摘要
由一名新闻记者-机器人和机器学习每日新闻的工作人员新闻编辑-眼睛疾病和条件的新研究-Myo Pia是一篇报道的主题。根据NewsRx记者在深圳的新闻报道，研究表明：“以前的研究已经探索了各种眼生物学参数与近视之间的联系。我们以前的研究还发现，瞳孔数据可以预测近视干预过程中的近视发生。”记者引用了南方医科大学的一篇文章，“然而，关于近视学龄前儿童瞳孔直径与近视关系的研究还很少。因此，本研究旨在基于真实世界的大规模数据集，调查近视学龄前儿童瞳孔直径与近视的关系。数据来自深圳市1943所幼儿园，包含650671名学龄前儿童。”在7种机器学习算法中选取随机森林(RF)和极梯度boosting(X GBoost)建立模型,模型的平均下降精度为(MDA),平均下降基尼系数为(MDG),平均下降精度为(MDA),平均下降基尼系数为(MDG),平均下降时间为15min。采用增益特征量表(GFI)技术量化瞳孔直径等特征量表的重要性,获得51325份完整瞳孔数据的有效记录。结果表明,近视眼学龄前儿童瞳孔直径比非近视眼学龄前儿童(6.22±0.67mm)缩小(5.00±0.99mm),瞳孔直径与屈光散点呈非线性关系(R=0.14),近视眼学龄前儿童瞳孔直径比非近视眼学龄前儿童(6.22±0.67mm)减小,近视眼学龄前儿童瞳孔直径比非近视眼学龄前儿童(5.00±0.99mm)但是hyperope没有出现额外的瞳孔扩大。在调整了其他协变量后，这种关系仍然一致(P<0.001)。XGBoost和RF算法表现出最高的性能，并验证了瞳孔直径在近视中的重要性。基于真实世界的大规模数据集，当前的研究表明，与具有非线性模式的正视学龄前儿童相比，近视学龄前儿童的瞳孔直径减小。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Eye Diseases and Conditions - Myo pia is the subject of a report. According to news reporting from Shenzhen, Peopl e's Republic of China, by NewsRx journalists, research stated, "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 pr ogression during the interventions for myopia." The news correspondents obtained a quote from the research from Southern Medical University, "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. Data containing 650,671 preschoolers were collected from a total of 1943 kindergartens in Shenzhen, Chi na. Refraction and pupil parameters were collected. After data filtering, the oc currence of myopia and its association with age, gender, pupil diameter, and oth er variables, were analyzed. Random forest (RF) and eXtreme gradient boosting (X GBoost) were selected from seven machine learning algorithms to build the model. The mean decrease accuracy (MDA), mean decrease Gini (MDG), and gain feature im portance (GFI) techniques were employed to quantify the importance of pupil diam eter and other features. After the assessments, 51,325 valid records with comple te pupil data were included, and 3468 (6.76%) were identified as my opia based on the calculated cycloplegic refraction. Preschoolers with myopia pr esented reduced pupil diameter and greater variation (5.00 ± 0.99 mm) compared t o non-myopic preschoolers (6.22 ± 0.67 mm). A nonlinear relationship was found a ccording to the scatterplots between pupil diameter and refraction (R = 0.14). E specially preschoolers with myopia had reduced pupil diameter compared to emmetr opic 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 p erformance and validated the importance of pupil diameter in myopia. 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 wit h a nonlinear pattern."
NETL
NSTL