Diagnostic accuracy of current machine learning classifiers for age-related macular degeneration: a systematic review and meta-analysis.

BACKGROUND AND OBJECTIVE: The objective of this study was to systematically review and meta-analyze the diagnostic accuracy of current machine learning classifiers for age-related macular degeneration (AMD). Artificial intelligence diagnostic algorithms can automatically detect and diagnose AMD through training data from large sets of fundus or OCT images. The use of AI algorithms is a powerful tool, and it is a method of obtaining a cost-effective, simple, and fast diagnosis of AMD. METHODS: MEDLINE, EMBASE, CINAHL, and ProQuest Dissertations and Theses were searched systematically and thoroughly. Conferences held through Association for Research in Vision and Ophthalmology, American Academy of Ophthalmology, and Canadian Society of Ophthalmology were searched. Studies were screened using Covidence software and data on sensitivity, specificity and area under curve were extracted from the included studies. STATA 15.0 was used to conduct the meta-analysis. RESULTS: Our search strategy identified 307 records from online databases and 174 records from gray literature. Total of 13 records, 64,798 subjects (and 612,429 images), were used for the quantitative analysis. The pooled estimate for sensitivity was 0.918 [95% CI: 0.678, 0.98] and specificity was 0.888 [95% CI: 0.578, 0.98] for AMD screening using machine learning classifiers. The relative odds of a positive screen test in AMD cases were 89.74 [95% CI: 3.05-2641.59] times more likely than a negative screen test in non-AMD cases. The positive likelihood ratio was 8.22 [95% CI: 1.52-44.48] and the negative likelihood ratio was 0.09 [95% CI: 0.02-0.52]. CONCLUSION: The included studies show promising results for the diagnostic accuracy of the machine learning classifiers for AMD and its implementation in clinical settings.

TGF-ß induces phosphorylation of phosphatase and tensin homolog: implications for fibrosis of the trabecular meshwork tissue in glaucoma.

Fundamental cell signaling mechanisms that regulate dynamic remodeling of the extracellular matrix (ECM) in mechanically loaded tissues are not yet clearly understood. Trabecular meshwork (TM) tissue in the eye is under constant mechanical stress and continuous remodeling of ECM is crucial to maintain normal aqueous humor drainage and intraocular pressure (IOP). However, excessive ECM remodeling can cause fibrosis of the TM as in primary open-angle glaucoma (POAG) patients, and is characterized by increased resistance to aqueous humor drainage, elevated IOP, optic nerve degeneration and blindness. Increased levels of active transforming growth factor-ß2 (TGF-ß2) in the aqueous humor is the main cause of fibrosis of TM in POAG patients. Herein, we report a novel finding that, in TM cells, TGF-ß-induced increase in collagen expression is associated with phosphorylation of phosphatase and tensin homolog (PTEN) at residues Ser380/Thr382/383. Exogenous overexpression of a mutated form of PTEN with enhanced phosphatase activity prevented the TGF-ß-induced collagen expression by TM cells. We propose that rapid alteration of PTEN activity through changes in its phosphorylation status could uniquely regulate the continuous remodeling of ECM in the normal TM. Modulating PTEN activity may have high therapeutic potential to alleviating the fibrosis of TM in POAG patients.

Comparison of allergy rates in glaucoma patients receiving brimonidine 0.2% monotherapy versus fixed-combination brimonidine 0.2%-timolol 0.5% therapy.

OBJECTIVE: To evaluate the incidence of ocular allergy in glaucoma patients prospectively treated with 0.2% brimonidine-0.5% timolol fixed combination (Combigan) compared with the incidence of ocular allergy in patients treated with 0.2% brimonidine (Alphagan) monotherapy. STUDY DESIGN AND METHODS: This was a comparative, non-randomized, single-site, interventional study involving patients with primary open-angle glaucoma or exfoliation syndrome who had not previously used brimonidine in any formulation and had no history of ocular allergy. In one study arm, 102 patients were prospectively treated with twice-daily 0.2% brimonidine-0.5% timolol fixed combination. In the other study arm, medical charts at the same center were reviewed to identify a control group of 102 patients who had been treated with twice-daily 0.2% brimonidine monotherapy. Follow-up was at 1, 3, 6, 9, 12, 15, and 18 months of treatment. MAIN OUTCOME MEASURE: Ocular allergy defined as the presence of follicles and redness severe enough to warrant discontinuation of the medication. RESULTS: The incidence of ocular allergy over 18 months of treatment was 8.8% (9/102) in the fixed-combination group compared with 17.6% (18/102) in the brimonidine group (p=0.097). Kaplan-Meier survival analysis suggested that ocular allergy may be reduced or delayed in patients treated with the brimonidine-timolol fixed combination (p=0.066). CONCLUSIONS: The brimonidine-timolol fixed combination was associated with a 50% lower incidence in ocular allergy compared with 0.2% brimonidine monotherapy. This difference between treatments was not statistically significant (p=0.097) but is likely to be clinically important. Additional studies are needed to evaluate the incidence of ocular allergy associated with brimonidine-timolol fixed combination treatment.