Objective: To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios and explored an AI-based medical referral pattern to improve collaborative efficiency and resource coverage. Methods: The training and validation datasets were derived from the Chinese Medical Alliance for Artificial Intelligence, covering multilevel healthcare facilities and capture modes. The datasets were labelled using a three step strategy: (1)capture mode recognition; (2) cataract diagnosis as a normal lens, cataract or a postoperative eye and (3) detection of referable cataracts with respect to aetiology and severity. Moreover, we integrated the cataract AI agent with a real-world multilevel referral pattern involving self-monitoring at home, primary healthcare and specialised hospital services. Results: The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance in three-step tasks: (1) capture mode recognition (area under the curve (AUC) 99.28%–99.71%), (2) cataract diagnosis (normal lens, cataract or postoperative eye with AUCs of 99.82%, 99.96% and 99.93% for mydriatic-slit lamp mode and AUCs >99% for other capture modes) and (3)detection of referable cataracts (AUCs >91% in all tests). In the real-world tertiary referral pattern, the agent suggested 30.3%  of people be ’referred’, substantially increasing the ophthalmologist-to-population service ratio by 10.2-fold compared with the traditional pattern. Conclusions: The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance and effective service for cataracts. The context of our AI-based medical referral pattern will be extended to other common disease conditions and resource-intensive situations.

Objective: with the intention of effective prevention and treatment for retinal vein occlusion (RVO), this meta-analysis was performed systematically, evaluating the risk factors of RVO in East Asia. Methods: PubMed, Web of Science, Cochrane Library, CNKI, Wanfang and VIP databases were searched for studies that reported risk factors of RVO in East Asia, published from the establishment of the database to May 2024. To further filter the articles, NOS evaluation method was utilized to assess the quality of selected articles. After valid data were extracted, Meta-analysis was performed by Review Manager software. Results: a total of 21 literatures were included, including 27561 cases in the RVO group (Case group) and 514578 cases in the NRVO group (Control group). Results of meta-analysis showed that chronic kidney disease [odds ratio (OR)=4.14, 95% confidence interval (CI): (1.86%, 9.24%)], hypertension [OR=4.11, 95% CI: (3.09%, 5.48%)], hyperlipidemia [OR=3.45, 95%CI: (2.32%, 5.12%)], diabetes mellitus [OR=3.00, 95%CI: (1.88%, 4.80%)], homocysteine [OR=0.87, 95%CI: (0.59%, 1.15%)], have statistically significant differences between the RVO group and the NRVO group(P<0.05). Conclusion: the occurrence of RVO is closely related to its risk factors, such as chronic kidney disease, hypertension, hyperlipidemia, diabetes mellitus and high homocysteine. In the process of diagnosis and treatment of RVO, doctors should focus on the above risk factors to prevent the occurrence of the disease.

Abstract: Corneal blindness represents one of the world’s three major causes of blindness, and the fundamental problem of corneal transplantation is a severe shortage of donor tissues worldwide, resulting in approximately 1.5 million new cases of blindness annually. To address the growing need for corneal transplants two main approaches are being pursued: allogenic and bioengineering cornea. Bioengineering corneas are constructed by naturally generating an extracellular matrix (ECM) component as the scaffold structure with or without corneal cells. It is well established that the scaffold structure directs the fate of cells, therefore, the fabrication of the correct scaffold structure components could produce an ideal corneal substitute, able to mimic the native corneal function. Another key factor in the construction of tissue engineering cornea is seed cells. However, unlike the epithelium and stroma cells, human cornea endothelium cells (HCECs) are notorious for having a limited proliferative capacity in vivo because of the mitotic block at the G1 phase of the cell cycle due to “contact-inhibition”. This review will focus on the main concepts of recent progress towards the scaffold and seed cells, especially endothelial cells for bioengineering cornea, along with future perspectives.