Gian-Gabriel P Garcia1, Koji Nitta2, Mariel S Lavieri1, Chris Andrews3, Xiang Liu1, Elizabeth Lobaza1, Mark P Van Oyen1, Kazuhisa Sugiyama4, Joshua D Stein5. 1. Department of Industrial and Operations Engineering, University of Michigan College of Engineering, Ann Arbor, Michigan, USA. 2. Fukui-ken Saiseikai Hospital, Fukui, Japan; Kanazawa University Graduate School of Medical Science, Kanazawa, Japan. 3. Department of Ophthalmology and Visual Sciences, University of Michigan Medical School, Ann Arbor, Michigan, USA; Center for Eye Policy and Innovation, University of Michigan, Ann Arbor, Michigan, USA. 4. Kanazawa University Graduate School of Medical Science, Kanazawa, Japan. 5. Department of Ophthalmology and Visual Sciences, University of Michigan Medical School, Ann Arbor, Michigan, USA; Center for Eye Policy and Innovation, University of Michigan, Ann Arbor, Michigan, USA; Department of Health Management and Policy, University of Michigan School of Public Health, Ann Arbor, Michigan, USA. Electronic address: jdstein@med.umich.edu.
Abstract
PURPOSE: To determine whether a machine learning technique called Kalman filtering (KF) can accurately forecast future values of mean deviation (MD), pattern standard deviation, and intraocular pressure for patients with normal tension glaucoma (NTG). DESIGN: Development and testing of a forecasting model for glaucoma progression. METHODS: We parameterized and validated a KF (KF-NTG) to forecast MD, pattern standard deviation, and intraocular pressure at 24 months into the future using 263 eyes of 263 Japanese patients with NTG. We determined the proportion of patients with MD forecasts within 0.5, 1.0, and 2.5 dBs of the actual values and calculated the root mean squared error (RMSE) for each forecast. We compared KF-NTG with a previously published KF model calibrated using patients with high-tension open-angle glaucoma (KF-HTG) and to 3 conventional forecasting algorithms. RESULTS: The 263 patients with NTG had mean ± standard deviation age of 63.4 ± 10.5 years. KF-NTG forecasted MD values 24 months ahead within 0.5, 1.0, and 2.5 dBs of the actual value for 78 eyes (32.2%), 122 eyes (50.4%), and 211 eyes (87.2%), respectively. The proportion of eyes with MD values forecasted within 2.5 dB of the actual value for the KF-NTG (87.2%) were similar to KF-HTG (86.0%) and the null model (86.4%), and much better than the 2 linear regression-based models (72.7-74.0%; P < .001). When forecasting MD, KF-NTG (RMSE = 2.71) and KF-HTG (RMSE = 2.68) achieved lower RMSE than the other 3 forecasting models (RMSE = 2.81-3.90), indicating better performance. CONCLUSION: As observed previously for patients with HTG, KF can also effectively forecast disease trajectory for many patients with NTG.
PURPOSE: To determine whether a machine learning technique called Kalman filtering (KF) can accurately forecast future values of mean deviation (MD), pattern standard deviation, and intraocular pressure for patients with normal tension glaucoma (NTG). DESIGN: Development and testing of a forecasting model for glaucoma progression. METHODS: We parameterized and validated a KF (KF-NTG) to forecast MD, pattern standard deviation, and intraocular pressure at 24 months into the future using 263 eyes of 263 Japanese patients with NTG. We determined the proportion of patients with MD forecasts within 0.5, 1.0, and 2.5 dBs of the actual values and calculated the root mean squared error (RMSE) for each forecast. We compared KF-NTG with a previously published KF model calibrated using patients with high-tension open-angle glaucoma (KF-HTG) and to 3 conventional forecasting algorithms. RESULTS: The 263 patients with NTG had mean ± standard deviation age of 63.4 ± 10.5 years. KF-NTG forecasted MD values 24 months ahead within 0.5, 1.0, and 2.5 dBs of the actual value for 78 eyes (32.2%), 122 eyes (50.4%), and 211 eyes (87.2%), respectively. The proportion of eyes with MD values forecasted within 2.5 dB of the actual value for the KF-NTG (87.2%) were similar to KF-HTG (86.0%) and the null model (86.4%), and much better than the 2 linear regression-based models (72.7-74.0%; P < .001). When forecasting MD, KF-NTG (RMSE = 2.71) and KF-HTG (RMSE = 2.68) achieved lower RMSE than the other 3 forecasting models (RMSE = 2.81-3.90), indicating better performance. CONCLUSION: As observed previously for patients with HTG, KF can also effectively forecast disease trajectory for many patients with NTG.
Authors: Joshua D Stein; Denise S Kim; Leslie M Niziol; Nidhi Talwar; Bin Nan; David C Musch; Julia E Richards Journal: Ophthalmology Date: 2011-02-18 Impact factor: 12.079
Authors: Oraorn Thonginnetra; Vivienne C Greenstein; David Chu; Jeffrey M Liebmann; Robert Ritch; Donald C Hood Journal: J Glaucoma Date: 2010-03 Impact factor: 2.503
Authors: David C Musch; Brenda W Gillespie; Paul R Lichter; Leslie M Niziol; Nancy K Janz Journal: Ophthalmology Date: 2008-11-18 Impact factor: 12.079
Authors: Greggory J Schell; Mariel S Lavieri; Jonathan E Helm; Xiang Liu; David C Musch; Mark P Van Oyen; Joshua D Stein Journal: Ophthalmology Date: 2014-04-04 Impact factor: 12.079
Authors: Brian C Stagg; Joshua D Stein; Felipe A Medeiros; Barbara Wirostko; Alan Crandall; M Elizabeth Hartnett; Mollie Cummins; Alan Morris; Rachel Hess; Kensaku Kawamoto Journal: Ophthalmol Glaucoma Date: 2020-08-15
Authors: Margarita Labkovich; Megan Paul; Eliott Kim; Randal A Serafini; Shreyas Lakhtakia; Aly A Valliani; Andrew J Warburton; Aashay Patel; Davis Zhou; Bonnie Sklar; James Chelnis; Ebrahim Elahi Journal: Digit Health Date: 2022-05-06
Authors: Mohammad Zhalechian; Mark P Van Oyen; Mariel S Lavieri; Carlos Gustavo De Moraes; Christopher A Girkin; Massimo A Fazio; Robert N Weinreb; Christopher Bowd; Jeffrey M Liebmann; Linda M Zangwill; Christopher A Andrews; Joshua D Stein Journal: Ophthalmol Sci Date: 2021-12-21