Predicting glaucomatous progression in glaucoma suspect eyes using relevance vector machine classifiers for combined structural and functional measurements.

PURPOSE The goal of this study was to determine if glaucomatous progression in suspect eyes can be predicted from baseline confocal scanning laser ophthalmoscope (CSLO) and standard automated perimetry (SAP) measurements analyzed with relevance vector machine (RVM) classifiers. METHODS Two hundred sixty-four eyes of 193 participants were included. All eyes had normal SAP results at baseline with five or more SAP tests over time. Eyes were labeled progressed (n = 47) or stable (n = 217) during follow-up based on SAP Guided Progression Analysis or serial stereophotograph assessment. Baseline CSLO-measured topographic parameters (n = 117) and baseline total deviation values from the 24-2 SAP test-grid (n = 52) were selected from each eye. Ten-fold cross-validation was used to train and test RVMs using the CSLO and SAP features. Receiver operating characteristic (ROC) curve areas were calculated using full and optimized feature sets. ROC curve results from RVM analyses of CSLO, SAP, and CSLO and SAP combined were compared to CSLO and SAP global indices (Glaucoma Probability Score, mean deviation and pattern standard deviation). RESULTS The areas under the ROC curves (AUROCs) for RVMs trained on optimized feature sets of CSLO parameters, SAP parameters, and CSLO and SAP parameters combined were 0.640, 0.762, and 0.805, respectively. AUROCs for CSLO Glaucoma Probability Score, SAP mean deviation (MD), and SAP pattern standard deviation (PSD) were 0.517, 0.513, and 0.620, respectively. No CSLO or SAP global indices discriminated between baseline measurements from progressed and stable eyes better than chance. CONCLUSIONS In our sample, RVM analyses of baseline CSLO and SAP measurements could identify eyes that showed future glaucomatous progression with a higher accuracy than the CSLO and SAP global indices. (ClinicalTrials.gov numbers, NCT00221897, NCT00221923.).

[1]  Mei-Ling Huang,et al.  Development and comparison of automated classifiers for glaucoma diagnosis using Stratus optical coherence tomography. , 2005, Investigative ophthalmology & visual science.

[2]  Anders Heijl,et al.  Effects of input data on the performance of a neural network in distinguishing normal and glaucomatous visual fields. , 2005, Investigative ophthalmology & visual science.

[3]  S. Miglior,et al.  Predictive factors for open-angle glaucoma among patients with ocular hypertension in the European Glaucoma Prevention Study. , 2007, Ophthalmology.

[4]  Terrence J. Sejnowski,et al.  Comparison of machine learning and traditional classifiers in glaucoma diagnosis , 2002, IEEE Transactions on Biomedical Engineering.

[5]  Anders Heijl,et al.  Trained Artificial Neural Network for Glaucoma Diagnosis Using Visual Field Data: A Comparison With Conventional Algorithms , 2007, Journal of glaucoma.

[6]  Robert N Weinreb,et al.  Comparing neural networks and linear discriminant functions for glaucoma detection using confocal scanning laser ophthalmoscopy of the optic disc. , 2002, Investigative ophthalmology & visual science.

[7]  Christopher Bowd,et al.  Machine Learning Classifiers in Glaucoma , 2008, Optometry and vision science : official publication of the American Academy of Optometry.

[8]  Robert N Weinreb,et al.  Combining Functional and Structural Tests Improves the Diagnostic Accuracy of Relevance Vector Machine Classifiers , 2010, Journal of glaucoma.

[9]  Edward A Essock,et al.  Predicting Visual Field Loss in Ocular Hypertensive Patients Using Wavelet-Fourier Analysis of GDx Scanning Laser Polarimetry , 2004, Optometry and vision science : official publication of the American Academy of Optometry.

[10]  S. Fieuws,et al.  Agreement and accuracy of non-expert ophthalmologists in assessing glaucomatous changes in serial stereo optic disc photographs. , 2011, Ophthalmology.

[11]  Robert N Weinreb,et al.  Confocal scanning laser ophthalmoscopy classifiers and stereophotograph evaluation for prediction of visual field abnormalities in glaucoma-suspect eyes. , 2004, Investigative ophthalmology & visual science.

[12]  C. Erb,et al.  Short wavelength automated perimetry, frequency doubling technology perimetry, and pattern electroretinography for prediction of progressive glaucomatous standard visual field defects. , 2002, Ophthalmology.

[13]  Susan Vitale,et al.  Agreement among glaucoma specialists in assessing progressive disc changes from photographs in open-angle glaucoma patients. , 2009, American journal of ophthalmology.

[14]  Christopher M. Bishop,et al.  Variational Relevance Vector Machines , 2000, UAI.

[15]  Anders Heijl,et al.  Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT , 2010, Acta ophthalmologica.

[16]  J. Jonas,et al.  Predictive factors of the optic nerve head for development or progression of glaucomatous visual field loss. , 2004, Investigative ophthalmology & visual science.

[17]  Robert N Weinreb,et al.  Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. , 2002, Investigative ophthalmology & visual science.

[18]  M. Morales i Ballús,et al.  Baseline Optical Coherence Tomography Predicts the Development of Glaucomatous Change in Glaucoma Suspects , 2007 .

[19]  Susan E. George,et al.  Artificial neural network analysis of noisy visual field data in glaucoma , 1997, Artif. Intell. Medicine.

[20]  T. Sejnowski,et al.  Relevance vector machine and support vector machine classifier analysis of scanning laser polarimetry retinal nerve fiber layer measurements. , 2005, Investigative ophthalmology & visual science.

[21]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[22]  A Heijl,et al.  Early Manifest Glaucoma Trial: design and baseline data. , 1999, Ophthalmology.

[23]  D. Garway-Heath,et al.  Predicting Progression to Glaucoma in Ocular Hypertensive Patients , 2009, Journal of glaucoma.

[24]  Gang Li,et al.  A Unified Approach to Nonparametric Comparison of Receiver Operating Characteristic Curves for Longitudinal and Clustered Data , 2008, Journal of the American Statistical Association.

[25]  Robert N Weinreb,et al.  Performance of confocal scanning laser tomograph Topographic Change Analysis (TCA) for assessing glaucomatous progression. , 2009, Investigative ophthalmology & visual science.

[26]  F. Medeiros,et al.  Prediction of functional loss in glaucoma from progressive optic disc damage. , 2009, Archives of ophthalmology.

[27]  J. Beiser,et al.  Baseline topographic optic disc measurements are associated with the development of primary open-angle glaucoma: the Confocal Scanning Laser Ophthalmoscopy Ancillary Study to the Ocular Hypertension Treatment Study. , 2005, Archives of ophthalmology.

[28]  T. Sejnowski,et al.  Heidelberg retina tomograph measurements of the optic disc and parapapillary retina for detecting glaucoma analyzed by machine learning classifiers. , 2004, Investigative ophthalmology & visual science.

[29]  V Rihani,et al.  Artificial Neural Network-Based Glaucoma Diagnosis Using Retinal Nerve Fiber Layer Analysis , 2008, European journal of ophthalmology.

[30]  Chris A. Johnson,et al.  The Ocular Hypertension Treatment Study: baseline factors that predict the onset of primary open-angle glaucoma. , 2002, Archives of ophthalmology.

[31]  Robert N Weinreb,et al.  Retinal nerve fiber layer thickness measurements with scanning laser polarimetry predict glaucomatous visual field loss. , 2004, American journal of ophthalmology.

[32]  C. Glymour,et al.  Optical coherence tomography machine learning classifiers for glaucoma detection: a preliminary study. , 2005, Investigative ophthalmology & visual science.

[33]  J Katz,et al.  Neural networks for visual field analysis: how do they compare with other algorithms? , 1999, Journal of glaucoma.

[34]  Te-Won Lee,et al.  Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes. , 2008, Investigative ophthalmology & visual science.

[35]  D B Henson,et al.  Spatial classification of glaucomatous visual field loss. , 1996, The British journal of ophthalmology.

[36]  Johan A. K. Suykens,et al.  Advances in learning theory : methods, models and applications , 2003 .

[37]  Jean L Freeman,et al.  A non-parametric method for the comparison of partial areas under ROC curves and its application to large health care data sets. , 2002, Statistics in medicine.

[38]  David Keating,et al.  Visual field interpretation with a personal computer based neural network , 1994, Eye.

[39]  Chris A Johnson,et al.  Predicting progressive glaucomatous optic neuropathy using baseline standard automated perimetry data. , 2009, Investigative ophthalmology & visual science.

[40]  M H Goldbaum,et al.  Interpretation of automated perimetry for glaucoma by neural network. , 1994, Investigative ophthalmology & visual science.

[41]  Terrence J. Sejnowski,et al.  Probability of Glaucoma Determined from Standard Automated Perimetry and from Optic Disk Topography using Relevance Vector Machine Classifiers , 2004 .

[42]  C. Micchelli,et al.  Bayesian Regression and Classification , 2003 .

[43]  C. Bunce,et al.  The ability of the GDx Nerve Fibre Analyser neural network to diagnose glaucoma , 2001, Graefe's Archive for Clinical and Experimental Ophthalmology.

[44]  L Brigatti,et al.  Neural networks to identify glaucoma with structural and functional measurements. , 1996, American journal of ophthalmology.

[45]  D B Henson,et al.  Visual field analysis using artificial neural networks , 1994, Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians.

[46]  K. A. Townsend,et al.  Heidelberg Retina Tomograph 3 machine learning classifiers for glaucoma detection , 2008, British Journal of Ophthalmology.

[47]  Robert N Weinreb,et al.  Comparison of HRT-3 glaucoma probability score and subjective stereophotograph assessment for prediction of progression in glaucoma. , 2008, Investigative ophthalmology & visual science.

[48]  F. Medeiros,et al.  Frequency doubling technology perimetry abnormalities as predictors of glaucomatous visual field loss. , 2004, American journal of ophthalmology.

[49]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.