Approximately 1 in 26 phakic adults in Singapore has MMD. Older age and myopic SE are major risk factors of MMD. Severe MMD has a substantial impact on visual impairment and functioning.

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.

Background/aimsTo evaluate the predictive performance of various predictors, including non-cycloplegic refractive error, for risk of myopia onset under pragmatic settings.MethodsThe 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.ResultsSchoolchildren 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.ConclusionApproximately 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.

No abstract