Artificial intelligence (AI) has great potential to transform healthcare by enhancing the workflow and productivity of clinicians, enabling existing staff to serve more patients, improving patient outcomes, and reducing health disparities. In the field of ophthalmology, AI systems have shown performance comparable with or even better than experienced ophthalmologists in tasks such as diabetic retinopathy detection and grading. However, despite these quite good results, very few AI systems have been deployed in real-world clinical settings, challenging the true value of these systems. This review provides an overview of the current main AI applications in ophthalmology, describes the challenges that need to be overcome prior to clinical implementation of the AI systems, and discusses the strategies that may pave the way to the clinical translation of these systems.

In this study, we explored the effects of particulate matter 2.5 (PM_2.5) eye drops on the ocular surface structure and tear function in mice and established a novel animal model for dry eye research. We found that, following treatment with PM_2.5, the tear volume and, the tear film break-up time showed statistical differences at each time point (P < 0.05). The FL score of the PM_2.5-treated group was higher than that of others (P < 0.05). The average number of corneal epithelial layer cells in groups A and B was significantly lower than that in group C (P < 0.05). Scanning electron microscopy and transmission electron microscopy revealed that the number of corneal epithelial microvilli and corneal desmosomes was drastically reduced in group C. PM_2.5 induced apoptosis in the corneal superficial and basal epithelium and led to abnormal differentiation and proliferation of the ocular surface with higher expression levels of Ki67 and a reduced number of goblet cells in the conjunctival fornix in group C. PM_2.5 significantly increased the levels of TNF-α, NF-κB p65 (phospho S536), and NF-κB in the cornea. Thus, the topical administration of PM_2.5 in mice induces ocular surface changes that are similar to those of dry eye in humans, representing a novel model of dry eye.

Objective: The aim of this study is to use amplitude of low-frequency fluctuation (ALFF) as a method to explore the local features of spontaneous brain activity in patients with primary angle - closure glaucoma (PACG) and ALFFs relationship with the behavioral performances. Methods: A total of twenty one patients with PACG (eight males and 13 females), and twenty one healthy subjects (nine males and twelve females) closely matched in age, sex, and education, each underwent a resting-state functional magnetic resonance imaging scan. The ALFF method was used to assess the local features of spontaneous brain activity. The correlation analysis was used to explore the relationships between the observed mean ALFF signal values of the different areas in PACG patients and the thickness of the retinal nerve fiber layer (RNFL). Results: Compared with the healthy subjects, patients with PACG had significant lower ALFF areas in the left precentral gyrus, bilateral middle frontal gyrus, bilateral superior frontal gyrus, right precuneus, and right angular gyrus, and higher areas in the right precentral gyrus. In the PACG group, there were significant negative correlations between the mean ALFF signal value of the right middle frontal gyrus and the left mean RNFL thickness (r=-0.487, P=0.033), and between the mean ALFF signal value of the left middle frontal gyrus and the right mean RNFL thickness (r=-0.504, P=0.020). Conclusion: PACG mainly involved in the dysfunction in the frontal lobe, which may reflect the underlying pathologic mechanism of PACG.