Retinal Vein Occlusion (RVO)

We developed an artificial intelligence system, called QiLin, which was designed to assist anti-VEGF treatment decisions in retinal diseases. QiLin was trained and validated via over 20,000 optical coherence tomography images from multicenter datasets, demonstrating strong performance on both internal and external validation. To evaluate its real-world clinical utility, we conducted a randomized controlled trial that rigorously compares the accuracy of treatment decisions between a physician-only arm and an AI-assisted physician arm.

This randomized controlled trial evaluates whether providing clinicians with AI-derived quantitative retinal information improves the quality and efficiency of retinal clinical assessment. Participating ophthalmologists and ophthalmology trainees will be randomly assigned to one of two groups. The intervention group will write clinical reports with access to automated quantitative measurements generated from fundus image analysis, including multiple retinal structural and vascular biomarkers. The control group will complete the same reporting tasks using only the original fundus images without AI-generated quantitative information. All reports produced by both groups will be de-identified and independently evaluated by a separate panel of senior ophthalmologists who are blinded to group allocation. The expert evaluators will assess report accuracy, completeness, clarity, and overall clinical quality using predefined scoring criteria. The study aims to determine whether access to quantitative retinal biomarkers enhances clinicians' reporting performance and reduces reporting time during retinal assessment tasks.

Retinal vein occlusion (RVO), a common retinal vascular disease, is frequently treated with anti-vascular endothelial growth factor (anti-VEGF) agents as first-line therapy. However, anti-VEGF monotherapy lacks neuroprotective effects, primarily targets vascular leakage and neovascularization, and requires frequent long-term injections that impose substantial economic burdens. Combined therapeutic strategies addressing both vascular pathology and neural damage are therefore being explored. This article describes the protocol for a randomized, outcome-blinded, placebo-controlled clinical trial evaluating mecobalamin (a widely used neuroprotective drug) in combination with anti-VEGF for the treatment of macular edema (ME). A total of 120 eligible RVO patients will be enrolled from the First Affiliated Hospital of Chongqing Medical University. Participants will be randomly assigned (1:1) to an experimental group and a control group. The experimental group will receive conventional anti-VEGF therapy plus oral mecobalamin capsules for 6 months, while the control group will receive the same anti-VEGF treatment plus a placebo for 6 months. All patients will undergo one year of follow-up after initial treatment, with visits at 1, 3, 6, 9, and 12 months. The primary outcome is the change in central subfield thickness (CST) from baseline to one year post-initial treatment. Secondary outcomes include: * Change in best-corrected visual acuity (BCVA) from baseline over time, * Capillary density, * Cone photoreceptor distribution characteristics, * Mean light sensitivity and fixation stability, * Serum vitamin B12 levels, * Number of anti-VEGF treatments, * Injection frequency (times per year), * Treatment interval, * Incidence and severity of adverse events (AEs) and serious adverse events (SAEs). This trial evaluates a novel "neuroprotection + vascular intervention" strategy combining mecobalamin with anti-VEGF therapy. The trial aims to provide high-level evidence for synergistic RVO treatment, with the potential to reduce recurrence rates and improve long-term visual function prognosis.

This observational study aims to establish key technologies for high-throughput, large-model-based AI-assisted diagnosis using optical coherence tomography (OCT) and OCT angiography (OCTA). The study will collect real-world OCT/OCTA images and corresponding clinical information from patients with common blinding retinal and optic nerve diseases at Peking Union Medical College Hospital. A high-throughput diagnostic framework based on large-scale artificial intelligence models will be developed and evaluated. The primary objective is to determine the diagnostic performance of the AI system, including its ability to identify diabetic retinopathy, branch retinal vein occlusion, central retinal vein occlusion, age-related macular degeneration, pathologic myopic choroidal neovascularization, and glaucoma-related optic nerve damage. The results of this study are expected to support the development of standardized, efficient, and scalable AI-assisted diagnostic pathways for OCT imaging in clinical practice.

Generally, DM is caused by insufficient insulin secretion in the body; however, the other biological mechanisms remain unclear. Long-term illness in patients with DM damages various organs in the body, such as the eyes, kidneys, and heart, seriously affecting organ function. Nowadays, the quality of life of people has improved significantly, eating habits have changed, sugar intake is increasing, and the number of patients with DM is increasing. Statistics show that in 2017, the number of patients with DM worldwide reached 425 million (aged 20-79 years), which will exceed 600 million in 30 years; moreover, patients in low- and middle-income countries, such as China and India, account for 80 percent of the total DM population (1). According to the WHO, patients with DM worldwide increased to 366 million in 2011, which is expected to increase to 500 million in 2025, with more than 150 million patients experiencing ocular complications, such as diabetic retinopathy (DR) (2, 3). DR is a form of ocular microangiopathy and the most serious DM-related complication; it seriously endangers the health of patients with DM (4). DR pathogenesis includes increased endothelial cells in the eye capillaries, increased intimal thickness, damaged pericytes, microangioma, and damaged blood-retina barrier due to increased permeability of the blood vessels, microvascular obstruction, and neovascularization (NV) (5, 6). Currently, the prevalence of DR is 34.6% worldwide; however, it is higher in some developed countries, reaching 40.3% (7). The proportion of patients with type 1 and 2 DM suffering from blindness due to DR is 3.6% and 1.6%, respectively (8). DR is associated with significantly reduced living standards, huge medical costs, and increased social burden (9, 10). Many anti-vascular endothelial growth factor (VEGF) drugs exist; however, the use of therapeutic drugs is strictly controlled. The main drugs recommended for treating DM-related visual complications are ranibizumab and aflibercept.