AI-powered portable fundus cameras show promise for diabetic retinopathy screening
AI-powered portable fundus cameras offer a highly acceptable, user-friendly, and cost-effective alternative for diabetic retinopathy (DR) screening, particularly in resource-limited settings, according to a study.
The pragmatic trial, conducted in an optometric clinic and two optical shops in Hong Kong, evaluated the feasibility of a self-testing system integrating a portable fundus camera with AI-driven DR detection. Of the 316 participants, 89% successfully completed the test without assistance. Follow-up interviews with 61 participants found that 85.3% found the system easy to use, while 75.4% understood the report. Overall, 64% expressed satisfaction, and 80% indicated willingness to use the system again.
From a cost perspective, AI screening resulted in significant savings, with an estimated reduction of $6,312.92 per quality-adjusted life year (QALY), while an optimized AI model achieved even greater savings of $18,639. Compared to traditional screening, AI screening showed a higher net monetary benefit.
Refernece
Chen Y, Song F, Zhao Z, et al. Acceptability, applicability, and cost-utility of artificial-intelligence-powered low-cost portable fundus camera for diabetic retinopathy screening in primary health care settings. Diabetes Res Clin Pract. 2025;112161. doi: 10.1016/j.diabres.2025.112161. Epub ahead of print. PMID: 40194705.
