Sung Soo Kim

PURPOSE: To assess the relationship between macular retinal thickness and volume and age, sex, and refractive error/axial length with spectral domain-optical coherence tomography (SD-OCT). METHODS: One randomly selected eye of 198 consecutive ophthalmically normal subjects (104 men, 94 women) between July 2008 and January 2009, with corrected visual acuities better than 20/30 were included in this cross-sectional study. Complete ophthalmic examination, axial length measurement with a laser interferometer, and macular cube 512 x 128 scan by SD-OCT were performed. RESULTS: The mean age was 55.6 +/- 16.4 years (range, 17-83), average refractive error was -2.17 +/- 4.82 (range, -23.50-3.75), and average axial length was 24.73 +/- 1.98 mm (range, 21.52-32.51). The central subfield thickness, average inner macular thickness, and overall macular volume were significantly lower in the female subjects (partial correlation: P = 0.009, P = 0.027, and P = 0.042, respectively). As age increased, average inner macular thickness, average outer macular thickness, overall average macular thickness, and macular volume decreased significantly (partial correlation: P = 0.002, P = 0.002, P = 0.002, and P = 0.000, respectively). Refractive error had no significant influence in partial correlation analysis. Axial length correlated negatively with average outer macular thickness, overall average macular thickness, and macular volume (partial correlation: P = 0.006, P = 0.044, and P = 0.003, respectively). CONCLUSIONS: In normal subjects, SD-OCT showed that retinal thickness is related to age, sex, and axial length, with regional variations.

BACKGROUND: Coronary artery calcium (CAC) score is a clinically validated marker of cardiovascular disease risk. We developed and validated a novel cardiovascular risk stratification system based on deep-learning-predicted CAC from retinal photographs. METHODS: We used 216 152 retinal photographs from five datasets from South Korea, Singapore, and the UK to train and validate the algorithms. First, using one dataset from a South Korean health-screening centre, we trained a deep-learning algorithm to predict the probability of the presence of CAC (ie, deep-learning retinal CAC score, RetiCAC). We stratified RetiCAC scores into tertiles and used Cox proportional hazards models to evaluate the ability of RetiCAC to predict cardiovascular events based on external test sets from South Korea, Singapore, and the UK Biobank. We evaluated the incremental values of RetiCAC when added to the Pooled Cohort Equation (PCE) for participants in the UK Biobank. FINDINGS: RetiCAC outperformed all single clinical parameter models in predicting the presence of CAC (area under the receiver operating characteristic curve of 0·742, 95% CI 0·732-0·753). Among the 527 participants in the South Korean clinical cohort, 33 (6·3%) had cardiovascular events during the 5-year follow-up. When compared with the current CAC risk stratification (0, >0-100, and >100), the three-strata RetiCAC showed comparable prognostic performance with a concordance index of 0·71. In the Singapore population-based cohort (n=8551), 310 (3·6%) participants had fatal cardiovascular events over 10 years, and the three-strata RetiCAC was significantly associated with increased risk of fatal cardiovascular events (hazard ratio [HR] trend 1·33, 95% CI 1·04-1·71). In the UK Biobank (n=47 679), 337 (0·7%) participants had fatal cardiovascular events over 10 years. When added to the PCE, the three-strata RetiCAC improved cardiovascular risk stratification in the intermediate-risk group (HR trend 1·28, 95% CI 1·07-1·54) and borderline-risk group (1·62, 1·04-2·54), and the continuous net reclassification index was 0·261 (95% CI 0·124-0·364). INTERPRETATION: A deep learning and retinal photograph-derived CAC score is comparable to CT scan-measured CAC in predicting cardiovascular events, and improves on current risk stratification approaches for cardiovascular disease events. These data suggest retinal photograph-based deep learning has the potential to be used as an alternative measure of CAC, especially in low-resource settings. FUNDING: Yonsei University College of Medicine; Ministry of Health and Welfare, Korea Institute for Advancement of Technology, South Korea; Agency for Science, Technology, and Research; and National Medical Research Council, Singapore.

BACKGROUND: The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored. METHODS: With use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development. FINDINGS: ≤0·14 across all external test sets). INTERPRETATION: Our work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms. FUNDING: Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology.