Original fundus photographs (2).

ObjectiveThis study aims to utilize artificial intelligence technology to conduct an in-depth analysis of fundus data from myopic children and adolescents, thoroughly exploring the correlation between retinal vascular parameters and axial length (AL), and ultimately revealing the changing patterns of retinal vascular characteristics in children with different refractive errors. The findings aim to provide a scientific basis for the prevention, early screening, and formulation of personalized treatment strategies for myopia.MethodsThe study selected 124 students from Jiandong Primary School in Changzhi City who underwent myopia prevention and control screening. Their axial length data were recorded, and fundus photographs were taken using the Topcon TNF506 non-mydriatic fundus camera. Subsequently, these fundus images were meticulously analyzed using the EVision AI fundus image analysis system, which is a commercial software that employs pre-trained algorithms to automatically extract retinal vascular parameters.Pearson and Spearman correlation coefficients were used to analyze the correlation between retinal vascular parameters and axial length, and multiple linear regression analysis was further conducted to explore their intrinsic associations.ResultsThe study found that in the low myopia group, axial length was significantly negatively correlated with various retinal vascular parameters, including the average diameters of arteries and veins, average vascular tortuosity, atrophy arc area, and leopard spot density. In the moderate to high myopia group, axial length also showed significant negative correlations with the average diameter of arteries, some average venous tortuosity, and average vascular diameter. However, fractal dimension of vessels and average branch angle did not show significant changes across all myopia groups.ConclusionThis study clearly demonstrates a significant correlation between axial length and retinal vascular parameters, with notable differences in this correlation among children with different refractive errors. These findings not only provide a new perspective for understanding the pathological mechanisms of myopia but also offer important scientific evidence for the development of more precise and personalized myopia prevention and control strategies in the future. They have potential guiding significance for clinical practice and policy formulation.

研究目的：本研究旨在借助人工智能技术，对近视儿童青少年的眼底数据开展深度分析，全面探究视网膜血管参数（retinal vascular parameters）与轴长（axial length, AL）之间的关联，最终揭示不同屈光不正（refractive errors）儿童的视网膜血管特征变化规律。本研究结果可为近视的预防、早期筛查以及个性化治疗策略制定提供科学依据。
研究方法：本研究选取长治市建东小学124名参与近视防控筛查的学生，记录其轴长数据，并使用托普康TNF506免散瞳眼底相机（Topcon TNF506 non-mydriatic fundus camera）拍摄眼底照片。随后，采用EVision AI眼底图像分析系统（EVision AI fundus image analysis system）对这些眼底图像进行精细化分析；该系统为一款商用软件，依托预训练算法（pre-trained algorithms）自动提取视网膜血管参数。本研究采用皮尔逊相关系数与斯皮尔曼相关系数（Pearson and Spearman correlation coefficients）分析视网膜血管参数与轴长的相关性，并进一步开展多重线性回归分析（multiple linear regression analysis）以探究二者的内在关联。
研究结果：本研究发现，在低度近视组中，轴长与多项视网膜血管参数均呈显著负相关，包括动静脉平均管径、血管平均弯曲度、萎缩弧面积以及豹纹状眼底密度。在中高度近视组中，轴长与动脉平均管径、部分静脉平均弯曲度以及平均血管管径亦呈显著负相关。但在所有近视亚组中，血管分形维数（fractal dimension of vessels）与平均分支角（average branch angle）均未出现显著变化。
研究结论：本研究明确证实轴长与视网膜血管参数存在显著相关性，且该相关性在不同屈光状态的儿童中存在显著差异。本研究结果不仅为理解近视的病理机制提供了新视角，也为未来制定更为精准、个性化的近视防控策略提供了重要科学依据，对临床实践与政策制定均具有潜在指导意义。