Large language models approach expert-level clinical knowledge and reasoning in ophthalmology: A head-to-head cross-sectional study.

Large language models (LLMs) underlie remarkable recent advanced in natural language processing, and they are beginning to be applied in clinical contexts. We aimed to evaluate the clinical potential of state-of-the-art LLMs in ophthalmology using a more robust benchmark than raw examination scores. We trialled GPT-3.5 and GPT-4 on 347 ophthalmology questions before GPT-3.5, GPT-4, PaLM 2, LLaMA, expert ophthalmologists, and doctors in training were trialled on a mock examination of 87 questions. Performance was analysed with respect to question subject and type (first order recall and higher order reasoning). Masked ophthalmologists graded the accuracy, relevance, and overall preference of GPT-3.5 and GPT-4 responses to the same questions. The performance of GPT-4 (69%) was superior to GPT-3.5 (48%), LLaMA (32%), and PaLM 2 (56%). GPT-4 compared favourably with expert ophthalmologists (median 76%, range 64-90%), ophthalmology trainees (median 59%, range 57-63%), and unspecialised junior doctors (median 43%, range 41-44%). Low agreement between LLMs and doctors reflected idiosyncratic differences in knowledge and reasoning with overall consistency across subjects and types (p>0.05). All ophthalmologists preferred GPT-4 responses over GPT-3.5 and rated the accuracy and relevance of GPT-4 as higher (p<0.05). LLMs are approaching expert-level knowledge and reasoning skills in ophthalmology. In view of the comparable or superior performance to trainee-grade ophthalmologists and unspecialised junior doctors, state-of-the-art LLMs such as GPT-4 may provide useful medical advice and assistance where access to expert ophthalmologists is limited. Clinical benchmarks provide useful assays of LLM capabilities in healthcare before clinical trials can be designed and conducted.

Eye growth pattern of myopic children wearing spectacle lenses with aspherical lenslets compared with non-myopic children.

INTRODUCTION: To evaluate eye growth of children wearing spectacle lenses with highly aspherical lenslets (HAL), slightly aspherical lenslets (SAL) and single-vision lenses (SVL) compared to eye growth patterns in non-myopes in Wenzhou, China. METHODS: The randomised trial had 170 myopic children (aged 8-13 years) randomly assigned to the HAL, SAL or SVL group. Normal eye growth was examined using 700 non-myopic schoolchildren (aged 7-9 years) in the Wenzhou Medical University-Essilor Progression and Onset of Myopia (WEPrOM) cohort study using logistic function models. Slow, normal and fast eye growth was defined as range of values <25th, 25th-75th and >75th percentiles, respectively. RESULTS: The predicted upper limits of slow eye growth (25th percentile) among non-myopes aged 7-10 years and 11-13 years were 0.20-0.13 and 0.08-0.01 mm (after 2-year period; 0.37-0.33 and 0.29-0.14 mm), respectively, while the upper limits of normal eye growth (75th percentile) were 0.32-0.31 and 0.28-0.10 mm (after 2-year period; 0.58-0.55 and 0.50-0.24 mm), respectively. The 2-year trial had 157 children, 96 of whom wore their lenses full time (everyday ≥12 h/day). The mean 2-year axial length change for HAL, SAL and SVL was 0.34, 0.51 and 0.69 mm (0.28, 0.46 and 0.69 mm in full-time wear), respectively. Slow eye growth was found in 35%, 17% and 2% (44%, 29% and 3% in full-time wear); normal eye growth in 35%, 26% and 12% (44%, 32% and 9% in full-time wear) and fast eye growth in 30%, 57% and 86% (12%, 39% and 88% in full-time wear), respectively (p < 0.001). CONCLUSIONS: The eye growth pattern in approximately 90% wearing HAL full time (compared with about 10% wearing SVL full time) was similar or slower than that of non-myopic children both after 1- and 2-year periods.

Longitudinal choroidal thickness changes among Chinese young adults with various refractive errors.

Purpose: To determine the characteristics of longitudinal choroidal thickness (CT) and axial length (AL) changes in a group of Chinese young adults with various refractive errors. Methods: In this 2 year prospective cohort study, a total of 291 (314 enrolled at baseline) Chinese medical freshmen aged 18 to 22 years (mean age, 18.7 ± 0.9 years) underwent eye examinations at baseline and follow-up visits, including cycloplegic refraction, ocular biometry measurements, and swept-source optical coherence tomography. Choroidal thickness measurements were performed at nine locations in the macular area. Results: At baseline, the CT and AL was significant differences among groups of emmetropia, mild to moderate myopia and high myopia. During a two-year period, there were significant differences found in the changes of the subfoveal CT (p < 0.001) and parafoveal CT of 7 locations between emmetropia and mild to moderate myopia, and the changes of the subfoveal CT (p = 0.002) and parafoveal CT of 6 locations between emmetropia and high myopia. But there were no differences for AL and SE (p > 0.05). The multivariable linear regression analysis showed that baseline subfoveal CT (per 1 µm) was a significant factor affecting the changes of subfoveal CT (p < 0.001), whereas age, gender, and baseline AL were not significantly associated. Conclusion: The longitudinal change in CT varies with refractive errors in Chinese young adults aged 18 to 22 years over a two-year period. The changes of subfoveal CT were significantly associated with the baseline subfoveal CT, but not associated with baseline AL.

Myopia and Its Association with Near Work, Outdoor Time, and Housing Type among Schoolchildren in South India.

SIGNIFICANCE: In this comprehensive assessment of environmental associations with refractive status among schoolchildren in India, outdoor time was the key modifiable risk factor associated with myopia rather than time spent on near work. PURPOSE: This study aimed to investigate the environmental risk factors associated with myopia among adolescent schoolchildren in South India. METHODS: Children in grades 8 to 10 from 11 schools in Tamil Nadu, South India, underwent eye examination and risk factor assessments through a modified version of the Sydney myopia questionnaire. Time spent on near work and outdoors was analyzed after division into three groups based on tertiles. Mixed-effects logistic regression was performed to assess the factors associated with myopia. RESULTS: A total of 3429 children (response rate, 78.4%) provided both questionnaire and refraction data. The mean (standard deviation) age was 14 (0.93) years with an equal distribution of sexes. Myopia was present among 867 children (noncycloplegic spherical equivalent refraction, ≤-0.75 D). Refraction was not associated with near work tertiles ( P = .22), whereas less time outdoors was associated with higher myopic refractions ( P = .01). Refraction shifted toward increased myopia with an increase in the near-work/outdoor time ratio ( P = .005). Children living in apartment housing had a higher prevalence of myopia compared with other types of housing ( P < .001). In multivariate analysis, increased time outdoors was a protective factor against myopia (odds ratio, 0.79; 95% confidence interval, 0.63 to 0.99; P = .04), whereas living in apartment housing (odds ratio, 1.27; 95% confidence interval, 1.04 to 1.55; P = .02) was a significant risk factor. CONCLUSIONS: In this cohort of Indian children, outdoor time, increased near-work/outdoor time ratio, and type of housing were the factors associated with myopia. Policies should target implementing a balance between near-work and outdoor time among children.

Incidence of myopic shift and related factors in young Chinese adults.

CLINICAL RELEVANCE: Myopia is a leading cause of visual impairment worldwide, and myopia progression in young adulthood may worsen this public health issue. BACKGROUND: The aim was to describe the changes in myopia and various ocular biometry parameters, and to determine the incidence and related factors of myopic shift among young adults in China. METHODS: This 2-year prospective cohort study was conducted at the Zhongshan Ophthalmic Center, Sun Yet-san University, China. A total of 291 Chinese medical freshmen (314 enrolled at baseline) were followed over 2 years. The participants underwent detailed eye examinations at baseline and follow-up visits, including cycloplegic refraction, ocular biometry measurements, and swept-source optical coherence tomography. Visual fatigue was assessed with the Convergence Insufficiency Symptom Survey (CISS) using Rasch analysis. Questionnaire on eye care habits and physical activities was administered. RESULTS: A total of 291 study participants (baseline mean [SD] age, 18.7 [0.9] years; 132 [45.4%] male) were analysed. Seventy eight (26.8%) developed a myopic shift (defined as negative change in spherical equivalent worse than or equal to -0.50 D) over a 2-year period. The magnitude of subfoveal choroidal thinning was greater in participants with myopic shift, compared to those without. Axial length increased significantly by 0.12 mm in the group with myopic shift, compared to 0.02 mm in those without the myopic shift (p < 0.001) over 2 years. After multivariable adjustment, visual fatigue (using CISS) was found to be associated with the myopic shift (p = 0.02). CONCLUSIONS: Approximately one in four Chinese medical students had a clinically significant myopic shift. Choroidal thinning and axial elongation were observed in young adults with myopic shift. Greater visual fatigue score at baseline was associated with myopic shift after multivariable adjustment.

Three-year change in refractive error and its risk factors: results from the Shahroud School Children Eye Cohort Study.

OBJECTIVES: To determine spherical equivalent (SE) progression among children in the Shahroud School Children Eye Cohort Study. METHODS: A prospective cohort study recruited children aged 6 to 12 years in 2015 (baseline) with a follow-up in 2018. Cycloplegic autorefraction and axial length (AL) measurements were included. SE progression over 3 years was analysed in non-myopic (SE ≥ + 0.76 D), pre-myopic (PM; SE between +0.75 D and -0.49 D), low myopic (LM; SE between -0.5 D and -5.99 D), and high myopic (HM; SE ≤ - 6 D) eyes. Age, sex, near work, outdoor time, living place, parental myopia, mother's education, and baseline SE were evaluated as risk factors for SE progression (≤ -0.50 D). RESULTS: Data were available for 3989 children (7945 eyes). At baseline, 40.3% (n = 3205), 3.4% (n = 274) and 0.1% (n = 7) eyes had PM, LM and HM, respectively. At the 3-year follow-up, 40.5% (n = 3216), 7.5% (n = 599) and 0.2% (n = 15) eyes had PM, LM, and HM, respectively. SE progression in eyes with LM and HM was -1.08 ± 0.76 D and -1.60 ± 1.19 D, respectively. SE progression was associated with age at baseline (Odds Ratio [OR] = 1.14; 95% confidence interval [CI], 1.08-1.21), female sex (OR = 1.80; 95% CI: 1.48-2.18), near work (OR = 1.08; 95% CI: 1.02-1.14), parental myopia (OR = 1.20; 95% CI: 1.01-1.42) and baseline SE (OR = 2.28; 95% CI: 1.88-2.78). CONCLUSION: A myopic shift was associated with older age, female sex, near work, parental myopia and greater myopic baseline SE. These results help identifying children at risk of progression that may benefit from treatment and lifestyle counselling.

Development and validation of a novel nomogram for predicting the occurrence of myopia in schoolchildren: A prospective cohort study.

PURPOSE: Myopia is a major public health issue and occurs at young ages. Apart from its high prevalence, myopia results in high costs and irreversible blinding diseases. Accurate prediction of the risk of myopia onset is crucial for its precise prevention. We aimed to develop and validate an effective nomogram for predicting myopia onset in schoolchildren. DESIGN: School-based prospective cohort study. METHODS: A total of 1073 schoolchildren were enrolled from November 2014 to May 2019 in China, and were divided into the training and validation cohorts. Myopia was defined as a spherical equivalent refraction (SER) ≤-0.5 diopters. Predictors of myopia were determined through the least absolute shrinkage and selection operator regression and multivariable Cox proportional hazard model based on the training cohort. The predictive performance of the nomogram was validated internally through time-dependent receiver operating characteristic (ROC) curves, calibration plot, decision curve analysis, and Kaplan-Meier curves. RESULTS: Independent predictors at baseline including gender, SER, axial length, corneal refractive power, and positive relative accommodation were included in the nomogram prediction model. This nomogram demonstrated excellent calibration, clinical net benefit, and discrimination, with all the area under the ROC curves (AUCs) between 0.74 and 0.86 in the training and validation cohorts. The Kaplan-Meier curves showed that 3 distinct risk groups stratified through X-tile analysis were well discriminated and robust among subgroups. The Harrell's C-index and net reclassification improvement demonstrated that the nomogram substantially improved compared with previous models. An online myopia risk calculator was generated for better individual prediction. CONCLUTIONS: The nomogram provides accurate and individual prediction of myopia onset in schoolchildren. External validation is needed to verify the generalizability of this nomogram.

Current Perspectives on Corneal Transplantation (Part 2).

Disease of the cornea is the third leading cause of blindness worldwide. Corneal graft surgery is one of the most successful forms of solid organ transplantations in humans, with ever increasing developments in surgical technique. To date, approximately 4504 corneal transplants are performed in the UK each year. While full thickness transplantation was the most commonly performed keratoplasty over the last few decades, selective lamellar transplantation of the diseased layers of the cornea has been universally adopted. This comprehensive review aims to provide an updated synthesis on different types of corneal transplantations, their treatment outcomes, and the associated complications of each procedure both in adult and pediatric populations. In addition, we also present an up-to-date summary of the emerging therapeutic approaches that have the potential to reduce the demand for donor-dependent keratoplasty.

Current Perspectives on Corneal Transplantation.

Disease of the cornea is the third leading cause of blindness worldwide. Corneal graft surgery is one of the most successful forms of solid organ transplantations in humans, with ever-increasing developments in surgical technique. To date, approximately 4504 corneal transplants are performed in the United Kingdom each year. While full thickness transplantation was the most commonly performed keratoplasty over the last few decades, selective lamellar transplantation of the diseased layers of the cornea has been universally adopted. This comprehensive review aims to provide an updated synthesis on different types of corneal transplantations, their treatment outcomes, and the associated complications of each procedure in both adult and paediatric population. In addition, we also present an up-to-date summary of the emerging therapeutic approaches that have the potential to reduce the demand for donor-dependent keratoplasty.

Prevalence of myopia among urban and suburban school children in Tamil Nadu, South India: findings from the Sankara Nethralaya Tamil Nadu Essilor Myopia (STEM) Study.

PURPOSE: To report the baseline prevalence of myopia among school children in Tamil Nadu, South India from a prospective cohort study. METHODS: Children between the ages of 5 and 16 years from 11 schools in two districts of Tamil Nadu underwent vision screening. All children underwent visual acuity assessment using a Pocket Vision Screener followed by non-cycloplegic open-field autorefraction (Grand Seiko WAM-5500). Myopia was defined as a spherical equivalent (SE) refraction of ≤-0.75 D and high myopia was defined as SE ≤ -6.00 D. Distribution of refraction, biometry and factors associated with prevalence of myopia were the outcome measures. RESULTS: A total of 14,699 children completed vision screening, with 2% (357) of them having ocular abnormalities other than refractive errors or poor vision despite spectacle correction. The remaining 14,342 children (7557 boys; 52.69%) had a mean age of 10.2 (Standard Deviation [SD] 2.8) years. A total of 2502 had myopia in at least one eye, a prevalence of 17.5% (95% CI: 14.7-20.5%), and 74 (0.5%; 95% CI: 0.3-0.9%) had high myopia. Myopia prevalence increased with age (p < 0.001), but sex was not associated with myopia prevalence (p = 0.24). Mean axial length (AL; 23.08 (SD = 0.91) mm) and mean anterior chamber depth (ACD; 3.45 (SD = 0.27) mm) positively correlated with age (p < 0.001). The mean flat (K1; 43.37 (SD = 1.49) D) and steep (K2; 44.50 (SD = 1.58) D) corneal curvatures showed negative correlation with age (p = 0.02 and p < 0.001, respectively). In the multivariable logistic regression, older age and urban school location had higher odds for prevalence of myopia. CONCLUSION: The baseline prevalence of myopia among 5- to 16-year-old children in South India is larger than that found in previous studies, indicating that myopia is becoming a major public health problem in this country.

Visual field defects and myopic macular degeneration in Singapore adults with high myopia.

AIMS: To characterise the association between visual field (VF) defects and myopic macular degeneration (MMD) in highly myopic adults without glaucoma. METHODS: Participants (n=106; 181 eyes) with high myopia (HM; spherical equivalent ≤-5.0 D or axial length (AL) ≥26 mm), after excluding glaucoma and glaucoma suspects, from the Singapore Epidemiology of Eye Diseases-HM study were included in this cross-sectional study. Humphrey VF (central 24-2 threshold), cup-disc ratio (CDR) and intraocular pressure (IOP) measurements were performed. Mean deviation (MD) and pattern SD (PSD), VF defects (normal or abnormal; p<0.05 in ≥3 non-edge contiguous locations) and pattern (eg, generalised sensitivity loss) were analysed. MMD presence was diagnosed from fundus photographs. Generalised estimating equations were used for analysing factors (MD, PSD, VF defects, CDR and IOP) associated with MMD. RESULTS: Mean age was 55.4±9.9 years and 51.9% were women (AL=26.7±1.1 mm). MMD eyes had lower MD (-3.8±2.9 dB vs -1.1±1.4 dB) and higher PSD (2.8±1.7 dB vs 1.7±0.6 dB). A higher percentage of MMD eyes (n=48) had abnormal VF (62.5% vs 28.6%; p<0.001) compared with no MMD (n=133 eyes). VF pattern in MMD eyes was significantly different from eyes without MMD (p=0.001) with greater generalised sensitivity loss (53.3% vs 10.5%) and arcuate defects (16.7% vs 10.5%). In multivariate analyses, MD (OR=1.52) and PSD (OR=1.67) were significantly (p=0.003) associated with MMD, but VF defects were not associated with MMD. CONCLUSION: Highly myopic adults with MMD may have VF loss when compared with highly myopic patients without MMD even in adults without glaucoma.

Surgical advancement in glaucoma during the past 10 years.

Recent years have seen a trend towards change in glaucoma treatment. In addition to classic trabeculectomy, implant surgeries such as those based on the Baerveldt, Ahmed and Molteno devices are increasingly performed as a primary procedure. This is doubtless partly due to the fact that surgeons have become more comfortable with the use of tube shunts and their postoperative management. The aim of this article is to present the currently available evidence on glaucoma surgery in a succinct format, to enable the best possible decisions to be made for patients.

Ophthalmology Going Greener: A Narrative Review.

The combined effects of fossil fuel combustion, mass agricultural production and deforestation, industrialisation and the evolution of modern transport systems have resulted in high levels of carbon emissions and accumulation of greenhouse gases, causing profound climate change and ozone layer depletion. The consequential depletion of Earth's natural ecosystems and biodiversity is not only a devastating loss but a threat to human health. Sustainability-the ability to continue activities indefinitely-underpins the principal solutions to these problems. Globally, the healthcare sector is a major contributor to carbon emissions, with waste production and transport systems being amongst the highest contributing factors. The aim of this review is to explore modalities by which the healthcare sector, particularly ophthalmology, can reduce carbon emissions, related costs and overall environmental impact, whilst maintaining a high standard of patient care.

Assessment of the Macular Microvasculature in High Myopes With Swept Source Optical Coherence Tomographic Angiography.

Background: The risk of pathologic myopia (PM) increases with worsening myopia and may be related to retinal microvasculature alterations. To evaluate this, we analyzed the macular microvasculature of myopes with swept source-optical coherence tomographic angiography (SS-OCTA) in adolescent and young adult Singaporeans. Methods: This is a prevalent case-control study including 93 young Chinese from the Strabismus, Amblyopia and Refractive error in Singaporean children (STARS, N = 45) study and the Singapore Cohort Study of Risk Factors for Myopia (SCORM, N = 48) studies. Macular vessel density (VD) measurements were obtained from 3 × 3 mm SS-OCTA scans and independently assessed using ImageJ. These measurements were compared between individuals with non-high myopia [non-HM, N = 40; SE >-5.0 diopter (D)] and HM (SE ≤-5.0D, N = 53). Results: The mean macular VD was 40.9 ± 0.6% and 38.2 ± 0.5% in the non-HM and HM, groups, respectively (p = 0.01 adjusted for age and gender). Mean FAZ area in the superficial layer was 0.22 ± 0.02 mm2 in the HM group, which was smaller compared to non-HM group (0.32 ± 0.03 mm2, p = 0.04). Mean deep FAZ area was similar between the two groups (0.45 ± 0.03 mm2 and 0.48 ± 0.04 mm2 in the HM and non-HM groups, respectively, p = 0.70). Conclusions: VD was lower and superficial FAZ area was smaller, in adolescents and young adults with HM compared to non-HM. These findings require validation in prospective studies to assess their impact on the subsequent development of PM.

Prediction of myopia onset with refractive error measured using non-cycloplegic subjective refraction: the WEPrOM Study.

BACKGROUND/AIMS: To evaluate the predictive performance of various predictors, including non-cycloplegic refractive error, for risk of myopia onset under pragmatic settings. METHODS: The Wenzhou Medical University Essilor Progression and Onset of Myopia Study is a prospective cohort study of schoolchildren aged 6-10 years from two elementary schools in Wenzhou, China. Non-cycloplegic refraction, ocular biometry and accommodation measurements were performed. Myopia was defined as spherical equivalent (SE) ≤-0.5 diopter (D). ORs using multivariable logistic regression were determined. Area under the curve (AUC) evaluation for predictors was performed. RESULTS: Schoolchildren who attended both baseline and 2-year follow-up were analysed (N=1022). Of 830 non-myopic children at baseline, the 2-year incidence of myopia was 27.6% (95% CI, 24.2% to 31.3%). Female gender (OR=2.2), more advanced study grades (OR=1.5), less hyperopic SE (OR=11.5 per D), longer axial length (AL; OR=2.3 per mm), worse presenting visual acuity (OR=2.3 per decimal), longer near work time (OR=1.1 per hour/day) and lower magnitude of positive relative accommodation (PRA; OR=1.4 per D) were associated with myopia onset. PRA (AUC=0.66), SE (AUC=0.64) and AL (AUC=0.62) had the highest AUC values. The combination of age, gender, parental myopia, SE, AL and PRA achieved an AUC of 0.74. CONCLUSION: Approximately one in four schoolchildren had myopia onset over a 2-year period. The predictors of myopia onset include lower magnitude of PRA, less hyperopic SE, longer AL and female gender. Of these, non-cycloplegic SE and PRA were the top single predictors, which can facilitate risk profiling for myopia onset.

The Sankara Nethralaya Tamil Nadu Essilor Myopia (STEM) Study-Defining a Threshold for Non-Cycloplegic Myopia Prevalence in Children.

The aim of this study was to investigate the agreement between cycloplegic and non-cycloplegic autorefraction with an open-field auto refractor in a school vision screening set up, and to define a threshold for myopia that agrees with the standard cycloplegic refraction threshold. The study was conducted as part of the Sankara Nethralaya Tamil Nadu Essilor Myopia (STEM) study, which investigated the prevalence, incidence, and risk factors for myopia among children in South India. Children from two schools aged 5 to 15 years, with no ocular abnormalities and whose parents gave informed consent for cycloplegic refraction were included in the study. All the children underwent visual acuity assessment (Pocket Vision Screener, Elite school of Optometry, India), followed by non-cycloplegic and cycloplegic (1% tropicamide) open-field autorefraction (Grand Seiko, WAM-5500). A total of 387 children were included in the study, of whom 201 were boys. The mean (SD) age of the children was 12.2 (±2.1) years. Overall, the mean difference between cycloplegic and non-cycloplegic spherical equivalent (SE) open-field autorefraction measures was 0.34 D (limits of agreement (LOA), 1.06 D to -0.38 D). For myopes, the mean difference between cycloplegic and non-cycloplegic SE was 0.13 D (LOA, 0.63D to -0.36D). The prevalence of myopia was 12% (95% CI, 8% to 15%) using the threshold of cycloplegic SE ≤ -0.50 D, and was 14% (95% CI, 11% to 17%) with SE ≤ -0.50 D using non-cycloplegic refraction. When myopia was defined as SE of ≤-0.75 D under non-cycloplegic conditions, there was no difference between cycloplegic and non-cycloplegic open-field autorefraction prevalence estimates (12%; 95% CI, 8% to 15%; p = 1.00). Overall, non-cycloplegic refraction underestimates hyperopia and overestimates myopia; but for subjects with myopia, this difference is minimal and not clinically significant. A threshold of SE ≤ -0.75 D agrees well for the estimation of myopia prevalence among children when using non-cycloplegic refraction and is comparable with the standard definition of cycloplegic myopic refraction of SE ≤ -0.50 D.

Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study.

BACKGROUND: By 2050, almost 5 billion people globally are projected to have myopia, of whom 20% are likely to have high myopia with clinically significant risk of sight-threatening complications such as myopic macular degeneration. These are diagnoses that typically require specialist assessment or measurement with multiple unconnected pieces of equipment. Artificial intelligence (AI) approaches might be effective for risk stratification and to identify individuals at highest risk of visual loss. However, unresolved challenges for AI medical studies remain, including paucity of transparency, auditability, and traceability. METHODS: In this retrospective multicohort study, we developed and tested retinal photograph-based deep learning algorithms for detection of myopic macular degeneration and high myopia, using a total of 226 686 retinal images. First we trained and internally validated the algorithms on datasets from Singapore, and then externally tested them on datasets from China, Taiwan, India, Russia, and the UK. We also compared the performance of the deep learning algorithms against six human experts in the grading of a randomly selected dataset of 400 images from the external datasets. As proof of concept, we used a blockchain-based AI platform to demonstrate the real-world application of secure data transfer, model transfer, and model testing across three sites in Singapore and China. FINDINGS: The deep learning algorithms showed robust diagnostic performance with areas under the receiver operating characteristic curves [AUC] of 0·969 (95% CI 0·959-0·977) or higher for myopic macular degeneration and 0·913 (0·906-0·920) or higher for high myopia across the external testing datasets with available data. In the randomly selected dataset, the deep learning algorithms outperformed all six expert graders in detection of each condition (AUC of 0·978 [0·957-0·994] for myopic macular degeneration and 0·973 [0·941-0·995] for high myopia). We also successfully used blockchain technology for data transfer, model transfer, and model testing between sites and across two countries. INTERPRETATION: Deep learning algorithms can be effective tools for risk stratification and screening of myopic macular degeneration and high myopia among the large global population with myopia. The blockchain platform developed here could potentially serve as a trusted platform for performance testing of future AI models in medicine. FUNDING: None.

Quality of Life in Presbyopes with Low and High Myopia Using Single-Vision and Progressive-Lens Correction.

This study evaluates the impact of the severity of myopia and the type of visual correction in presbyopia on vision-related quality of life (QOL), using the refractive status and vision profile (RSVP) questionnaire. A total of 149 subjects aged 41-75 years with myopic presbyopia were recruited: 108 had low myopia and 41 had high myopia. The RSVP questionnaire was administered. Rasch analysis was performed on five subscales: perception, expectation, functionality, symptoms, and problems with glasses. Highly myopic subjects had a significantly lower mean QOL score (51.65), compared to low myopes (65.24) (p < 0.001). They also had a significantly lower functionality score with glasses (49.38), compared to low myopes (57.00) (p = 0.018), and they had a worse functionality score without glasses (29.12), compared to low myopes (36.24) (p = 0.045). Those who wore progressive addition lenses (PAL) in the high-myope group (n = 25) scored significantly better, compared to those who wore single-vision distance (SVD) lenses (n = 14), with perception scores of 61.19 and 46.94, respectively (p = 0.029). Highly myopic presbyopes had worse overall QOL and functionality, both with and without glasses, compared to presbyopes with low myopia. High-myopic PAL users had a better perception outcome than SVD lens wearers. Low-myopic PAL wearers had a better QOL than SVD wearers.