Evaluating the optimised font size and viewing time of online learning in young children: a multicentre cross-sectional study.

OBJECTIVES: Near viewing distance (VD) and longer viewing times are associated with myopia. This study aimed to identify the font size and viewing time that guarantee the appropriate VD and pixels per degree (PPD) for children's online learning. DESIGN: This cross-sectional study comprised two experiments. In experiment A, participants read text in five font sizes on three backlit displays (a personal computer, a smartphone and a tablet), an E-ink display and paper for 5 min per font size. In experiment B, participants watched videos for 30 min on three backlit displays. SETTING: The Peking University People's Hospital in Beijing (China) and the School of Ophthalmology and Optometry, Wenzhou Medical University (Zhejiang Province, China). PARTICIPANTS: Thirty-five participants completed experiment A. Ten of them participated in experiment B. PRIMARY AND SECONDARY OUTCOME MEASURES: VDs were measured by Clouclip. The corresponding PPD was calculated. RESULTS: In experiment A, font size and display type significantly affected VD (F(4840)=149.44, p<0.001, ES (Effect size)=0.77; F(4840), p<0.001, ES=0.37). VDs were >33 cm for all five font sizes on the PC, the tablet and paper and for 18-pt on the smartphone and 16-pt on E-ink. PPD for 16-pt on the PC, 14-pt on the tablet and all five font sizes on the phone were >60. In experiment B, VD increased over the four previous 5 min periods but decreased slightly on tablets and PCs in the fifth 5 min period. PPD was >60. CONCLUSION: Children demonstrated different VDs and PPDs based on font size and display type. To ensure a 33 cm VD and 60 PPD, the minimum font size for online reading should be 18-pt on smartphones, 16-pt on PCs and E-ink, 10.5-pt on tablets and 9-pt on paper. More attention should be given to children's VD with continuous video viewing of more than 25 min. TRIAL REGISTRATION NUMBER: ChiCTR2100049584.

Machine learning algorithm improves accuracy of ortho-K lens fitting in vision shaping treatment.

PURPOSE: To construct a machine learning (ML)-based model for estimating the alignment curve (AC) curvature in orthokeratology lens fitting for vision shaping treatment (VST), which can minimize the number of lens trials, improving efficiency while maintaining accuracy, with regards to its improvement over a previous calculation method. METHODS: Data were retrospectively collected from the clinical case files of 1271 myopic subjects (1271 right eyes). The AC curvatures calculated with a previously published algorithm were used as the target data sets. Four kinds of machine learning algorithms were implemented in the experimental analyses to predict the targeted AC curvatures: robust linear regression models, support vector machine (SVM) regression models with linear kernel functions, bagging decision trees, and Gaussian processes. The previously published calculation method and the novel machine learning method were then compared to assess the final parameters of ordered lenses. RESULTS: The linear SVM and Gaussian process machine learning models achieved the best performance. The input variables included sex, age, horizontal visible iris diameter (HVID), spherical refraction (SER), cylindrical refraction, eccentricity value (e value), flat K (K1) and steep K (K2) readings, anterior chamber depth (ACD), and axial length (AL). The R-squared values for the output AC1K1, AC1K2 and AC2K1 values were 0.91, 0.84, and 0.73, respectively. The previous calculation method and machine learning methods displayed excellent consistency, and the proposed methods performed best based on flat K reading and e values. CONCLUSIONS: The ML model can provide practitioners with an efficient method for estimating the AC curvatures of VST lenses and reducing the probability of cross-infection originating from trial lenses, which is especially useful during pandemics, such as that for COVID-19.