Peer-reviewed article
Artificial intelligence prediction algorithms for refractive error onset and progression in children and adolescents: A systematic review and meta-analysis.
Athanasia Sandali, Anna Nikolaidou, Theodora Gianni, Andreas Katsimpris, Ioannis D Apostolopoulos et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This systematic review examined 16 studies that use artificial intelligence to predict refractive error (myopia, hyperopia) onset and progression in children and adolescents. The meta-analysis of 8 studies found that AI models achieved moderate accuracy, with a pooled prediction error of 0.50 diopters. However, there was substantial variation between studies due to different study populations, model designs, and validation methods. The authors conclude that while AI shows promise, standardized frameworks are needed before these tools can be used in clinical practice.
Key points
- All 16 included studies evaluated myopia prediction; two also addressed hyperopia; none focused on astigmatism
- Pooled root-mean-squared error for spherical equivalent prediction was 0.50 D (95% CI: 0.37-0.62)
- High between-study heterogeneity (I² = 100%) reflects major differences in study populations, prediction targets, model architectures and validation strategies
- Most models predicted continuous refractive values, while some focused on classification outcomes like myopia onset or progression
- 43.8% of studies were rated high risk in the analysis domain during quality assessment
Limitations
The review does not specify which countries' populations were studied, making it unclear whether findings apply globally or to specific regions. The substantial heterogeneity between studies means the pooled accuracy estimate represents an average across diverse settings rather than a generalizable performance measure for clinical use.
Abstract
This systematic review and meta-analysis evaluates the performance of artificial intelligence (AI)-based models for predicting the onset and progression of refractive error (RE) in children and adolescents and quantitatively synthesizes their prediction accuracy. The study was preregistered in the PROSPERO database (CRD420251075160) and conducted in accordance with PRISMA guidelines. MEDLINE (via PubMed), Web of Science and Scopus were searched without time restrictions. Eligible studies involved children and adolescents (≤18 years) and applied AI-based technologies to predict the onset or progression of RE, using non-image-based input data. To evaluate the prediction accuracy of the included studies, a meta-analysis was performed. Quality assessment was conducted using the PROBAST+AI tool. Sixteen studies were included in the analysis. All studies evaluated myopia, two additionally addressed hyperopia and none focused on astigmatism. Most models predicted continuous SE values across the refractive spectrum, whereas a subset focused on classification-based outcomes, such as myopia onset or progression. Included studies used diverse input data, including age, gender and parental myopia. Eight studies comprising 18 independent evaluations were included in the meta-analysis. The pooled root-mean-squared error (RMSE) for spherical equivalent prediction was 0.50 D (95% confidence intervals: 0.37-0.62). Between-study heterogeneity was substantial (τ2 = 0.0695, I2 = 100%), indicating major differences across models. This high heterogeneity reflects substantial differences in study populations, prediction targets and horizons, model architectures and validation strategies across included studies, and therefore, the pooled estimate should be interpreted as an average across diverse settings rather than a directly generalizable performance measure. Leave-one-out sensitivity analyses demonstrated that no single study materially influenced the pooled effect. Across all iterations, RMSE estimates ranged narrowly from 0.48 to 0.52 D, with confidence intervals overlapping the main analysis. The studies' quality assessment showed mostly low concern, apart from the analysis domain, in which 43.8% of studies were rated high risk. AI models using non-image-based clinical data demonstrate moderate accuracy for predicting paediatric RE onset and progression. However, substantial methodological heterogeneity and limited external validation indicate that standardized development and validation frameworks are required before clinical implementation.