This paper presents a study that uses deep learning to predict cardiovascular risk factors from retinal fundus images. The researchers trained deep learning models on data from 284,335 patients and validated them on two independent datasets of 12,026 and 999 patients. The models successfully predicted various cardiovascular risk factors, including age (within 3.26 years), gender (0.97 AUC), smoking status (0.71 AUC), HbA1c (within 1.39%), systolic blood pressure (within 11.23 mmHg), and major adverse cardiac events (0.70 AUC). The models also used distinct aspects of the retinal anatomy, such as the optic disc or blood vessels, to generate these predictions. The study demonstrates the potential of using retinal images for cardiovascular risk stratification, which could be a non-invasive and cost-effective method for identifying and managing cardiovascular disease risk. However, the study acknowledges limitations, including the relatively small dataset size and the need for further validation on larger datasets.This paper presents a study that uses deep learning to predict cardiovascular risk factors from retinal fundus images. The researchers trained deep learning models on data from 284,335 patients and validated them on two independent datasets of 12,026 and 999 patients. The models successfully predicted various cardiovascular risk factors, including age (within 3.26 years), gender (0.97 AUC), smoking status (0.71 AUC), HbA1c (within 1.39%), systolic blood pressure (within 11.23 mmHg), and major adverse cardiac events (0.70 AUC). The models also used distinct aspects of the retinal anatomy, such as the optic disc or blood vessels, to generate these predictions. The study demonstrates the potential of using retinal images for cardiovascular risk stratification, which could be a non-invasive and cost-effective method for identifying and managing cardiovascular disease risk. However, the study acknowledges limitations, including the relatively small dataset size and the need for further validation on larger datasets.