Retinal screening contributes to early detection of diabetic retinopathy and timely treatment. To facilitate the screening process, we develop a deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy. DeepDR is trained for real-time image quality assessment, lesion detection and grading using 466,247 fundus images from 121,342 patients with diabetes. Evaluation is performed on a local dataset with 200,136 fundus images from 52,004 patients and three external datasets with a total of 209,322 images. The area under the receiver operating characteristic curves for detecting microaneurysms, cotton-wool spots, hard exudates and hemorrhages are 0.901, 0.941, 0.954 and 0.967, respectively. The grading of diabetic retinopathy as mild, moderate, severe and proliferative achieves area under the curves of 0.943, 0.955, 0.960 and 0.972, respectively. In external validations, the area under the curves for grading range from 0.916 to 0.970, which further supports the system is efficient for diabetic retinopathy grading.

The global burden of myopia is growing. Myopia affected nearly 30% of the world population in 2020 and this number is expected to rise to 50% by 2050. This review aims to analyze the impact of myopia on individuals and society; summarizing the evidence for recent research on the prevalence of myopia and high myopia, lifetime pathological manifestations of myopia, direct health expenditure, and indirect costs such as lost productivity and reduced quality of life (QOL). The principal trends are a rising prevalence of myopia and high myopia, with a disproportionately greater increase in the prevalence of high myopia. This forecasts a future increase in vision loss due to uncorrected myopia as well as high myopia-related complications such as myopic macular degeneration. QOL is affected for those with uncorrected myopia, high myopia, or complications of high myopia. Overall the current global cost estimates related to direct health expenditure and lost productivity are in the billions. Health expenditure is greater in adults, reflecting the added costs due to myopia-related complications. Unless the current trajectory for the rising prevalence of myopia and high myopia change, the costs will continue to grow. The past few decades have seen the emergence of several novel approaches to prevent and slow myopia. Further work is needed to understand the life-long impact of myopia on an individual and the cost-effectiveness of the various novel approaches in reducing the burden.

No abstract