AI-assisted diabetic retinopathy screening shows potential economic value
A systematic review by Wei et al. identified 14 model-based economic evaluations published between 2017 and 2025, assessing the cost-effectiveness of AI-assisted diabetic retinopathy screening compared with human grader-based screening or no screening.
Key Findings:
- Incremental net monetary benefit (INMB) was used to quantify the economic value of AI-assisted screening by accounting for differences in costs and health outcomes between screening strategies; a positive INMB indicates greater economic value than the comparators.
- Of the 14 studies, 11 had enough data for a meta-analysis, which found a pooled INMB of $1,498 per individual for AI-assisted screening compared with human screening. The pooled INMB was $2,179 from a societal perspective and $1,583 from a healthcare system perspective.
- Three studies also compared AI-assisted screening with no screening, with a pooled INMB of $4,124 per individual. The pooled INMB was $3,606 from a societal perspective and $5,078 from a healthcare system perspective.
- The economic value of AI-assisted screening was context-dependent, and implementation decisions should consider local factors such as healthcare structures, accessibility, referral pathways and labour costs.
Reference: Wei C, Zhang L, Chen C, et al. Quantifying the Economic Value of Artificial Intelligence–Assisted Diabetic Retinopathy Screening: A Meta-Analysis Using the Incremental Net Benefit Framework. Value Health. 2026. doi:10.1016/j.jval.2026.06.005
