Comparison and Correlation of Retinal Sensitivity between Microperimetry and Standard Automated Perimetry in Low-Tension Glaucoma

AbstractThe main goal of this study is to identify the association between corneal shape, elevation, and thickness parameters and visual field damage using machine learning. A total of 676 eyes from 568 patients from the Jichi Medical University in Japan were included in this study. Corneal topography, pachymetry, and elevation images were obtained using anterior segment optical coherence tomography (OCT) and visual field tests were collected using standard automated perimetry with 24-2 Swedish Interactive Threshold Algorithm. The association between corneal structural parameters and visual field damage was investigated using machine learning and evaluated through tenfold cross-validation of the area under the receiver operating characteristic curves (AUC). The average mean deviation was − 8.0 dB and the average central corneal thickness (CCT) was 513.1 µm. Using ensemble machine learning bagged trees classifiers, we detected visual field abnormality from corneal parameters with an AUC of 0.83. Using a tree-based machine learning classifier, we detected four visual field severity levels from corneal parameters with an AUC of 0.74. Although CCT and corneal hysteresis have long been accepted as predictors of glaucoma development and future visual field loss, corneal shape and elevation parameters may also predict glaucoma-induced visual functional loss.

Download Full-text

Ganglion cell complex scan in the early prediction of glaucoma

Nepalese Journal of Ophthalmology ◽

10.3126/nepjoph.v4i2.6538 ◽

2012 ◽

Vol 4 (2) ◽

pp. 236-241

Author(s):

S Ganekal

Keyword(s):

Ganglion Cell ◽

Cell Complex ◽

P Value ◽

Ganglion Cell Complex ◽

Automated Perimetry ◽

Standard Automated Perimetry ◽

Fiber Layer ◽

Color Code ◽

Rnfl Thickness ◽

Significant Difference

Objective: To compare the macular ganglion cell complex (GCC) with peripapillary retinal fiber layer (RNFL) thickness map in glaucoma suspects and patients. Subjects and methods: Forty participants (20 glaucoma suspects and 20 glaucoma patients) were enrolled. Macular GCC and RNFL thickness maps were performed in both eyes of each participant in the same visit. The sensitivity and specificity of a color code less than 5% (red or yellow) for glaucoma diagnosis were calculated. Standard Automated Perimetry was performed with the Octopus 3.1.1 Dynamic 24-2 program. Statistics: The statistical analysis was performed with the SPSS 10.1 (SPSS Inc. Chicago, IL, EUA). Results were expressed as mean ± standard deviation and a p value of 0.05 or less was considered significant. Results: Provide absolute numbers of these findings with their units of measurement. There was a statistically significant difference in average RNFL thickness (p=0.004), superior RNFL thickness (p=0.006), inferior RNFL thickness (p=0.0005) and average GCC (p=0.03) between the suspects and glaucoma patients. There was no difference in optic disc area (p=0.35) and vertical cup/disc ratio (p=0.234) in both groups. While 38% eyes had an abnormal GCC and 13% had an abnormal RNFL thickness in the glaucoma suspect group, 98% had an abnormal GCC and 90% had an abnormal RNFL thickness in the glaucoma group.Conclusion: The ability to diagnose glaucoma with macular GCC thickness is comparable to that with peripapillary RNFL thickness. Macular GCC thickness measurements may be a good alternative or a complementary measurement to RNFL thickness assessment in the clinical evaluation of glaucoma.DOI: http://dx.doi.org/10.3126/nepjoph.v4i2.6538 Nepal J Ophthalmol 2012; 4 (2): 236-241

Download Full-text