Quantitative analysis of retinal vascular parameters changes in school-age children with refractive error using artificial intelligence

Abstract

Aim: To quantitatively analyze the relationship between spherical equivalent refraction (SER) and retinal vascular changes in school-age children with refractive error by applying fundus photography combined with artificial intelligence (AI) technology and explore the structural changes in retinal vasculature in these children.

Methods: We conducted a retrospective case-control study, collecting data on 113 cases involving 226 eyes of schoolchildren aged 6-12 years who attended outpatient clinics in our hospital between October 2021 and May 2022. Based on the refractive spherical equivalent refraction, we categorized the participants into four groups: 66 eyes in the low myopia group, 60 eyes in the intermediate myopia group, 50 eyes in the high myopia group, and 50 eyes in the control group. All participants underwent a series of examinations, including naked-eye and best-corrected visual acuity, cycloplegic spherical equivalent refraction, intraocular pressure measurement, ocular axial measurement (AL), and color fundus photography. Using fundus photography, we quantitatively analyzed changes in the retinal vascular arteriovenous ratio (AVR), average curvature, and vascular density with AI technology. Data were analyzed using the χ² test and one-way analysis of variance.

Results: The AVR in the low myopia group, moderate myopia group, high myopia group, and control group were 0.80 ± 0.05, 0.80 ± 0.04, 0.76 ± 0.04, and 0.79 ± 0.04, respectively, and the vessel densities were 0.1024 ± 0.0076, 0.1024 ± 0.0074, 0.0880 ± 0.0126, and 0.1037 ± 0.0143, respectively The difference between the AVR and vascular density in the high myopia group was statistically significant compared to the other three groups (p < 0.05). Linear correlation analysis showed a strong negative correlation between the spherical equivalent refraction and the ocular axis (r = -0.874, p < 0001), a moderate positive correlation between the spherical equivalent refraction and the vascular density (r = 0.527, p < 0001), and a moderate negative correlation between the ocular axis and the vascular density (r = -0.452, p < 0001).

Conclusion: Schoolchildren with high myopia showed a decreased AVR and decreased vascular density in the retinal vasculature. The AVR and vascular density may be early predictors of myopia progression.

Keywords: ametropia; artificial intelligence; quantitative analysis; retinal vascular changes; school-age children.