No abstract

This study confirms the high prevalence of eye diseases in the elderly. Its main strength is the combination of nutritional, vascular and genetic information, collected over a 7 year period of time before the first eye examination. It may help design future interventional studies, which might be common with other age-related disorders, because of common nutritional factors.

and for the BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) Study Group Objective: To compare the diagnostic performance of an artificial intelligence deep learning system with that of expert neuro-ophthalmologists in classifying optic disc appearance. Methods: The deep learning system was previously trained and validated on 14,341 ocular fundus photographs from 19 international centers. The performance of the system was evaluated on 800 new fundus photographs (400 normal optic discs, 201 papilledema [disc edema from elevated intracranial pressure], 199 other optic disc abnormalities) and compared with that of 2 expert neuro-ophthalmologists who independently reviewed the same randomly presented images without clinical information. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were calculated. Results: The system correctly classified 678 of 800 (84.7%) photographs, compared with 675 of 800 (84.4%) for Expert 1 and 641 of 800 (80.1%) for Expert 2. The system yielded areas under the receiver operating characteristic curve of 0.97 (95% confidence interval [CI] = 0.96-0.98), 0.96 (95% CI = 0.94-0.97), and 0.89 (95% CI = 0.87-0.92) for the detection of normal discs, papilledema, and other disc abnormalities, respectively. The accuracy, sensitivity, and specificity of the system's classification of optic discs were similar to or better than the 2 experts. Intergrader agreement at the eye level was 0.71 (95% CI = 0.67-0.76) between Expert 1 and Expert 2, 0.72 (95% CI = 0.68-0.76) between the system and Expert 1, and 0.65 (95% CI = 0.61-0.70) between the system and Expert 2. Interpretation: The performance of this deep learning system at classifying optic disc abnormalities was at least as good as 2 expert neuro-ophthalmologists. Future prospective studies are needed to validate this system as a diagnostic aid in relevant clinical settings.

BackgroundSeveral genes implicated in high-density lipoprotein (HDL) metabolism have been reported to be associated with age-related macular degeneration (AMD). Furthermore, HDL transport the two carotenoids, lutein and zeaxanthin, which are highly suspected to play a key-role in the protection against AMD. The objective is to confirm the associations of HDL-related loci with AMD and to assess their associations with plasma lutein and zeaxanthin concentrations.MethodsAlienor study is a prospective population-based study on nutrition and age-related eye diseases performed in 963 elderly residents of Bordeaux, France. AMD was graded according to the international classification, from non-mydriatic colour retinal photographs. Plasma lutein and zeaxanthin were determined by normal-phase high-performance liquid chromatography. The following polymorphisms were studied: rs493258 and rs10468017 (LIPC), rs3764261 (CETP), rs12678919 (LPL) and rs1883025 (ABCA1).ResultsAfter multivariate adjustment, the TT genotype of the LIPC rs493258 variant was significantly associated with a reduced risk for early and late AMD (OR=0.64, 95%CI: 0.41-0.99; p=0.049 and OR=0.26, 95%CI: 0.08-0.85; p=0.03, respectively), and with higher plasma zeaxanthin concentrations (p=0.03), while plasma lipids were not significantly different according to this SNP. Besides, the LPL variant was associated with early AMD (OR=0.67, 95%CI: 0.45-1.00; p=0.05) and both with plasma lipids and plasma lutein (p=0.047). Associations of LIPC rs10468017, CETP and ABCA1 polymorphisms with AMD did not reach statistical significance.ConclusionThese findings suggest that LIPC and LPL genes could both modify the risk for AMD and the metabolism of lutein and zeaxanthin.