Logistic regression analysis for glaucoma diagnosis using Stratus Optical Coherence Tomography.

摘要

PURPOSES: The purposes of this study are to investigate the diagnostic performance of logistic regression analysis (LRA) applied to multidimensional information on glaucoma disease and to determine the area under receiver operator characteristic curves (AROCs) for differentiating between normal and glaucomatous eyes in the Taiwan Chinese population based on the summary data from the Stratus Optical Coherence Tomography (OCT). METHODS: One randomly selected eye from each of the 89 patients with glaucoma and from each of the 88 age- and gender-matched normal individuals were included in the study. Nine glaucomatous eyes and eight normal eyes were excluded as a result of poor OCT scans. Finally, 80 normal eyes and 80 glaucomatous eyes (mean deviation, -4.5 +/- 4.12 dB) were analyzed. The whole dataset was split into four equal sets. Each set combines 20 patients with glaucoma and 20 normal individuals. Fourfold crossvalidation was conducted. Retinal nerve fiber layer thickness and optic nerve head were measured by Stratus OCT in each patient. Twenty-five OCT parameters were included in a LRA method to determine the best combination of parameters for discriminating between glaucomatous and healthy eyes based on AROCs. RESULTS: With the LRA method, the AROC for glaucoma detection was 0.911 with sensitivity at 80% and 90% specificity were 83.7% and 80.0%, respectively. CONCLUSIONS: Compared with the OCT-provided parameters, the LRA method improved the ability to differentiate between normal and glaucomatous eyes in the Taiwan Chinese population.