A deep-learning system predicts glaucoma incidence and progression using retinal photographs.

BackgroundDeep learning has been widely used for glaucoma diagnosis. However, there is no clinically validated algorithm for glaucoma incidence and progression prediction. This study aims to develop a clinically feasible deep-learning system for predicting and stratifying the risk of glaucoma onset and progression based on color fundus photographs (CFPs), with clinical validation of performance in external population cohorts.MethodsWe established data sets of CFPs and visual fields collected from longitudinal cohorts. The mean follow-up duration was 3 to 5 years across the data sets. Artificial intelligence (AI) models were developed to predict future glaucoma incidence and progression based on the CFPs of 17,497 eyes in 9346 patients. The area under the receiver operating characteristic (AUROC) curve, sensitivity, and specificity of the AI models were calculated with reference to the labels provided by experienced ophthalmologists. Incidence and progression of glaucoma were determined based on longitudinal CFP images or visual fields, respectively.ResultsThe AI model to predict glaucoma incidence achieved an AUROC of 0.90 (0.81-0.99) in the validation set and demonstrated good generalizability, with AUROCs of 0.89 (0.83-0.95) and 0.88 (0.79-0.97) in external test sets 1 and 2, respectively. The AI model to predict glaucoma progression achieved an AUROC of 0.91 (0.88-0.94) in the validation set, and also demonstrated outstanding predictive performance with AUROCs of 0.87 (0.81-0.92) and 0.88 (0.83-0.94) in external test sets 1 and 2, respectively.ConclusionOur study demonstrates the feasibility of deep-learning algorithms in the early detection and prediction of glaucoma progression.FUNDINGNational Natural Science Foundation of China (NSFC); the High-level Hospital Construction Project, Zhongshan Ophthalmic Center, Sun Yat-sen University; the Science and Technology Program of Guangzhou, China (2021), the Science and Technology Development Fund (FDCT) of Macau, and FDCT-NSFC.

Effect of steam explosion pretreatment on the structure and bioactivity of Ampelopsis grossedentata polysaccharides.

Steam explosion (SE) was a friendly environmentally pretreatment method. In this study, the effect of steam explosion (SE) pretreatment on structure and α-glucosidase inhibitory activity of Ampelopsis grossedentata polysaccharides was evaluated. Two novel polysaccharides (AGP and AGP-SE) were extracted, isolated, purified and analyzed by NMR, FT-IR and methylation. The results indicated that AGP mainly consisted of Rha, Xyl, Glc, and Ara with a molecular weight of 2.74 × 103 kDa and AGP-SE mainly consisted of Man, Ara, and Gal with a molecular weight of 2.14 × 103 kDa. Furthermore, the backbone of AGP and AGP-SE were mainly composed of 5)-Araf-(1→, -Glcp-(1→, 6)-Glcp-(1→, 6)-Galp-(1→, 3,6)-Manp-(1→, and 2,3,6)-Glcp-(1→. Finally, we demonstrated that all polysaccharides exhibited obviously α-glucosidase inhibition activity and mixed type inhibition. AGP-SE had better α-glucosidase inhibition activity and the binding affinity KD on α-glucosidase by using Surface Plasmon Resonance (SPR) than AGP. Overall, SE pretreatment is an effective method for extracting polysaccharide and provides a new idea into the improvement of biological activity.

[The correlation between carotid stenosis detected by neck vascular ultrasound and branch retinal vein occlusion].

OBJECTIVE: To discuss the clinical significance of the neck vascular ultrasound examination in patients with branch retinal vein occlusion (BRVO). METHODS: Case-control study. Thirty patients of BRVO and 30 healthy subjects with no ophthalmic and systemic symptoms were recruited from January 2010 to January 2012 in the Department of Ophthalmology of the First People's Hospital of Dali Prefecture. The neck vascular ultrasound examination was performed in two groups. The incidence of carotid atheromatous plaque, the rate of carotid stenosis and the carotid artery resistance index (RI) were compared using chi square test. Logistic regression analysis of the rate of carotid stenosis and carotid artery RI were performed. RESULTS: In BRVO group, 23 cases had carotid atheromatous plaque with the incidence of 76.7% Nineteen cases had carotid stenosis with the incidence of 63.3%. The average carotid artery RI was 0.66. In control group, carotid artery atheromatous plaque was found on 6 subjects with incidence of 20.0%. Carotid artery stenosis was detected in 3 subjects with incidence of 10.0%. The average carotid artery RI was 0.61. The incidence of carotid artery atheromatous plaque and carotid stenosis and carotid artery RI in BRVO group were significantly higher than the control group. The difference was statistically significant (P < 0.05). Logistic regression analysis showed that carotid artery stenosis (partial regression coefficien t = 2.263, OR = 9.611, P = 0.004) and carotid artery RI (partial regression coefficien t = 23.713, OR = 669.273, P = 0.006) had influence in BRVO patients as risk factors. CONCLUSION: Early detection of carotid scleratheroma and carotid artery stenosis by the carotid artery ultrasound examination played an important role in prevention or treatment of BRVO.