Xiaoqin Huang1, Fatemeh Saki2, Mengyu Wang3, Tobias Elze3, Michael V Boland4, Louis R Pasquale5, Chris A Johnson6, Siamak Yousefi1,7. 1. Departments of Ophthalmology. 2. Qualcomm Inc., San Diego, CA. 3. Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School. 4. Department of Ophthalmology, Massachusetts Eye and Ear, Boston, MA. 5. Department of Ophthalmology, Icahn School of Medicine at Mount Sinai, New York, NY. 6. Department of Ophthalmology & Visual Sciences, University of Iowa Hospitals and Clinics, Iowa City, IA. 7. Genetics, Genomics, and Informatics, University of Tennessee Health Science Center, Memphis, TN.
Abstract
OBJECTIVE: The objective of this study was to develop an objective and easy-to-use glaucoma staging system based on visual fields (VFs). SUBJECTS AND PARTICIPANTS: A total of 13,231 VFs from 8077 subjects were used to develop models and 8024 VFs from 4445 subjects were used to validate models. METHODS: We developed an unsupervised machine learning model to identify clusters with similar VF values. We annotated the clusters based on their respective mean deviation (MD). We computed optimal MD thresholds that discriminate clusters with the highest accuracy based on Bayes minimum error principle. We evaluated the accuracy of the staging system and validated findings based on an independent validation dataset. RESULTS: The unsupervised k -means algorithm discovered 4 clusters with 6784, 4034, 1541, and 872 VFs and average MDs of 0.0 dB (±1.4: SD), -4.8 dB (±1.9), -12.2 dB (±2.9), and -23.0 dB (±3.8), respectively. The supervised Bayes minimum error classifier identified optimal MD thresholds of -2.2, -8.0, and -17.3 dB for discriminating normal eyes and eyes at the early, moderate, and advanced stages of glaucoma. The accuracy of the glaucoma staging system was 94%, based on identified MD thresholds with respect to the initial k -means clusters. CONCLUSIONS: We discovered that 4 severity levels based on MD thresholds of -2.2, -8.0, and -17.3 dB, provides the optimal number of severity stages based on unsupervised and supervised machine learning. This glaucoma staging system is unbiased, objective, easy-to-use, and consistent, which makes it highly suitable for use in glaucoma research and for day-to-day clinical practice.
OBJECTIVE: The objective of this study was to develop an objective and easy-to-use glaucoma staging system based on visual fields (VFs). SUBJECTS AND PARTICIPANTS: A total of 13,231 VFs from 8077 subjects were used to develop models and 8024 VFs from 4445 subjects were used to validate models. METHODS: We developed an unsupervised machine learning model to identify clusters with similar VF values. We annotated the clusters based on their respective mean deviation (MD). We computed optimal MD thresholds that discriminate clusters with the highest accuracy based on Bayes minimum error principle. We evaluated the accuracy of the staging system and validated findings based on an independent validation dataset. RESULTS: The unsupervised k -means algorithm discovered 4 clusters with 6784, 4034, 1541, and 872 VFs and average MDs of 0.0 dB (±1.4: SD), -4.8 dB (±1.9), -12.2 dB (±2.9), and -23.0 dB (±3.8), respectively. The supervised Bayes minimum error classifier identified optimal MD thresholds of -2.2, -8.0, and -17.3 dB for discriminating normal eyes and eyes at the early, moderate, and advanced stages of glaucoma. The accuracy of the glaucoma staging system was 94%, based on identified MD thresholds with respect to the initial k -means clusters. CONCLUSIONS: We discovered that 4 severity levels based on MD thresholds of -2.2, -8.0, and -17.3 dB, provides the optimal number of severity stages based on unsupervised and supervised machine learning. This glaucoma staging system is unbiased, objective, easy-to-use, and consistent, which makes it highly suitable for use in glaucoma research and for day-to-day clinical practice.
Authors: Siamak Yousefi; Michael H Goldbaum; Madhusudhanan Balasubramanian; Felipe A Medeiros; Linda M Zangwill; Jeffrey M Liebmann; Christopher A Girkin; Robert N Weinreb; Christopher Bowd Journal: IEEE Trans Biomed Eng Date: 2014-04-01 Impact factor: 4.538
Authors: Tobias Elze; Louis R Pasquale; Lucy Q Shen; Teresa C Chen; Janey L Wiggs; Peter J Bex Journal: J R Soc Interface Date: 2015-02-06 Impact factor: 4.118
Authors: Henry D Jampel; David Friedman; Harry Quigley; Susan Vitale; Rhonda Miller; Frederick Knezevich; Yulan Ding Journal: Am J Ophthalmol Date: 2008-09-13 Impact factor: 5.258
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: Christopher Bowd; Robert N Weinreb; Madhusudhanan Balasubramanian; Intae Lee; Giljin Jang; Siamak Yousefi; Linda M Zangwill; Felipe A Medeiros; Christopher A Girkin; Jeffrey M Liebmann; Michael H Goldbaum Journal: PLoS One Date: 2014-01-30 Impact factor: 3.240