Youngseok Song1, Hiroshi Ishikawa1, Mengfei Wu2, Yu-Ying Liu3, Katie A Lucy1, Fabio Lavinsky1, Mengling Liu4, Gadi Wollstein5, Joel S Schuman1. 1. New York University Langone Eye Center, New York University School of Medicine, New York, New York. 2. New York University Langone Eye Center, New York University School of Medicine, New York, New York; Division of Biostatistics, Department of Population Health and Environmental Medicine, New York University School of Medicine, New York, New York. 3. Georgia College of Computing, Georgia Institute of Technology, Atlanta, Georgia. 4. Division of Biostatistics, Department of Population Health and Environmental Medicine, New York University School of Medicine, New York, New York. 5. New York University Langone Eye Center, New York University School of Medicine, New York, New York. Electronic address: Gadi.Wollstein@nyumc.org.
Abstract
PURPOSE: Previously, we introduced a state-based 2-dimensional continuous-time hidden Markov model (2D CT HMM) to model the pattern of detected glaucoma changes using structural and functional information simultaneously. The purpose of this study was to evaluate the detected glaucoma change prediction performance of the model in a real clinical setting using a retrospective longitudinal dataset. DESIGN: Longitudinal, retrospective study. PARTICIPANTS: One hundred thirty-four eyes from 134 participants diagnosed with glaucoma or as glaucoma suspects (average follow-up, 4.4±1.2 years; average number of visits, 7.1±1.8). METHODS: A 2D CT HMM model was trained using OCT (Cirrus HD-OCT; Zeiss, Dublin, CA) average circumpapillary retinal nerve fiber layer (cRNFL) thickness and visual field index (VFI) or mean deviation (MD; Humphrey Field Analyzer; Zeiss). The model was trained using a subset of the data (107 of 134 eyes [80%]) including all visits except for the last visit, which was used to test the prediction performance (training set). Additionally, the remaining 27 eyes were used for secondary performance testing as an independent group (validation set). The 2D CT HMM predicts 1 of 4 possible detected state changes based on 1 input state. MAIN OUTCOME MEASURES: Prediction accuracy was assessed as the percentage of correct prediction against the patient's actual recorded state. In addition, deviations of the predicted long-term detected change paths from the actual detected change paths were measured. RESULTS: Baseline mean ± standard deviation age was 61.9±11.4 years, VFI was 90.7±17.4, MD was -3.50±6.04 dB, and cRNFL thickness was 74.9±12.2 μm. The accuracy of detected glaucoma change prediction using the training set was comparable with the validation set (57.0% and 68.0%, respectively). Prediction deviation from the actual detected change path showed stability throughout patient follow-up. CONCLUSIONS: The 2D CT HMM demonstrated promising prediction performance in detecting glaucoma change performance in a simulated clinical setting using an independent cohort. The 2D CT HMM allows information from just 1 visit to predict at least 5 subsequent visits with similar performance.
PURPOSE: Previously, we introduced a state-based 2-dimensional continuous-time hidden Markov model (2D CT HMM) to model the pattern of detected glaucoma changes using structural and functional information simultaneously. The purpose of this study was to evaluate the detected glaucoma change prediction performance of the model in a real clinical setting using a retrospective longitudinal dataset. DESIGN: Longitudinal, retrospective study. PARTICIPANTS: One hundred thirty-four eyes from 134 participants diagnosed with glaucoma or as glaucoma suspects (average follow-up, 4.4±1.2 years; average number of visits, 7.1±1.8). METHODS: A 2D CT HMM model was trained using OCT (Cirrus HD-OCT; Zeiss, Dublin, CA) average circumpapillary retinal nerve fiber layer (cRNFL) thickness and visual field index (VFI) or mean deviation (MD; Humphrey Field Analyzer; Zeiss). The model was trained using a subset of the data (107 of 134 eyes [80%]) including all visits except for the last visit, which was used to test the prediction performance (training set). Additionally, the remaining 27 eyes were used for secondary performance testing as an independent group (validation set). The 2D CT HMM predicts 1 of 4 possible detected state changes based on 1 input state. MAIN OUTCOME MEASURES: Prediction accuracy was assessed as the percentage of correct prediction against the patient's actual recorded state. In addition, deviations of the predicted long-term detected change paths from the actual detected change paths were measured. RESULTS: Baseline mean ± standard deviation age was 61.9±11.4 years, VFI was 90.7±17.4, MD was -3.50±6.04 dB, and cRNFL thickness was 74.9±12.2 μm. The accuracy of detected glaucoma change prediction using the training set was comparable with the validation set (57.0% and 68.0%, respectively). Prediction deviation from the actual detected change path showed stability throughout patient follow-up. CONCLUSIONS: The 2D CT HMM demonstrated promising prediction performance in detecting glaucoma change performance in a simulated clinical setting using an independent cohort. The 2D CT HMM allows information from just 1 visit to predict at least 5 subsequent visits with similar performance.
Authors: Christopher Kai-Shun Leung; Carol Yim-Lui Cheung; Robert Neal Weinreb; Shu Liu; Cong Ye; Gilda Lai; Nancy Liu; Chi Pui Pang; Kwok Kay Tse; Dennis Shun Chiu Lam Journal: Ophthalmology Date: 2010-11-20 Impact factor: 12.079
Authors: Gadi Wollstein; Joel S Schuman; Lori L Price; Ali Aydin; Paul C Stark; Ellen Hertzmark; Edward Lai; Hiroshi Ishikawa; Cynthia Mattox; James G Fujimoto; Lelia A Paunescu Journal: Arch Ophthalmol Date: 2005-04
Authors: Allison K Ungar; Gadi Wollstein; Hiroshi Ishikawa; Lindsey S Folio; Yun Ling; Richard A Bilonick; Robert J Noecker; Juan Xu; Larry Kagemann; Cynthia Mattox; Joel S Schuman Journal: Ophthalmic Surg Lasers Imaging Date: 2012-05-31
Authors: Gadi Wollstein; Larry Kagemann; Richard A Bilonick; Hiroshi Ishikawa; Lindsey S Folio; Michelle L Gabriele; Allison K Ungar; Jay S Duker; James G Fujimoto; Joel S Schuman Journal: Br J Ophthalmol Date: 2011-04-08 Impact factor: 4.638
Authors: Christopher Kai-shun Leung; Carol Yim Lui Cheung; Robert N Weinreb; Kunliang Qiu; Shu Liu; Haitao Li; Guihua Xu; Ning Fan; Chi Pui Pang; Kwok Kay Tse; Dennis Shun Chiu Lam Journal: Invest Ophthalmol Vis Sci Date: 2009-08-13 Impact factor: 4.799
Authors: Ya Xing Wang; Hongli Yang; Haomin Luo; Seung Woo Hong; Stuart K Gardiner; Jin Wook Jeoung; Christy Hardin; Glen P Sharpe; Kouros Nouri-Mahdavi; Joseph Caprioli; Shaban Demirel; Christopher A Girkin; Jeffrey M Liebmann; Christian Y Mardin; Harry A Quigley; Alexander F Scheuerle; Brad Fortune; Balwantray C Chauhan; Claude F Burgoyne Journal: Am J Ophthalmol Date: 2020-04-13 Impact factor: 5.488