Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore.
Asia Pac J Ophthalmol (Phila). 2022;11(2):149-159. doi: 10.1097/APO.0000000000000509.
Structural and functional alterations in the microcirculation by systemic hypertension can cause significant organ damage at the eye, heart, brain, and kidneys. As the retina is the only tissue in the body that allows direct imaging of small vessels, the relationship of hypertensive retinopathy signs with development of disease states in other organs have been extensively studied; large-scale epidemiological studies using fundus photography and advanced semi-automated analysis software have reported the association of retinopathy signs with hypertensive end-organ damage includes the following: stroke, dementia, and coronary heart disease. Although yielding much useful information, the vessels assessed from fundus photographs remain limited to the larger retinal arterioles and venules, and abnormalities observed may not be that of the earliest changes. Newer imaging modalities such as optical coherence tomography angiography and adaptive optics technology, which allow a greater precision in the structural quantification of retinal vessels, including capillaries, may facilitate the assessment and management of these patients. The advent of deep learning technology has also augmented the utility of fundus photographs to help create diagnostic and risk stratification systems. Particularly, deep learning systems have been shown in several large studies to be able to predict multiple cardiovascular risk factors, major adverse cardiovascular events within 5 years, and presence of coronary artery calcium, from fundus photographs alone. In the future, combining deep learning systems with the imaging precision offered by optical coherence tomography angiography and adaptive optics could pave way for systems that are able to predict adverse clinical outcomes even more accurately.
系统性高血压引起的微循环结构和功能改变可导致眼、心、脑和肾脏等重要器官损伤。由于视网膜是体内唯一允许直接观察小血管的组织，因此高血压性视网膜病变的特征与其他器官疾病状态的发展之间的关系已得到广泛研究；使用眼底摄影和先进的半自动分析软件进行的大规模流行病学研究报告了视网膜病变特征与高血压靶器官损伤之间的相关性，包括中风、痴呆和冠心病。尽管眼底照片提供了大量有用的信息，但从眼底照片评估的血管仍然仅限于较大的视网膜动脉和静脉，并且观察到的异常可能不是最早的变化。新的成像方式，如光相干断层扫描血管造影和自适应光学技术，可更精确地评估视网膜血管（包括毛细血管）的结构，这可能有助于这些患者的评估和管理。深度学习技术的出现也增加了眼底照片的用途，有助于创建诊断和风险分层系统。特别是，深度学习系统在几项大型研究中已被证明能够仅从眼底照片预测多种心血管危险因素、5 年内的主要不良心血管事件以及冠状动脉钙的存在。未来，将深度学习系统与光相干断层扫描血管造影和自适应光学提供的成像精度相结合，可能会开发出能够更准确预测不良临床结果的系统。
