Phacoemulsification combined with intraocular lens (IOL) implantation is the international standard operation procedure for cataract and has been generalized worldwide. However, lens capsule opacification, one of the common complications after cataract surgery, impacts the recovery of patients’ visual function to a large extent. Lens capsule opacification has two types, anterior capsule opacification (ACO) and posterior capsule opacification (PCO), according to the location. There is not an accepted approach to treat ACO. Nd : YAG laser capsulotomy, the common treatment of PCO, can effectively improve the vision, but may cause a series of complications and is inappropriate for children who are too young to cooperate with this treatment. It is generally known that the responses of lens epithelial cells (LECs) after cataract surgery, including cell proliferation, migration, and epithelial-mesenchymal transition (EMT), play a key role in the pathogenesis of lens capsule opacification. Scholars found that substantial drugs can reduce the occurrence of lens capsule opacification by inhibiting, clearing, or killing LECs, and made great efforts as well as innovations on the exploration of drug species or modes of administration. This article is a systematic interpretation and elaboration about how to prevent lens capsule opacification after cataract surgery via different drugs.

Background To investigate the application effect of artificial intelligence (AI)-based fundus screening system in real-world clinical environment. Methods A total of 637 color fundus images were included in the analysis of the application of the AI-based fundus screening system in the clinical environment and 20,355 images were analyzed in the population screening. Results The AI-based fundus screening system demonstrated superior diagnostic effectiveness for diabetic retinopathy (DR), retinal vein occlusion (RVO) and pathological myopia (PM) according to gold standard referral. The sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of three fundus abnormalities were greater (all > 80%) than those for age-related macular degeneration (ARMD), referable glaucoma and other abnormalities. The percentages of different diagnostic conditions were similar in both the clinical environment and the population screening. Conclusions In a real-world setting, our AI-based fundus screening system could detect 7 conditions, with better performance for DR, RVO and PM. Testing in the clinical environment and through population screening demonstrated the clinical utility of our AI-based fundus screening system in the early detection of ocular fundus abnormalities and the prevention of blindness.