Association of retinal microvascular density and complexity with incident coronary heart disease

The high mortality rate and huge disease burden of coronary heart disease (CHD) highlight the importance of its early detection and timely intervention. Given the non-invasive nature of fundus photography and recent development in the quantification of retinal microvascular parameters with deep learning techniques, our study aims to investigate the association between incident CHD and retinal microvascular parameters. UK Biobanks participants with gradable fundus images and without a history of diagnosed CHD at recruitment were included for analysis. A fully automated artificial intelligence system was used to extract quantitative measurements that represent the density and complexity of the retinal microvasculature, including fractal dimension (Df), number of vascular segments (NS), vascular skeleton density (VSD) and vascular area density (VAD). A total of 57,947 participants (mean age 55.6 ± 8.1 years; 56% female) without a history of diagnosed CHD were included. During a median follow-up of 11.0 (interquartile range, 10.88 to 11.19) years, 3211 incident CHD events occurred. In multivariable Cox proportional hazards models, we found decreasing Df (adjusted HR = 0.80, 95% CI, 0.65–0.98, p = 0.033), lower NS of arteries (adjusted HR = 0.69, 95% CI, 0.54–0.88, p = 0.002) and venules (adjusted HR = 0.77, 95% CI, 0.61–0.97, p = 0.024), and reduced arterial VSD (adjusted HR = 0.72, 95% CI, 0.57–0.91, p = 0.007) and venous VSD (adjusted HR = 0.78, 95% CI, 0.62–0.98, p = 0.034) were related to an increased risk of incident CHD. Our study revealed a significant association between retinal microvascular parameters and incident CHD. As the lower complexity and density of the retinal vascular network may indicate an increased risk of incident CHD, this may empower its prediction with the quantitative measurements of retinal structure. [Display omitted] •Coronary heart disease (CHD) is one of leading causes of morbidity and death around world, and the disease burden remains increasing.•Current assessment methods are unsuitable to be a screening tool for CHD, due to technically challenging and operating hardly.•The accuracy and efficacy of retinal feature measurements has significantly been improved with the constant development of deep learning (DL).•We integrated the clinical data from the UK Biobank, a large cohort with gradable retinal fundus images, to reduce the limitation of small samples.•The study supports the potential of the quantitative retinal structure