Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 17, 2025Frontiers in MedicineOpen Access

Prediction of myopia onset and shift in premyopic school-aged children: a machine learning-based algorithm

View Full Paper
Ask AI
Bookmark
Share

Authors

MGMingjun GaoYHYanhua HouYLYutong Lu

Discussion

Loading...

Member takes

Overview

Longitudinal study finds machine learning predicts myopia onset in children, suggesting effective prevention strategies.

Key Points

  • The research aims to predict myopia onset and shift in premyopic children by analyzing ocular parameters.
  • Prospective cohort study with 320 premyopic children aged 6–12 years.
  • Measured ocular parameters like uncorrected visual acuity and axial length at intervals.
  • Used machine learning models and multivariable analysis for predictions.
  • 49.3% of participants developed myopia within a year.
  • The optimal model achieved an AUC-ROC of 0.963 for predicting myopia onset.
  • Baseline spherical equivalent was the most significant predictor, followed by parental myopia.

Cite This Study

Gao et al. (2025) studied this question.

synapsesocial.com/papers/692509eec0ce034ddc3528fahttps://doi.org/10.3389/fmed.2025.1646277
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1School-level prediction and management of myopia in children and adolescents2025 · 6 citations
  2. 2Predicting onset of myopic refractive error in children using machine learning on routine pediatric eye examinations only2025
  3. 3Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents2024 · 36 citations
  4. 4Machine learning identifies pupil size and corneal thickness as key predictors of axial elongation rate2026
  5. 5Optimizing myopia prediction in children and adolescents using machine learning: a multi-factorial risk assessment model2025