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.

Association of Antihypertensive Medication with Retinal Nerve Fiber Layer and Ganglion Cell-Inner Plexiform Layer Thickness.

PURPOSE: To evaluate the association between different classes of antihypertensive medication with retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (GC-IPL) thickness in a nonglaucomatous multiethnic Asian population. DESIGN: Population-based, cross-sectional study. PARTICIPANTS: A total of 9144 eyes for RNFL analysis (2668 Malays, 3554 Indians, and 2922 Chinese) and 8549 eyes for GC-IPL analysis (2460 Malays, 3230 Indians, and 2859 Chinese) aged 44 to 86 years. METHODS: Participants underwent standardized systemic and ocular examinations and interviewer-administered questionnaires for collection of data on medication and other variables. Intraocular pressure (IOP) readings were obtained by Goldmann applanation tonometry before pupil dilation for fundoscopy and OCT imaging. Blood pressure (BP) was measured with an automatic BP monitor. Mean arterial pressure (MAP) was defined as diastolic BP plus 1/3 (systolic BP - diastolic BP). Regression models were used to investigate the association of antihypertensive medication with OCT measurements of RNFL and GC-IPL. MAIN OUTCOME MEASURES: Average and sectoral RNFL and GC-IPL thickness. RESULTS: After adjusting for age, gender, ethnicity, MAP, IOP, body mass index (BMI), and presence of diabetes, we found that participants taking any type of antihypertensive medication (ß = -0.83; 95% confidence interval [CI], -1.46 to -0.02; P = 0.01), specifically angiotensin-converting enzyme inhibitors (ACEIs) (ß = -1.66; 95% CI, -2.57 to -0.75; P < 0.001) or diuretics (ß = -1.38; 95% CI, -2.59 to -0.17; P < 0.05), had thinner average RNFL in comparison with participants who were not receiving antihypertensive treatment. Use of a greater number of antihypertensive medications was significantly associated with thinner average RNFL (P for trend = 0.001). This association was most evident in the inferior RNFL quadrant in participants using ACEIs (ß = -2.44; 95% CI, -3.99 to -0.89; P = 0.002) or diuretics (ß = -2.76; 95% CI, -4.76 to -0.76; P = 0.007). A similar trend was noted in our analysis of macular GC-IPL thickness. CONCLUSIONS: Use of 2 or more antihypertensive medications, ACEI, and diuretics were associated with a loss of structural markers of retinal ganglion cell health in a multiethnic Asian population.

Six-Year Incidence and Risk Factors for Primary Open-Angle Glaucoma and Ocular Hypertension: The Singapore Epidemiology of Eye Diseases Study.

OBJECTIVE: To determine the incidence and risk factors for primary open-angle glaucoma (POAG) and ocular hypertension (OHT) in a multiethnic Asian population. DESIGN: Population-based cohort study. PARTICIPANTS: The Singapore Epidemiology of Eye Diseases study included 10 033 participants in the baseline examination between 2004 and 2011. Of those, 6762 (response rate = 78.8%) participated in the 6-year follow-up visit between 2011 and 2017. METHODS: Standardized examination and investigations were performed, including slit lamp biomicroscopy, intraocular pressure (IOP) measurement, pachymetry, gonioscopy, optic disc examination and static automated perimetry. Glaucoma was defined according to a combination of clinical evaluation, ocular imaging (fundus photo, visual field, and OCT) and criteria given by International Society of Geographical and Epidemiological Ophthalmology. OHT was defined on the basis of elevated IOP over the upper limit of normal; i.e., 20.4 mmHg, 21.5 mmHg, and 22.6 mmHg for the Chinese, Indian, and Malay cohort respectively, without glaucomatous optic disc change. MAIN OUTCOME MEASURES: Incidence of POAG, OHT, and OHT progression. RESULTS: The overall 6-year age-adjusted incidences of POAG and OHT were 1.31% (95% confidence interval [CI], 1.04-1.62) and 0.47% (95% CI, 0.30-0.70). The rate of progression of baseline OHT to POAG at 6 years was 5.32%. Primary open-angle glaucoma incidence was similar (1.37%) in Chinese and Indians and lower (0.80%) in Malays. Malays had higher incidence (0.79%) of OHT than Indians (0.38%) and Chinese (0.37%). Baseline parameters associated with higher risk of POAG were older age (per decade: odds ratio [OR], 1.90; 95% CI, 1.54-2.35; P < 0.001), higher baseline IOP (per mmHg: OR, 1.20; 95% CI, 1.12-1.29; P < 0.001) and longer axial length (per mm: OR, 1.22; 95% CI, 1.07-1.40, P = 0.004). CONCLUSION: Six-year incidence of POAG was 1.31% in a multiethnic Asian population. Older age, higher IOP, and longer axial length were associated with higher risk of POAG. These findings can help in future projections and guide public healthcare policy decisions for screening at-risk individuals. FINANCIAL DISCLOSURE(S): The authors have no proprietary or commercial interest in any materials discussed in this article.

Prognostic potentials of AI in ophthalmology: systemic disease forecasting via retinal imaging.

BACKGROUND: Artificial intelligence (AI) that utilizes deep learning (DL) has potential for systemic disease prediction using retinal imaging. The retina's unique features enable non-invasive visualization of the central nervous system and microvascular circulation, aiding early detection and personalized treatment plans for personalized care. This review explores the value of retinal assessment, AI-based retinal biomarkers, and the importance of longitudinal prediction models in personalized care. MAIN TEXT: This narrative review extensively surveys the literature for relevant studies in PubMed and Google Scholar, investigating the application of AI-based retina biomarkers in predicting systemic diseases using retinal fundus photography. The study settings, sample sizes, utilized AI models and corresponding results were extracted and analysed. This review highlights the substantial potential of AI-based retinal biomarkers in predicting neurodegenerative, cardiovascular, and chronic kidney diseases. Notably, DL algorithms have demonstrated effectiveness in identifying retinal image features associated with cognitive decline, dementia, Parkinson's disease, and cardiovascular risk factors. Furthermore, longitudinal prediction models leveraging retinal images have shown potential in continuous disease risk assessment and early detection. AI-based retinal biomarkers are non-invasive, accurate, and efficient for disease forecasting and personalized care. CONCLUSION: AI-based retinal imaging hold promise in transforming primary care and systemic disease management. Together, the retina's unique features and the power of AI enable early detection, risk stratification, and help revolutionizing disease management plans. However, to fully realize the potential of AI in this domain, further research and validation in real-world settings are essential.

Multivariate Normative Comparison, a Novel Method for Improved Use of Retinal Nerve Fiber Layer Thickness to Detect Early Glaucoma.

PURPOSE: Detection of early glaucoma remains limited with the conventional analysis of the retinal nerve fiber layer (RNFL). This study assessed whether compensating the RNFL thickness for multiple demographic and anatomic factors improves the detection of glaucoma. DESIGN: Cross-sectional study. PARTICIPANTS: Three hundred eighty-seven patients with glaucoma and 2699 healthy participants. METHODS: Two thousand six hundred ninety-nine healthy participants were enrolled to construct and test a multivariate compensation model, which then was applied in 387 healthy participants and 387 patients with glaucoma (early glaucoma, n = 219; moderate glaucoma, n = 97; and advanced glaucoma, n = 71). Participants underwent Cirrus spectral-domain OCT (Carl Zeiss Meditec) imaging of the optic disc and macular cubes. Compensated RNFL thickness was generated based on ethnicity, age, refractive error, optic disc (ratio, orientation, and area), fovea (distance and angle), and retinal vessel density. The RNFL thickness measurements and their corresponding areas under the receiver operating characteristic curve (AUCs) were obtained. MAIN OUTCOME AND MEASURES: Measured and compensated RNFL thickness measurements. RESULTS: After applying the Asian-specific compensation model, the standard deviation of RNFL thickness reduced, where the effect was greatest for Chinese participants (16.9%), followed by Malay participants (13.9%), and Indian participants (12.1%). Multivariate normative comparison outperformed measured RNFL for discrimination of early glaucoma (AUC, 0.90 vs. 0.85; P < 0.001), moderate glaucoma (AUC, 0.94 vs. 0.91; P < 0.001), and advanced glaucoma (AUC, 0.98 vs. 0.96; P < 0.001). CONCLUSIONS: The multivariate normative database of RNFL showed better glaucoma discrimination capability than conventional age-matched comparisons, suggesting that accounting for demographic and anatomic variance in RNFL thickness may have usefulness in improving glaucoma detection.

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.