Keunheung Park1, Jinmi Kim2, Jiwoong Lee1,3. 1. Department of Ophthalmology, Pusan National University College of Medicine, Busan, Korea. 2. Department of Biostatistics, Clinical Trial Center, Biomedical Research Institute, Pusan National University Hospital, Busan, Korea. 3. Biomedical Research Institute, Pusan National University Hospital, Busan, Korea.
Abstract
PURPOSE: We evaluate the relationship between Bruch's membrane opening minimum rim width (BMO-MRW) and peripapillary retinal nerve fiber layer thickness (pRNFLT) and develop a new parameter combining BMO-MRW and pRNFLT using a neural network to maximize their compensatory values. METHODS: A total of 402 subjects were divided into two groups: 273 (validation group) and 129 (neural net training) subjects. Linear quadratic and broken-stick regression models were used to explore the relationship between BMO-MRW and pRNFLT. A multilayer neural network was used to create a combined parameter, and diagnostic performances were compared using area under the receiver operating characteristic curves (AUROCs). RESULTS: Regression analyses between BMO-MRW and pRNFLT revealed that the broken-stick model afforded the best fit. Globally, the tipping point was a BMO-MRW of 226.5 μm. BMO-MRW and pRNFLT were correlated significantly with visual field. When differentiating normal from glaucoma subjects, the neural network exhibited the largest AUROC. When differentiating normal from early glaucoma subjects, the overall diagnostic performance decreased, but the neural network still exhibited the largest AUROC. CONCLUSIONS: The optimal relationship between BMO-MRW and pRNFLT was revealed using the broken-stick model. Considerable BMO-MRW thinning preceded pRNFLT thinning. The neural network significantly improved diagnostic power by combining BMO-MRW and pRNFLT. TRANSLATIONAL RELEVANCE: A combined index featuring BMO-MRW and pRNFLT data can aid clinical decision-making, particularly when individual parameters yield confusing results. Our neural network effectively combines information from separate parameters.
PURPOSE: We evaluate the relationship between Bruch's membrane opening minimum rim width (BMO-MRW) and peripapillary retinal nerve fiber layer thickness (pRNFLT) and develop a new parameter combining BMO-MRW and pRNFLT using a neural network to maximize their compensatory values. METHODS: A total of 402 subjects were divided into two groups: 273 (validation group) and 129 (neural net training) subjects. Linear quadratic and broken-stick regression models were used to explore the relationship between BMO-MRW and pRNFLT. A multilayer neural network was used to create a combined parameter, and diagnostic performances were compared using area under the receiver operating characteristic curves (AUROCs). RESULTS: Regression analyses between BMO-MRW and pRNFLT revealed that the broken-stick model afforded the best fit. Globally, the tipping point was a BMO-MRW of 226.5 μm. BMO-MRW and pRNFLT were correlated significantly with visual field. When differentiating normal from glaucoma subjects, the neural network exhibited the largest AUROC. When differentiating normal from early glaucoma subjects, the overall diagnostic performance decreased, but the neural network still exhibited the largest AUROC. CONCLUSIONS: The optimal relationship between BMO-MRW and pRNFLT was revealed using the broken-stick model. Considerable BMO-MRW thinning preceded pRNFLT thinning. The neural network significantly improved diagnostic power by combining BMO-MRW and pRNFLT. TRANSLATIONAL RELEVANCE: A combined index featuring BMO-MRW and pRNFLT data can aid clinical decision-making, particularly when individual parameters yield confusing results. Our neural network effectively combines information from separate parameters.
Authors: Felipe A Medeiros; Linda M Zangwill; Christopher Bowd; Roberto M Vessani; Remo Susanna; Robert N Weinreb Journal: Am J Ophthalmol Date: 2005-01 Impact factor: 5.258
Authors: D S Kamal; A C Viswanathan; D F Garway-Heath; R A Hitchings; D Poinoosawmy; C Bunce Journal: Br J Ophthalmol Date: 1999-03 Impact factor: 4.638
Authors: Vishva M Danthurebandara; Glen P Sharpe; Donna M Hutchison; Jonathan Denniss; Marcelo T Nicolela; Allison M McKendrick; Andrew Turpin; Balwantray C Chauhan Journal: Invest Ophthalmol Vis Sci Date: 2014-12-11 Impact factor: 4.799
Authors: M H Goldbaum; P A Sample; H White; B Côlt; P Raphaelian; R D Fechtner; R N Weinreb Journal: Invest Ophthalmol Vis Sci Date: 1994-08 Impact factor: 4.799
Authors: Hongli Yang; Haomin Luo; Christy Hardin; Yaxing Wang; Jin Wook Jeoung; Cindy Albert; Jayme R Vianna; Glen P Sharpe; Juan Reynaud; Shaban Demirel; Steven L Mansberger; Brad Fortune; Marcelo Nicolela; Stuart K Gardiner; Balwantray C Chauhan; Claude F Burgoyne Journal: Am J Ophthalmol Date: 2019-12-30 Impact factor: 5.258
Authors: Sol La Bruna; Emmanouil Tsamis; Zane Z Zemborain; Zhichao Wu; Carlos Gustavo De Moraes; Robert Ritch; Donald C Hood Journal: J Glaucoma Date: 2020-08 Impact factor: 2.503
Authors: Wendy W Liu; Michael McClurkin; Edem Tsikata; Pui-Chuen Hui; Tobias Elze; Ali R C Celebi; Ziad Khoueir; Ramon Lee; Eric Shieh; Huseyin Simavli; Christian Que; Rong Guo; Johannes de Boer; Teresa C Chen Journal: J Glaucoma Date: 2020-10 Impact factor: 2.290