fan; Edem Tsikata; Ziad Khoueir; Huseyin Simavli; Rong Guo; Regina A de Luna; Sumir Pandit; Christian J Que; Johannes F de Boer; Teresa C Chen Journal: J Glaucoma Date: 2017-05 Impact factor: 2.503
Authors: Gianmarco Vizzeri; Christopher Bowd; Felipe A Medeiros; Robert N Weinreb; Linda M Zangwill Journal: J Glaucoma Date: 2009-01 Impact factor: 2.503
Authors: Gianmarco Vizzeri; Christopher Bowd; Felipe A Medeiros; Robert N Weinreb; Linda M Zangwill Journal: J Glaucoma Date: 2008-08 Impact factor: 2.503
Authors: Gianmarco Vizzeri; Christopher Bowd; Felipe A Medeiros; Robert N Weinreb; Linda M Zangwill Journal: Am J Ophthalmol Date: 2009-05-09 Impact factor: 5.258
Authors: Ake Tzu-Hui Lu; Mingwu Wang; Rohit Varma; Joel S Schuman; David S Greenfield; Scott D Smith; David Huang Journal: Ophthalmology Date: 2008-06-02 Impact factor: 12.079
Authors: G Vizzeri; R N Weinreb; A O Gonzalez-Garcia; C Bowd; F A Medeiros; P A Sample; L M Zangwill Journal: Br J Ophthalmol Date: 2009-03-19 Impact factor: 4.638