Association of DeepLearning-Based Fundus Age Difference with Carotid Atherosclerosis and Mortality

Jooyoung Chang, Joo Young Shin, Taehoon Ko, Jinho Lee, Baek-Lok Oh, Ki Ho Park, Ahryoung Ko, Sang Min Park, Seulggie Choi, Kyuwoong Kim, Sung Min Kim, Jae Moon Yun, Uk Kang, Il Hyung Shin

Abstract: Retinal fundus images provide an opportunity to visualize vessels directly and non-invasively. Here, we develop a deep learning model that estimates the patients' age using only retinal fundus images and investigate its association with abnormal carotid artery intima-media thickness (CIMT) and all-cause mortality. Using the database at the Health Promotion Center of Seoul National University Hospital, the model was trained on 96,968 fundus images and validated using 6,579 independent participants via cross-sectional and retrospective cohort analysis. The primary exposure of the study was the fundus age difference (FAD), or the fundus age minus the actual age, where the fundus age was defined as the averaged predicted age of both left and right fundus images. Compared to participants with fundus age younger than their actual age ( FAD \leqslant 0), those with had significantly higher odds of abnormal CIMT (OR, 95%CI; 1.55, 1.07-2.23; p-trend, 0.002). Over a median follow-up of 5.6 years among 6,579 persons, was associated with all-cause mortality (HR, 95%CI; 2.13, 1.08-4.21; p-trend, 0.040). The fundus age difference was significantly associated with abnormal CIMT and all-cause mortality. With deep learning, retinal fundus images can be used to stratify risks of atherosclerosis and all-cause mortality and may benefit the clinical evaluation of patients.