Hiroshi Murata1, Linda M Zangwill2, Yuri Fujino1, Masato Matsuura1, Atsuya Miki3, Kazunori Hirasawa4,5, Masaki Tanito6, Shiro Mizoue7, Kazuhiko Mori8, Katsuyoshi Suzuki9, Takehiro Yamashita10, Kenji Kashiwagi11, Nobuyuki Shoji5, Ryo Asaoka1. 1. Department of Ophthalmology, University of Tokyo Graduate School of Medicine, Tokyo, Japan. 2. Shiley Eye Institute Hamilton Glaucoma Center, University of California, San Diego, La Jolla, California, United States. 3. Department of Ophthalmology, Osaka University Graduate School of Medicine, Osaka, Japan. 4. Moorfields Eye Hospital NHS Foundation Trust and University College London, Institute of Ophthalmology, London, United Kingdom. 5. Orthoptics and Visual Science, Department of Rehabilitation, School of Allied Health Sciences, Kitasato University, Kanagawa, Japan. 6. Department of Ophthalmology, Shimane University Faculty of Medicine, Shimane, Japan. 7. Department of Ophthalmology, Ehime University Graduate School of Medicine, Ehime, Japan. 8. Department of Ophthalmology, Kyoto Prefectural University of Medicine, Kyoto, Japan. 9. Department of Ophthalmology, Yamaguchi University Graduate School of Medicine, Yamaguchi, Japan. 10. Department of Ophthalmology, Kagoshima University Graduate School of Medical and Dental Sciences, Kagoshima, Japan. 11. Department of Ophthalmology, University of Yamanashi Faculty of Medicine, Yamanashi, Japan.
Abstract
Purpose: To validate the prediction accuracy of variational Bayes linear regression (VBLR) with two datasets external to the training dataset. Method: The training dataset consisted of 7268 eyes of 4278 subjects from the University of Tokyo Hospital. The Japanese Archive of Multicentral Databases in Glaucoma (JAMDIG) dataset consisted of 271 eyes of 177 patients, and the Diagnostic Innovations in Glaucoma Study (DIGS) dataset includes 248 eyes of 173 patients, which were used for validation. Prediction accuracy was compared between the VBLR and ordinary least squared linear regression (OLSLR). First, OLSLR and VBLR were carried out using total deviation (TD) values at each of the 52 test points from the second to fourth visual fields (VFs) (VF2-4) to 2nd to 10th VF (VF2-10) of each patient in JAMDIG and DIGS datasets, and the TD values of the 11th VF test were predicted every time. The predictive accuracy of each method was compared through the root mean squared error (RMSE) statistic. Results: OLSLR RMSEs with the JAMDIG and DIGS datasets were between 31 and 4.3 dB, and between 19.5 and 3.9 dB. On the other hand, VBLR RMSEs with JAMDIG and DIGS datasets were between 5.0 and 3.7, and between 4.6 and 3.6 dB. There was statistically significant difference between VBLR and OLSLR for both datasets at every series (VF2-4 to VF2-10) (P < 0.01 for all tests). However, there was no statistically significant difference in VBLR RMSEs between JAMDIG and DIGS datasets at any series of VFs (VF2-2 to VF2-10) (P > 0.05). Conclusions: VBLR outperformed OLSLR to predict future VF progression, and the VBLR has a potential to be a helpful tool at clinical settings.
Purpose: To validate the prediction accuracy of variational Bayes linear regression (VBLR) with two datasets external to the training dataset. Method: The training dataset consisted of 7268 eyes of 4278 subjects from the University of Tokyo Hospital. The Japanese Archive of Multicentral Databases in Glaucoma (JAMDIG) dataset consisted of 271 eyes of 177 patients, and the Diagnostic Innovations in Glaucoma Study (DIGS) dataset includes 248 eyes of 173 patients, which were used for validation. Prediction accuracy was compared between the VBLR and ordinary least squared linear regression (OLSLR). First, OLSLR and VBLR were carried out using total deviation (TD) values at each of the 52 test points from the second to fourth visual fields (VFs) (VF2-4) to 2nd to 10th VF (VF2-10) of each patient in JAMDIG and DIGS datasets, and the TD values of the 11th VF test were predicted every time. The predictive accuracy of each method was compared through the root mean squared error (RMSE) statistic. Results: OLSLR RMSEs with the JAMDIG and DIGS datasets were between 31 and 4.3 dB, and between 19.5 and 3.9 dB. On the other hand, VBLR RMSEs with JAMDIG and DIGS datasets were between 5.0 and 3.7, and between 4.6 and 3.6 dB. There was statistically significant difference between VBLR and OLSLR for both datasets at every series (VF2-4 to VF2-10) (P < 0.01 for all tests). However, there was no statistically significant difference in VBLR RMSEs between JAMDIG and DIGS datasets at any series of VFs (VF2-2 to VF2-10) (P > 0.05). Conclusions: VBLR outperformed OLSLR to predict future VF progression, and the VBLR has a potential to be a helpful tool at clinical settings.
Authors: David F Garway-Heath; David P Crabb; Catey Bunce; Gerassimos Lascaratos; Francesca Amalfitano; Nitin Anand; Augusto Azuara-Blanco; Rupert R Bourne; David C Broadway; Ian A Cunliffe; Jeremy P Diamond; Scott G Fraser; Tuan A Ho; Keith R Martin; Andrew I McNaught; Anil Negi; Krishna Patel; Richard A Russell; Ameet Shah; Paul G Spry; Katsuyoshi Suzuki; Edward T White; Richard P Wormald; Wen Xing; Thierry G Zeyen Journal: Lancet Date: 2014-12-19 Impact factor: 79.321
Authors: Haogang Zhu; Richard A Russell; Luke J Saunders; Stefano Ceccon; David F Garway-Heath; David P Crabb Journal: PLoS One Date: 2014-01-17 Impact factor: 3.240
Authors: Vahid Mohammadzadeh; Erica Su; Alessandro Rabiolo; Lynn Shi; Sepideh Heydar Zadeh; Simon K Law; Anne L Coleman; Joseph Caprioli; Robert E Weiss; Kouros Nouri-Mahdavi Journal: Am J Ophthalmol Date: 2021-12-21 Impact factor: 5.488
Authors: Vahid Mohammadzadeh; Erica Su; Sepideh Heydar Zadeh; Simon K Law; Anne L Coleman; Joseph Caprioli; Robert E Weiss; Kouros Nouri-Mahdavi Journal: Transl Vis Sci Technol Date: 2021-04-01 Impact factor: 3.283