Association between deep learning measured retinal vessel calibre and incident myocardial infarction in a retrospective cohort from the UK Biobank.

BACKGROUND: Cardiovascular disease is a leading cause of global death. Prospective population-based studies have found that changes in retinal microvasculature are associated with the development of coronary artery disease. Recently, artificial intelligence deep learning (DL) algorithms have been developed for the fully automated assessment of retinal vessel calibres. METHODS: In this study, we validate the association between retinal vessel calibres measured by a DL system (Singapore I Vessel Assessment) and incident myocardial infarction (MI) and assess its incremental performance in discriminating patients with and without MI when added to risk prediction models, using a large UK Biobank cohort. RESULTS: Retinal arteriolar narrowing was significantly associated with incident MI in both the age, gender and fellow calibre-adjusted (HR=1.67 (95% CI: 1.19 to 2.36)) and multivariable models (HR=1.64 (95% CI: 1.16 to 2.32)) adjusted for age, gender and other cardiovascular risk factors such as blood pressure, diabetes mellitus (DM) and cholesterol status. The area under the receiver operating characteristic curve increased from 0.738 to 0.745 (p=0.018) in the age-gender-adjusted model and from 0.782 to 0.787 (p=0.010) in the multivariable model. The continuous net reclassification improvements (NRIs) were significant in the age and gender-adjusted (NRI=21.56 (95% CI: 3.33 to 33.42)) and the multivariable models (NRI=18.35 (95% CI: 6.27 to 32.61)). In the subgroup analysis, similar associations between retinal arteriolar narrowing and incident MI were observed, particularly for men (HR=1.62 (95% CI: 1.07 to 2.46)), non-smokers (HR=1.65 (95% CI: 1.13 to 2.42)), patients without DM (HR=1.73 (95% CI: 1.19 to 2.51)) and hypertensive patients (HR=1.95 (95% CI: 1.30 to 2.93)) in the multivariable models. CONCLUSION: Our results support DL-based retinal vessel measurements as markers of incident MI in a predominantly Caucasian population.

Blood biomarkers improve the prediction of prevalent and incident severe chronic kidney disease.

BACKGROUND: The prevalence of chronic kidney disease (CKD) is high. Identification of cases with CKD or at high risk of developing it is important to tailor early interventions. The objective of this study was to identify blood metabolites associated with prevalent and incident severe CKD, and to quantify the corresponding improvement in CKD detection and prediction. METHODS: Data from four cohorts were analyzed: Singapore Epidemiology of Eye Diseases (SEED) (n = 8802), Copenhagen Chronic Kidney Disease (CPH) (n = 916), Singapore Diabetic Nephropathy (n = 714), and UK Biobank (UKBB) (n = 103,051). Prevalent CKD (stages 3-5) was defined as estimated glomerular filtration rate (eGFR) < 60 mL/min/1.73 m2; incident severe CKD as CKD-related mortality or kidney failure occurring within 10 years. We used multivariable regressions to identify, among 146 blood metabolites, those associated with CKD, and quantify the corresponding increase in performance. RESULTS: Chronic kidney disease prevalence (stages 3-5) and severe incidence were 11.4% and 2.2% in SEED, and 2.3% and 0.2% in UKBB. Firstly, phenylalanine (Odds Ratio [OR] 1-SD increase = 1.83 [1.73, 1.93]), tyrosine (OR = 0.75 [0.71, 0.79]), docosahexaenoic acid (OR = 0.90 [0.85, 0.95]), citrate (OR = 1.41 [1.34, 1.47]) and triglycerides in medium high density lipoprotein (OR = 1.07 [1.02, 1.13]) were associated with prevalent stages 3-5 CKD. Mendelian randomization analyses suggested causal relationships. Adding these metabolites beyond traditional risk factors increased the area under the curve (AUC) by 3% and the sensitivity by 7%. Secondly, lactate (HR = 1.33 [1.08, 1.64]) and tyrosine (HR = 0.74 [0.58, 0.95]) were associated with incident severe CKD among individuals with eGFR < 90 mL/min/1.73 m2 at baseline. These metabolites increased the c-index by 2% and sensitivity by 5% when added to traditional risk factors. CONCLUSION: The performance improvements of CKD detection and prediction achieved by adding metabolites to traditional risk factors are modest and further research is necessary to fully understand the clinical implications of these findings.

A deep learning system for retinal vessel calibre improves cardiovascular risk prediction in Asians with chronic kidney disease.

Backgraund: Cardiovascular disease (CVD) and mortality is elevated in chronic kidney disease (CKD). Retinal vessel calibre in retinal photographs is associated with cardiovascular risk and automated measurements may aid CVD risk prediction. Methods: Retrospective cohort study of 860 Chinese, Malay and Indian participants aged 40-80 years with CKD [estimated glomerular filtration rate (eGFR) <60 ml/min/1.73 m2] who attended the baseline visit (2004-2011) of the Singapore Epidemiology of Eye Diseases Study. Retinal vessel calibre measurements were obtained by a deep learning system (DLS). Incident CVD [non-fatal acute myocardial infarction (MI) and stroke, and death due to MI, stroke and other CVD] in those who were free of CVD at baseline was ascertained until 31 December 2019. Risk factors (established, kidney, and retinal features) were examined using Cox proportional hazards regression models. Model performance was assessed for discrimination, fit, and net reclassification improvement (NRI). Results: Incident CVD occurred in 289 (33.6%) over mean follow-up of 9.3 (4.3) years. After adjusting for established cardiovascular risk factors, eGFR [adjusted HR 0.98 (95% CI: 0.97-0.99)] and retinal arteriolar narrowing [adjusted HR 1.40 (95% CI: 1.17-1.68)], but not venular dilation, were independent predictors for CVD in CKD. The addition of eGFR and retinal features to established cardiovascular risk factors improved model discrimination with significantly better fit and better risk prediction according to the low (<15%), intermediate (15-29.9%), and high (30% or more) risk categories (NRI 5.8%), and with higher risk thresholds (NRI 12.7%). Conclusions: Retinal vessel calibre measurements by DLS were significantly associated with incident CVD independent of established CVD risk factors. Addition of kidney function and retinal vessel calibre parameters may improve CVD risk prediction among Asians with CKD.

Circulating Metabolites and Cardiovascular Disease in Asians with Chronic Kidney Disease.

INTRODUCTION: Chronic kidney disease (CKD) is a growing public health problem, with significant burden of cardiovascular disease and mortality. The risk of cardiovascular disease in CKD is elevated beyond that predicted by traditional cardiovascular risk factors, suggesting that other factors may account for this increased risk. Through metabolic profiling, this study aimed to investigate the associations between serum metabolites and prevalent cardiovascular disease in Asian patients with CKD to provide insights into the complex interactions between metabolism, cardiovascular disease and CKD. METHODS: This was a single-center cross-sectional study of 1,122 individuals from three ethnic cohorts in the population-based Singapore Epidemiology of Eye Disease (SEED) study (153 Chinese, 262 Indians, and 707 Malays) aged 40-80 years with CKD (estimated glomerular filtration rate <60 mL/min/1.73 m2). Nuclear magnetic resonance spectroscopy was used to quantify 228 metabolites from the participants' serum or plasma. Prevalent cardiovascular disease was defined as self-reported myocardial infarction, angina, or stroke. Multivariate logistic regression identified metabolites independently associated with cardiovascular disease in each ethnic cohort. Metabolites with the same direction of association with cardiovascular disease in all three cohorts were selected and subjected to meta-analysis. RESULTS: Cardiovascular disease was present in 275 (24.5%). Participants with cardiovascular disease tend to be male; of older age; with hypertension, hyperlipidemia, and diabetes; with lower systolic and diastolic blood pressure (BP); lower high-density lipoprotein (HDL) and low-density lipoprotein (LDL) cholesterol than those without cardiovascular disease. After adjusting for age, sex, systolic BP, diabetes, total cholesterol, and HDL cholesterol, 10 lipoprotein subclass ratios and 6 other metabolites were significantly associated with prevalent cardiovascular disease in at least one cohort. Meta-analysis with Bonferroni correction for multiple comparisons found that lower tyrosine, leucine, and valine concentrations and lower cholesteryl esters to total lipid ratio in intermediate-density lipoprotein (IDL) were associated with cardiovascular disease. CONCLUSION: In Chinese, Indian, and Malay participants with CKD, prevalent cardiovascular disease was associated with tyrosine, leucine, valine, and cholesteryl esters to total lipid ratios in IDL. Increased cardiovascular risk in CKD patients may be contributed by altered amino acid and lipoprotein metabolism. The presence of CKD and ethnic differences may affect interactions between metabolites in health and disease, hence greater understanding will allow us to better risk stratify patients, and also individualize care with consideration of ethnic disparities.

Relationship between dry eye symptoms and quality of life: associations and mediation analysis.

PURPOSE: (1) To determine the independent association of dry eye symptoms with health-related quality of life (HRQoL) in the Singapore population and (2) to further investigate which factors mediate this association. METHODS: In this cross-sectional study, 7707 participants were included. The presence of dry eye symptoms was defined as experiencing at least one out of the six symptoms either 'often' or 'all the time'. The EuroQoL-5 dimensions (EQ-5D) utility instrument (raw scores converted to UK time trade-off (TTO) values) was used to assess generic HRQoL and the overall score from the Visual Functioning Questionnaire for visual functioning. The association between dry eye symptoms and EQ-5D was investigated using multivariable linear regression, adjusting for demographic and socioeconomic information, comorbidities, systemic and ocular examinations results. Mediation analysis was used to determine whether certain factors mediated this association. RESULTS: After adjusting for relevant factors, those with dry eye symptoms had significantly lower HRQoL (difference in EQ-5D TTO: -0.062 (95% CI -0.073 to -0.050)), with the inability to open eyes affected the most (-0.101 (95% CI -0.161 to -0.042)), followed by a sandy sensation (-0.089 (95% CI -0.121 to -0.058)), a burning sensation (-0.070 (95% CI -0.105 to -0.036)), red eyes (-0.059 (95% CI -0.082 to -0.036)), a dry sensation (-0.058 (95% CI -0.072 to -0.044)) and crusting of eyelids (-0.040 (95% CI -0.071 to -0.008)). Visual functioning and the presence of recent falls accounted for 8.63% (4.98%-14.5%) and 2.93% (0.04%-5.68%) of the indirect relationship between dry eye and HRQoL, respectively. CONCLUSION: Dry eye symptoms were independently associated with poor HRQoL. Moreover, this was partly mediated by reduced visual functioning and experiencing recent falls. Our results suggest that efforts to reduce severity of dry eye symptoms are essential to optimise patients' overall functioning and well-being.

Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective.

Background: Many artificial intelligence (AI) studies have focused on development of AI models, novel techniques, and reporting guidelines. However, little is understood about clinicians' perspectives of AI applications in medical fields including ophthalmology, particularly in light of recent regulatory guidelines. The aim for this study was to evaluate the perspectives of ophthalmologists regarding AI in 4 major eye conditions: diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and cataract. Methods: This was a multi-national survey of ophthalmologists between March 1st, 2020 to February 29th, 2021 disseminated via the major global ophthalmology societies. The survey was designed based on microsystem, mesosystem and macrosystem questions, and the software as a medical device (SaMD) regulatory framework chaired by the Food and Drug Administration (FDA). Factors associated with AI adoption for ophthalmology analyzed with multivariable logistic regression random forest machine learning. Results: One thousand one hundred seventy-six ophthalmologists from 70 countries participated with a response rate ranging from 78.8 to 85.8% per question. Ophthalmologists were more willing to use AI as clinical assistive tools (88.1%, n = 890/1,010) especially those with over 20 years' experience (OR 3.70, 95% CI: 1.10-12.5, p = 0.035), as compared to clinical decision support tools (78.8%, n = 796/1,010) or diagnostic tools (64.5%, n = 651). A majority of Ophthalmologists felt that AI is most relevant to DR (78.2%), followed by glaucoma (70.7%), AMD (66.8%), and cataract (51.4%) detection. Many participants were confident their roles will not be replaced (68.2%, n = 632/927), and felt COVID-19 catalyzed willingness to adopt AI (80.9%, n = 750/927). Common barriers to implementation include medical liability from errors (72.5%, n = 672/927) whereas enablers include improving access (94.5%, n = 876/927). Machine learning modeling predicted acceptance from participant demographics with moderate to high accuracy, and area under the receiver operating curves of 0.63-0.83. Conclusion: Ophthalmologists are receptive to adopting AI as assistive tools for DR, glaucoma, and AMD. Furthermore, ML is a useful method that can be applied to evaluate predictive factors on clinical qualitative questionnaires. This study outlines actionable insights for future research and facilitation interventions to drive adoption and operationalization of AI tools for Ophthalmology.

Normative Data and Associations of OCT Angiography Measurements of the Macula: The Singapore Malay Eye Study.

OBJECTIVE: To describe the normative quantitative parameters of the macular retinal vasculature, as well as their systemic and ocular associations using OCT angiography (OCTA). DESIGN: Population-based, cross-sectional study. SUBJECTS: Adults aged > 50 years were recruited from the third examination of the population-based Singapore Malay Eye Study. METHODS: All participants underwent a standardized comprehensive examination and spectral-domain OCTA (Optovue) of the macula. OCT angiography scans that revealed pre-existing retinal disease, revealed macular pathology, and had poor quality were excluded. MAIN OUTCOME MEASURES: The normative quantitative vessel densities of the superficial layer, deep layer, and foveal avascular zone (FAZ) were evaluated. Ocular and systemic associations with macular retinal vasculature parameters were also evaluated in a multivariable analysis using linear regression models with generalized estimating equation models. RESULTS: We included 1184 scans (1184 eyes) of 749 participants. The mean macular superficial vessel density (SVD) and deep vessel density (DVD) were 45.1 ± 4.2% (95% confidence interval [CI], 37.8%-51.4%) and 44.4 ± 5.2% (95% CI, 36.9%-53.2%), respectively. The mean SVD and DVD were highest in the superior quadrant (48.7 ± 5.9%) and nasal quadrant (52.7 ± 4.6%), respectively. The mean FAZ area and perimeter were 0.32 ± 0.11 mm2 (95% CI, 0.17-0.51 mm) and 2.14 ± 0.38 mm (95% CI, 1.54-2.75 mm), respectively. In the multivariable regression analysis, female sex was associated with higher SVD (ß = 1.25, P ≤ 0.001) and DVD (ß = 0.75, P = 0.021). Older age (ß = -0.67, P < 0.001) was associated with lower SVD, whereas longer axial length (ß = -0.42, P = 0.003) was associated with lower DVD. Female sex, shorter axial length, and worse best-corrected distance visual acuity were associated with a larger FAZ area. No association of a range of systemic parameters with vessel density was found. CONCLUSIONS: This study provided normative macular vasculature parameters in an adult Asian population, which may serve as reference values for quantitative interpretation of OCTA data in normal and disease states.

Retinal photograph-based deep learning predicts biological age, and stratifies morbidity and mortality risk.

BACKGROUND: ageing is an important risk factor for a variety of human pathologies. Biological age (BA) may better capture ageing-related physiological changes compared with chronological age (CA). OBJECTIVE: we developed a deep learning (DL) algorithm to predict BA based on retinal photographs and evaluated the performance of our new ageing marker in the risk stratification of mortality and major morbidity in general populations. METHODS: we first trained a DL algorithm using 129,236 retinal photographs from 40,480 participants in the Korean Health Screening study to predict the probability of age being ≥65 years ('RetiAGE') and then evaluated the ability of RetiAGE to stratify the risk of mortality and major morbidity among 56,301 participants in the UK Biobank. Cox proportional hazards model was used to estimate the hazard ratios (HRs). RESULTS: in the UK Biobank, over a 10-year follow up, 2,236 (4.0%) died; of them, 636 (28.4%) were due to cardiovascular diseases (CVDs) and 1,276 (57.1%) due to cancers. Compared with the participants in the RetiAGE first quartile, those in the RetiAGE fourth quartile had a 67% higher risk of 10-year all-cause mortality (HR = 1.67 [1.42-1.95]), a 142% higher risk of CVD mortality (HR = 2.42 [1.69-3.48]) and a 60% higher risk of cancer mortality (HR = 1.60 [1.31-1.96]), independent of CA and established ageing phenotypic biomarkers. Likewise, compared with the first quartile group, the risk of CVD and cancer events in the fourth quartile group increased by 39% (HR = 1.39 [1.14-1.69]) and 18% (HR = 1.18 [1.10-1.26]), respectively. The best discrimination ability for RetiAGE alone was found for CVD mortality (c-index = 0.70, sensitivity = 0.76, specificity = 0.55). Furthermore, adding RetiAGE increased the discrimination ability of the model beyond CA and phenotypic biomarkers (increment in c-index between 1 and 2%). CONCLUSIONS: the DL-derived RetiAGE provides a novel, alternative approach to measure ageing.

Retinal Nerve Fiber Layer Thickness and Rim Area Profiles in Asians: Pooled Analysis from the Asian Eye Epidemiology Consortium.

PURPOSE: To evaluate ethnic variations, ocular and systemic determinants of retinal nerve fiber layer (RNFL) thickness, and neuroretinal rim area among Asians using a large consortium of population-based eye studies. DESIGN: Cross-sectional pooled analysis. PARTICIPANTS: Twenty-two thousand four hundred thirty-six participants (22 436 eyes) from 10 population-based studies (in China, Hong Kong, India, Japan, Russia, and Singapore) of the Asian Eye Epidemiology Consortium. METHODS: Participants 40 years of age or older without glaucoma were included. All participants underwent spectral-domain OCT imaging and systemic and ocular examinations. Data were pooled from each study. Multivariable regression was performed to evaluate interethnic differences, intermachine variations, and ocular and systemic factors associated with RNFL thickness and rim area, adjusting for age, gender, diabetes, intraocular pressure (IOP), spherical equivalent (SE), ethnicity, OCT model, and study group. When evaluating body mass index, smoking, and hypertension as exposures, these factors were additionally adjusted for in the model. MAIN OUTCOME MEASURES: Average RNFL thickness (in micrometers) and rim area (in square millimeters). RESULTS: Indian and Japanese eyes have thinner RNFLs than those of other Asian ethnicities (ß values range, 7.31-12.76 µm; P < 0.001 for all pairwise comparisons). Compared with measurements by Cirrus HD-OCT (Carl Zeiss Meditec, Inc), RNFL on average was 7.29 µm thicker when measured by Spectralis (Heidelberg Engineering), 12.85 µm thicker when measured by RS-3000 (NIDEK Co, Ltd), and 17.48 µm thicker when measured by iVue/RTVue (Optovue, Inc) devices (all P < 0.001). Additionally, older age (per decade, ß = -2.70), diabetes (ß = -0.72), higher IOP (per 1 mmHg, ß = -0.07), more myopic SE (per diopter, ß = -1.13), cardiovascular disease (ß = -0.94), and hypertension (ß = -0.68) were associated with thinner RNFL (all P ≤ 0.003). Similarly, older age (ß = -0.019), higher IOP (ß = -0.010), and more myopic SE (ß = -0.025) were associated with smaller rim area (all P < 0.001). CONCLUSIONS: In this large pooled analysis of Asian population studies, Indian and Japanese eyes were observed to have thinner RNFL profiles. These findings suggest the need for an ethnic-specific normative database to improve glaucoma detection.

Deep-learning-based cardiovascular risk stratification using coronary artery calcium scores predicted from retinal photographs.

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.

Ethnic differences in the incidence of pterygium in a multi-ethnic Asian population: the Singapore Epidemiology of Eye Diseases Study.

We evaluated the 6-year incidence and risk factors of pterygium in a multi-ethnic Asian population. Participants who attended the baseline visit of the Singapore Epidemiology of Eye Diseases Study (year 2004-2011) and returned six years later, were included in this study. Pterygium was diagnosed based on anterior segment photographs. Incident pterygium was defined as presence of pterygium at 6-year follow-up in either eye, among individuals without pterygium at baseline. Multivariable logistic regression models were used to determine factors associated with incident pterygium, adjusting for baseline age, gender, ethnicity, body mass index, occupation type, educational level, income status, smoking, alcohol consumption, presence of hypertension, diabetes and hyperlipidemia. The overall age-adjusted 6-year incidence of pterygium was 1.2% (95% confidence interval [CI] 1.0-1.6%); with Chinese (1.9%; 95% CI 1.4%-2.5%) having the highest incidence rate followed by Malays (1.4%; 95% CI 0.9%-2.1%) and Indians (0.3%; 95% CI 0.3-0.7%). In multivariable analysis, Chinese (compared with Indians; odds ratio [OR] = 4.21; 95% CI 2.12-9.35) and Malays (OR 3.22; 95% CI 1.52-7.45), male (OR 2.13; 95% CI 1.26-3.63), outdoor occupation (OR 2.33; 95% CI 1.16-4.38), and smoking (OR 0.41; 95% CI 0.16-0.87) were significantly associated with incident pterygium. Findings from this multi-ethnic Asian population provide useful information in identifying at-risk individuals for pterygium.

Patterns and Determinants of Choroidal Thickness in a Multiethnic Asian Population: The Singapore Epidemiology of Eye Diseases Study.

PURPOSE: To describe the distribution and determinants of choroidal thickness (CT) in participants in a population study based on spectral-domain (SD)-OCT measurements. DESIGN: Population-based, cross-sectional study. PARTICIPANTS: Ethnic Chinese, Indian, and Malay adults aged more than 50 years without any retinal diseases (e.g., diabetic retinopathy, macular edema, age-related macular degeneration, central serous chorioretinopathy) that might affect the CT were recruited from the Singapore Epidemiology of Eye Diseases Study. METHODS: Choroidal imaging was performed by SD-OCT (Spectralis, Heidelberg Engineering, Heidelberg, Germany) in enhanced depth imaging (EDI) mode. Subfoveal choroidal thickness (SFCT) was measured on the foveal line scan by 2 retinal experts independently (YS and KT), and the average was used in the analyses. In Chinese and Indian cohorts in whom macular raster scans were captured, the manufacturer-supplied research software (Heyex SP-X version 6.4.8.116; Heidelberg Engineering) was used to obtain automated segmentation yielding mean choroidal thickness in each of the 9 ETDRS grid sectors. MAIN OUTCOME MEASURES: Subfoveal choroidal thickness and regional CT in the 9 ETDRS grid sectors. RESULTS: For the SFCT analysis, 2794 eyes of 1619 participants (Chinese, Indian, and Malay ) were included. The mean age was 60.9 years (standard deviation, 7.7), and 797 (49.2%) were male. Mean SFCT was 255.2 µm (standard deviation, 102.6). The normal range of SFCT was 106 to 447 µm (corresponding to 5th and 95th percentile limits of SFCT, respectively). In multivariable models, thinner SFCT was associated with older age, female gender, longer axial length, and Malay (vs. Chinese) ethnicity. In the subset of Chinese and Indian eyes (n = 1842) in whom regional variation was evaluated, the choroid was thickest at the superior and temporal sectors and thinner at the inferior and nasal sectors. CONCLUSIONS: Subfoveal choroidal thickness is influenced by age, gender, and ethnicity along with regional differences even within individual eyes. Subfoveal choroidal thickness also shows a wide range in physiologic limits. These data may be used as a reference in future studies.

Decrease in Choroidal Vascularity Index of Haller's layer in diabetic eyes precedes retinopathy.

INTRODUCTION: The study aimed to evaluate Choroidal Vascularity Index (CVI) of Haller's and Sattler's layers and their relationships with choroidal and retinal thickness, volumes measured on enhanced depth imaging-optical coherence tomography (OCT) scans in the eyes of patients without diabetes, patients with diabetes with no diabetic retinopathy (DR) and patients with diabetes and DR. RESEARCH DESIGN AND METHODS: Retrospective analysis of 165 eyes from 84 Singapore Indian Eye Study-2 study participants (group 1: no diabetes, group 2: diabetes with no DR and group 3: with DR). Groups 1 and 2 were matched by age and gender from group 3. RESULTS: In the eyes of patients with diabetes without DR, the macular CVI of Haller's but not Sattler's layer was significantly reduced compared with eyes of patients without diabetes. Eyes with >5 years of diabetes have significantly decreased CVI of Sattler's layers (mean difference=0.06 ± 0.10, p=0.04) and also decreased subfoveal choroidal volume (mean difference=0.89 ± 0.16 mm3, p=0.02), compared with those with ≤5 years of diabetes. CONCLUSION: Diabetic eyes without DR had significantly lower CVI of macular Haller's layer than those of healthy controls. With a longer duration of diabetes, CVI of subfoveal Sattler's layer and choroidal volume continue to decrease, irrespective of diabetic control, suggesting that early diabetic choroidopathy mainly affects larger choroidal veins initially before medium-sized arterioles. The CVI of macular Haller's layer could potentially be used as a marker on spectral domain OCT imaging in newly diagnosed patients with diabetes for the onset of DR and as a possible prognostication tool in diabetic eyes. Future prospective longitudinal studies in diabetic eyes would be useful in establishing the relationship between CVIs of Haller's and Sattler's layer with visual acuity as a marker of photoreceptor health and visual prognosis.

Technical and imaging factors influencing performance of deep learning systems for diabetic retinopathy.

Deep learning (DL) has been shown to be effective in developing diabetic retinopathy (DR) algorithms, possibly tackling financial and manpower challenges hindering implementation of DR screening. However, our systematic review of the literature reveals few studies studied the impact of different factors on these DL algorithms, that are important for clinical deployment in real-world settings. Using 455,491 retinal images, we evaluated two technical and three image-related factors in detection of referable DR. For technical factors, the performances of four DL models (VGGNet, ResNet, DenseNet, Ensemble) and two computational frameworks (Caffe, TensorFlow) were evaluated while for image-related factors, we evaluated image compression levels (reducing image size, 350, 300, 250, 200, 150 KB), number of fields (7-field, 2-field, 1-field) and media clarity (pseudophakic vs phakic). In detection of referable DR, four DL models showed comparable diagnostic performance (AUC 0.936-0.944). To develop the VGGNet model, two computational frameworks had similar AUC (0.936). The DL performance dropped when image size decreased below 250 KB (AUC 0.936, 0.900, p < 0.001). The DL performance performed better when there were increased number of fields (dataset 1: 2-field vs 1-field-AUC 0.936 vs 0.908, p < 0.001; dataset 2: 7-field vs 2-field vs 1-field, AUC 0.949 vs 0.911 vs 0.895). DL performed better in the pseudophakic than phakic eyes (AUC 0.918 vs 0.833, p < 0.001). Various image-related factors play more significant roles than technical factors in determining the diagnostic performance, suggesting the importance of having robust training and testing datasets for DL training and deployment in the real-world settings.