Diagnostic Accuracy of Novel Amblyopia Screening Technologies in Children: A Systematic Review and Meta-analysis

Background : Novel screening technologies may facilitate early detection of amblyopia and amblyopia risk factors (ARFs) in children. This systematic review and meta-analysis assessed the diagnostic accuracy of technology-assisted screening tools, such as photoscreeners, smartphone-based tools, AI-based systems, and other automated technologies.

Methods : This review was conducted according to the PRISMA 2020 guidelines. We searched PubMed, Scopus, and Web of Science for English-language published between 2016 and 2026, involving participants younger than 18 years. The appropriate ophthalmic reference standards were used to evaluate diagnostic accuracy.

Results : Pooled sensitivity for ARF detection was 84.2 % (95% CI: 77. 7–89.1%), and pooled specificity was 87.3 % (95% CI: 81.6–91.4 %). SPOT demonstrated a pooled sensitivity of 80.4% and specificity of 91.5%, whereas GoCheckKids demonstrated 82.2% sensitivity and 78.9% specificity. For established amblyopia pooled sensitivity and specificity were 82.6% and 95.8%, respectively. The effectiveness of diagnostics differed depending on the technology and screening circumstances.

Conclusion : technology-assisted screening shows promising diagnostic accuracy for detecting children with amblyopia and ARFs and may help identify those who require further ophthalmic evaluation. However, direct comparisons between technologies were limited with substantial heterogeneity.