Sophie Cai1, Tobias Elze2,3, Peter J Bex2,4, Janey L Wiggs1, Louis R Pasquale1,5, Lucy Q Shen1. 1. a Department of Ophthalmology , Harvard Medical School, Massachusetts Eye and Ear , Boston , MA , USA. 2. b Department of Ophthalmology, Harvard Medical School , Schepens Eye Research Institute , Boston , MA , USA. 3. c Max Planck Institute for Mathematics in the Sciences , Leipzig , Germany. 4. d Department of Psychology , Northeastern University , Boston , MA , USA. 5. e Channing Division of Network Medicine , Brigham and Women's Hospital , Boston , MA , USA.
Abstract
PURPOSE: To assess the clinical validity of visual field (VF) archetypal analysis, a previously developed machine learning method for decomposing any Humphrey VF (24-2) into a weighted sum of clinically recognizable VF loss patterns. MATERIALS AND METHODS: For each of 16 previously identified VF loss patterns ("archetypes," denoted AT1 through AT16), we screened 30,995 reliable VFs to select 10-20 representative patients whose VFs had the highest decomposition coefficients for each archetype. VF global indices and patient ocular and demographic features were extracted retrospectively. Based on resemblances between VF archetypes and clinically observed VF patterns, hypotheses were generated for associations between certain VF archetypes and clinical features, such as an association between AT6 (central island, representing severe VF loss) and large cup-to-disk ratio (CDR). Distributions of the selected clinical features were compared between representative eyes of certain archetypes and all other eyes using the two-tailed t-test or Fisher exact test. RESULTS: 243 eyes from 243 patients were included, representative of AT1 through AT16. CDR was more often ≥ 0.7 among eyes representative of AT6 (central island; p = 0.002), AT10 (inferior arcuate defect; p = 0.048), AT14 (superior paracentral defect; p = 0.016), and AT16 (inferior paracentral defect; p = 0.016) than other eyes. CDR was more often < 0.7 among eyes representative of AT1 (no focal defect; p < 0.001) and AT2 (superior defect; p = 0.027), which was also associated with ptosis (p < 0.001). AT12 (temporal hemianopia) was associated with history of stroke (p = 0.022). AT11 (concentric peripheral defect) trended toward association with trial lens correction > 6D (p = 0.069). CONCLUSIONS: Shared clinical features between computationally derived VF archetypes and clinically observed VF patterns support the clinical validity of VF archetypal analysis.
PURPOSE: To assess the clinical validity of visual field (VF) archetypal analysis, a previously developed machine learning method for decomposing any Humphrey VF (24-2) into a weighted sum of clinically recognizable VF loss patterns. MATERIALS AND METHODS: For each of 16 previously identified VF loss patterns ("archetypes," denoted AT1 through AT16), we screened 30,995 reliable VFs to select 10-20 representative patients whose VFs had the highest decomposition coefficients for each archetype. VF global indices and patient ocular and demographic features were extracted retrospectively. Based on resemblances between VF archetypes and clinically observed VF patterns, hypotheses were generated for associations between certain VF archetypes and clinical features, such as an association between AT6 (central island, representing severe VF loss) and large cup-to-disk ratio (CDR). Distributions of the selected clinical features were compared between representative eyes of certain archetypes and all other eyes using the two-tailed t-test or Fisher exact test. RESULTS: 243 eyes from 243 patients were included, representative of AT1 through AT16. CDR was more often ≥ 0.7 among eyes representative of AT6 (central island; p = 0.002), AT10 (inferior arcuate defect; p = 0.048), AT14 (superior paracentral defect; p = 0.016), and AT16 (inferior paracentral defect; p = 0.016) than other eyes. CDR was more often < 0.7 among eyes representative of AT1 (no focal defect; p < 0.001) and AT2 (superior defect; p = 0.027), which was also associated with ptosis (p < 0.001). AT12 (temporal hemianopia) was associated with history of stroke (p = 0.022). AT11 (concentric peripheral defect) trended toward association with trial lens correction > 6D (p = 0.069). CONCLUSIONS: Shared clinical features between computationally derived VF archetypes and clinically observed VF patterns support the clinical validity of VF archetypal analysis.
Entities:
Keywords:
Archetype; glaucoma; machine learning; statistical models; visual field
Authors: Sung Chul Park; Carlos Gustavo De Moraes; Christopher C W Teng; Celso Tello; Jeffrey M Liebmann; Robert Ritch Journal: Ophthalmology Date: 2011-06-12 Impact factor: 12.079
Authors: John L Keltner; Chris A Johnson; Kimberly E Cello; Mary A Edwards; Shannan E Bandermann; Michael A Kass; Mae O Gordon Journal: Arch Ophthalmol Date: 2003-05
Authors: George L Spaeth; Jeffrey Henderer; Connie Liu; Muge Kesen; Undraa Altangerel; Atilla Bayer; L Jay Katz; Jonathan Myers; Douglas Rhee; William Steinmann Journal: Trans Am Ophthalmol Soc Date: 2002
Authors: Maltish M Lorenzo; Julia Devlin; Chhavi Saini; Kin-Sang Cho; Eleftherios I Paschalis; Dong Feng Chen; Rafaella Nascimento E Silva; Sherleen H Chen; Milica A Margeta; Courtney Ondeck; David Solá-Del Valle; James Chodosh; Joseph B Ciolino; Roberto Pineda; Louis R Pasquale; Lucy Q Shen Journal: Ophthalmol Glaucoma Date: 2021-08-18
Authors: Mengyu Wang; Jorryt Tichelaar; Louis R Pasquale; Lucy Q Shen; Michael V Boland; Sarah R Wellik; Carlos Gustavo De Moraes; Jonathan S Myers; Pradeep Ramulu; MiYoung Kwon; Osamah J Saeedi; Hui Wang; Neda Baniasadi; Dian Li; Peter J Bex; Tobias Elze Journal: JAMA Ophthalmol Date: 2020-02-01 Impact factor: 7.389
Authors: Mengyu Wang; Lucy Q Shen; Louis R Pasquale; Michael V Boland; Sarah R Wellik; Carlos Gustavo De Moraes; Jonathan S Myers; Thao D Nguyen; Robert Ritch; Pradeep Ramulu; Hui Wang; Jorryt Tichelaar; Dian Li; Peter J Bex; Tobias Elze Journal: Ophthalmology Date: 2019-12-12 Impact factor: 12.079
Authors: Eun Young Choi; Dian Li; Yuying Fan; Louis R Pasquale; Lucy Q Shen; Michael V Boland; Pradeep Ramulu; Siamak Yousefi; Carlos Gustavo De Moraes; Sarah R Wellik; Jonathan S Myers; Peter J Bex; Tobias Elze; Mengyu Wang Journal: Ophthalmol Glaucoma Date: 2020-12-11
Authors: Mengyu Wang; Lucy Q Shen; Louis R Pasquale; Paul Petrakos; Sydney Formica; Michael V Boland; Sarah R Wellik; Carlos Gustavo De Moraes; Jonathan S Myers; Osamah Saeedi; Hui Wang; Neda Baniasadi; Dian Li; Jorryt Tichelaar; Peter J Bex; Tobias Elze Journal: Invest Ophthalmol Vis Sci Date: 2019-01-02 Impact factor: 4.799
Authors: Bettina Teng; Dian Li; Eun Young Choi; Lucy Q Shen; Louis R Pasquale; Michael V Boland; Pradeep Ramulu; Sarah R Wellik; Carlos Gustavo De Moraes; Jonathan S Myers; Siamak Yousefi; Thao Nguyen; Yuying Fan; Hui Wang; Peter J Bex; Tobias Elze; Mengyu Wang Journal: Transl Vis Sci Technol Date: 2020-11-17 Impact factor: 3.048