Machine learning classifiers were employed to detect glaucomatous progression using longitudinal series of structural data extracted from retinal nerve fiber layer thickness measurements and visual functional data recorded from standard automated perimetry tests. Using the collected data, a longitudinal feature vector was created for each patient's eye by computing the norm 1 difference vector of the data at the baseline and at each follow-up visit. The longitudinal features from each patient's eye were then fed to the machine learning classifier to classify each eye as stable or progressed over time. This study was performed using several machine learning classifiers including Bayesian, Lazy, Meta, and Tree, composing different families. Combinations of structural and functional features were selected and ranked to determine the relative effectiveness of each feature. Finally, the outcomes of the classifiers were assessed by several performance metrics and the effectiveness of structural and functional features were analyzed.
Purpose: To investigate the association between the microstructure of β-zone parapapillary atrophy (βPPA) and parapapillary deep-layer microvasculature dropout assessed by optical coherence tomography angiography (OCT-A). Methods: Thirty-seven eyes with βPPA devoid of the Bruch's membrane (BM) (γPPA) ranging between completely absent and discontinuous BM were matched by severity of the visual field (VF) damage with 37 eyes with fully intact BM (βPPA+BM) based on the spectral-domain (SD) OCT imaging. Parapapillary deep-layer microvasculature dropout was defined as a dropout of the microvasculature within choroid or scleral flange in the βPPA on the OCT-A. The widths of βPPA, γPPA, and βPPA+BM were measured on six radial SD-OCT images. Prevalence of the dropout was compared between eyes with and without γPPA. Logistic regression was performed for evaluating association of the dropout with the width of βPPA, γPPA, and βPPA+BM, and the γPPA presence. Results: Eyes with γPPA had significantly higher prevalence of the dropout than did those without γPPA (75.7% versus 40.8%; P = 0.004). In logistic regression, presence and longer width of the γPPA, worse VF mean deviation, and presence of focal lamina cribrosa defects were significantly associated with the dropout (P < 0.05), whereas width of the βPPA and βPPA+BM, axial length, and choroidal thickness were not (P > 0.10). Conclusions: Parapapillary deep-layer microvasculature dropout was associated with the presence and larger width of γPPA, but not with the βPPA+BM width. Presence and width of the exposed scleral flange, rather than the retinal pigmented epithelium atrophy, may be associated with deep-layer microvasculature dropout.
To evaluate the long-term variability of GDx VCC retinal nerve fiber layer (RNFL) thickness measurements.The study enrolled a cohort of glaucoma suspects who did not develop any evidence of visual field damage or change in the appearance of the optic nerve during an average follow-up of 9.1+/-3.2 years. Subjects underwent ocular imaging using the commercially available GDx VCC scanning laser polarimeter. At each visit, each eye was imaged 3 times. Subjects underwent repeated testing with GDx VCC at approximately 12-month intervals during their follow-up. In total, 255 examinations were obtained in 31 eyes of 31 individuals during an average GDx VCC follow-up time of 26.0+/-8.9 months. A random effects analysis of variance model was used to estimate intraclass correlation coefficients and long-term and short-term variability estimates.Intraclass correlation coefficients ranged from 0.77 to 0.86 for GDx VCC parameters. Short-term variability estimates ranged from 2.45 to 3.89 microm for RNFL thickness parameters, whereas the short-term variability estimate for the parameter Nerve Fiber Indicator was 3.71. Long-term variability was slightly higher than short-term variability for all parameters. For RNFL thickness parameters, long-term variability estimates ranged from 3.21 to 4.97 microm, whereas for the parameter Nerve Fiber Indicator the long-term variability estimate was 4.93.RNFL measurements obtained with the GDx VCC were found to be highly reproducible in a long-term test-retest situation, supporting the use of this instrument for longitudinal assessment of the RNFL.
A population-based study found an overall incidence rate of symptomatic retinal vein occlusion (RVO) in a 4-year period to be 2.14 per 1,000 in the 40 years and over age group. When cases found among glaucoma clinic patients were separated from the remainder of the population there was marked difference in the incidence rate of RVO in the same time period (1.85 and 17.3 per 1,000, respectively). The rate of RVO increased significantly (p less than 0.001) with age in the general population from 0.93 per 1,000 among persons under 64 years of age to 5.36 per 1,000 among persons over 65. The increase in the rate of RVO by age was less dramatic in the glaucoma clinic population. The two populations also differed in the frequency of the occlusion type: the ratio of the rate of branch vein occlusion to central vein occlusion was 3.2:1 in the general population, but equally distributed in the glaucoma clinic population. Persons with increased intraocular pressure and/or glaucoma were found to have a higher prevalence of RVO than persons with no history of elevated intraocular pressure.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)