Prediction of spherical equivalent difference before and after cycloplegia in school-age children with machine learning algorithms

• DOI: 10.3389/fpubh.2023.1096330
• Publication Date: 2023-04-11T05:05:08Z
• Authors: Bei Du; Qingxin Wang; Yuan Luo; Nan Jin; Hua Rong; Xilian Wang; Hong Nian; Li Guo; Meng Liang; Ruihua Wei
• Keywords: Cycloplegia

Purpose To predict the need for cycloplegic assessment, as well refractive state under cycloplegia, based on non-cycloplegic ocular parameters in school-age children. Design Random cluster sampling. Methods The cross-sectional study was conducted from December 2018 to January 2019. sampling used select 2,467 students aged 6–18 years. All participants were primary school, middle school and high school. Visual acuity, optical biometry, intraocular pressure, accommodation lag, gaze deviation position, autorefraction conducted. A binary classification model a three-way established necessity of cycloplegia status, respectively. regression also developed error using machine learning algorithms. Results accuracy recognizing requirement 68.5–77.0% AUC 0.762–0.833. prediction SE had performances R^2 0.889–0.927, MSE 0.250–0.380, MAE 0.372–0.436 r 0.943–0.963. As F1 score 80.3–81.7% 0.757–0.775, There no statistical difference between distribution status predicted by models one obtained conditions students. Conclusion Based big data acquisition techniques, before after can be effectively This provides theoretical basis supporting evidence epidemiological myopia accurate analysis vision screening optometry services.