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.

To evaluate the use of digital devices, reading habits and the prevalence of eyestrain among urban Indian school children, aged 11–17 years. The study included 576 adolescents attending urban schools who were surveyed regarding their electronic device usage. Additional information on the factors that may have an effect on ocular symptoms was collected. Twenty percent of students aged 11 in the study population use digital devices on a daily basis, in comparison with 50% of students aged 17. In addition to using these devices as homework aids, one third of study participants reported using digital devices for reading instead of conventional textbooks. The majority of students preferred sitting on a chair while reading (77%; 445 students), with only 21% (123 students) preferring to lie on the bed and 8 students alternating between chair and bed. There was a significant association between the students who preferred to lie down and those who experienced eyestrain, as reported by a little over one fourth of the student population (27%). Out of 576 students, 18% (103) experienced eyestrain at the end of the day after working on digital devices. The increased use of digital devices by adolescents brings a new challenge of digital eyestrain at an early age. Our study reports the patterns of electronic device usage by school children, evaluates factors associated with eyestrain and highlights the need for further investigation of these issues.

Visual impairment (VI), defined as low vision or blindness, affects approximately 441.1 million individuals, disproportionately affecting individuals 50 years and older.¹ With the rapidly aging populations,² the prevalence of VI is expected to increase 3-fold by 2050.¹ VI imposes a substantial health burden in terms of quality-adjusted life-years or years lived with disability that is comparable to major chronic diseases, such as diabetes, dyslipidemia, cardiovascular diseases (CVD), and obesity.^3,4 Likewise, deficits in cognitive function are also a major cause of morbidity.⁴ Previous studies^5-7 have found a close association between VI and decline in cognitive function.