Acceptability, applicability, and cost-utility of artificial-intelligence-powered low-cost portable fundus camera for diabetic retinopathy screening in primary health care settings
Authors' conclusion
The AI-powered portable fundus camera demonstrated high acceptability and applicability in real-world settings, suggesting that AI screening could be a viable alternative in resource-limited settings.
Study context
- Population
- Subjects screened for diabetic retinopathy (DR) in an optometric clinic and two optical shops, Hong Kong; age 60.80 ± 8.30 years61 completed follow-up interview
- Participants
- 316 subjects
- Comparison
- AI-powered portable fundus camera DR screening vs traditional screening
- Outcome
- Acceptability and applicability of self-testing system
Methodological detailscost-utility analysis, Open-ended questionnaire to selected participants 3 months after screening
- Cost-utility analysis
- Open-ended questionnaire to selected participants 3 months after screening
Main finding
As reported in the abstract
- Success rate of self-testing without active assistance
- 89 %
- System easy to follow (follow-up interview)
- 85.3 %
- Report easy to understand (follow-up interview)
- 75.4 %
- Satisfaction rate
- 64 %
- Willingness to use again
- 80 %
Further findings
Cost-utility
Cost saving per QALY AI screening 6312.92 USD
Saved Adjusted AI model 18639
Cost-utility
- AI screening and adjusted model outperformed traditional screening
Original publication
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. Published 5 April 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →