Use of smartphones to detect diabetic retinopathy: scoping review and meta-analysis of diagnostic test accuracy studies

AI Generated Summary*

A scoping review with meta-analysis examined how accurately smartphone-based retinal imaging detects diabetic retinopathy. Nine studies with 1430 diabetic patients, identified through database searches covering 2000 to 2018, all used mydriatic imaging, with reference standards ranging from slit-lamp biomicroscopy to tabletop fundus photography. Pooled sensitivity and specificity reached 87% and 94% for any retinopathy, 39% and 95% for mild nonproliferative disease, 71% and 95% for moderate, 80% and 97% for severe, 92% and 99% for proliferative disease, 79% and 93% for macular edema, and 91% and 89% for referral-warranted disease. Two conference abstracts using artificial intelligence grading showed 91% sensitivity but 50% specificity. Evidence was heterogeneous and imprecise; consistent reference and grading criteria and primary care recruitment are urged.

*This summary was generated by AI and is published unedited. Oku does not alter these summaries. It may contain errors or omissions and is provided for general informational purposes only. Oku does not guarantee its accuracy, completeness, or reliability. For authoritative information, please refer to the original, peer-reviewed article.