Are digital devices a new risk factor for myopia?

Association Between Myopia and Pupil Diameter in Preschoolers: Evidence from a Machine Learning Approach Based on a Real-World Large-Scale Dataset

INTRODUCTION

Previous studies have explored the connections between various ocular biological parameters with myopia. Our previous study also found that pupil data can predict the myopic progression during the interventions for myopia. However, studies exploring the association between pupil diameter and myopia in preschoolers with myopia were lacking. Hence this study was aimed to investigate the association between pupil diameter and myopia in preschoolers with myopia based on a real-world, large-scale dataset.

METHODS

Data containing 650,671 preschoolers were collected from a total of 1943 kindergartens in Shenzhen, China. Refraction and pupil parameters were collected. After data filtering, the occurrence of myopia and its association with age, gender, pupil diameter, and other variables, were analyzed. Random forest (RF) and eXtreme gradient boosting (XGBoost) were selected from seven machine learning algorithms to build the model. The mean decrease accuracy (MDA), mean decrease Gini (MDG), and gain feature importance (GFI) techniques were employed to quantify the importance of pupil diameter and other features.

RESULTS

After the assessments, 51,325 valid records with complete pupil data were included, and 3468 (6.76%) were identified as myopia based on the calculated cycloplegic refraction. Preschoolers with myopia presented reduced pupil diameter and greater variation (5.00 ± 0.99 mm) compared to non-myopic preschoolers (6.22 ± 0.67 mm). A nonlinear relationship was found according to the scatterplots between pupil diameter and refraction (R2 = 0.14). Especially preschoolers with myopia had reduced pupil diameter compared to emmetropic preschoolers, but hyperope did not experience additional pupil enlargement. After adjusting for other covariates, this relationship is still consistent (P < 0.001). XGBoost and RF algorithms presented the highest performance and validated the importance of pupil diameter in myopia.

CONCLUSIONS

Based on a real-world large-scale dataset, the current study illuminated that preschoolers with myopia had a reduced pupil diameter compared to emmetropic preschoolers with a nonlinear pattern. Machine learning algorithms visualized and validated the pivotal role of pupil diameter in myopia.

TRIAL REGISTRATION

chictr.org Identifier: ChiCTR2200057391.

Regional variations and temporal trends of childhood myopia prevalence in Africa: A systematic review and meta-analysis

PURPOSE

To provide contemporary and future estimates of childhood myopia prevalence in Africa.

METHODS

A systematic online literature search was conducted for articles on childhood (≤18 years) myopia (spherical equivalent [SE] ≤ -0.50D; high myopia: SE ≤ -6.00D) in Africa. Population- or school-based cross-sectional studies published from 1 Jan 2000 to 30 May 2021 were included. Meta-analysis using Freeman-Tukey double arcsine transformation was performed to estimate the prevalence of childhood myopia and high myopia. Myopia prevalence from subgroup analyses for age groups and settings were used as baseline for generating a prediction model using linear regression.

RESULTS

Forty-two studies from 19 (of 54) African countries were included in the meta-analysis (N = 737,859). Overall prevalence of childhood myopia and high myopia were 4.7% (95% CI: 3.3%-6.5%) and 0.6% (95% CI: 0.2%-1.1%), respectively. Estimated prevalence across the African regions was highest in the North (6.8% [95% CI: 4.0%-10.2%]), followed by Southern (6.3% [95% CI: 3.9%-9.1%]), East (4.7% [95% CI: 3.1%-6.7%]) and West (3.5% [95% CI: 1.9%-6.3%]) Africa. Prevalence from 2011 to 2021 was approximately double that from 2000 to 2010 for all studies combined, and between 1.5 and 2.5 times higher for ages 5-11 and 12-18 years, for boys and girls and for urban and rural settings, separately. Childhood myopia prevalence is projected to increase in urban settings and older children to 11.1% and 10.8% by 2030, 14.4% and 14.1% by 2040 and 17.7% and 17.4% by 2050, respectively; marginally higher than projected in the overall population (16.4% by 2050).

CONCLUSIONS

Childhood myopia prevalence has approximately doubled since 2010, with a further threefold increase predicted by 2050. Given this trajectory and the specific public health challenges in Africa, it is imperative to implement basic myopia prevention programmes, enhance spectacle coverage and ophthalmic services and generate more data to understand the changing myopia epidemiology to mitigate the expanding risk of the African population.